{"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 (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":41,"tagged_in_all":109,"items":[{"url":"/paper/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","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_unverified":1,"n_pointer_only":0}},{"url":"/paper/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","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","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","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","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","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_unverified":1,"n_pointer_only":0}},{"url":"/paper/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","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","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","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","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":0,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/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","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","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","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","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","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_unverified":1,"n_pointer_only":4}},{"url":"/paper/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_unverified":0,"n_pointer_only":2}},{"url":"/paper/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","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","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_unverified":0,"n_pointer_only":0}},{"url":"/paper/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","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_unverified":4,"n_pointer_only":0}},{"url":"/paper/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","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","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_unverified":1,"n_pointer_only":1}},{"url":"/paper/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","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}],"syntology_records":8,"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"},"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":"2026-09-24T18:15:14+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; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"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"}}