{"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/small-language-model","name":"Small Language Model","slug":"small-language-model","description_markdown":null,"categories":[],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"derived"},"counts":{"papers_tagged":109,"papers_with_code":41,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"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":0,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[],"subtasks":[],"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":2,"rows_per_page":100,"shown":100,"of":109,"of_with_code":41,"tagged_in_all":109,"counts":{"archive_papers_tagged":109,"with_a_code_link":41,"where_syntology_ran_a_sample":11,"not_listed_spam_title":0,"listed":109,"listed_where_code_ran":11,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":9,"every_run_a_failure_of_syntologys_instrument":2,"listed_with_a_run_with_no_instrument_failure":9,"listed_every_run_a_failure_of_syntologys_instrument":2,"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/atla-selene-mini-a-general-purpose-evaluation","slug":"atla-selene-mini-a-general-purpose-evaluation","title":"Atla Selene Mini: A General Purpose Evaluation Model","date":"2025-01-27","arxiv_id":"2501.17195","repositories_listed":2,"syntology":null},{"url":"/paper/tinyllama-an-open-source-small-language-model","slug":"tinyllama-an-open-source-small-language-model","title":"TinyLlama: An Open-Source Small Language Model","date":"2024-01-04","arxiv_id":"2401.02385","repositories_listed":2,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":4,"n_instrument":4,"n_unverified":1,"n_honours":2,"n_violates":2,"n_no_contract":0,"n_pointer_only":2,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 2 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/tinyllama-an-open-source-small-language-model#ran","syntology_url":"https://syntology.ai/paper/2401.02385","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.02385"}},"official":{"repos":["Lightning-AI/lit-gpt","jzhang38/tinyllama"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/lightweight-relevance-grader-in-rag","slug":"lightweight-relevance-grader-in-rag","title":"Lightweight Relevance Grader in RAG","date":"2025-06-17","arxiv_id":"2506.14084","repositories_listed":1,"syntology":null},{"url":"/paper/prompt-candidates-then-distill-a-teacher","slug":"prompt-candidates-then-distill-a-teacher","title":"Prompt Candidates, then Distill: A Teacher-Student Framework for LLM-driven Data Annotation","date":"2025-06-04","arxiv_id":"2506.03857","repositories_listed":1,"syntology":null},{"url":"/paper/zero-shot-vision-encoder-grafting-via-llm","slug":"zero-shot-vision-encoder-grafting-via-llm","title":"Zero-Shot Vision Encoder Grafting via LLM Surrogates","date":"2025-05-28","arxiv_id":"2505.22664","repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-online-data-to-enhance-medical","slug":"leveraging-online-data-to-enhance-medical","title":"Leveraging Online Data to Enhance Medical Knowledge in a Small Persian Language Model","date":"2025-05-21","arxiv_id":"2505.16000","repositories_listed":1,"syntology":null},{"url":"/paper/crave-a-conflicting-reasoning-approach-for","slug":"crave-a-conflicting-reasoning-approach-for","title":"CRAVE: A Conflicting Reasoning Approach for Explainable Claim Verification Using LLMs","date":"2025-04-21","arxiv_id":"2504.14905","repositories_listed":1,"syntology":null},{"url":"/paper/collab-rag-boosting-retrieval-augmented","slug":"collab-rag-boosting-retrieval-augmented","title":"Collab-RAG: Boosting Retrieval-Augmented Generation for Complex Question Answering via White-Box and Black-Box LLM Collaboration","date":"2025-04-07","arxiv_id":"2504.04915","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":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/collab-rag-boosting-retrieval-augmented#ran","syntology_url":"https://syntology.ai/paper/2504.04915","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.04915"}},"official":{"repos":["ritaranx/collab-rag"],"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/mobile-videogpt-fast-and-accurate-video","slug":"mobile-videogpt-fast-and-accurate-video","title":"Mobile-VideoGPT: Fast and Accurate Video Understanding Language Model","date":"2025-03-27","arxiv_id":"2503.21782","repositories_listed":1,"syntology":null},{"url":"/paper/distributed-llms-and-multimodal-large","slug":"distributed-llms-and-multimodal-large","title":"Distributed LLMs and Multimodal Large Language Models: A Survey on Advances, Challenges, and Future Directions","date":"2025-03-20","arxiv_id":"2503.16585","repositories_listed":1,"syntology":null},{"url":"/paper/small-language-model-makes-an-effective-long","slug":"small-language-model-makes-an-effective-long","title":"Small Language Model Makes an Effective Long Text Extractor","date":"2025-02-11","arxiv_id":"2502.07286","repositories_listed":1,"syntology":null},{"url":"/paper/adaptivelog-an-adaptive-log-analysis","slug":"adaptivelog-an-adaptive-log-analysis","title":"AdaptiveLog: An Adaptive Log Analysis Framework with the Collaboration of Large and Small Language Model","date":"2025-01-19","arxiv_id":"2501.11031","repositories_listed":1,"syntology":null},{"url":"/paper/embodied-cot-distillation-from-llm-to-off-the","slug":"embodied-cot-distillation-from-llm-to-off-the","title":"Embodied CoT Distillation From LLM To Off-the-shelf Agents","date":"2024-12-16","arxiv_id":"2412.11499","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":3,"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) · 3 unverified","sample_list":"/paper/embodied-cot-distillation-from-llm-to-off-the#ran","syntology_url":"https://syntology.ai/paper/2412.11499","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.11499"}},"official":{"repos":["osu-nlp-group/llm-planner"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/is-training-data-quality-or-quantity-more","slug":"is-training-data-quality-or-quantity-more","title":"Is Training Data Quality or Quantity More Impactful to Small Language Model Performance?","date":"2024-11-24","arxiv_id":"2411.15821","repositories_listed":1,"syntology":null},{"url":"/paper/codesam-source-code-representation-learning","slug":"codesam-source-code-representation-learning","title":"CodeSAM: Source Code Representation Learning by Infusing Self-Attention with Multi-Code-View Graphs","date":"2024-11-21","arxiv_id":"2411.14611","repositories_listed":1,"syntology":null},{"url":"/paper/preempting-text-sanitization-utility-in","slug":"preempting-text-sanitization-utility-in","title":"Preempting Text Sanitization Utility in Resource-Constrained Privacy-Preserving LLM Interactions","date":"2024-11-18","arxiv_id":"2411.11521","repositories_listed":1,"syntology":null},{"url":"/paper/phonelm-an-efficient-and-capable-small","slug":"phonelm-an-efficient-and-capable-small","title":"PhoneLM:an Efficient and Capable Small Language Model Family through Principled Pre-training","date":"2024-11-07","arxiv_id":"2411.05046","repositories_listed":1,"syntology":null},{"url":"/paper/teleoracle-fine-tuned-retrieval-augmented","slug":"teleoracle-fine-tuned-retrieval-augmented","title":"TeleOracle: Fine-Tuned Retrieval-Augmented Generation with Long-Context Support for Network","date":"2024-11-04","arxiv_id":"2411.02617","repositories_listed":1,"syntology":null},{"url":"/paper/improving-in-context-learning-with-small","slug":"improving-in-context-learning-with-small","title":"Improving In-Context Learning with Small Language Model Ensembles","date":"2024-10-29","arxiv_id":"2410.21868","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"3 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; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/improving-in-context-learning-with-small#ran","syntology_url":"https://syntology.ai/paper/2410.21868","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.21868"}},"official":{"repos":["mehdimojarradi/Ensemble-SuperICL"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/bilinear-mlps-enable-weight-based-mechanistic","slug":"bilinear-mlps-enable-weight-based-mechanistic","title":"Bilinear MLPs enable weight-based mechanistic interpretability","date":"2024-10-10","arxiv_id":"2410.08417","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/bilinear-mlps-enable-weight-based-mechanistic#ran","syntology_url":"https://syntology.ai/paper/2410.08417","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.08417"}},"official":{"repos":["tdooms/bilinear-decomposition"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/small-language-models-can-outperform-humans","slug":"small-language-models-can-outperform-humans","title":"Small Language Models can Outperform Humans in Short Creative Writing: A Study Comparing SLMs with Humans and LLMs","date":"2024-09-17","arxiv_id":"2409.11547","repositories_listed":1,"syntology":null},{"url":"/paper/anymatch-efficient-zero-shot-entity-matching","slug":"anymatch-efficient-zero-shot-entity-matching","title":"AnyMatch -- Efficient Zero-Shot Entity Matching with a Small Language Model","date":"2024-09-06","arxiv_id":"2409.04073","repositories_listed":1,"syntology":null},{"url":"/paper/tinyagent-function-calling-at-the-edge","slug":"tinyagent-function-calling-at-the-edge","title":"TinyAgent: Function Calling at the Edge","date":"2024-09-01","arxiv_id":"2409.00608","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":1,"n_no_contract":0,"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, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/tinyagent-function-calling-at-the-edge#ran","syntology_url":"https://syntology.ai/paper/2409.00608","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.00608"}},"official":{"repos":["squeezeailab/tinyagent"],"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/assessing-generative-language-models-in","slug":"assessing-generative-language-models-in","title":"Assessing Generative Language Models in Classification Tasks: Performance and Self-Evaluation Capabilities in the Environmental and Climate Change Domain","date":"2024-08-30","arxiv_id":"2408.17362","repositories_listed":1,"syntology":null},{"url":"/paper/llamaduo-llmops-pipeline-for-seamless","slug":"llamaduo-llmops-pipeline-for-seamless","title":"LlamaDuo: LLMOps Pipeline for Seamless Migration from Service LLMs to Small-Scale Local LLMs","date":"2024-08-24","arxiv_id":"2408.13467","repositories_listed":1,"syntology":{"n":14,"n_ran":10,"n_constructed":0,"n_ran_checked":6,"n_instrument":4,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/llamaduo-llmops-pipeline-for-seamless#ran","syntology_url":"https://syntology.ai/paper/2408.13467","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.13467"}},"official":{"repos":["deep-diver/llamaduo"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/slm-meets-llm-balancing-latency","slug":"slm-meets-llm-balancing-latency","title":"SLM Meets LLM: Balancing Latency, Interpretability and Consistency in Hallucination Detection","date":"2024-08-22","arxiv_id":"2408.12748","repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-fine-tuned-retrieval-augmented","slug":"leveraging-fine-tuned-retrieval-augmented","title":"Leveraging Fine-Tuned Retrieval-Augmented Generation with Long-Context Support: For 3GPP Standards","date":"2024-08-21","arxiv_id":"2408.11775","repositories_listed":1,"syntology":null},{"url":"/paper/versusdebias-universal-zero-shot-debiasing","slug":"versusdebias-universal-zero-shot-debiasing","title":"VersusDebias: Universal Zero-Shot Debiasing for Text-to-Image Models via SLM-Based Prompt Engineering and Generative Adversary","date":"2024-07-28","arxiv_id":"2407.19524","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/versusdebias-universal-zero-shot-debiasing#ran","syntology_url":"https://syntology.ai/paper/2407.19524","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.19524"}},"official":{"repos":["versusdebias/versusdebias"],"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/tinystyler-efficient-few-shot-text-style","slug":"tinystyler-efficient-few-shot-text-style","title":"TinyStyler: Efficient Few-Shot Text Style Transfer with Authorship Embeddings","date":"2024-06-21","arxiv_id":"2406.15586","repositories_listed":1,"syntology":null},{"url":"/paper/small-e-small-language-model-with-linear","slug":"small-e-small-language-model-with-linear","title":"Small-E: Small Language Model with Linear Attention for Efficient Speech Synthesis","date":"2024-06-06","arxiv_id":"2406.04467","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-medical-question-answering-with","slug":"efficient-medical-question-answering-with","title":"Efficient Medical Question Answering with Knowledge-Augmented Question Generation","date":"2024-05-23","arxiv_id":"2405.14654","repositories_listed":1,"syntology":null},{"url":"/paper/xampler-learning-to-retrieve-cross-lingual-in","slug":"xampler-learning-to-retrieve-cross-lingual-in","title":"XAMPLER: Learning to Retrieve Cross-Lingual In-Context Examples","date":"2024-05-08","arxiv_id":"2405.05116","repositories_listed":1,"syntology":null},{"url":"/paper/cofipara-a-coarse-to-fine-paradigm-for","slug":"cofipara-a-coarse-to-fine-paradigm-for","title":"CofiPara: A Coarse-to-fine Paradigm for Multimodal Sarcasm Target Identification with Large Multimodal Models","date":"2024-05-01","arxiv_id":"2405.00390","repositories_listed":1,"syntology":{"n":21,"n_ran":18,"n_constructed":0,"n_ran_checked":18,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":18,"n_pointer_only":21,"phrase":"18 ran (of which 0 constructed an object rather than computing a result; 18 with no instrument failure: 0 honoured, 0 violated, 18 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/cofipara-a-coarse-to-fine-paradigm-for#ran","syntology_url":"https://syntology.ai/paper/2405.00390","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.00390"}},"official":{"repos":["lbotirx/cofipara"],"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"]}}},{"url":"/paper/cognitive-visual-language-mapper-advancing","slug":"cognitive-visual-language-mapper-advancing","title":"Cognitive Visual-Language Mapper: Advancing Multimodal Comprehension with Enhanced Visual Knowledge Alignment","date":"2024-02-21","arxiv_id":"2402.13561","repositories_listed":1,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":4,"n_honours":1,"n_violates":1,"n_no_contract":2,"n_pointer_only":10,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 1 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/cognitive-visual-language-mapper-advancing#ran","syntology_url":"https://syntology.ai/paper/2402.13561","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.13561"}},"official":{"repos":["hitsz-tmg/cognitive-visual-language-mapper"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/grasping-the-essentials-tailoring-large","slug":"grasping-the-essentials-tailoring-large","title":"Grasping the Essentials: Tailoring Large Language Models for Zero-Shot Relation Extraction","date":"2024-02-17","arxiv_id":"2402.11142","repositories_listed":1,"syntology":null},{"url":"/paper/towards-explainable-harmful-meme-detection","slug":"towards-explainable-harmful-meme-detection","title":"Towards Explainable Harmful Meme Detection through Multimodal Debate between Large Language Models","date":"2024-01-24","arxiv_id":"2401.13298","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"4 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; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/towards-explainable-harmful-meme-detection#ran","syntology_url":"https://syntology.ai/paper/2401.13298","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.13298"}},"official":{"repos":["hkbunlp/explainhm-www2024"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/llava-ph-efficient-multi-modal-assistant-with","slug":"llava-ph-efficient-multi-modal-assistant-with","title":"LLaVA-Phi: Efficient Multi-Modal Assistant with Small Language Model","date":"2024-01-04","arxiv_id":"2401.02330","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":3,"n_honours":2,"n_violates":1,"n_no_contract":0,"n_pointer_only":9,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/llava-ph-efficient-multi-modal-assistant-with#ran","syntology_url":"https://syntology.ai/paper/2401.02330","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.02330"}},"official":{"repos":["zhuyiche/llava-phi"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/soul-towards-sentiment-and-opinion","slug":"soul-towards-sentiment-and-opinion","title":"SOUL: Towards Sentiment and Opinion Understanding of Language","date":"2023-10-27","arxiv_id":"2310.17924","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/soul-towards-sentiment-and-opinion#ran","syntology_url":"https://syntology.ai/paper/2310.17924","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.17924"}},"official":{"repos":["damo-nlp-sg/soul"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/pive-prompting-with-iterative-verification","slug":"pive-prompting-with-iterative-verification","title":"PiVe: Prompting with Iterative Verification Improving Graph-based Generative Capability of LLMs","date":"2023-05-21","arxiv_id":"2305.12392","repositories_listed":1,"syntology":null},{"url":"/paper/the-birth-of-bias-a-case-study-on-the-1","slug":"the-birth-of-bias-a-case-study-on-the-1","title":"The Birth of Bias: A case study on the evolution of gender bias in an English language model","date":"2022-07-21","arxiv_id":"2207.10245","repositories_listed":1,"syntology":null},{"url":"/paper/siamese-bert-based-model-for-web-search","slug":"siamese-bert-based-model-for-web-search","title":"Siamese BERT-based Model for Web Search Relevance Ranking Evaluated on a New Czech Dataset","date":"2021-12-03","arxiv_id":"2112.01810","repositories_listed":1,"syntology":null},{"url":null,"slug":"scaling-up-rl-unlocking-diverse-reasoning-in","title":"Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training","date":"2025-07-16","arxiv_id":"2507.12507","repositories_listed":0,"syntology":null},{"url":null,"slug":"domain-adaptive-small-language-models-for","title":"Domain-Adaptive Small Language Models for Structured Tax Code Prediction","date":"2025-07-15","arxiv_id":"2507.10880","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-privacy-preserving-and-personalized","title":"Towards Privacy-Preserving and Personalized Smart Homes via Tailored Small Language Models","date":"2025-07-10","arxiv_id":"2507.08878","repositories_listed":0,"syntology":null},{"url":null,"slug":"biomed-enriched-a-biomedical-dataset-enriched","title":"Biomed-Enriched: A Biomedical Dataset Enriched with LLMs for Pretraining and Extracting Rare and Hidden Content","date":"2025-06-25","arxiv_id":"2506.20331","repositories_listed":0,"syntology":null},{"url":null,"slug":"counterfactual-influence-as-a-distributional","title":"Counterfactual Influence as a Distributional Quantity","date":"2025-06-25","arxiv_id":"2506.20481","repositories_listed":0,"syntology":null},{"url":null,"slug":"distilling-on-device-language-models-for","title":"Distilling On-device Language Models for Robot Planning with Minimal Human Intervention","date":"2025-06-20","arxiv_id":"2506.17486","repositories_listed":0,"syntology":null},{"url":null,"slug":"hyper-literature-grounded-hypothesis","title":"HypER: Literature-grounded Hypothesis Generation and Distillation with Provenance","date":"2025-06-15","arxiv_id":"2506.12937","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-a-small-language-model-lifecycle","title":"Towards a Small Language Model Lifecycle Framework","date":"2025-06-09","arxiv_id":"2506.07695","repositories_listed":0,"syntology":null},{"url":null,"slug":"whisq-cross-modal-representation-learning-for","title":"WhisQ: Cross-Modal Representation Learning for Text-to-Music MOS Prediction","date":"2025-06-06","arxiv_id":"2506.05899","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-task-vectors-for-large-language","title":"Adaptive Task Vectors for Large Language Models","date":"2025-06-03","arxiv_id":"2506.03426","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-lightweight-multi-expert-generative","title":"A Lightweight Multi-Expert Generative Language Model System for Engineering Information and Knowledge Extraction","date":"2025-05-27","arxiv_id":"2505.21109","repositories_listed":0,"syntology":null},{"url":null,"slug":"skip-thinking-chunk-wise-chain-of-thought","title":"Skip-Thinking: Chunk-wise Chain-of-Thought Distillation Enable Smaller Language Models to Reason Better and Faster","date":"2025-05-24","arxiv_id":"2505.18642","repositories_listed":0,"syntology":null},{"url":null,"slug":"communication-efficient-hybrid-language-model","title":"Communication-Efficient Hybrid Language Model via Uncertainty-Aware Opportunistic and Compressed Transmission","date":"2025-05-17","arxiv_id":"2505.11788","repositories_listed":0,"syntology":null},{"url":null,"slug":"tinyrs-r1-compact-multimodal-language-model","title":"TinyRS-R1: Compact Multimodal Language Model for Remote Sensing","date":"2025-05-17","arxiv_id":"2505.12099","repositories_listed":0,"syntology":null},{"url":null,"slug":"milchat-introducing-chain-of-thought","title":"MilChat: Introducing Chain of Thought Reasoning and GRPO to a Multimodal Small Language Model for Remote Sensing","date":"2025-05-12","arxiv_id":"2505.07984","repositories_listed":0,"syntology":null},{"url":null,"slug":"sadeed-advancing-arabic-diacritization","title":"Sadeed: Advancing Arabic Diacritization Through Small Language Model","date":"2025-04-30","arxiv_id":"2504.21635","repositories_listed":0,"syntology":null},{"url":null,"slug":"simplifying-data-integration-slm-driven","title":"Simplifying Data Integration: SLM-Driven Systems for Unified Semantic Queries Across Heterogeneous Databases","date":"2025-04-08","arxiv_id":"2504.05634","repositories_listed":0,"syntology":null},{"url":null,"slug":"biomedical-question-answering-via-multi-level","title":"Biomedical Question Answering via Multi-Level Summarization on a Local Knowledge Graph","date":"2025-04-02","arxiv_id":"2504.01309","repositories_listed":0,"syntology":null},{"url":null,"slug":"distil-xlstm-learning-attention-mechanisms","title":"Distil-xLSTM: Learning Attention Mechanisms through Recurrent Structures","date":"2025-03-24","arxiv_id":"2503.18565","repositories_listed":0,"syntology":null},{"url":null,"slug":"audio-flamingo-2-an-audio-language-model-with","title":"Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilities","date":"2025-03-06","arxiv_id":"2503.03983","repositories_listed":0,"syntology":null},{"url":null,"slug":"2503-01151","title":"ReaderLM-v2: Small Language Model for HTML to Markdown and JSON","date":"2025-03-03","arxiv_id":"2503.01151","repositories_listed":0,"syntology":null},{"url":null,"slug":"bridging-the-gap-enabling-natural-language","title":"Bridging the Gap: Enabling Natural Language Queries for NoSQL Databases through Text-to-NoSQL Translation","date":"2025-02-16","arxiv_id":"2502.11201","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-achieving-concept-completeness-for","title":"Towards Achieving Concept Completeness for Textual Concept Bottleneck Models","date":"2025-02-16","arxiv_id":"2502.11100","repositories_listed":0,"syntology":null},{"url":null,"slug":"3d-grounded-vision-language-framework-for","title":"3D-Grounded Vision-Language Framework for Robotic Task Planning: Automated Prompt Synthesis and Supervised Reasoning","date":"2025-02-13","arxiv_id":"2502.08903","repositories_listed":0,"syntology":null},{"url":null,"slug":"adapt-pruner-adaptive-structural-pruning-for","title":"Adapt-Pruner: Adaptive Structural Pruning for Efficient Small Language Model Training","date":"2025-02-05","arxiv_id":"2502.03460","repositories_listed":0,"syntology":null},{"url":null,"slug":"smollm2-when-smol-goes-big-data-centric","title":"SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model","date":"2025-02-04","arxiv_id":"2502.02737","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-superficial-patterns-to-semantic","title":"From Superficial Patterns to Semantic Understanding: Fine-Tuning Language Models on Contrast Sets","date":"2025-01-05","arxiv_id":"2501.02683","repositories_listed":0,"syntology":null},{"url":null,"slug":"technical-report-small-language-model-for","title":"Technical Report: Small Language Model for Japanese Clinical and Medicine","date":"2024-12-21","arxiv_id":"2412.16423","repositories_listed":0,"syntology":null},{"url":null,"slug":"uncertainty-aware-hybrid-inference-with-on","title":"Uncertainty-Aware Hybrid Inference with On-Device Small and Remote Large Language Models","date":"2024-12-17","arxiv_id":"2412.12687","repositories_listed":0,"syntology":null},{"url":null,"slug":"small-language-model-as-data-prospector-for","title":"Small Language Model as Data Prospector for Large Language Model","date":"2024-12-13","arxiv_id":"2412.09990","repositories_listed":0,"syntology":null},{"url":null,"slug":"jppo-joint-power-and-prompt-optimization-for","title":"JPPO: Joint Power and Prompt Optimization for Accelerated Large Language Model Services","date":"2024-11-27","arxiv_id":"2411.18010","repositories_listed":0,"syntology":null},{"url":null,"slug":"radphi-3-small-language-models-for-radiology","title":"RadPhi-3: Small Language Models for Radiology","date":"2024-11-19","arxiv_id":"2411.13604","repositories_listed":0,"syntology":null},{"url":null,"slug":"slimlm-an-efficient-small-language-model-for","title":"SlimLM: An Efficient Small Language Model for On-Device Document Assistance","date":"2024-11-15","arxiv_id":"2411.09944","repositories_listed":0,"syntology":null},{"url":null,"slug":"secencoder-logs-are-all-you-need-in-security","title":"SecEncoder: Logs are All You Need in Security","date":"2024-11-12","arxiv_id":"2411.07528","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-multi-modal-mastery-a-4-5b-parameter","title":"Towards Multi-Modal Mastery: A 4.5B Parameter Truly Multi-Modal Small Language Model","date":"2024-11-08","arxiv_id":"2411.05903","repositories_listed":0,"syntology":null},{"url":null,"slug":"wave-network-an-ultra-small-language-model","title":"Wave Network: An Ultra-Small Language Model","date":"2024-11-04","arxiv_id":"2411.02674","repositories_listed":0,"syntology":null},{"url":null,"slug":"humanizing-the-machine-proxy-attacks-to","title":"Humanizing the Machine: Proxy Attacks to Mislead LLM Detectors","date":"2024-10-25","arxiv_id":"2410.19230","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-little-help-goes-a-long-way-efficient-llm","title":"A Little Help Goes a Long Way: Efficient LLM Training by Leveraging Small LMs","date":"2024-10-24","arxiv_id":"2410.18779","repositories_listed":0,"syntology":null},{"url":null,"slug":"methods-of-improving-llm-training-stability","title":"Methods of improving LLM training stability","date":"2024-10-22","arxiv_id":"2410.16682","repositories_listed":0,"syntology":null},{"url":null,"slug":"bridging-large-language-models-and-graph","title":"Bridging Large Language Models and Graph Structure Learning Models for Robust Representation Learning","date":"2024-10-15","arxiv_id":"2410.12096","repositories_listed":0,"syntology":null},{"url":"/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","repositories_listed":0,"syntology":null},{"url":null,"slug":"generating-long-horizon-stock-buy-signals","title":"Generating long-horizon stock \"buy\" signals with a neural language model","date":"2024-10-09","arxiv_id":"2410.18988","repositories_listed":0,"syntology":null},{"url":null,"slug":"personal-intelligence-system-unilm-hybrid-on","title":"Personal Intelligence System UniLM: Hybrid On-Device Small Language Model and Server-Based Large Language Model for Malay Nusantara","date":"2024-10-09","arxiv_id":"2410.06973","repositories_listed":0,"syntology":null},{"url":null,"slug":"decoratelm-data-engineering-through-corpus","title":"DecorateLM: Data Engineering through Corpus Rating, Tagging, and Editing with Language Models","date":"2024-10-08","arxiv_id":"2410.05639","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-lingual-transfer-for-automatic-question","title":"Cross-lingual Transfer for Automatic Question Generation by Learning Interrogative Structures in Target Languages","date":"2024-10-04","arxiv_id":"2410.03197","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-domain-content-generation-with-domain","title":"Cross-Domain Content Generation with Domain-Specific Small Language Models","date":"2024-09-19","arxiv_id":"2409.17171","repositories_listed":0,"syntology":null},{"url":null,"slug":"small-language-models-are-equation-reasoners","title":"Small Language Models are Equation Reasoners","date":"2024-09-19","arxiv_id":"2409.12393","repositories_listed":0,"syntology":null},{"url":null,"slug":"inkubalm-a-small-language-model-for-low","title":"InkubaLM: A small language model for low-resource African languages","date":"2024-08-30","arxiv_id":"2408.17024","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-domain-robust-lightweight-reward","title":"Exploring Domain Robust Lightweight Reward Models based on Router Mechanism","date":"2024-07-24","arxiv_id":"2407.17546","repositories_listed":0,"syntology":null},{"url":null,"slug":"graph-structured-speculative-decoding","title":"Graph-Structured Speculative Decoding","date":"2024-07-23","arxiv_id":"2407.16207","repositories_listed":0,"syntology":null},{"url":null,"slug":"rdbe-reasoning-distillation-based-evaluation","title":"RDBE: Reasoning Distillation-Based Evaluation Enhances Automatic Essay Scoring","date":"2024-07-03","arxiv_id":"2407.13781","repositories_listed":0,"syntology":null},{"url":null,"slug":"pdss-a-privacy-preserving-framework-for-step","title":"PDSS: A Privacy-Preserving Framework for Step-by-Step Distillation of Large Language Models","date":"2024-06-18","arxiv_id":"2406.12403","repositories_listed":0,"syntology":null},{"url":null,"slug":"hare-human-priors-a-key-to-small-language","title":"HARE: HumAn pRiors, a key to small language model Efficiency","date":"2024-06-17","arxiv_id":"2406.11410","repositories_listed":0,"syntology":null},{"url":null,"slug":"plug-and-play-with-prompts-a-prompt-tuning","title":"Plug and Play with Prompts: A Prompt Tuning Approach for Controlling Text Generation","date":"2024-04-08","arxiv_id":"2404.05143","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-pareto-optimal-throughput-in-small","title":"Towards Pareto Optimal Throughput in Small Language Model Serving","date":"2024-04-04","arxiv_id":"2404.03353","repositories_listed":0,"syntology":null},{"url":null,"slug":"think-big-generate-quick-llm-to-slm-for-fast","title":"Think Big, Generate Quick: LLM-to-SLM for Fast Autoregressive Decoding","date":"2024-02-26","arxiv_id":"2402.16844","repositories_listed":0,"syntology":null},{"url":null,"slug":"recursive-speculative-decoding-accelerating","title":"Recursive Speculative Decoding: Accelerating LLM Inference via Sampling Without Replacement","date":"2024-02-21","arxiv_id":"2402.14160","repositories_listed":0,"syntology":null},{"url":null,"slug":"purifying-large-language-models-by-ensembling","title":"Purifying Large Language Models by Ensembling a Small Language Model","date":"2024-02-19","arxiv_id":"2402.14845","repositories_listed":0,"syntology":null},{"url":"/paper/small-language-model-meets-with-reinforced","slug":"small-language-model-meets-with-reinforced","title":"Small Language Model Meets with Reinforced Vision Vocabulary","date":"2024-01-23","arxiv_id":"2401.12503","repositories_listed":0,"syntology":null}],"syntology_records":13,"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":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"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":[]},"papers_where_code_ran":11,"papers_where_code_ran_first_page":"/task/small-language-model/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":2,"url":"/task/small-language-model/papers/2","json":"/task/small-language-model/papers/2.json","rows":9},{"order":"ran","page":1,"of":1,"url":"/task/small-language-model/papers/ran/1","json":"/task/small-language-model/papers/ran/1.json","rows":11}],"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":"322e1c1dc220429d06ba14c4df3a33944dd53a1f91bea666fb1051aefc93bf9c","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}