{"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":"/task/chatbot","name":"Chatbot","slug":"chatbot","description_markdown":"**Chatbot** or conversational AI is a language model designed and implemented to have conversations with humans. \r\n\r\n\r\n<span class=\"description-source\">Source: [Open Data Chatbot ](https://arxiv.org/abs/1909.03653)</span>\r\n\r\n[Image source](https://arxiv.org/pdf/2006.16779v3.pdf)","categories":[{"name":"Methodology","url":"/area/methodology"},{"name":"Natural Language Processing","url":"/area/natural-language-processing"},{"name":"Speech","url":"/area/speech"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":971,"papers_with_code":269,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":10,"subtasks":1,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/chatbot-on-alpacaeval","slug":"chatbot-on-alpacaeval","dataset":"AlpacaEval","dataset_url":"/dataset/alpacaeval","rows_in_archive":1,"metrics":["Average win rate"],"first_row_in_archive_order":{"model":"Yi 34B Chat","paper_title":"Yi: Open Foundation Models by 01.AI","paper_url":"/paper/yi-open-foundation-models-by-01-ai","paper_date":"2024-03-07","arxiv_id":"2403.04652","code_links":[{"title":"01-ai/yi","url":"https://github.com/01-ai/yi"}],"syntology":{"n":8,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/yi-open-foundation-models-by-01-ai#ran","syntology_url":"https://syntology.ai/paper/2403.04652","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.04652"}},"official":{"repos":["01-ai/yi"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":6,"ran_from_kinds":["official"]}}}}],"datasets":[{"url":"/dataset/alpacaeval","name":"AlpacaEval","full_name":"","num_papers_in_archive":131},{"url":"/dataset/blended-skill-talk","name":"Blended Skill Talk","full_name":"Blended Skill Talk","num_papers_in_archive":32},{"url":"/dataset/photobook","name":"PhotoBook","full_name":"","num_papers_in_archive":11},{"url":"/dataset/taiga-corpus","name":"Taiga Corpus","full_name":"An open-source corpus for machine learning.","num_papers_in_archive":5},{"url":"/dataset/metaphorical-connections","name":"Metaphorical Connections","full_name":null,"num_papers_in_archive":2},{"url":"/dataset/alpacaeval-th","name":"AlpacaEval-TH","full_name":"","num_papers_in_archive":1},{"url":"/dataset/chatgpt-software-testing-study","name":"ChatGPT Software Testing Study","full_name":"ChatGPT Software Testing Study Dataset","num_papers_in_archive":1},{"url":"/dataset/finchat","name":"FinChat","full_name":"Finnish Chat Conversations on Everyday Topics","num_papers_in_archive":1},{"url":"/dataset/mt-bench-th","name":"MT-Bench-TH","full_name":"","num_papers_in_archive":1},{"url":"/dataset/chatgpt-software-testing","name":"ChatGPT-software-testing","full_name":"ChatGPT Software Testing","num_papers_in_archive":0}],"subtasks":[{"url":"/task/dialogue-generation","name":"Dialogue Generation"}],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":10,"rows_per_page":100,"shown":100,"of":971,"of_with_code":269,"tagged_in_all":971,"counts":{"archive_papers_tagged":971,"with_a_code_link":269,"where_syntology_ran_a_sample":56,"not_listed_spam_title":0,"listed":971,"listed_where_code_ran":56,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":45,"every_run_a_failure_of_syntologys_instrument":11,"listed_with_a_run_with_no_instrument_failure":45,"listed_every_run_a_failure_of_syntologys_instrument":11,"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 the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/qlora-efficient-finetuning-of-quantized-llms","slug":"qlora-efficient-finetuning-of-quantized-llms","title":"QLoRA: Efficient Finetuning of Quantized LLMs","date":"2023-05-23","arxiv_id":"2305.14314","repositories_listed":20,"syntology":{"n":26,"n_ran":18,"n_constructed":1,"n_ran_checked":6,"n_instrument":12,"n_unverified":8,"n_honours":2,"n_violates":2,"n_no_contract":2,"n_pointer_only":17,"phrase":"18 ran (of which 1 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 2 violated, 2 with no contract checked; 12 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/qlora-efficient-finetuning-of-quantized-llms#ran","syntology_url":"https://syntology.ai/paper/2305.14314","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14314"}},"official":{"repos":["artidoro/qlora","timdettmers/bitsandbytes"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["community","listed","official","unlocated"]}}},{"url":"/paper/end-to-end-task-completion-neural-dialogue","slug":"end-to-end-task-completion-neural-dialogue","title":"End-to-End Task-Completion Neural Dialogue Systems","date":"2017-03-03","arxiv_id":"1703.01008","repositories_listed":13,"syntology":{"n":8,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/end-to-end-task-completion-neural-dialogue#ran","syntology_url":"https://syntology.ai/paper/1703.01008","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.01008"}},"official":{"repos":["MiuLab/TC-Bot"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/judging-llm-as-a-judge-with-mt-bench-and-1","slug":"judging-llm-as-a-judge-with-mt-bench-and-1","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","date":"2023-06-09","arxiv_id":"2306.05685","repositories_listed":11,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/judging-llm-as-a-judge-with-mt-bench-and-1#ran","syntology_url":"https://syntology.ai/paper/2306.05685","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.05685"}},"official":{"repos":["lm-sys/fastchat"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/visual-dialog","slug":"visual-dialog","title":"Visual Dialog","date":"2016-11-26","arxiv_id":"1611.08669","repositories_listed":11,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/visual-dialog#ran","syntology_url":"https://syntology.ai/paper/1611.08669","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1611.08669"}},"official":{"repos":["batra-mlp-lab/visdial-amt-chat"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/recipes-for-building-an-open-domain-chatbot","slug":"recipes-for-building-an-open-domain-chatbot","title":"Recipes for building an open-domain chatbot","date":"2020-04-28","arxiv_id":"2004.13637","repositories_listed":8,"syntology":null},{"url":"/paper/deep-reinforcement-learning-for-dialogue","slug":"deep-reinforcement-learning-for-dialogue","title":"Deep Reinforcement Learning for Dialogue Generation","date":"2016-06-05","arxiv_id":"1606.01541","repositories_listed":8,"syntology":null},{"url":"/paper/mistral-7b","slug":"mistral-7b","title":"Mistral 7B","date":"2023-10-10","arxiv_id":"2310.06825","repositories_listed":6,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":2,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/mistral-7b#ran","syntology_url":"https://syntology.ai/paper/2310.06825","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.06825"}},"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"]}}},{"url":"/paper/chatbot-arena-an-open-platform-for-evaluating","slug":"chatbot-arena-an-open-platform-for-evaluating","title":"Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference","date":"2024-03-07","arxiv_id":"2403.04132","repositories_listed":5,"syntology":{"n":9,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":4,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":3,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/chatbot-arena-an-open-platform-for-evaluating#ran","syntology_url":"https://syntology.ai/paper/2403.04132","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.04132"}},"official":null}},{"url":"/paper/lmsys-chat-1m-a-large-scale-real-world-llm","slug":"lmsys-chat-1m-a-large-scale-real-world-llm","title":"LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset","date":"2023-09-21","arxiv_id":"2309.11998","repositories_listed":5,"syntology":null},{"url":"/paper/baize-an-open-source-chat-model-with","slug":"baize-an-open-source-chat-model-with","title":"Baize: An Open-Source Chat Model with Parameter-Efficient Tuning on Self-Chat Data","date":"2023-04-03","arxiv_id":"2304.01196","repositories_listed":5,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":2,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/baize-an-open-source-chat-model-with#ran","syntology_url":"https://syntology.ai/paper/2304.01196","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.01196"}},"official":{"repos":["project-baize/baize","project-baize/baize-chatbot"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/from-crowdsourced-data-to-high-quality","slug":"from-crowdsourced-data-to-high-quality","title":"From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipeline","date":"2024-06-17","arxiv_id":"2406.11939","repositories_listed":4,"syntology":{"n":21,"n_ran":19,"n_constructed":0,"n_ran_checked":4,"n_instrument":15,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"19 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 15 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/from-crowdsourced-data-to-high-quality#ran","syntology_url":"https://syntology.ai/paper/2406.11939","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.11939"}},"official":{"repos":["lm-sys/arena-hard-auto","lmarena/arena-hard-auto"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/wildteaming-at-scale-from-in-the-wild","slug":"wildteaming-at-scale-from-in-the-wild","title":"WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language Models","date":"2024-06-26","arxiv_id":"2406.18510","repositories_listed":3,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/wildteaming-at-scale-from-in-the-wild#ran","syntology_url":"https://syntology.ai/paper/2406.18510","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.18510"}},"official":{"repos":["allenai/wildteaming"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/rlhf-workflow-from-reward-modeling-to-online","slug":"rlhf-workflow-from-reward-modeling-to-online","title":"RLHF Workflow: From Reward Modeling to Online RLHF","date":"2024-05-13","arxiv_id":"2405.07863","repositories_listed":3,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/rlhf-workflow-from-reward-modeling-to-online#ran","syntology_url":"https://syntology.ai/paper/2405.07863","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.07863"}},"official":{"repos":["RLHFlow/RLHF-Reward-Modeling","rlhflow/online-rlhf"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/don-t-forget-your-abc-s-evaluating-the-state","slug":"don-t-forget-your-abc-s-evaluating-the-state","title":"Don't Forget Your ABC's: Evaluating the State-of-the-Art in Chat-Oriented Dialogue Systems","date":"2022-12-18","arxiv_id":"2212.09180","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/don-t-forget-your-abc-s-evaluating-the-state#ran","syntology_url":"https://syntology.ai/paper/2212.09180","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.09180"}},"official":{"repos":["emora-chat/chatevaluationplatform","emorynlp/chatevaluationplatform"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/plato-2-towards-building-an-open-domain","slug":"plato-2-towards-building-an-open-domain","title":"PLATO-2: Towards Building an Open-Domain Chatbot via Curriculum Learning","date":"2020-06-30","arxiv_id":"2006.16779","repositories_listed":3,"syntology":null},{"url":"/paper/subword-semantic-hashing-for-intent","slug":"subword-semantic-hashing-for-intent","title":"Subword Semantic Hashing for Intent Classification on Small Datasets","date":"2018-10-16","arxiv_id":"1810.07150","repositories_listed":3,"syntology":null},{"url":"/paper/llama-omni2-llm-based-real-time-spoken","slug":"llama-omni2-llm-based-real-time-spoken","title":"LLaMA-Omni2: LLM-based Real-time Spoken Chatbot with Autoregressive Streaming Speech Synthesis","date":"2025-05-05","arxiv_id":"2505.02625","repositories_listed":2,"syntology":{"n":11,"n_ran":9,"n_constructed":3,"n_ran_checked":4,"n_instrument":5,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":10,"phrase":"9 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/llama-omni2-llm-based-real-time-spoken#ran","syntology_url":"https://syntology.ai/paper/2505.02625","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.02625"}},"official":{"repos":["ictnlp/llama-omni2"],"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":["found_in_text","listed"]}}},{"url":"/paper/eliza-reanimated-the-world-s-first-chatbot","slug":"eliza-reanimated-the-world-s-first-chatbot","title":"ELIZA Reanimated: The world's first chatbot restored on the world's first time sharing system","date":"2025-01-12","arxiv_id":"2501.06707","repositories_listed":2,"syntology":null},{"url":"/paper/low-code-from-frontend-to-backend-connecting","slug":"low-code-from-frontend-to-backend-connecting","title":"Low-code from frontend to backend: Connecting conversational user interfaces to backend services via a low-code IoT platform","date":"2024-09-13","arxiv_id":"2410.00006","repositories_listed":2,"syntology":null},{"url":"/paper/jamba-1-5-hybrid-transformer-mamba-models-at","slug":"jamba-1-5-hybrid-transformer-mamba-models-at","title":"Jamba-1.5: Hybrid Transformer-Mamba Models at Scale","date":"2024-08-22","arxiv_id":"2408.12570","repositories_listed":2,"syntology":null},{"url":"/paper/simpo-simple-preference-optimization-with-a","slug":"simpo-simple-preference-optimization-with-a","title":"SimPO: Simple Preference Optimization with a Reference-Free Reward","date":"2024-05-23","arxiv_id":"2405.14734","repositories_listed":2,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":1,"n_pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/simpo-simple-preference-optimization-with-a#ran","syntology_url":"https://syntology.ai/paper/2405.14734","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.14734"}},"official":{"repos":["princeton-nlp/simpo"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/using-adaptive-empathetic-responses-for","slug":"using-adaptive-empathetic-responses-for","title":"Using Adaptive Empathetic Responses for Teaching English","date":"2024-04-21","arxiv_id":"2404.13764","repositories_listed":2,"syntology":null},{"url":"/paper/length-controlled-alpacaeval-a-simple-way-to","slug":"length-controlled-alpacaeval-a-simple-way-to","title":"Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators","date":"2024-04-06","arxiv_id":"2404.04475","repositories_listed":2,"syntology":null},{"url":"/paper/three-ways-of-using-large-language-models-to","slug":"three-ways-of-using-large-language-models-to","title":"Three Ways of Using Large Language Models to Evaluate Chat","date":"2023-08-12","arxiv_id":"2308.06502","repositories_listed":2,"syntology":null},{"url":"/paper/educhat-a-large-scale-language-model-based","slug":"educhat-a-large-scale-language-model-based","title":"EduChat: A Large-Scale Language Model-based Chatbot System for Intelligent Education","date":"2023-08-05","arxiv_id":"2308.02773","repositories_listed":2,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":9,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/educhat-a-large-scale-language-model-based#ran","syntology_url":"https://syntology.ai/paper/2308.02773","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.02773"}},"official":{"repos":["icalk-nlp/educhat"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/h2ogpt-democratizing-large-language-models","slug":"h2ogpt-democratizing-large-language-models","title":"h2oGPT: Democratizing Large Language Models","date":"2023-06-13","arxiv_id":"2306.08161","repositories_listed":2,"syntology":null},{"url":"/paper/task-optimized-adapters-for-an-end-to-end","slug":"task-optimized-adapters-for-an-end-to-end","title":"Task-Optimized Adapters for an End-to-End Task-Oriented Dialogue System","date":"2023-05-04","arxiv_id":"2305.02468","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/task-optimized-adapters-for-an-end-to-end#ran","syntology_url":"https://syntology.ai/paper/2305.02468","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.02468"}},"official":{"repos":["budzianowski/multiwoz","sogang-isds/TOATOD"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/chai-a-chatbot-ai-for-task-oriented-dialogue","slug":"chai-a-chatbot-ai-for-task-oriented-dialogue","title":"CHAI: A CHatbot AI for Task-Oriented Dialogue with Offline Reinforcement Learning","date":"2022-04-18","arxiv_id":"2204.08426","repositories_listed":2,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/chai-a-chatbot-ai-for-task-oriented-dialogue#ran","syntology_url":"https://syntology.ai/paper/2204.08426","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.08426"}},"official":{"repos":["siddharthverma314/chai-naacl-2022"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/eva2-0-investigating-open-domain-chinese","slug":"eva2-0-investigating-open-domain-chinese","title":"EVA2.0: Investigating Open-Domain Chinese Dialogue Systems with Large-Scale Pre-Training","date":"2022-03-17","arxiv_id":"2203.09313","repositories_listed":2,"syntology":{"n":13,"n_ran":13,"n_constructed":0,"n_ran_checked":12,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":2,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/eva2-0-investigating-open-domain-chinese#ran","syntology_url":"https://syntology.ai/paper/2203.09313","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.09313"}},"official":{"repos":["thu-coai/EVA"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/automatic-evaluation-and-moderation-of-open","slug":"automatic-evaluation-and-moderation-of-open","title":"Automatic Evaluation and Moderation of Open-domain Dialogue Systems","date":"2021-11-03","arxiv_id":"2111.02110","repositories_listed":2,"syntology":null},{"url":"/paper/few-shot-bot-prompt-based-learning-for","slug":"few-shot-bot-prompt-based-learning-for","title":"Few-Shot Bot: Prompt-Based Learning for Dialogue Systems","date":"2021-10-15","arxiv_id":"2110.08118","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/few-shot-bot-prompt-based-learning-for#ran","syntology_url":"https://syntology.ai/paper/2110.08118","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.08118"}},"official":{"repos":["andreamad8/FSB","tunib-ai/parallelformers"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/cass-towards-building-a-social-support","slug":"cass-towards-building-a-social-support","title":"CASS: Towards Building a Social-Support Chatbot for Online Health Community","date":"2021-01-04","arxiv_id":"2101.01583","repositories_listed":2,"syntology":null},{"url":"/paper/time-to-transfer-predicting-and-evaluating","slug":"time-to-transfer-predicting-and-evaluating","title":"Time to Transfer: Predicting and Evaluating Machine-Human Chatting Handoff","date":"2020-12-14","arxiv_id":"2012.07610","repositories_listed":2,"syntology":null},{"url":"/paper/pchatbot-a-large-scale-dataset-for","slug":"pchatbot-a-large-scale-dataset-for","title":"Pchatbot: A Large-Scale Dataset for Personalized Chatbot","date":"2020-09-28","arxiv_id":"2009.13284","repositories_listed":2,"syntology":null},{"url":"/paper/seq2seq-ai-chatbot-with-attention-mechanism","slug":"seq2seq-ai-chatbot-with-attention-mechanism","title":"Seq2Seq AI Chatbot with Attention Mechanism","date":"2020-06-04","arxiv_id":"2006.02767","repositories_listed":2,"syntology":null},{"url":"/paper/hhh-an-online-medical-chatbot-system-based-on-1","slug":"hhh-an-online-medical-chatbot-system-based-on-1","title":"HHH: An Online Medical Chatbot System based on Knowledge Graph and Hierarchical Bi-Directional Attention","date":"2020-02-08","arxiv_id":"2002.03140","repositories_listed":2,"syntology":null},{"url":"/paper/asking-questions-the-human-way-scalable","slug":"asking-questions-the-human-way-scalable","title":"Asking Questions the Human Way: Scalable Question-Answer Generation from Text Corpus","date":"2020-01-27","arxiv_id":"2002.00748","repositories_listed":2,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/asking-questions-the-human-way-scalable#ran","syntology_url":"https://syntology.ai/paper/2002.00748","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.00748"}},"official":{"repos":["bangliu/ACS-QG"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/towards-a-human-like-open-domain-chatbot","slug":"towards-a-human-like-open-domain-chatbot","title":"Towards a Human-like Open-Domain Chatbot","date":"2020-01-27","arxiv_id":"2001.09977","repositories_listed":2,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/towards-a-human-like-open-domain-chatbot#ran","syntology_url":"https://syntology.ai/paper/2001.09977","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2001.09977"}},"official":null}},{"url":"/paper/topic-aware-chatbot-using-recurrent-neural","slug":"topic-aware-chatbot-using-recurrent-neural","title":"Topic-aware chatbot using Recurrent Neural Networks and Nonnegative Matrix Factorization","date":"2019-12-01","arxiv_id":"1912.00315","repositories_listed":2,"syntology":null},{"url":"/paper/caire-an-end-to-end-empathetic-chatbot","slug":"caire-an-end-to-end-empathetic-chatbot","title":"CAiRE: An Empathetic Neural Chatbot","date":"2019-07-28","arxiv_id":"1907.12108","repositories_listed":2,"syntology":null},{"url":"/paper/generalized-adaptive-transfer-network","slug":"generalized-adaptive-transfer-network","title":"Generalized Adaptive Transfer Network: Enhancing Transfer Learning in Reinforcement Learning Across Domains","date":"2025-07-02","arxiv_id":"2507.03026","repositories_listed":1,"syntology":null},{"url":"/paper/medal-a-framework-for-benchmarking-llms-as","slug":"medal-a-framework-for-benchmarking-llms-as","title":"MEDAL: A Framework for Benchmarking LLMs as Multilingual Open-Domain Chatbots and Dialogue Evaluators","date":"2025-05-28","arxiv_id":"2505.22777","repositories_listed":1,"syntology":null},{"url":"/paper/is-your-llm-overcharging-you-tokenization","slug":"is-your-llm-overcharging-you-tokenization","title":"Is Your LLM Overcharging You? Tokenization, Transparency, and Incentives","date":"2025-05-27","arxiv_id":"2505.21627","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/is-your-llm-overcharging-you-tokenization#ran","syntology_url":"https://syntology.ai/paper/2505.21627","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.21627"}},"official":{"repos":["Networks-Learning/token-pricing"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["community"]}}},{"url":"/paper/a-fully-generative-motivational-interviewing","slug":"a-fully-generative-motivational-interviewing","title":"A Fully Generative Motivational Interviewing Counsellor Chatbot for Moving Smokers Towards the Decision to Quit","date":"2025-05-23","arxiv_id":"2505.17362","repositories_listed":1,"syntology":null},{"url":"/paper/swe-dev-evaluating-and-training-autonomous","slug":"swe-dev-evaluating-and-training-autonomous","title":"SWE-Dev: Evaluating and Training Autonomous Feature-Driven Software Development","date":"2025-05-22","arxiv_id":"2505.16975","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/swe-dev-evaluating-and-training-autonomous#ran","syntology_url":"https://syntology.ai/paper/2505.16975","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.16975"}},"official":{"repos":["dorothyduuu/swe-dev"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/x-mas-towards-building-multi-agent-systems","slug":"x-mas-towards-building-multi-agent-systems","title":"X-MAS: Towards Building Multi-Agent Systems with Heterogeneous LLMs","date":"2025-05-22","arxiv_id":"2505.16997","repositories_listed":1,"syntology":null},{"url":"/paper/decentralized-arena-towards-democratic-and","slug":"decentralized-arena-towards-democratic-and","title":"Decentralized Arena: Towards Democratic and Scalable Automatic Evaluation of Language Models","date":"2025-05-19","arxiv_id":"2505.12808","repositories_listed":1,"syntology":null},{"url":"/paper/what-is-stigma-attributed-to-a-theory","slug":"what-is-stigma-attributed-to-a-theory","title":"What is Stigma Attributed to? A Theory-Grounded, Expert-Annotated Interview Corpus for Demystifying Mental-Health Stigma","date":"2025-05-19","arxiv_id":"2505.12727","repositories_listed":1,"syntology":null},{"url":"/paper/social-biases-in-knowledge-representations-of","slug":"social-biases-in-knowledge-representations-of","title":"Social Biases in Knowledge Representations of Wikidata separates Global North from Global South","date":"2025-05-05","arxiv_id":"2505.02352","repositories_listed":1,"syntology":null},{"url":"/paper/cancer-myth-evaluating-ai-chatbot-on-patient","slug":"cancer-myth-evaluating-ai-chatbot-on-patient","title":"Cancer-Myth: Evaluating AI Chatbot on Patient Questions with False Presuppositions","date":"2025-04-15","arxiv_id":"2504.11373","repositories_listed":1,"syntology":null},{"url":"/paper/charm-calibrating-reward-models-with-chatbot","slug":"charm-calibrating-reward-models-with-chatbot","title":"CHARM: Calibrating Reward Models With Chatbot Arena Scores","date":"2025-04-14","arxiv_id":"2504.10045","repositories_listed":1,"syntology":null},{"url":"/paper/safechat-a-framework-for-building-trustworthy","slug":"safechat-a-framework-for-building-trustworthy","title":"SafeChat: A Framework for Building Trustworthy Collaborative Assistants and a Case Study of its Usefulness","date":"2025-04-08","arxiv_id":"2504.07995","repositories_listed":1,"syntology":null},{"url":"/paper/evaltree-profiling-language-model-weaknesses","slug":"evaltree-profiling-language-model-weaknesses","title":"EvalTree: Profiling Language Model Weaknesses via Hierarchical Capability Trees","date":"2025-03-11","arxiv_id":"2503.08893","repositories_listed":1,"syntology":null},{"url":"/paper/litlinker-supporting-the-ideation-of","slug":"litlinker-supporting-the-ideation-of","title":"LitLinker: Supporting the Ideation of Interdisciplinary Contexts with Large Language Models for Teaching Literature in Elementary Schools","date":"2025-02-22","arxiv_id":"2502.16097","repositories_listed":1,"syntology":null},{"url":"/paper/prompt-to-leaderboard","slug":"prompt-to-leaderboard","title":"Prompt-to-Leaderboard","date":"2025-02-20","arxiv_id":"2502.14855","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-personalized-health-support-through","slug":"exploring-personalized-health-support-through","title":"Exploring Personalized Health Support through Data-Driven, Theory-Guided LLMs: A Case Study in Sleep Health","date":"2025-02-19","arxiv_id":"2502.13920","repositories_listed":1,"syntology":null},{"url":"/paper/kl-penalty-control-via-perturbation-for","slug":"kl-penalty-control-via-perturbation-for","title":"KL Penalty Control via Perturbation for Direct Preference Optimization","date":"2025-02-18","arxiv_id":"2502.13177","repositories_listed":1,"syntology":null},{"url":"/paper/presumed-cultural-identity-how-names-shape","slug":"presumed-cultural-identity-how-names-shape","title":"Presumed Cultural Identity: How Names Shape LLM Responses","date":"2025-02-17","arxiv_id":"2502.11995","repositories_listed":1,"syntology":null},{"url":"/paper/knowledge-graph-driven-retrieval-augmented","slug":"knowledge-graph-driven-retrieval-augmented","title":"Knowledge Graph-Driven Retrieval-Augmented Generation: Integrating Deepseek-R1 with Weaviate for Advanced Chatbot Applications","date":"2025-02-16","arxiv_id":"2502.11108","repositories_listed":1,"syntology":null},{"url":"/paper/grammar-control-in-dialogue-response","slug":"grammar-control-in-dialogue-response","title":"Grammar Control in Dialogue Response Generation for Language Learning Chatbots","date":"2025-02-11","arxiv_id":"2502.07544","repositories_listed":1,"syntology":null},{"url":"/paper/evaluation-of-large-language-models-via","slug":"evaluation-of-large-language-models-via","title":"Evaluation of Large Language Models via Coupled Token Generation","date":"2025-02-03","arxiv_id":"2502.01754","repositories_listed":1,"syntology":null},{"url":"/paper/improving-your-model-ranking-on-chatbot-arena","slug":"improving-your-model-ranking-on-chatbot-arena","title":"Improving Your Model Ranking on Chatbot Arena by Vote Rigging","date":"2025-01-29","arxiv_id":"2501.17858","repositories_listed":1,"syntology":null},{"url":"/paper/ricota-red-teaming-of-in-the-wild","slug":"ricota-red-teaming-of-in-the-wild","title":"RICoTA: Red-teaming of In-the-wild Conversation with Test Attempts","date":"2025-01-29","arxiv_id":"2501.17715","repositories_listed":1,"syntology":null},{"url":"/paper/finding-a-voice-evaluating-african-american","slug":"finding-a-voice-evaluating-african-american","title":"Finding A Voice: Evaluating African American Dialect Generation for Chatbot Technology","date":"2025-01-07","arxiv_id":"2501.03441","repositories_listed":1,"syntology":null},{"url":"/paper/layer-level-self-exposure-and-patch","slug":"layer-level-self-exposure-and-patch","title":"Layer-Level Self-Exposure and Patch: Affirmative Token Mitigation for Jailbreak Attack Defense","date":"2025-01-05","arxiv_id":"2501.02629","repositories_listed":1,"syntology":null},{"url":"/paper/a-statistical-framework-for-ranking-llm-based","slug":"a-statistical-framework-for-ranking-llm-based","title":"A Statistical Framework for Ranking LLM-Based Chatbots","date":"2024-12-24","arxiv_id":"2412.18407","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/a-statistical-framework-for-ranking-llm-based#ran","syntology_url":"https://syntology.ai/paper/2412.18407","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.18407"}},"official":{"repos":["suquark/leaderbot"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/chai-tea-a-benchmark-for-evaluating","slug":"chai-tea-a-benchmark-for-evaluating","title":"ChaI-TeA: A Benchmark for Evaluating Autocompletion of Interactions with LLM-based Chatbots","date":"2024-12-24","arxiv_id":"2412.18377","repositories_listed":1,"syntology":null},{"url":"/paper/minigpt-pancreas-multimodal-large-language","slug":"minigpt-pancreas-multimodal-large-language","title":"MiniGPT-Pancreas: Multimodal Large Language Model for Pancreas Cancer Classification and Detection","date":"2024-12-20","arxiv_id":"2412.15925","repositories_listed":1,"syntology":null},{"url":"/paper/recsys-arena-pair-wise-recommender-system","slug":"recsys-arena-pair-wise-recommender-system","title":"RecSys Arena: Pair-wise Recommender System Evaluation with Large Language Models","date":"2024-12-15","arxiv_id":"2412.11068","repositories_listed":1,"syntology":null},{"url":"/paper/ai-predicts-agi-leveraging-agi-forecasting","slug":"ai-predicts-agi-leveraging-agi-forecasting","title":"AI Predicts AGI: Leveraging AGI Forecasting and Peer Review to Explore LLMs' Complex Reasoning Capabilities","date":"2024-12-12","arxiv_id":"2412.09385","repositories_listed":1,"syntology":null},{"url":"/paper/transitgpt-a-generative-ai-based-framework","slug":"transitgpt-a-generative-ai-based-framework","title":"TransitGPT: A Generative AI-based framework for interacting with GTFS data using Large Language Models","date":"2024-12-07","arxiv_id":"2412.06831","repositories_listed":1,"syntology":null},{"url":"/paper/glm-4-voice-towards-intelligent-and-human","slug":"glm-4-voice-towards-intelligent-and-human","title":"GLM-4-Voice: Towards Intelligent and Human-Like End-to-End Spoken Chatbot","date":"2024-12-03","arxiv_id":"2412.02612","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/glm-4-voice-towards-intelligent-and-human#ran","syntology_url":"https://syntology.ai/paper/2412.02612","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.02612"}},"official":{"repos":["thudm/glm-4-voice"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/scaling-speech-text-pre-training-with","slug":"scaling-speech-text-pre-training-with","title":"Scaling Speech-Text Pre-training with Synthetic Interleaved Data","date":"2024-11-26","arxiv_id":"2411.17607","repositories_listed":1,"syntology":null},{"url":"/paper/rv4chatbot-are-chatbots-allowed-to-dream-of","slug":"rv4chatbot-are-chatbots-allowed-to-dream-of","title":"RV4Chatbot: Are Chatbots Allowed to Dream of Electric Sheep?","date":"2024-11-21","arxiv_id":"2411.14368","repositories_listed":1,"syntology":null},{"url":"/paper/the-illusion-of-empathy-how-ai-chatbots-shape","slug":"the-illusion-of-empathy-how-ai-chatbots-shape","title":"The Illusion of Empathy: How AI Chatbots Shape Conversation Perception","date":"2024-11-19","arxiv_id":"2411.12877","repositories_listed":1,"syntology":null},{"url":"/paper/structured-dialogue-system-for-mental-health","slug":"structured-dialogue-system-for-mental-health","title":"Structured Dialogue System for Mental Health: An LLM Chatbot Leveraging the PM+ Guidelines","date":"2024-11-16","arxiv_id":"2411.10681","repositories_listed":1,"syntology":null},{"url":"/paper/intellbot-retrieval-augmented-llm-chatbot-for","slug":"intellbot-retrieval-augmented-llm-chatbot-for","title":"IntellBot: Retrieval Augmented LLM Chatbot for Cyber Threat Knowledge Delivery","date":"2024-11-08","arxiv_id":"2411.05442","repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-assist-humans-without-inferring","slug":"learning-to-assist-humans-without-inferring","title":"Learning to Assist Humans without Inferring Rewards","date":"2024-11-04","arxiv_id":"2411.02623","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/learning-to-assist-humans-without-inferring#ran","syntology_url":"https://syntology.ai/paper/2411.02623","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.02623"}},"official":{"repos":["vivekmyers/empowerment_successor_representations"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/beyond-ontology-in-dialogue-state-tracking","slug":"beyond-ontology-in-dialogue-state-tracking","title":"Beyond Ontology in Dialogue State Tracking for Goal-Oriented Chatbot","date":"2024-10-30","arxiv_id":"2410.22767","repositories_listed":1,"syntology":null},{"url":"/paper/improving-model-evaluation-using-smart","slug":"improving-model-evaluation-using-smart","title":"Improving Model Evaluation using SMART Filtering of Benchmark Datasets","date":"2024-10-26","arxiv_id":"2410.20245","repositories_listed":1,"syntology":null},{"url":"/paper/katzbot-revolutionizing-academic-chatbot-for","slug":"katzbot-revolutionizing-academic-chatbot-for","title":"KatzBot: Revolutionizing Academic Chatbot for Enhanced Communication","date":"2024-10-21","arxiv_id":"2410.16385","repositories_listed":1,"syntology":null},{"url":"/paper/does-chatgpt-have-a-poetic-style","slug":"does-chatgpt-have-a-poetic-style","title":"Does ChatGPT Have a Poetic Style?","date":"2024-10-20","arxiv_id":"2410.15299","repositories_listed":1,"syntology":null},{"url":"/paper/refusal-trained-llms-are-easily-jailbroken-as","slug":"refusal-trained-llms-are-easily-jailbroken-as","title":"Refusal-Trained LLMs Are Easily Jailbroken As Browser Agents","date":"2024-10-11","arxiv_id":"2410.13886","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":4,"n_pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/refusal-trained-llms-are-easily-jailbroken-as#ran","syntology_url":"https://syntology.ai/paper/2410.13886","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.13886"}},"official":{"repos":["scaleapi/browser-art"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-recipe-for-building-a-compliant-real-estate","slug":"a-recipe-for-building-a-compliant-real-estate","title":"A Recipe For Building a Compliant Real Estate Chatbot","date":"2024-10-07","arxiv_id":"2410.10860","repositories_listed":1,"syntology":null},{"url":"/paper/ram2c-a-liberal-arts-educational-chatbot","slug":"ram2c-a-liberal-arts-educational-chatbot","title":"RAM2C: A Liberal Arts Educational Chatbot based on Retrieval-augmented Multi-role Multi-expert Collaboration","date":"2024-09-23","arxiv_id":"2409.15461","repositories_listed":1,"syntology":null},{"url":"/paper/a-new-perspective-on-adhd-research-knowledge","slug":"a-new-perspective-on-adhd-research-knowledge","title":"A New Perspective on ADHD Research: Knowledge Graph Construction with LLMs and Network Based Insights","date":"2024-09-19","arxiv_id":"2409.12853","repositories_listed":1,"syntology":null},{"url":"/paper/what-you-say-what-you-want-teaching-humans-to","slug":"what-you-say-what-you-want-teaching-humans-to","title":"What Should We Engineer in Prompts? Training Humans in Requirement-Driven LLM Use","date":"2024-09-13","arxiv_id":"2409.08775","repositories_listed":1,"syntology":null},{"url":"/paper/unleashing-worms-and-extracting-data","slug":"unleashing-worms-and-extracting-data","title":"Unleashing Worms and Extracting Data: Escalating the Outcome of Attacks against RAG-based Inference in Scale and Severity Using Jailbreaking","date":"2024-09-12","arxiv_id":"2409.08045","repositories_listed":1,"syntology":null},{"url":"/paper/bio-eng-lmm-ai-assist-chatbot-a-comprehensive","slug":"bio-eng-lmm-ai-assist-chatbot-a-comprehensive","title":"Bio-Eng-LMM AI Assist chatbot: A Comprehensive Tool for Research and Education","date":"2024-09-11","arxiv_id":"2409.07110","repositories_listed":1,"syntology":null},{"url":"/paper/bioinformatics-retrieval-augmentation-data","slug":"bioinformatics-retrieval-augmentation-data","title":"Language Model Powered Digital Biology with BRAD","date":"2024-09-04","arxiv_id":"2409.02864","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-llm-scheduling-by-learning-to-rank","slug":"efficient-llm-scheduling-by-learning-to-rank","title":"Efficient LLM Scheduling by Learning to Rank","date":"2024-08-28","arxiv_id":"2408.15792","repositories_listed":1,"syntology":{"n":3,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 3 unverified","sample_list":"/paper/efficient-llm-scheduling-by-learning-to-rank#ran","syntology_url":"https://syntology.ai/paper/2408.15792","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.15792"}},"official":{"repos":["hao-ai-lab/vllm-ltr"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}},{"url":"/paper/retail-gpt-leveraging-retrieval-augmented","slug":"retail-gpt-leveraging-retrieval-augmented","title":"Retail-GPT: leveraging Retrieval Augmented Generation (RAG) for building E-commerce Chat Assistants","date":"2024-08-15","arxiv_id":"2408.08925","repositories_listed":1,"syntology":null},{"url":"/paper/ifship-a-large-vision-language-model-for","slug":"ifship-a-large-vision-language-model-for","title":"IFShip: Interpretable Fine-grained Ship Classification with Domain Knowledge-Enhanced Vision-Language Models","date":"2024-08-13","arxiv_id":"2408.06631","repositories_listed":1,"syntology":null},{"url":"/paper/a-jailbroken-genai-model-can-cause","slug":"a-jailbroken-genai-model-can-cause","title":"A Jailbroken GenAI Model Can Cause Substantial Harm: GenAI-powered Applications are Vulnerable to PromptWares","date":"2024-08-09","arxiv_id":"2408.05061","repositories_listed":1,"syntology":null},{"url":"/paper/improving-ontology-requirements-engineering","slug":"improving-ontology-requirements-engineering","title":"Improving Ontology Requirements Engineering with OntoChat and Participatory Prompting","date":"2024-08-09","arxiv_id":"2408.15256","repositories_listed":1,"syntology":null},{"url":"/paper/conversational-ai-powered-by-large-language","slug":"conversational-ai-powered-by-large-language","title":"Conversational AI Powered by Large Language Models Amplifies False Memories in Witness Interviews","date":"2024-08-08","arxiv_id":"2408.04681","repositories_listed":1,"syntology":null},{"url":"/paper/solo-escuchame-spanish-emotional","slug":"solo-escuchame-spanish-emotional","title":"Sólo Escúchame: Spanish Emotional Accompaniment Chatbot","date":"2024-08-03","arxiv_id":"2408.01852","repositories_listed":1,"syntology":null},{"url":"/paper/prometheus-chatbot-knowledge-graph","slug":"prometheus-chatbot-knowledge-graph","title":"Prometheus Chatbot: Knowledge Graph Collaborative Large Language Model for Computer Components Recommendation","date":"2024-07-29","arxiv_id":"2407.19643","repositories_listed":1,"syntology":null},{"url":"/paper/interactive-learning-in-computer-science","slug":"interactive-learning-in-computer-science","title":"Interactive Learning in Computer Science Education Supported by a Discord Chatbot","date":"2024-07-27","arxiv_id":"2407.19266","repositories_listed":1,"syntology":null},{"url":"/paper/psydi-towards-a-personalized-and","slug":"psydi-towards-a-personalized-and","title":"PsyDI: Towards a Personalized and Progressively In-depth Chatbot for Psychological Measurements","date":"2024-07-22","arxiv_id":"2408.03337","repositories_listed":1,"syntology":null}],"syntology_records":27,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_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'","n_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":19,"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/chatbot-on-alpacaeval","since_archive":"/sota/chatbot-on-alpacaeval#since-judged","papers_judged":19,"placed":0}]},"papers_where_code_ran":56,"papers_where_code_ran_first_page":"/task/chatbot/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":10,"url":"/task/chatbot/papers/2","json":"/task/chatbot/papers/2.json","rows":100},{"order":"archive","page":3,"of":10,"url":"/task/chatbot/papers/3","json":"/task/chatbot/papers/3.json","rows":100},{"order":"archive","page":4,"of":10,"url":"/task/chatbot/papers/4","json":"/task/chatbot/papers/4.json","rows":100},{"order":"archive","page":5,"of":10,"url":"/task/chatbot/papers/5","json":"/task/chatbot/papers/5.json","rows":100},{"order":"archive","page":6,"of":10,"url":"/task/chatbot/papers/6","json":"/task/chatbot/papers/6.json","rows":100},{"order":"archive","page":7,"of":10,"url":"/task/chatbot/papers/7","json":"/task/chatbot/papers/7.json","rows":100},{"order":"archive","page":8,"of":10,"url":"/task/chatbot/papers/8","json":"/task/chatbot/papers/8.json","rows":100},{"order":"archive","page":9,"of":10,"url":"/task/chatbot/papers/9","json":"/task/chatbot/papers/9.json","rows":100},{"order":"archive","page":10,"of":10,"url":"/task/chatbot/papers/10","json":"/task/chatbot/papers/10.json","rows":71},{"order":"ran","page":1,"of":1,"url":"/task/chatbot/papers/ran/1","json":"/task/chatbot/papers/ran/1.json","rows":56}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper 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"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"db1ad7d6fd12975e6aa165d80d7b1d73377b05dca05187329e81d0931d1cedb5","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}