{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/dataset/triviaqa","name":"TriviaQA","full_name":null,"description_markdown":"**TriviaQA** is a realistic text-based question answering dataset which includes 950K question-answer pairs from 662K documents collected from Wikipedia and the web. This dataset is more challenging than standard QA benchmark datasets such as Stanford Question Answering Dataset (SQuAD), as the answers for a question may not be directly obtained by span prediction and the context is very long. TriviaQA dataset consists of both human-verified and machine-generated QA subsets.\r\n\r\nSource: [Episodic Memory Reader: Learning What to Rememberfor Question Answering from Streaming Data](https://arxiv.org/abs/1903.06164)\r\nImage Source: [Joshi et al](https://arxiv.org/pdf/1705.03551v2.pdf)","description_withheld":null,"homepage":"http://nlp.cs.washington.edu/triviaqa/","introduced_date":"2017-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/triviaqa-a-large-scale-distantly-supervised","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","first_author":"Mandar Joshi","url":null},"license":{"name":"Unknown","url":"http://nlp.cs.washington.edu/triviaqa/#:~:text=copyright"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/question-answering"},{"name":"Text Generation","url":"/task/text-generation","datasets_with_task":"/datasets/task/text-generation"},{"name":"Reading Comprehension","url":"/task/reading-comprehension","datasets_with_task":"/datasets/task/reading-comprehension"},{"name":"Open-Domain Question Answering","url":"/task/open-domain-question-answering","datasets_with_task":"/datasets/task/open-domain-question-answering"},{"name":"Question Generation","url":"/task/question-generation","datasets_with_task":"/datasets/task/question-generation"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["TriviaQA","KILT: TriviaQA"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/trivia_qa","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/mandarjoshi/trivia_qa","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/facebookresearch/ParlAI","url":"https://parl.ai/docs/tasks.html#triviaqa","frameworks":["pytorch"]},{"repo":"https://github.com/tensorflow/datasets","url":"https://www.tensorflow.org/datasets/catalog/trivia_qa","frameworks":["tf","jax"]},{"repo":"https://github.com/RUCAIBox/LLMBox","url":"https://github.com/RUCAIBox/LLMBox","frameworks":["pytorch"]},{"repo":"https://github.com/allenai/allennlp-models","url":"https://docs.allennlp.org/models/main/models/rc/dataset_readers/triviaqa/","frameworks":["pytorch"]}],"num_papers_in_archive":953,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/question-answering-on-triviaqa","task":"Question Answering","dataset_variant":"TriviaQA","rows":56,"metrics":["EM","F1"],"first_row_in_archive_order":{"model":"Claude 2 (few-shot, k=5)","paper":"/paper/model-card-and-evaluations-for-claude-models","metrics":{"EM":"87.5"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/open-domain-question-answering-on-kilt-2","task":"Open-Domain Question Answering","dataset_variant":"KILT: TriviaQA","rows":15,"metrics":["KILT-EM","R-Prec","Recall@5","EM","F1","KILT-F1"],"first_row_in_archive_order":{"model":"Re2G","paper":"/paper/re2g-retrieve-rerank-generate-2","metrics":{"EM":"76.27","F1":"81.4","KILT-EM":"57.91","KILT-F1":"61.78","R-Prec":"72.68","Recall@5":"74.23"},"code_links":[{"title":"ibm/kgi-slot-filling","url":"https://github.com/ibm/kgi-slot-filling"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/question-generation-on-triviaqa","task":"Question Generation","dataset_variant":"TriviaQA","rows":2,"metrics":["QAE","R-QAE"],"first_row_in_archive_order":{"model":"Info-HCVAE","paper":"/paper/generating-diverse-and-consistent-qa-pairs","metrics":{"QAE":"35.45","R-QAE":"21.65"},"code_links":[{"title":"seanie12/Info-HCVAE","url":"https://github.com/seanie12/Info-HCVAE"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/open-domain-question-answering-on-triviaqa","task":"Open-Domain Question Answering","dataset_variant":"TriviaQA","rows":1,"metrics":["Exact Match"],"first_row_in_archive_order":{"model":"UnitedQA (Hybrid)","paper":"/paper/unitedqa-a-hybrid-approach-for-open-domain","metrics":{"Exact Match":"70.5"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/text-generation-on-triviaqa","task":"Text Generation","dataset_variant":"TriviaQA","rows":0,"metrics":["acc"],"first_row_in_archive_order":null,"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"shown":41,"of":41,"counts":{"papers_with_a_benchmark_row":41,"with_a_code_link":30,"where_syntology_ran_a_sample":22,"not_listed_spam_title":0,"listed":41,"listed_where_code_ran":22,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":19,"every_run_a_failure_of_syntologys_instrument":3,"listed_with_a_run_with_no_instrument_failure":19,"listed_every_run_a_failure_of_syntologys_instrument":3,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"paper":"/paper/search-o1-agentic-search-enhanced-large","slug":"search-o1-agentic-search-enhanced-large","title":"Search-o1: Agentic Search-Enhanced Large Reasoning Models","date":"2025-01-09","arxiv_id":"2501.05366","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/shakti-a-2-5-billion-parameter-small-language","slug":"shakti-a-2-5-billion-parameter-small-language","title":"SHAKTI: A 2.5 Billion Parameter Small Language Model Optimized for Edge AI and Low-Resource Environments","date":"2024-10-15","arxiv_id":"2410.11331","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/rankrag-unifying-context-ranking-with","slug":"rankrag-unifying-context-ranking-with","title":"RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMs","date":"2024-07-02","arxiv_id":"2407.02485","rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/understand-what-llm-needs-dual-preference","slug":"understand-what-llm-needs-dual-preference","title":"Understand What LLM Needs: Dual Preference Alignment for Retrieval-Augmented Generation","date":"2024-06-26","arxiv_id":"2406.18676","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":3,"official":{"repos":["dongguanting/dpa-rag"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/understand-what-llm-needs-dual-preference#ran","syntology_url":"https://syntology.ai/paper/2406.18676","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.18676"}}}},{"paper":"/paper/breaking-the-ceiling-of-the-llm-community-by","slug":"breaking-the-ceiling-of-the-llm-community-by","title":"Breaking the Ceiling of the LLM Community by Treating Token Generation as a Classification for Ensembling","date":"2024-06-18","arxiv_id":"2406.12585","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":3,"samples_unverified":2,"pointer_only_for_licence":1,"official":{"repos":["yaoching0/gac"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/breaking-the-ceiling-of-the-llm-community-by#ran","syntology_url":"https://syntology.ai/paper/2406.12585","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12585"}}}},{"paper":"/paper/branch-train-mix-mixing-expert-llms-into-a","slug":"branch-train-mix-mixing-expert-llms-into-a","title":"Branch-Train-MiX: Mixing Expert LLMs into a Mixture-of-Experts LLM","date":"2024-03-12","arxiv_id":"2403.07816","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/chatqa-building-gpt-4-level-conversational-qa","slug":"chatqa-building-gpt-4-level-conversational-qa","title":"ChatQA: Surpassing GPT-4 on Conversational QA and RAG","date":"2024-01-18","arxiv_id":"2401.10225","rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/mistral-7b","slug":"mistral-7b","title":"Mistral 7B","date":"2023-10-10","arxiv_id":"2310.06825","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":10,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":2,"official":{"repos":["mistralai/mistral-src"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/mistral-7b#ran","syntology_url":"https://syntology.ai/paper/2310.06825","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.06825"}}}},{"paper":"/paper/ra-dit-retrieval-augmented-dual-instruction","slug":"ra-dit-retrieval-augmented-dual-instruction","title":"RA-DIT: Retrieval-Augmented Dual Instruction Tuning","date":"2023-10-02","arxiv_id":"2310.01352","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/llama-2-open-foundation-and-fine-tuned-chat","slug":"llama-2-open-foundation-and-fine-tuned-chat","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","date":"2023-07-18","arxiv_id":"2307.09288","rows_on_this_dataset":1,"code_links":19,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":52,"samples_ran":33,"samples_constructed":7,"samples_ran_checked":20,"samples_ran_instrument_failed":13,"samples_unverified":19,"pointer_only_for_licence":20,"official":{"repos":["facebookresearch/llama"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/llama-2-open-foundation-and-fine-tuned-chat#ran","syntology_url":"https://syntology.ai/paper/2307.09288","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.09288"}}}},{"paper":"/paper/model-card-and-evaluations-for-claude-models","slug":"model-card-and-evaluations-for-claude-models","title":"Model Card and Evaluations for Claude Models","date":"2023-07-11","arxiv_id":null,"rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/palm-2-technical-report-1","slug":"palm-2-technical-report-1","title":"PaLM 2 Technical Report","date":"2023-05-17","arxiv_id":"2305.10403","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/gpt-4-technical-report-1","slug":"gpt-4-technical-report-1","title":"GPT-4 Technical Report","date":"2023-03-15","arxiv_id":"2303.08774","rows_on_this_dataset":1,"code_links":11,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["openai/evals"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/gpt-4-technical-report-1#ran","syntology_url":"https://syntology.ai/paper/2303.08774","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.08774"}}}},{"paper":"/paper/llama-open-and-efficient-foundation-language-1","slug":"llama-open-and-efficient-foundation-language-1","title":"LLaMA: Open and Efficient Foundation Language Models","date":"2023-02-27","arxiv_id":"2302.13971","rows_on_this_dataset":4,"code_links":57,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":58,"samples_ran":37,"samples_constructed":9,"samples_ran_checked":25,"samples_ran_instrument_failed":12,"samples_unverified":21,"pointer_only_for_licence":4,"official":{"repos":["facebookresearch/llama"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/llama-open-and-efficient-foundation-language-1#ran","syntology_url":"https://syntology.ai/paper/2302.13971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.13971"}}}},{"paper":"/paper/replug-retrieval-augmented-black-box-language","slug":"replug-retrieval-augmented-black-box-language","title":"REPLUG: Retrieval-Augmented Black-Box Language Models","date":"2023-01-30","arxiv_id":"2301.12652","rows_on_this_dataset":2,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":13,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":10,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":13,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/replug-retrieval-augmented-black-box-language#ran","syntology_url":"https://syntology.ai/paper/2301.12652","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.12652"}}}},{"paper":"/paper/fie-building-a-global-probability-space-by","slug":"fie-building-a-global-probability-space-by","title":"FiE: Building a Global Probability Space by Leveraging Early Fusion in Encoder for Open-Domain Question Answering","date":"2022-11-18","arxiv_id":"2211.10147","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/dyrex-dynamic-query-representation-for","slug":"dyrex-dynamic-query-representation-for","title":"DyREx: Dynamic Query Representation for Extractive Question Answering","date":"2022-10-26","arxiv_id":"2210.15048","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":3,"official":{"repos":["urchade/dyrex"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/dyrex-dynamic-query-representation-for#ran","syntology_url":"https://syntology.ai/paper/2210.15048","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.15048"}}}},{"paper":"/paper/re2g-retrieve-rerank-generate-2","slug":"re2g-retrieve-rerank-generate-2","title":"Re2G: Retrieve, Rerank, Generate","date":"2022-07-13","arxiv_id":"2207.06300","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":1,"official":{"repos":["ibm/kgi-slot-filling"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/re2g-retrieve-rerank-generate-2#ran","syntology_url":"https://syntology.ai/paper/2207.06300","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.06300"}}}},{"paper":"/paper/palm-scaling-language-modeling-with-pathways-1","slug":"palm-scaling-language-modeling-with-pathways-1","title":"PaLM: Scaling Language Modeling with Pathways","date":"2022-04-05","arxiv_id":"2204.02311","rows_on_this_dataset":3,"code_links":7,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":37,"samples_ran":32,"samples_constructed":16,"samples_ran_checked":24,"samples_ran_instrument_failed":8,"samples_unverified":5,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/palm-scaling-language-modeling-with-pathways-1#ran","syntology_url":"https://syntology.ai/paper/2204.02311","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.02311"}}}},{"paper":"/paper/linkbert-pretraining-language-models-with","slug":"linkbert-pretraining-language-models-with","title":"LinkBERT: Pretraining Language Models with Document Links","date":"2022-03-29","arxiv_id":"2203.15827","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":14,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":11,"pointer_only_for_licence":0,"official":{"repos":["michiyasunaga/LinkBERT"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":5,"ran_from_kinds":["found_in_text"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/linkbert-pretraining-language-models-with#ran","syntology_url":"https://syntology.ai/paper/2203.15827","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.15827"}}}},{"paper":"/paper/glam-efficient-scaling-of-language-models","slug":"glam-efficient-scaling-of-language-models","title":"GLaM: Efficient Scaling of Language Models with Mixture-of-Experts","date":"2021-12-13","arxiv_id":"2112.06905","rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/mention-memory-incorporating-textual-1","slug":"mention-memory-incorporating-textual-1","title":"Mention Memory: incorporating textual knowledge into Transformers through entity mention attention","date":"2021-10-12","arxiv_id":"2110.06176","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/reasonbert-pre-trained-to-reason-with-distant","slug":"reasonbert-pre-trained-to-reason-with-distant","title":"ReasonBERT: Pre-trained to Reason with Distant Supervision","date":"2021-09-10","arxiv_id":"2109.04912","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":2,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["sunlab-osu/reasonbert"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/reasonbert-pre-trained-to-reason-with-distant#ran","syntology_url":"https://syntology.ai/paper/2109.04912","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.04912"}}}},{"paper":"/paper/finetuned-language-models-are-zero-shot","slug":"finetuned-language-models-are-zero-shot","title":"Finetuned Language Models Are Zero-Shot Learners","date":"2021-09-03","arxiv_id":"2109.01652","rows_on_this_dataset":1,"code_links":8,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["google-research/flan"],"state":"official: harvested for another paper","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/finetuned-language-models-are-zero-shot#ran","syntology_url":"https://syntology.ai/paper/2109.01652","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.01652"}}}},{"paper":"/paper/end-to-end-training-of-multi-document-reader","slug":"end-to-end-training-of-multi-document-reader","title":"End-to-End Training of Multi-Document Reader and Retriever for Open-Domain Question Answering","date":"2021-06-09","arxiv_id":"2106.05346","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":4,"samples_unverified":0,"pointer_only_for_licence":4,"official":{"repos":["DevSinghSachan/emdr2"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["community","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/end-to-end-training-of-multi-document-reader#ran","syntology_url":"https://syntology.ai/paper/2106.05346","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.05346"}}}},{"paper":"/paper/unitedqa-a-hybrid-approach-for-open-domain","slug":"unitedqa-a-hybrid-approach-for-open-domain","title":"UnitedQA: A Hybrid Approach for Open Domain Question Answering","date":"2021-01-01","arxiv_id":"2101.00178","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/distilling-knowledge-from-reader-to-retriever-1","slug":"distilling-knowledge-from-reader-to-retriever-1","title":"Distilling Knowledge from Reader to Retriever for Question Answering","date":"2020-12-08","arxiv_id":"2012.04584","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["facebookresearch/FiD"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/distilling-knowledge-from-reader-to-retriever-1#ran","syntology_url":"https://syntology.ai/paper/2012.04584","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2012.04584"}}}},{"paper":"/paper/kilt-a-benchmark-for-knowledge-intensive","slug":"kilt-a-benchmark-for-knowledge-intensive","title":"KILT: a Benchmark for Knowledge Intensive Language Tasks","date":"2020-09-04","arxiv_id":"2009.02252","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["facebookresearch/KILT"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/kilt-a-benchmark-for-knowledge-intensive#ran","syntology_url":"https://syntology.ai/paper/2009.02252","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.02252"}}}},{"paper":"/paper/big-bird-transformers-for-longer-sequences","slug":"big-bird-transformers-for-longer-sequences","title":"Big Bird: Transformers for Longer Sequences","date":"2020-07-28","arxiv_id":"2007.14062","rows_on_this_dataset":1,"code_links":14,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":15,"samples_ran":10,"samples_constructed":1,"samples_ran_checked":2,"samples_ran_instrument_failed":8,"samples_unverified":5,"pointer_only_for_licence":11,"official":{"repos":["google-research/bigbird"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/big-bird-transformers-for-longer-sequences#ran","syntology_url":"https://syntology.ai/paper/2007.14062","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.14062"}}}},{"paper":"/paper/leveraging-passage-retrieval-with-generative","slug":"leveraging-passage-retrieval-with-generative","title":"Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering","date":"2020-07-02","arxiv_id":"2007.01282","rows_on_this_dataset":1,"code_links":8,"syntology":null},{"paper":"/paper/generating-diverse-and-consistent-qa-pairs","slug":"generating-diverse-and-consistent-qa-pairs","title":"Generating Diverse and Consistent QA pairs from Contexts with Information-Maximizing Hierarchical Conditional VAEs","date":"2020-05-28","arxiv_id":"2005.13837","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":16,"samples_ran":11,"samples_constructed":0,"samples_ran_checked":11,"samples_ran_instrument_failed":0,"samples_unverified":5,"pointer_only_for_licence":3,"official":{"repos":["seanie12/Info-HCVAE"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":5,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/generating-diverse-and-consistent-qa-pairs#ran","syntology_url":"https://syntology.ai/paper/2005.13837","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.13837"}}}},{"paper":"/paper/language-models-are-few-shot-learners","slug":"language-models-are-few-shot-learners","title":"Language Models are Few-Shot Learners","date":"2020-05-28","arxiv_id":"2005.14165","rows_on_this_dataset":1,"code_links":67,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":65,"samples_ran":45,"samples_constructed":0,"samples_ran_checked":37,"samples_ran_instrument_failed":8,"samples_unverified":20,"pointer_only_for_licence":7,"official":{"repos":["openai/gpt-3"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/language-models-are-few-shot-learners#ran","syntology_url":"https://syntology.ai/paper/2005.14165","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.14165"}}}},{"paper":"/paper/retrieval-augmented-generation-for-knowledge","slug":"retrieval-augmented-generation-for-knowledge","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","date":"2020-05-22","arxiv_id":"2005.11401","rows_on_this_dataset":1,"code_links":18,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":6,"samples_constructed":3,"samples_ran_checked":5,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/retrieval-augmented-generation-for-knowledge#ran","syntology_url":"https://syntology.ai/paper/2005.11401","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.11401"}}}},{"paper":"/paper/dense-passage-retrieval-for-open-domain","slug":"dense-passage-retrieval-for-open-domain","title":"Dense Passage Retrieval for Open-Domain Question Answering","date":"2020-04-10","arxiv_id":"2004.04906","rows_on_this_dataset":1,"code_links":19,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":14,"samples_ran":11,"samples_constructed":6,"samples_ran_checked":10,"samples_ran_instrument_failed":1,"samples_unverified":3,"pointer_only_for_licence":9,"official":{"repos":["facebookresearch/DPR"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/dense-passage-retrieval-for-open-domain#ran","syntology_url":"https://syntology.ai/paper/2004.04906","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.04906"}}}},{"paper":"/paper/spanbert-improving-pre-training-by","slug":"spanbert-improving-pre-training-by","title":"SpanBERT: Improving Pre-training by Representing and Predicting Spans","date":"2019-07-24","arxiv_id":"1907.10529","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":15,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":4,"samples_unverified":6,"pointer_only_for_licence":6,"official":{"repos":["facebookresearch/SpanBERT"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/spanbert-improving-pre-training-by#ran","syntology_url":"https://syntology.ai/paper/1907.10529","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.10529"}}}},{"paper":"/paper/190600300","slug":"190600300","title":"Latent Retrieval for Weakly Supervised Open Domain Question Answering","date":"2019-06-01","arxiv_id":"1906.00300","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/memoreader-large-scale-reading-comprehension","slug":"memoreader-large-scale-reading-comprehension","title":"MemoReader: Large-Scale Reading Comprehension through Neural Memory Controller","date":"2018-10-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/simple-and-effective-multi-paragraph-reading","slug":"simple-and-effective-multi-paragraph-reading","title":"Simple and Effective Multi-Paragraph Reading Comprehension","date":"2017-10-29","arxiv_id":"1710.10723","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["allenai/document-qa"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/simple-and-effective-multi-paragraph-reading#ran","syntology_url":"https://syntology.ai/paper/1710.10723","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1710.10723"}}}},{"paper":"/paper/memen-multi-layer-embedding-with-memory","slug":"memen-multi-layer-embedding-with-memory","title":"MEMEN: Multi-layer Embedding with Memory Networks for Machine Comprehension","date":"2017-07-28","arxiv_id":"1707.09098","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/dynamic-integration-of-background-knowledge","slug":"dynamic-integration-of-background-knowledge","title":"Dynamic Integration of Background Knowledge in Neural NLU Systems","date":"2017-06-08","arxiv_id":"1706.02596","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/reinforced-mnemonic-reader-for-machine","slug":"reinforced-mnemonic-reader-for-machine","title":"Reinforced Mnemonic Reader for Machine Reading Comprehension","date":"2017-05-08","arxiv_id":"1705.02798","rows_on_this_dataset":1,"code_links":3,"syntology":null}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/search-o1-agentic-search-enhanced-large","slug":"search-o1-agentic-search-enhanced-large","title":"Search-o1: Agentic Search-Enhanced Large Reasoning Models","date":"2025-01-09","arxiv_id":"2501.05366","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/shakti-a-2-5-billion-parameter-small-language","slug":"shakti-a-2-5-billion-parameter-small-language","title":"SHAKTI: A 2.5 Billion Parameter Small Language Model Optimized for Edge AI and Low-Resource Environments","date":"2024-10-15","arxiv_id":"2410.11331","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/rankrag-unifying-context-ranking-with","slug":"rankrag-unifying-context-ranking-with","title":"RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMs","date":"2024-07-02","arxiv_id":"2407.02485","rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/understand-what-llm-needs-dual-preference","slug":"understand-what-llm-needs-dual-preference","title":"Understand What LLM Needs: Dual Preference Alignment for Retrieval-Augmented Generation","date":"2024-06-26","arxiv_id":"2406.18676","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":2,"pointer_only_for_licence":3,"official":{"repos":["dongguanting/dpa-rag"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/understand-what-llm-needs-dual-preference#ran","syntology_url":"https://syntology.ai/paper/2406.18676","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.18676"}}}},{"paper":"/paper/breaking-the-ceiling-of-the-llm-community-by","slug":"breaking-the-ceiling-of-the-llm-community-by","title":"Breaking the Ceiling of the LLM Community by Treating Token Generation as a Classification for Ensembling","date":"2024-06-18","arxiv_id":"2406.12585","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":7,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":3,"samples_unverified":2,"pointer_only_for_licence":1,"official":{"repos":["yaoching0/gac"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/breaking-the-ceiling-of-the-llm-community-by#ran","syntology_url":"https://syntology.ai/paper/2406.12585","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12585"}}}},{"paper":"/paper/branch-train-mix-mixing-expert-llms-into-a","slug":"branch-train-mix-mixing-expert-llms-into-a","title":"Branch-Train-MiX: Mixing Expert LLMs into a Mixture-of-Experts LLM","date":"2024-03-12","arxiv_id":"2403.07816","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/chatqa-building-gpt-4-level-conversational-qa","slug":"chatqa-building-gpt-4-level-conversational-qa","title":"ChatQA: Surpassing GPT-4 on Conversational QA and RAG","date":"2024-01-18","arxiv_id":"2401.10225","rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/mistral-7b","slug":"mistral-7b","title":"Mistral 7B","date":"2023-10-10","arxiv_id":"2310.06825","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":10,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":2,"official":{"repos":["mistralai/mistral-src"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/mistral-7b#ran","syntology_url":"https://syntology.ai/paper/2310.06825","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.06825"}}}},{"paper":"/paper/ra-dit-retrieval-augmented-dual-instruction","slug":"ra-dit-retrieval-augmented-dual-instruction","title":"RA-DIT: Retrieval-Augmented Dual Instruction Tuning","date":"2023-10-02","arxiv_id":"2310.01352","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/llama-2-open-foundation-and-fine-tuned-chat","slug":"llama-2-open-foundation-and-fine-tuned-chat","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","date":"2023-07-18","arxiv_id":"2307.09288","rows_on_this_dataset":1,"code_links":19,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":52,"samples_ran":33,"samples_constructed":7,"samples_ran_checked":20,"samples_ran_instrument_failed":13,"samples_unverified":19,"pointer_only_for_licence":20,"official":{"repos":["facebookresearch/llama"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/llama-2-open-foundation-and-fine-tuned-chat#ran","syntology_url":"https://syntology.ai/paper/2307.09288","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.09288"}}}},{"paper":"/paper/model-card-and-evaluations-for-claude-models","slug":"model-card-and-evaluations-for-claude-models","title":"Model Card and Evaluations for Claude Models","date":"2023-07-11","arxiv_id":null,"rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/palm-2-technical-report-1","slug":"palm-2-technical-report-1","title":"PaLM 2 Technical Report","date":"2023-05-17","arxiv_id":"2305.10403","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/gpt-4-technical-report-1","slug":"gpt-4-technical-report-1","title":"GPT-4 Technical Report","date":"2023-03-15","arxiv_id":"2303.08774","rows_on_this_dataset":1,"code_links":11,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":5,"samples_ran":5,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["openai/evals"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/gpt-4-technical-report-1#ran","syntology_url":"https://syntology.ai/paper/2303.08774","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.08774"}}}},{"paper":"/paper/llama-open-and-efficient-foundation-language-1","slug":"llama-open-and-efficient-foundation-language-1","title":"LLaMA: Open and Efficient Foundation Language Models","date":"2023-02-27","arxiv_id":"2302.13971","rows_on_this_dataset":4,"code_links":57,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":58,"samples_ran":37,"samples_constructed":9,"samples_ran_checked":25,"samples_ran_instrument_failed":12,"samples_unverified":21,"pointer_only_for_licence":4,"official":{"repos":["facebookresearch/llama"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/llama-open-and-efficient-foundation-language-1#ran","syntology_url":"https://syntology.ai/paper/2302.13971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.13971"}}}},{"paper":"/paper/replug-retrieval-augmented-black-box-language","slug":"replug-retrieval-augmented-black-box-language","title":"REPLUG: Retrieval-Augmented Black-Box Language Models","date":"2023-01-30","arxiv_id":"2301.12652","rows_on_this_dataset":2,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":13,"samples_ran":10,"samples_constructed":0,"samples_ran_checked":10,"samples_ran_instrument_failed":0,"samples_unverified":3,"pointer_only_for_licence":13,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/replug-retrieval-augmented-black-box-language#ran","syntology_url":"https://syntology.ai/paper/2301.12652","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.12652"}}}},{"paper":"/paper/fie-building-a-global-probability-space-by","slug":"fie-building-a-global-probability-space-by","title":"FiE: Building a Global Probability Space by Leveraging Early Fusion in Encoder for Open-Domain Question Answering","date":"2022-11-18","arxiv_id":"2211.10147","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/dyrex-dynamic-query-representation-for","slug":"dyrex-dynamic-query-representation-for","title":"DyREx: Dynamic Query Representation for Extractive Question Answering","date":"2022-10-26","arxiv_id":"2210.15048","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":3,"official":{"repos":["urchade/dyrex"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official","unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/dyrex-dynamic-query-representation-for#ran","syntology_url":"https://syntology.ai/paper/2210.15048","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.15048"}}}},{"paper":"/paper/re2g-retrieve-rerank-generate-2","slug":"re2g-retrieve-rerank-generate-2","title":"Re2G: Retrieve, Rerank, Generate","date":"2022-07-13","arxiv_id":"2207.06300","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":8,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":6,"samples_ran_instrument_failed":1,"samples_unverified":1,"pointer_only_for_licence":1,"official":{"repos":["ibm/kgi-slot-filling"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/re2g-retrieve-rerank-generate-2#ran","syntology_url":"https://syntology.ai/paper/2207.06300","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.06300"}}}},{"paper":"/paper/palm-scaling-language-modeling-with-pathways-1","slug":"palm-scaling-language-modeling-with-pathways-1","title":"PaLM: Scaling Language Modeling with Pathways","date":"2022-04-05","arxiv_id":"2204.02311","rows_on_this_dataset":3,"code_links":7,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":37,"samples_ran":32,"samples_constructed":16,"samples_ran_checked":24,"samples_ran_instrument_failed":8,"samples_unverified":5,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/palm-scaling-language-modeling-with-pathways-1#ran","syntology_url":"https://syntology.ai/paper/2204.02311","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.02311"}}}},{"paper":"/paper/linkbert-pretraining-language-models-with","slug":"linkbert-pretraining-language-models-with","title":"LinkBERT: Pretraining Language Models with Document Links","date":"2022-03-29","arxiv_id":"2203.15827","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":14,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":3,"samples_ran_instrument_failed":0,"samples_unverified":11,"pointer_only_for_licence":0,"official":{"repos":["michiyasunaga/LinkBERT"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":5,"ran_from_kinds":["found_in_text"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/linkbert-pretraining-language-models-with#ran","syntology_url":"https://syntology.ai/paper/2203.15827","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.15827"}}}},{"paper":"/paper/glam-efficient-scaling-of-language-models","slug":"glam-efficient-scaling-of-language-models","title":"GLaM: Efficient Scaling of Language Models with Mixture-of-Experts","date":"2021-12-13","arxiv_id":"2112.06905","rows_on_this_dataset":3,"code_links":0,"syntology":null},{"paper":"/paper/mention-memory-incorporating-textual-1","slug":"mention-memory-incorporating-textual-1","title":"Mention Memory: incorporating textual knowledge into Transformers through entity mention attention","date":"2021-10-12","arxiv_id":"2110.06176","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/reasonbert-pre-trained-to-reason-with-distant","slug":"reasonbert-pre-trained-to-reason-with-distant","title":"ReasonBERT: Pre-trained to Reason with Distant Supervision","date":"2021-09-10","arxiv_id":"2109.04912","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":11,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":2,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["sunlab-osu/reasonbert"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/reasonbert-pre-trained-to-reason-with-distant#ran","syntology_url":"https://syntology.ai/paper/2109.04912","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.04912"}}}},{"paper":"/paper/finetuned-language-models-are-zero-shot","slug":"finetuned-language-models-are-zero-shot","title":"Finetuned Language Models Are Zero-Shot Learners","date":"2021-09-03","arxiv_id":"2109.01652","rows_on_this_dataset":1,"code_links":8,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":0,"official":{"repos":["google-research/flan"],"state":"official: harvested for another paper","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/finetuned-language-models-are-zero-shot#ran","syntology_url":"https://syntology.ai/paper/2109.01652","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.01652"}}}},{"paper":"/paper/end-to-end-training-of-multi-document-reader","slug":"end-to-end-training-of-multi-document-reader","title":"End-to-End Training of Multi-Document Reader and Retriever for Open-Domain Question Answering","date":"2021-06-09","arxiv_id":"2106.05346","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":4,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":4,"samples_unverified":0,"pointer_only_for_licence":4,"official":{"repos":["DevSinghSachan/emdr2"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["community","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/end-to-end-training-of-multi-document-reader#ran","syntology_url":"https://syntology.ai/paper/2106.05346","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.05346"}}}},{"paper":"/paper/unitedqa-a-hybrid-approach-for-open-domain","slug":"unitedqa-a-hybrid-approach-for-open-domain","title":"UnitedQA: A Hybrid Approach for Open Domain Question Answering","date":"2021-01-01","arxiv_id":"2101.00178","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/distilling-knowledge-from-reader-to-retriever-1","slug":"distilling-knowledge-from-reader-to-retriever-1","title":"Distilling Knowledge from Reader to Retriever for Question Answering","date":"2020-12-08","arxiv_id":"2012.04584","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["facebookresearch/FiD"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/distilling-knowledge-from-reader-to-retriever-1#ran","syntology_url":"https://syntology.ai/paper/2012.04584","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2012.04584"}}}},{"paper":"/paper/kilt-a-benchmark-for-knowledge-intensive","slug":"kilt-a-benchmark-for-knowledge-intensive","title":"KILT: a Benchmark for Knowledge Intensive Language Tasks","date":"2020-09-04","arxiv_id":"2009.02252","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":1,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":1,"official":{"repos":["facebookresearch/KILT"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/kilt-a-benchmark-for-knowledge-intensive#ran","syntology_url":"https://syntology.ai/paper/2009.02252","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.02252"}}}},{"paper":"/paper/big-bird-transformers-for-longer-sequences","slug":"big-bird-transformers-for-longer-sequences","title":"Big Bird: Transformers for Longer Sequences","date":"2020-07-28","arxiv_id":"2007.14062","rows_on_this_dataset":1,"code_links":14,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":15,"samples_ran":10,"samples_constructed":1,"samples_ran_checked":2,"samples_ran_instrument_failed":8,"samples_unverified":5,"pointer_only_for_licence":11,"official":{"repos":["google-research/bigbird"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/big-bird-transformers-for-longer-sequences#ran","syntology_url":"https://syntology.ai/paper/2007.14062","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.14062"}}}},{"paper":"/paper/leveraging-passage-retrieval-with-generative","slug":"leveraging-passage-retrieval-with-generative","title":"Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering","date":"2020-07-02","arxiv_id":"2007.01282","rows_on_this_dataset":1,"code_links":8,"syntology":null},{"paper":"/paper/generating-diverse-and-consistent-qa-pairs","slug":"generating-diverse-and-consistent-qa-pairs","title":"Generating Diverse and Consistent QA pairs from Contexts with Information-Maximizing Hierarchical Conditional VAEs","date":"2020-05-28","arxiv_id":"2005.13837","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":16,"samples_ran":11,"samples_constructed":0,"samples_ran_checked":11,"samples_ran_instrument_failed":0,"samples_unverified":5,"pointer_only_for_licence":3,"official":{"repos":["seanie12/Info-HCVAE"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":5,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/generating-diverse-and-consistent-qa-pairs#ran","syntology_url":"https://syntology.ai/paper/2005.13837","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.13837"}}}},{"paper":"/paper/language-models-are-few-shot-learners","slug":"language-models-are-few-shot-learners","title":"Language Models are Few-Shot Learners","date":"2020-05-28","arxiv_id":"2005.14165","rows_on_this_dataset":1,"code_links":67,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":65,"samples_ran":45,"samples_constructed":0,"samples_ran_checked":37,"samples_ran_instrument_failed":8,"samples_unverified":20,"pointer_only_for_licence":7,"official":{"repos":["openai/gpt-3"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/language-models-are-few-shot-learners#ran","syntology_url":"https://syntology.ai/paper/2005.14165","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.14165"}}}},{"paper":"/paper/retrieval-augmented-generation-for-knowledge","slug":"retrieval-augmented-generation-for-knowledge","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","date":"2020-05-22","arxiv_id":"2005.11401","rows_on_this_dataset":1,"code_links":18,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":6,"samples_ran":6,"samples_constructed":3,"samples_ran_checked":5,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/retrieval-augmented-generation-for-knowledge#ran","syntology_url":"https://syntology.ai/paper/2005.11401","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.11401"}}}},{"paper":"/paper/dense-passage-retrieval-for-open-domain","slug":"dense-passage-retrieval-for-open-domain","title":"Dense Passage Retrieval for Open-Domain Question Answering","date":"2020-04-10","arxiv_id":"2004.04906","rows_on_this_dataset":1,"code_links":19,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":14,"samples_ran":11,"samples_constructed":6,"samples_ran_checked":10,"samples_ran_instrument_failed":1,"samples_unverified":3,"pointer_only_for_licence":9,"official":{"repos":["facebookresearch/DPR"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/dense-passage-retrieval-for-open-domain#ran","syntology_url":"https://syntology.ai/paper/2004.04906","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.04906"}}}},{"paper":"/paper/spanbert-improving-pre-training-by","slug":"spanbert-improving-pre-training-by","title":"SpanBERT: Improving Pre-training by Representing and Predicting Spans","date":"2019-07-24","arxiv_id":"1907.10529","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":15,"samples_ran":9,"samples_constructed":0,"samples_ran_checked":5,"samples_ran_instrument_failed":4,"samples_unverified":6,"pointer_only_for_licence":6,"official":{"repos":["facebookresearch/SpanBERT"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/spanbert-improving-pre-training-by#ran","syntology_url":"https://syntology.ai/paper/1907.10529","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.10529"}}}},{"paper":"/paper/190600300","slug":"190600300","title":"Latent Retrieval for Weakly Supervised Open Domain Question Answering","date":"2019-06-01","arxiv_id":"1906.00300","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/memoreader-large-scale-reading-comprehension","slug":"memoreader-large-scale-reading-comprehension","title":"MemoReader: Large-Scale Reading Comprehension through Neural Memory Controller","date":"2018-10-01","arxiv_id":null,"rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/simple-and-effective-multi-paragraph-reading","slug":"simple-and-effective-multi-paragraph-reading","title":"Simple and Effective Multi-Paragraph Reading Comprehension","date":"2017-10-29","arxiv_id":"1710.10723","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":4,"samples_ran":2,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["allenai/document-qa"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/simple-and-effective-multi-paragraph-reading#ran","syntology_url":"https://syntology.ai/paper/1710.10723","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1710.10723"}}}},{"paper":"/paper/memen-multi-layer-embedding-with-memory","slug":"memen-multi-layer-embedding-with-memory","title":"MEMEN: Multi-layer Embedding with Memory Networks for Machine Comprehension","date":"2017-07-28","arxiv_id":"1707.09098","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/dynamic-integration-of-background-knowledge","slug":"dynamic-integration-of-background-knowledge","title":"Dynamic Integration of Background Knowledge in Neural NLU Systems","date":"2017-06-08","arxiv_id":"1706.02596","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/reinforced-mnemonic-reader-for-machine","slug":"reinforced-mnemonic-reader-for-machine","title":"Reinforced Mnemonic Reader for Machine Reading Comprehension","date":"2017-05-08","arxiv_id":"1705.02798","rows_on_this_dataset":1,"code_links":3,"syntology":null}],"papers_where_code_ran":22,"papers_where_code_ran_first_page":"/dataset/triviaqa/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/dataset/triviaqa/papers/ran/1","json":"/dataset/triviaqa/papers/ran/1.json","rows":22}],"row_route":"each paper's syntology object carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":23,"samples_harvested":364,"samples_ran":254,"samples_constructed":42,"samples_ran_checked":186,"samples_ran_instrument_failed":68,"samples_unverified":110,"pointer_only_for_licence":90,"papers_with_no_sample_that_ran":1,"papers_with_a_sample_that_ran":22,"papers_with_a_run_with_no_instrument_failure":19,"papers_where_every_run_was_an_instrument_failure":3,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","samples_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":23,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[{"leaderboard":"/sota/question-answering-on-triviaqa","since_archive":"/sota/question-answering-on-triviaqa#since-judged","papers_judged":20,"placed":0},{"leaderboard":"/sota/open-domain-question-answering-on-triviaqa","since_archive":"/sota/open-domain-question-answering-on-triviaqa#since-judged","papers_judged":6,"placed":0}]},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"7ffdb51c1ec19b14773b589d8253e1e6338833173ae7fd88abebdc6007edbb9f","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}