{"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":"/method/sft","slug":"sft","name":"SFT","full_name":"Shrink and Fine-Tune","full_name_withheld":false,"description_markdown":"**Shrink and Fine-Tune**, or **SFT**, is a type of distillation that avoids explicit distillation by copying parameters to a student student model and then fine-tuning. Specifically it extracts a student model from the maximally spaced layers of a fine-tuned teacher. Each layer $l \\in L'$ is copied fully from $L$. For example, when creating a [BART](https://paperswithcode.com/method/bart) student with 3 decoder layers from the 12 encoder layer 12 decoder layer teacher, we copy the teacher’s full $Enc^{L}$ and decoder layers 0, 6, and 11 to the student. When deciding which layers to copy, we break ties arbitrarily; copying layers 0, 5, and 11 might work just as well. When copy only 1 decoder layer, we copy layer 0. This was found this to work better than copying layer 11. The impact of initialization on performance is measured experimentally in Section 6.1. After initialization, the student model continues to fine-tune on the summarization dataset, with the objective of minimizing $\\mathcal{L}\\_{Data}$.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Pre-trained Summarization Distillation","paper":"/paper/pre-trained-summarization-distillation","first_author":"Sam Shleifer","n_authors":2,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/pre-trained-summarization-distillation"},"source":{"url":"https://arxiv.org/abs/2010.13002v2","title":"Pre-trained Summarization Distillation","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"General","area_id":"general","collection":"Distillation","url":"/methods/category/distillation","pwc_aliases":[]},{"area":"General","area_id":"general","collection":"Knowledge Distillation","url":"/methods/category/knowledge-distillation","pwc_aliases":[]}],"n_papers_tagged":415,"archive_num_papers":415,"papers_newest_first":[{"paper":"/paper/a-practical-two-stage-recipe-for-mathematical","slug":"a-practical-two-stage-recipe-for-mathematical","title":"A Practical Two-Stage Recipe for Mathematical LLMs: Maximizing Accuracy with SFT and Efficiency with Reinforcement Learning","date":"2025-07-11","arxiv_id":"2507.08267","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":1,"n_instrument":5,"unverified":0,"pointer_only":6,"phrase":"6 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; 5 where Syntology's instrument failed) · 0 unverified","official":{"repos":["analokmaus/kaggle-aimo2-fast-math-r1"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/investalign-overcoming-data-scarcity-in","slug":"investalign-overcoming-data-scarcity-in","title":"InvestAlign: Overcoming Data Scarcity in Aligning Large Language Models with Investor Decision-Making Processes under Herd Behavior","date":"2025-07-09","arxiv_id":"2507.06528","n_code_links":1,"syntology":null},{"paper":"/paper/autotriton-automatic-triton-programming-with","slug":"autotriton-automatic-triton-programming-with","title":"AutoTriton: Automatic Triton Programming with Reinforcement Learning in LLMs","date":"2025-07-08","arxiv_id":"2507.05687","n_code_links":1,"syntology":null},{"paper":null,"slug":"cognisql-r1-zero-lightweight-reinforced","title":"CogniSQL-R1-Zero: Lightweight Reinforced Reasoning for Efficient SQL Generation","date":"2025-07-08","arxiv_id":"2507.06013","n_code_links":0,"syntology":null},{"paper":"/paper/reinforcement-fine-tuning-naturally-mitigates","slug":"reinforcement-fine-tuning-naturally-mitigates","title":"Reinforcement Fine-Tuning Naturally Mitigates Forgetting in Continual Post-Training","date":"2025-07-07","arxiv_id":"2507.05386","n_code_links":0,"syntology":{"ran":6,"of":10,"n_ran_checked":2,"n_instrument":4,"unverified":4,"pointer_only":10,"phrase":"6 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; 4 where Syntology's instrument failed) · 4 unverified","official":null}},{"paper":"/paper/spiral-self-play-on-zero-sum-games","slug":"spiral-self-play-on-zero-sum-games","title":"SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning","date":"2025-06-30","arxiv_id":"2506.24119","n_code_links":1,"syntology":{"ran":9,"of":9,"n_ran_checked":3,"n_instrument":6,"unverified":0,"pointer_only":0,"phrase":"9 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; 6 where Syntology's instrument failed) · 0 unverified","official":{"repos":["spiral-rl/spiral"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/complexity-aware-fine-tuning","slug":"complexity-aware-fine-tuning","title":"Complexity-aware fine-tuning","date":"2025-06-26","arxiv_id":"2506.21220","n_code_links":1,"syntology":null},{"paper":"/paper/longwriter-zero-mastering-ultra-long-text","slug":"longwriter-zero-mastering-ultra-long-text","title":"LongWriter-Zero: Mastering Ultra-Long Text Generation via Reinforcement Learning","date":"2025-06-23","arxiv_id":"2506.18841","n_code_links":1,"syntology":{"ran":12,"of":14,"n_ran_checked":4,"n_instrument":8,"unverified":2,"pointer_only":1,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 8 where Syntology's instrument failed) · 2 unverified","official":null}},{"paper":null,"slug":"smart-llama-dpo-reinforced-large-language","title":"Smart-LLaMA-DPO: Reinforced Large Language Model for Explainable Smart Contract Vulnerability Detection","date":"2025-06-23","arxiv_id":"2506.18245","n_code_links":0,"syntology":null},{"paper":null,"slug":"rlrc-reinforcement-learning-based-recovery","title":"RLRC: Reinforcement Learning-based Recovery for Compressed Vision-Language-Action Models","date":"2025-06-21","arxiv_id":"2506.17639","n_code_links":0,"syntology":null},{"paper":null,"slug":"differentiation-based-extraction-of","title":"Differentiation-Based Extraction of Proprietary Data from Fine-Tuned LLMs","date":"2025-06-20","arxiv_id":"2506.17353","n_code_links":0,"syntology":null},{"paper":null,"slug":"refine-poi-reinforcement-fine-tuned-large","title":"Refine-POI: Reinforcement Fine-Tuned Large Language Models for Next Point-of-Interest Recommendation","date":"2025-06-19","arxiv_id":"2506.21599","n_code_links":0,"syntology":null},{"paper":null,"slug":"massive-supervised-fine-tuning-experiments","title":"Massive Supervised Fine-tuning Experiments Reveal How Data, Layer, and Training Factors Shape LLM Alignment Quality","date":"2025-06-17","arxiv_id":"2506.14681","n_code_links":0,"syntology":null},{"paper":null,"slug":"acereason-nemotron-1-1-advancing-math-and","title":"AceReason-Nemotron 1.1: Advancing Math and Code Reasoning through SFT and RL Synergy","date":"2025-06-16","arxiv_id":"2506.13284","n_code_links":0,"syntology":null},{"paper":null,"slug":"ego-r1-chain-of-tool-thought-for-ultra-long","title":"Ego-R1: Chain-of-Tool-Thought for Ultra-Long Egocentric Video Reasoning","date":"2025-06-16","arxiv_id":"2506.13654","n_code_links":0,"syntology":null},{"paper":"/paper/metis-rise-rl-incentivizes-and-sft-enhances","slug":"metis-rise-rl-incentivizes-and-sft-enhances","title":"Metis-RISE: RL Incentivizes and SFT Enhances Multimodal Reasoning Model Learning","date":"2025-06-16","arxiv_id":"2506.13056","n_code_links":1,"syntology":null},{"paper":"/paper/qfft-question-free-fine-tuning-for-adaptive","slug":"qfft-question-free-fine-tuning-for-adaptive","title":"QFFT, Question-Free Fine-Tuning for Adaptive Reasoning","date":"2025-06-15","arxiv_id":"2506.12860","n_code_links":1,"syntology":{"ran":14,"of":14,"n_ran_checked":11,"n_instrument":3,"unverified":0,"pointer_only":7,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 2 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["lwl-cpu/question-free-fine-tuning"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"vgr-visual-grounded-reasoning","title":"VGR: Visual Grounded Reasoning","date":"2025-06-13","arxiv_id":"2506.11991","n_code_links":0,"syntology":null},{"paper":"/paper/vision-matters-simple-visual-perturbations","slug":"vision-matters-simple-visual-perturbations","title":"Vision Matters: Simple Visual Perturbations Can Boost Multimodal Math Reasoning","date":"2025-06-11","arxiv_id":"2506.09736","n_code_links":1,"syntology":null},{"paper":"/paper/eliciting-fine-tuned-transformer-capabilities","slug":"eliciting-fine-tuned-transformer-capabilities","title":"Eliciting Fine-Tuned Transformer Capabilities via Inference-Time Techniques","date":"2025-06-09","arxiv_id":"2506.08060","n_code_links":1,"syntology":null},{"paper":"/paper/learning-what-reinforcement-learning-can-t","slug":"learning-what-reinforcement-learning-can-t","title":"Learning What Reinforcement Learning Can't: Interleaved Online Fine-Tuning for Hardest Questions","date":"2025-06-09","arxiv_id":"2506.07527","n_code_links":1,"syntology":null},{"paper":"/paper/nearness-of-neighbors-attention-for","slug":"nearness-of-neighbors-attention-for","title":"Nearness of Neighbors Attention for Regression in Supervised Finetuning","date":"2025-06-09","arxiv_id":"2506.08139","n_code_links":1,"syntology":null},{"paper":null,"slug":"learning-to-clarify-by-reinforcement-learning","title":"Learning to Clarify by Reinforcement Learning Through Reward-Weighted Fine-Tuning","date":"2025-06-08","arxiv_id":"2506.06964","n_code_links":0,"syntology":null},{"paper":null,"slug":"sde-sql-enhancing-text-to-sql-generation-in","title":"SDE-SQL: Enhancing Text-to-SQL Generation in Large Language Models via Self-Driven Exploration with SQL Probes","date":"2025-06-08","arxiv_id":"2506.07245","n_code_links":0,"syntology":null},{"paper":"/paper/writing-rl-advancing-long-form-writing-via","slug":"writing-rl-advancing-long-form-writing-via","title":"Writing-RL: Advancing Long-form Writing via Adaptive Curriculum Reinforcement Learning","date":"2025-06-06","arxiv_id":"2506.05760","n_code_links":1,"syntology":null},{"paper":"/paper/mint-cot-enabling-interleaved-visual-tokens","slug":"mint-cot-enabling-interleaved-visual-tokens","title":"MINT-CoT: Enabling Interleaved Visual Tokens in Mathematical Chain-of-Thought Reasoning","date":"2025-06-05","arxiv_id":"2506.05331","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-the-mechanism-of-reasoning-pattern","title":"On the Mechanism of Reasoning Pattern Selection in Reinforcement Learning for Language Models","date":"2025-06-05","arxiv_id":"2506.04695","n_code_links":0,"syntology":null},{"paper":null,"slug":"crowd-sft-crowdsourcing-for-llm-alignment","title":"Crowd-SFT: Crowdsourcing for LLM Alignment","date":"2025-06-04","arxiv_id":"2506.04063","n_code_links":0,"syntology":null},{"paper":null,"slug":"roborefer-towards-spatial-referring-with","title":"RoboRefer: Towards Spatial Referring with Reasoning in Vision-Language Models for Robotics","date":"2025-06-04","arxiv_id":"2506.04308","n_code_links":0,"syntology":null},{"paper":null,"slug":"corrigibility-as-a-singular-target-a-vision","title":"Corrigibility as a Singular Target: A Vision for Inherently Reliable Foundation Models","date":"2025-06-03","arxiv_id":"2506.03056","n_code_links":0,"syntology":null},{"paper":"/paper/reasoning-table-exploring-reinforcement","slug":"reasoning-table-exploring-reinforcement","title":"Reasoning-Table: Exploring Reinforcement Learning for Table Reasoning","date":"2025-06-02","arxiv_id":"2506.01710","n_code_links":1,"syntology":null},{"paper":"/paper/reasoning-like-an-economist-post-training-on","slug":"reasoning-like-an-economist-post-training-on","title":"Reasoning Like an Economist: Post-Training on Economic Problems Induces Strategic Generalization in LLMs","date":"2025-05-31","arxiv_id":"2506.00577","n_code_links":1,"syntology":null},{"paper":"/paper/exploring-multimodal-challenges-in-toxic","slug":"exploring-multimodal-challenges-in-toxic","title":"Exploring Multimodal Challenges in Toxic Chinese Detection: Taxonomy, Benchmark, and Findings","date":"2025-05-30","arxiv_id":"2505.24341","n_code_links":1,"syntology":null},{"paper":null,"slug":"from-macro-to-micro-probing-dataset-diversity","title":"From Macro to Micro: Probing Dataset Diversity in Language Model Fine-Tuning","date":"2025-05-30","arxiv_id":"2505.24768","n_code_links":0,"syntology":null},{"paper":"/paper/harnessing-negative-signals-reinforcement","slug":"harnessing-negative-signals-reinforcement","title":"Harnessing Negative Signals: Reinforcement Distillation from Teacher Data for LLM Reasoning","date":"2025-05-30","arxiv_id":"2505.24850","n_code_links":1,"syntology":null},{"paper":null,"slug":"how-much-backtracking-is-enough-exploring-the","title":"How Much Backtracking is Enough? Exploring the Interplay of SFT and RL in Enhancing LLM Reasoning","date":"2025-05-30","arxiv_id":"2505.24273","n_code_links":0,"syntology":null},{"paper":null,"slug":"reason-svg-hybrid-reward-rl-for-aha-moments","title":"Reason-SVG: Hybrid Reward RL for Aha-Moments in Vector Graphics Generation","date":"2025-05-30","arxiv_id":"2505.24499","n_code_links":0,"syntology":null},{"paper":null,"slug":"afterburner-reinforcement-learning","title":"Afterburner: Reinforcement Learning Facilitates Self-Improving Code Efficiency Optimization","date":"2025-05-29","arxiv_id":"2505.23387","n_code_links":0,"syntology":null},{"paper":"/paper/jigsaw-r1-a-study-of-rule-based-visual","slug":"jigsaw-r1-a-study-of-rule-based-visual","title":"Jigsaw-R1: A Study of Rule-based Visual Reinforcement Learning with Jigsaw Puzzles","date":"2025-05-29","arxiv_id":"2505.23590","n_code_links":1,"syntology":null},{"paper":null,"slug":"robot-r1-reinforcement-learning-for-enhanced","title":"Robot-R1: Reinforcement Learning for Enhanced Embodied Reasoning in Robotics","date":"2025-05-29","arxiv_id":"2506.00070","n_code_links":0,"syntology":null},{"paper":"/paper/cadrille-multi-modal-cad-reconstruction-with","slug":"cadrille-multi-modal-cad-reconstruction-with","title":"cadrille: Multi-modal CAD Reconstruction with Online Reinforcement Learning","date":"2025-05-28","arxiv_id":"2505.22914","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"2 ran (of which 2 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) · 1 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","official":null}},{"paper":"/paper/enhancing-paraphrase-type-generation-the","slug":"enhancing-paraphrase-type-generation-the","title":"Enhancing Paraphrase Type Generation: The Impact of DPO and RLHF Evaluated with Human-Ranked Data","date":"2025-05-28","arxiv_id":"2506.02018","n_code_links":1,"syntology":null},{"paper":null,"slug":"evolvesearch-an-iterative-self-evolving","title":"EvolveSearch: An Iterative Self-Evolving Search Agent","date":"2025-05-28","arxiv_id":"2505.22501","n_code_links":0,"syntology":null},{"paper":null,"slug":"workforceagent-r1-incentivizing-reasoning","title":"WorkForceAgent-R1: Incentivizing Reasoning Capability in LLM-based Web Agents via Reinforcement Learning","date":"2025-05-28","arxiv_id":"2505.22942","n_code_links":0,"syntology":null},{"paper":"/paper/r1-code-interpreter-training-llms-to-reason","slug":"r1-code-interpreter-training-llms-to-reason","title":"R1-Code-Interpreter: Training LLMs to Reason with Code via Supervised and Reinforcement Learning","date":"2025-05-27","arxiv_id":"2505.21668","n_code_links":1,"syntology":null},{"paper":"/paper/masksearch-a-universal-pre-training-framework","slug":"masksearch-a-universal-pre-training-framework","title":"MASKSEARCH: A Universal Pre-Training Framework to Enhance Agentic Search Capability","date":"2025-05-26","arxiv_id":"2505.20285","n_code_links":1,"syntology":null},{"paper":"/paper/unveiling-the-compositional-ability-gap-in","slug":"unveiling-the-compositional-ability-gap-in","title":"Unveiling the Compositional Ability Gap in Vision-Language Reasoning Model","date":"2025-05-26","arxiv_id":"2505.19406","n_code_links":1,"syntology":null},{"paper":null,"slug":"what-can-rl-bring-to-vla-generalization-an","title":"What Can RL Bring to VLA Generalization? An Empirical Study","date":"2025-05-26","arxiv_id":"2505.19789","n_code_links":0,"syntology":null},{"paper":null,"slug":"alchemist-turning-public-text-to-image-data","title":"Alchemist: Turning Public Text-to-Image Data into Generative Gold","date":"2025-05-25","arxiv_id":"2505.19297","n_code_links":0,"syntology":null},{"paper":null,"slug":"controlling-language-confusion-in","title":"Controlling Language Confusion in Multilingual LLMs","date":"2025-05-25","arxiv_id":"2505.19116","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-pragmatic-mind-of-machines-tracing-the","title":"The Pragmatic Mind of Machines: Tracing the Emergence of Pragmatic Competence in Large Language Models","date":"2025-05-24","arxiv_id":"2505.18497","n_code_links":0,"syntology":null},{"paper":null,"slug":"astromlab-4-benchmark-topping-performance-in","title":"AstroMLab 4: Benchmark-Topping Performance in Astronomy Q&A with a 70B-Parameter Domain-Specialized Reasoning Model","date":"2025-05-23","arxiv_id":"2505.17592","n_code_links":0,"syntology":null},{"paper":null,"slug":"t2i-eval-r1-reinforcement-learning-driven","title":"T2I-Eval-R1: Reinforcement Learning-Driven Reasoning for Interpretable Text-to-Image Evaluation","date":"2025-05-23","arxiv_id":"2505.17897","n_code_links":0,"syntology":null},{"paper":"/paper/towards-revealing-the-effectiveness-of-small","slug":"towards-revealing-the-effectiveness-of-small","title":"Towards Revealing the Effectiveness of Small-Scale Fine-tuning in R1-style Reinforcement Learning","date":"2025-05-23","arxiv_id":"2505.17988","n_code_links":1,"syntology":null},{"paper":null,"slug":"decoupledesc-enhancing-emotional-support","title":"DecoupledESC: Enhancing Emotional Support Generation via Strategy-Response Decoupled Preference Optimization","date":"2025-05-22","arxiv_id":"2505.16995","n_code_links":0,"syntology":null},{"paper":null,"slug":"interactive-post-training-for-vision-language","title":"Interactive Post-Training for Vision-Language-Action Models","date":"2025-05-22","arxiv_id":"2505.17016","n_code_links":0,"syntology":null},{"paper":null,"slug":"longer-context-deeper-thinking-uncovering-the","title":"Longer Context, Deeper Thinking: Uncovering the Role of Long-Context Ability in Reasoning","date":"2025-05-22","arxiv_id":"2505.17315","n_code_links":0,"syntology":null},{"paper":"/paper/mpl-multiple-programming-languages-with-large","slug":"mpl-multiple-programming-languages-with-large","title":"MPL: Multiple Programming Languages with Large Language Models for Information Extraction","date":"2025-05-22","arxiv_id":"2505.16107","n_code_links":1,"syntology":null},{"paper":"/paper/r1-searcher-incentivizing-the-dynamic","slug":"r1-searcher-incentivizing-the-dynamic","title":"R1-Searcher++: Incentivizing the Dynamic Knowledge Acquisition of LLMs via Reinforcement Learning","date":"2025-05-22","arxiv_id":"2505.17005","n_code_links":3,"syntology":{"ran":9,"of":10,"n_ran_checked":8,"n_instrument":1,"unverified":1,"pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["rucaibox/r1-searcher-plus"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"reflectevo-improving-meta-introspection-of","title":"ReflectEvo: Improving Meta Introspection of Small LLMs by Learning Self-Reflection","date":"2025-05-22","arxiv_id":"2505.16475","n_code_links":0,"syntology":null},{"paper":"/paper/simpledeepsearcher-deep-information-seeking","slug":"simpledeepsearcher-deep-information-seeking","title":"SimpleDeepSearcher: Deep Information Seeking via Web-Powered Reasoning Trajectory Synthesis","date":"2025-05-22","arxiv_id":"2505.16834","n_code_links":3,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"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","official":{"repos":["rucaibox/simpledeepsearcher"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/uft-unifying-supervised-and-reinforcement","slug":"uft-unifying-supervised-and-reinforcement","title":"UFT: Unifying Supervised and Reinforcement Fine-Tuning","date":"2025-05-22","arxiv_id":"2505.16984","n_code_links":1,"syntology":{"ran":5,"of":9,"n_ran_checked":2,"n_instrument":3,"unverified":4,"pointer_only":0,"phrase":"5 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; 3 where Syntology's instrument failed) · 4 unverified","official":{"repos":["liumy2010/uft"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"chain-of-focus-adaptive-visual-search-and","title":"Chain-of-Focus: Adaptive Visual Search and Zooming for Multimodal Reasoning via RL","date":"2025-05-21","arxiv_id":"2505.15436","n_code_links":0,"syntology":null},{"paper":null,"slug":"deftx-denoised-sparse-fine-tuning-for-zero","title":"DeFTX: Denoised Sparse Fine-Tuning for Zero-Shot Cross-Lingual Transfer","date":"2025-05-21","arxiv_id":"2505.15090","n_code_links":0,"syntology":null},{"paper":"/paper/from-problem-solving-to-teaching-problem","slug":"from-problem-solving-to-teaching-problem","title":"From Problem-Solving to Teaching Problem-Solving: Aligning LLMs with Pedagogy using Reinforcement Learning","date":"2025-05-21","arxiv_id":"2505.15607","n_code_links":1,"syntology":null},{"paper":null,"slug":"kaft-knowledge-aware-fine-tuning-for-boosting","title":"KaFT: Knowledge-aware Fine-tuning for Boosting LLMs' Domain-specific Question-Answering Performance","date":"2025-05-21","arxiv_id":"2505.15480","n_code_links":0,"syntology":null},{"paper":null,"slug":"star-r1-spacial-transformation-reasoning-by","title":"STAR-R1: Spacial TrAnsformation Reasoning by Reinforcing Multimodal LLMs","date":"2025-05-21","arxiv_id":"2505.15804","n_code_links":0,"syntology":null},{"paper":null,"slug":"cross-lingual-optimization-for-language","title":"Cross-Lingual Optimization for Language Transfer in Large Language Models","date":"2025-05-20","arxiv_id":"2505.14297","n_code_links":0,"syntology":null},{"paper":"/paper/deepeyes-incentivizing-thinking-with-images","slug":"deepeyes-incentivizing-thinking-with-images","title":"DeepEyes: Incentivizing \"Thinking with Images\" via Reinforcement Learning","date":"2025-05-20","arxiv_id":"2505.14362","n_code_links":1,"syntology":{"ran":12,"of":17,"n_ran_checked":8,"n_instrument":4,"unverified":5,"pointer_only":4,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified","official":{"repos":["visual-agent/deepeyes"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"fishersft-data-efficient-supervised-fine","title":"FisherSFT: Data-Efficient Supervised Fine-Tuning of Language Models Using Information Gain","date":"2025-05-20","arxiv_id":"2505.14826","n_code_links":0,"syntology":null},{"paper":"/paper/infigfusion-graph-on-logits-distillation-via","slug":"infigfusion-graph-on-logits-distillation-via","title":"InfiGFusion: Graph-on-Logits Distillation via Efficient Gromov-Wasserstein for Model Fusion","date":"2025-05-20","arxiv_id":"2505.13893","n_code_links":1,"syntology":null},{"paper":null,"slug":"interpretable-traces-unexpected-outcomes","title":"Interpretable Traces, Unexpected Outcomes: Investigating the Disconnect in Trace-Based Knowledge Distillation","date":"2025-05-20","arxiv_id":"2505.13792","n_code_links":0,"syntology":null},{"paper":"/paper/jolt-sql-joint-loss-tuning-of-text-to-sql","slug":"jolt-sql-joint-loss-tuning-of-text-to-sql","title":"JOLT-SQL: Joint Loss Tuning of Text-to-SQL with Confusion-aware Noisy Schema Sampling","date":"2025-05-20","arxiv_id":"2505.14305","n_code_links":1,"syntology":{"ran":16,"of":18,"n_ran_checked":6,"n_instrument":10,"unverified":2,"pointer_only":1,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 4 violated, 2 with no contract checked; 10 where Syntology's instrument failed) · 2 unverified","official":{"repos":["songjw133/joint-loss-tuning-of-text-to-sql"],"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"]}}},{"paper":null,"slug":"ideal-data-equilibrium-adaptation-for-multi","title":"IDEAL: Data Equilibrium Adaptation for Multi-Capability Language Model Alignment","date":"2025-05-19","arxiv_id":"2505.12762","n_code_links":0,"syntology":null},{"paper":null,"slug":"step-wise-adaptive-integration-of-supervised","title":"Step-wise Adaptive Integration of Supervised Fine-tuning and Reinforcement Learning for Task-Specific LLMs","date":"2025-05-19","arxiv_id":"2505.13026","n_code_links":0,"syntology":null},{"paper":null,"slug":"uishift-enhancing-vlm-based-gui-agents","title":"UIShift: Enhancing VLM-based GUI Agents through Self-supervised Reinforcement Learning","date":"2025-05-18","arxiv_id":"2505.12493","n_code_links":0,"syntology":null},{"paper":"/paper/videorft-incentivizing-video-reasoning","slug":"videorft-incentivizing-video-reasoning","title":"VideoRFT: Incentivizing Video Reasoning Capability in MLLMs via Reinforced Fine-Tuning","date":"2025-05-18","arxiv_id":"2505.12434","n_code_links":1,"syntology":{"ran":6,"of":8,"n_ran_checked":6,"n_instrument":0,"unverified":2,"pointer_only":2,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 4 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["qiwang98/videorft"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"enhancing-complex-instruction-following-for","title":"Enhancing Complex Instruction Following for Large Language Models with Mixture-of-Contexts Fine-tuning","date":"2025-05-17","arxiv_id":"2505.11922","n_code_links":0,"syntology":null},{"paper":"/paper/2505-11049","slug":"2505-11049","title":"GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning","date":"2025-05-16","arxiv_id":"2505.11049","n_code_links":1,"syntology":{"ran":9,"of":12,"n_ran_checked":7,"n_instrument":2,"unverified":3,"pointer_only":1,"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) · 3 unverified","official":{"repos":["yueliu1999/guardreasoner-vl"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"critique-guided-distillation-improving","title":"Critique-Guided Distillation: Improving Supervised Fine-tuning via Better Distillation","date":"2025-05-16","arxiv_id":"2505.11628","n_code_links":0,"syntology":null},{"paper":"/paper/reasoning-on-a-budget-miniaturizing-deepseek","slug":"reasoning-on-a-budget-miniaturizing-deepseek","title":"Reasoning on a Budget: Miniaturizing DeepSeek R1 with SFT-GRPO Alignment for Instruction-Tuned LLMs","date":"2025-05-16","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"cafe-retrieval-head-based-coarse-to-fine","title":"CAFE: Retrieval Head-based Coarse-to-Fine Information Seeking to Enhance Multi-Document QA Capability","date":"2025-05-15","arxiv_id":"2505.10063","n_code_links":0,"syntology":null},{"paper":null,"slug":"reinforcing-the-diffusion-chain-of-lateral","title":"Reinforcing the Diffusion Chain of Lateral Thought with Diffusion Language Models","date":"2025-05-15","arxiv_id":"2505.10446","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-to-reason-and-navigate-parameter","title":"Learning to Reason and Navigate: Parameter Efficient Action Planning with Large Language Models","date":"2025-05-12","arxiv_id":"2505.07500","n_code_links":0,"syntology":null},{"paper":null,"slug":"making-small-language-models-efficient","title":"Making Small Language Models Efficient Reasoners: Intervention, Supervision, Reinforcement","date":"2025-05-12","arxiv_id":"2505.07961","n_code_links":0,"syntology":null},{"paper":null,"slug":"assessing-robustness-to-spurious-correlations","title":"Assessing Robustness to Spurious Correlations in Post-Training Language Models","date":"2025-05-09","arxiv_id":"2505.05704","n_code_links":0,"syntology":null},{"paper":"/paper/multimodal-integrated-knowledge-transfer-to","slug":"multimodal-integrated-knowledge-transfer-to","title":"Multimodal Integrated Knowledge Transfer to Large Language Models through Preference Optimization with Biomedical Applications","date":"2025-05-09","arxiv_id":"2505.05736","n_code_links":1,"syntology":null},{"paper":null,"slug":"soaesv2-7b-72b-full-pipeline-optimization-for","title":"SOAEsV2-7B/72B: Full-Pipeline Optimization for State-Owned Enterprise LLMs via Continual Pre-Training, Domain-Progressive SFT and Distillation-Enhanced Speculative Decoding","date":"2025-05-07","arxiv_id":"2505.04723","n_code_links":0,"syntology":null},{"paper":"/paper/long-short-chain-of-thought-mixture","slug":"long-short-chain-of-thought-mixture","title":"Long-Short Chain-of-Thought Mixture Supervised Fine-Tuning Eliciting Efficient Reasoning in Large Language Models","date":"2025-05-06","arxiv_id":"2505.03469","n_code_links":1,"syntology":null},{"paper":null,"slug":"vlm-q-learning-aligning-vision-language","title":"VLM Q-Learning: Aligning Vision-Language Models for Interactive Decision-Making","date":"2025-05-06","arxiv_id":"2505.03181","n_code_links":0,"syntology":null},{"paper":"/paper/100-days-after-deepseek-r1-a-survey-on","slug":"100-days-after-deepseek-r1-a-survey-on","title":"100 Days After DeepSeek-R1: A Survey on Replication Studies and More Directions for Reasoning Language Models","date":"2025-05-01","arxiv_id":"2505.00551","n_code_links":0,"syntology":null},{"paper":null,"slug":"knowledge-distillation-of-domain-adapted-llms","title":"Knowledge Distillation of Domain-adapted LLMs for Question-Answering in Telecom","date":"2025-04-28","arxiv_id":"2504.20000","n_code_links":0,"syntology":null},{"paper":null,"slug":"nemotron-research-tool-n1-exploring-tool","title":"Nemotron-Research-Tool-N1: Exploring Tool-Using Language Models with Reinforced Reasoning","date":"2025-04-25","arxiv_id":"2505.00024","n_code_links":0,"syntology":null},{"paper":null,"slug":"sari-structured-audio-reasoning-via","title":"SARI: Structured Audio Reasoning via Curriculum-Guided Reinforcement Learning","date":"2025-04-22","arxiv_id":"2504.15900","n_code_links":0,"syntology":null},{"paper":null,"slug":"donod-robust-and-generalizable-instruction","title":"DONOD: Robust and Generalizable Instruction Fine-Tuning for LLMs via Model-Intrinsic Dataset Pruning","date":"2025-04-21","arxiv_id":"2504.14810","n_code_links":0,"syntology":null},{"paper":null,"slug":"think2sql-reinforce-llm-reasoning","title":"Think2SQL: Reinforce LLM Reasoning Capabilities for Text2SQL","date":"2025-04-21","arxiv_id":"2504.15077","n_code_links":0,"syntology":null},{"paper":"/paper/leetcodedataset-a-temporal-dataset-for-robust","slug":"leetcodedataset-a-temporal-dataset-for-robust","title":"LeetCodeDataset: A Temporal Dataset for Robust Evaluation and Efficient Training of Code LLMs","date":"2025-04-20","arxiv_id":"2504.14655","n_code_links":1,"syntology":null},{"paper":null,"slug":"relation-r1-cognitive-chain-of-thought-guided","title":"Relation-R1: Cognitive Chain-of-Thought Guided Reinforcement Learning for Unified Relational Comprehension","date":"2025-04-20","arxiv_id":"2504.14642","n_code_links":0,"syntology":null},{"paper":"/paper/compile-scene-graphs-with-reinforcement","slug":"compile-scene-graphs-with-reinforcement","title":"Compile Scene Graphs with Reinforcement Learning","date":"2025-04-18","arxiv_id":"2504.13617","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":0,"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) · 0 unverified","official":{"repos":["gpt4vision/r1-sgg"],"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":["official"]}}},{"paper":null,"slug":"mig-automatic-data-selection-for-instruction","title":"MIG: Automatic Data Selection for Instruction Tuning by Maximizing Information Gain in Semantic Space","date":"2025-04-18","arxiv_id":"2504.13835","n_code_links":0,"syntology":null}],"papers_shown":100,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":415,"with_a_code_link":204,"where_syntology_ran_a_sample":103,"not_listed_spam_title":0,"listed":415,"listed_where_code_ran":103,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":82,"every_run_a_failure_of_syntologys_instrument":21,"listed_with_a_run_with_no_instrument_failure":82,"listed_every_run_a_failure_of_syntologys_instrument":21,"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"},"papers_where_code_ran":103,"papers_where_code_ran_first_page":"/method/sft/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[{"order":"archive","page":2,"of":5,"url":"/method/sft/papers/2","json":"/method/sft/papers/2.json","rows":100},{"order":"archive","page":3,"of":5,"url":"/method/sft/papers/3","json":"/method/sft/papers/3.json","rows":100},{"order":"archive","page":4,"of":5,"url":"/method/sft/papers/4","json":"/method/sft/papers/4.json","rows":100},{"order":"archive","page":5,"of":5,"url":"/method/sft/papers/5","json":"/method/sft/papers/5.json","rows":15},{"order":"ran","page":1,"of":2,"url":"/method/sft/papers/ran/1","json":"/method/sft/papers/ran/1.json","rows":100},{"order":"ran","page":2,"of":2,"url":"/method/sft/papers/ran/2","json":"/method/sft/papers/ran/2.json","rows":3}],"tasks":[{"task":"/task/reinforcement-learning-1","name":"Reinforcement Learning (RL)","papers":73},{"task":"/task/language-modelling","name":"Language Modelling","papers":50},{"task":"/task/language-modeling","name":"Language Modeling","papers":41},{"task":"/task/large-language-model","name":"Large Language Model","papers":35},{"task":"/task/instruction-following","name":"Instruction Following","papers":34},{"task":"/task/question-answering","name":"Question Answering","papers":30},{"task":"/task/math","name":"Math","papers":29},{"task":"/task/diversity","name":"Diversity","papers":23},{"task":"/task/mathematical-reasoning","name":"Mathematical Reasoning","papers":21},{"task":"/task/reinforcement-learning","name":"Reinforcement Learning","papers":20},{"task":"/task/reinforcement-learning-2","name":"reinforcement-learning","papers":20},{"task":"/task/in-context-learning","name":"In-Context Learning","papers":17},{"task":"/task/code-generation","name":"Code Generation","papers":13},{"task":"/task/gsm8k","name":"GSM8K","papers":13},{"task":"/task/retrieval","name":"Retrieval","papers":11},{"task":"/task/rag","name":"RAG","papers":10},{"task":"/task/text-generation","name":"Text Generation","papers":10},{"task":"/task/visual-reasoning","name":"Visual Reasoning","papers":10},{"task":"/task/retrieval-augmented-generation","name":"Retrieval-augmented Generation","papers":9},{"task":"/task/machine-translation","name":"Machine Translation","papers":8}],"tasks_shown":20,"n_tasks":206,"usage_by_year":[{"year":"2020","papers":1},{"year":"2022","papers":3},{"year":"2023","papers":41},{"year":"2024","papers":187},{"year":"2025","papers":183}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/sft"},"syntology_read_at":"2026-10-05T00:36:11+00:00","syntology":{"source":"Syntology's have check for this name (the free coverage lookup), read from Syntology's graph","have_url":"https://syntology.ai/api/graph/have?x=SFT","read_at":"2026-10-05T01:01:52+00:00","query":"SFT","kind":"paper","have":"no_code","tier":"paper_only","verified_implementation":false,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":{"arxiv_id":"openreview_m4eD6HDGGX"},"resolution":"paper","resolved_name_differs":false,"absence_asserted":"for_this_paper_only","absence_unchecked":null,"no_code_is_about_this_method":false,"subject":"unknown","archive_paper_arxiv_id":"2010.13002","repositories":{"listed":null,"in_graph":0,"list_truncated":null,"strongest_link":null},"retrieve_with":null,"name_competition":{"verdict":"outranked","may_be_wrong_sense":true,"bearers_found":7,"served":{"arxiv_id":"openreview_m4eD6HDGGX","citations":null},"leading_other_bearer":{"arxiv_id":"2208.11351","title":"Self-Filtering: A Noise-Aware Sample Selection for Label Noise with Confidence Penalization","citations":64,"named_by":["acronym_expansion"],"bearer_name":"Self-Filtering (SFT)","ask_with":"have('2208.11351')"},"n_other_bearers_listed":5,"note":"'SFT' is ALSO the name of 'Self-Filtering (SFT)', a method in 'Self-Filtering: A Noise-Aware Sample Selection for Label Noise with Confidence Penalization' (arXiv:2208.11351, 64 citations), which is cited FAR more than the paper this answer is about (citations not recorded). This answer may be about the wrong SFT. If you meant the better-known one, ask again with that entry of `also_named`."},"name_competition_text":"The same name also belongs to “Self-Filtering (SFT)”, a method in the paper “Self-Filtering: A Noise-Aware Sample Selection for Label Noise with Confidence Penalization” (arXiv:2208.11351, 64 citations), which the lookup finds cited far more than the paper this answer is about (citations not recorded), so this answer may be about a different sense of the name.","near_matches":null,"code_nearby":[],"code_nearby_caption":null,"origin_paper":{"arxiv_id":"openreview_m4eD6HDGGX","page":null,"syntology_url":null,"in_graph_layer":false,"samples":0},"line":"the paper matched by title, the paper Syntology's graph keys as openreview_m4eD6HDGGX, held, no code (no_code; paper_only). The lookup matched a paper by its title, the paper Syntology's graph keys as openreview_m4eD6HDGGX, not a method entry. The archive credits no paper with an arXiv id for this method, so whether this answer (about the paper Syntology's graph keys as openreview_m4eD6HDGGX) is about this method is not checked; it does not say whether this method has code.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"559885e9af9190dd04ca06c98436983d39a5059e925fc9e2adf7cfe3f90a4e04","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}