{"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/papers/3","list_of":"/method/sft","method":"SFT","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"date (newest first), then slug","page":3,"pages_in_order":5,"rows_per_page":100,"rows":[201,300],"of":415,"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":86,"every_run_a_failure_of_syntologys_instrument":17,"listed_with_a_run_with_no_instrument_failure":86,"listed_every_run_a_failure_of_syntologys_instrument":17,"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"},"first_page":"/method/sft","prev":"/method/sft/papers/2","next":"/method/sft/papers/4","papers":[{"paper":null,"slug":"self-improvement-in-language-models-the","title":"Self-Improvement in Language Models: The Sharpening Mechanism","date":"2024-12-02","arxiv_id":"2412.01951","n_code_links":0,"syntology":null},{"paper":null,"slug":"continual-sft-matches-multimodal-rlhf-with","title":"Continual SFT Matches Multimodal RLHF with Negative Supervision","date":"2024-11-22","arxiv_id":"2411.14797","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-from-silly-questions-improves-large","title":"Learning from \"Silly\" Questions Improves Large Language Models, But Only Slightly","date":"2024-11-21","arxiv_id":"2411.14121","n_code_links":0,"syntology":null},{"paper":null,"slug":"multimodal-large-language-model-for-wheat","title":"Multimodal large language model for wheat breeding: a new exploration of smart breeding","date":"2024-11-20","arxiv_id":"2411.15203","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-active-privacy-auditing-in-supervised-fine","title":"On Active Privacy Auditing in Supervised Fine-tuning for White-Box Language Models","date":"2024-11-11","arxiv_id":"2411.07070","n_code_links":0,"syntology":null},{"paper":"/paper/iopo-empowering-llms-with-complex-instruction","slug":"iopo-empowering-llms-with-complex-instruction","title":"IOPO: Empowering LLMs with Complex Instruction Following via Input-Output Preference Optimization","date":"2024-11-09","arxiv_id":"2411.06208","n_code_links":1,"syntology":null},{"paper":null,"slug":"q-sft-q-learning-for-language-models-via","title":"Q-SFT: Q-Learning for Language Models via Supervised Fine-Tuning","date":"2024-11-07","arxiv_id":"2411.05193","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-post-training-enhanced-optimization","title":"A Post-Training Enhanced Optimization Approach for Small Language Models","date":"2024-11-05","arxiv_id":"2411.02939","n_code_links":0,"syntology":null},{"paper":null,"slug":"llms-for-domain-generation-algorithm","title":"LLMs for Domain Generation Algorithm Detection","date":"2024-11-05","arxiv_id":"2411.03307","n_code_links":0,"syntology":null},{"paper":"/paper/metrex-a-benchmark-for-verilog-code-metric","slug":"metrex-a-benchmark-for-verilog-code-metric","title":"MetRex: A Benchmark for Verilog Code Metric Reasoning Using LLMs","date":"2024-11-05","arxiv_id":"2411.03471","n_code_links":1,"syntology":{"ran":8,"of":13,"n_ran_checked":8,"n_instrument":0,"unverified":5,"pointer_only":13,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","official":{"repos":["scale-lab/MetRex"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/on-the-loss-of-context-awareness-in-general","slug":"on-the-loss-of-context-awareness-in-general","title":"On the Loss of Context-awareness in General Instruction Fine-tuning","date":"2024-11-05","arxiv_id":"2411.02688","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"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":["YihanWang617/context_awareness"],"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":["unlocated"]}}},{"paper":null,"slug":"l3ms-lagrange-large-language-models","title":"L3Ms -- Lagrange Large Language Models","date":"2024-10-28","arxiv_id":"2410.21533","n_code_links":0,"syntology":null},{"paper":"/paper/longreward-improving-long-context-large","slug":"longreward-improving-long-context-large","title":"LongReward: Improving Long-context Large Language Models with AI Feedback","date":"2024-10-28","arxiv_id":"2410.21252","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["THUDM/LongReward"],"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","unlocated"]}}},{"paper":null,"slug":"reducing-the-scope-of-language-models-with","title":"Reducing the Scope of Language Models","date":"2024-10-28","arxiv_id":"2410.21597","n_code_links":0,"syntology":null},{"paper":null,"slug":"uft-unifying-fine-tuning-of-sft-and-rlhf-dpo","title":"UFT: Unifying Fine-Tuning of SFT and RLHF/DPO/UNA through a Generalized Implicit Reward Function","date":"2024-10-28","arxiv_id":"2410.21438","n_code_links":0,"syntology":null},{"paper":"/paper/fictitious-synthetic-data-can-improve-llm","slug":"fictitious-synthetic-data-can-improve-llm","title":"Fictitious Synthetic Data Can Improve LLM Factuality via Prerequisite Learning","date":"2024-10-25","arxiv_id":"2410.19290","n_code_links":1,"syntology":null},{"paper":null,"slug":"toolflow-boosting-llm-tool-calling-through","title":"ToolFlow: Boosting LLM Tool-Calling Through Natural and Coherent Dialogue Synthesis","date":"2024-10-24","arxiv_id":"2410.18447","n_code_links":0,"syntology":null},{"paper":"/paper/voicetextblender-augmenting-large-language","slug":"voicetextblender-augmenting-large-language","title":"VoiceTextBlender: Augmenting Large Language Models with Speech Capabilities via Single-Stage Joint Speech-Text Supervised Fine-Tuning","date":"2024-10-23","arxiv_id":"2410.17485","n_code_links":1,"syntology":null},{"paper":"/paper/dean-deactivating-the-coupled-neurons-to","slug":"dean-deactivating-the-coupled-neurons-to","title":"DEAN: Deactivating the Coupled Neurons to Mitigate Fairness-Privacy Conflicts in Large Language Models","date":"2024-10-22","arxiv_id":"2410.16672","n_code_links":1,"syntology":null},{"paper":"/paper/bayesian-scaling-laws-for-in-context-learning","slug":"bayesian-scaling-laws-for-in-context-learning","title":"Bayesian scaling laws for in-context learning","date":"2024-10-21","arxiv_id":"2410.16531","n_code_links":1,"syntology":{"ran":2,"of":3,"n_ran_checked":0,"n_instrument":2,"unverified":1,"pointer_only":3,"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) · 1 unverified","official":{"repos":["aryamanarora/bayesian-laws-icl"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/mitigating-forgetting-in-llm-supervised-fine","slug":"mitigating-forgetting-in-llm-supervised-fine","title":"Mitigating Forgetting in LLM Supervised Fine-Tuning and Preference Learning","date":"2024-10-20","arxiv_id":"2410.15483","n_code_links":1,"syntology":null},{"paper":null,"slug":"training-language-models-to-critique-with","title":"Training Language Models to Critique With Multi-agent Feedback","date":"2024-10-20","arxiv_id":"2410.15287","n_code_links":0,"syntology":null},{"paper":null,"slug":"persistent-pre-training-poisoning-of-llms","title":"Persistent Pre-Training Poisoning of LLMs","date":"2024-10-17","arxiv_id":"2410.13722","n_code_links":0,"syntology":null},{"paper":"/paper/rag-ddr-optimizing-retrieval-augmented","slug":"rag-ddr-optimizing-retrieval-augmented","title":"RAG-DDR: Optimizing Retrieval-Augmented Generation Using Differentiable Data Rewards","date":"2024-10-17","arxiv_id":"2410.13509","n_code_links":1,"syntology":{"ran":10,"of":10,"n_ran_checked":10,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["openmatch/rag-ddr"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/semievol-semi-supervised-fine-tuning-for-llm","slug":"semievol-semi-supervised-fine-tuning-for-llm","title":"SemiEvol: Semi-supervised Fine-tuning for LLM Adaptation","date":"2024-10-17","arxiv_id":"2410.14745","n_code_links":2,"syntology":null},{"paper":null,"slug":"rosepo-aligning-llm-based-recommenders-with","title":"RosePO: Aligning LLM-based Recommenders with Human Values","date":"2024-10-16","arxiv_id":"2410.12519","n_code_links":0,"syntology":null},{"paper":null,"slug":"improving-the-language-understanding","title":"Improving the Language Understanding Capabilities of Large Language Models Using Reinforcement Learning","date":"2024-10-14","arxiv_id":"2410.11020","n_code_links":0,"syntology":null},{"paper":null,"slug":"self-data-distillation-for-recovering-quality","title":"Self-Data Distillation for Recovering Quality in Pruned Large Language Models","date":"2024-10-13","arxiv_id":"2410.09982","n_code_links":0,"syntology":null},{"paper":null,"slug":"llinstruct-an-instruction-tuned-model-for","title":"\\llinstruct: An Instruction-tuned model for English Language Proficiency Assessments","date":"2024-10-12","arxiv_id":"2410.09314","n_code_links":0,"syntology":null},{"paper":"/paper/rethinking-data-selection-at-scale-random","slug":"rethinking-data-selection-at-scale-random","title":"Rethinking Data Selection at Scale: Random Selection is Almost All You Need","date":"2024-10-12","arxiv_id":"2410.09335","n_code_links":1,"syntology":{"ran":6,"of":10,"n_ran_checked":6,"n_instrument":0,"unverified":4,"pointer_only":10,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["xiatingyu/sft-dataselection-at-scale"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/packing-analysis-packing-is-more-appropriate","slug":"packing-analysis-packing-is-more-appropriate","title":"Packing Analysis: Packing Is More Appropriate for Large Models or Datasets in Supervised Fine-tuning","date":"2024-10-10","arxiv_id":"2410.08081","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":6,"n_instrument":0,"unverified":0,"pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["shuhewang1998/packing-analysis"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"preference-fine-tuning-for-factuality-in","title":"Preference Fine-Tuning for Factuality in Chest X-Ray Interpretation Models Without Human Feedback","date":"2024-10-09","arxiv_id":"2410.07025","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-self-improvement-of-llms-via-mcts","title":"Towards Self-Improvement of LLMs via MCTS: Leveraging Stepwise Knowledge with Curriculum Preference Learning","date":"2024-10-09","arxiv_id":"2410.06508","n_code_links":0,"syntology":null},{"paper":"/paper/utilize-the-flow-before-stepping-into-the","slug":"utilize-the-flow-before-stepping-into-the","title":"Utilize the Flow before Stepping into the Same River Twice: Certainty Represented Knowledge Flow for Refusal-Aware Instruction Tuning","date":"2024-10-09","arxiv_id":"2410.06913","n_code_links":1,"syntology":null},{"paper":null,"slug":"self-rationalization-improves-llm-as-a-fine","title":"Self-rationalization improves LLM as a fine-grained judge","date":"2024-10-07","arxiv_id":"2410.05495","n_code_links":0,"syntology":null},{"paper":null,"slug":"sftmix-elevating-language-model-instruction","title":"SFTMix: Elevating Language Model Instruction Tuning with Mixup Recipe","date":"2024-10-07","arxiv_id":"2410.05248","n_code_links":0,"syntology":null},{"paper":"/paper/how-to-train-long-context-language-models","slug":"how-to-train-long-context-language-models","title":"How to Train Long-Context Language Models (Effectively)","date":"2024-10-03","arxiv_id":"2410.02660","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["princeton-nlp/prolong"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/an-exploration-of-self-supervised-mutual","slug":"an-exploration-of-self-supervised-mutual","title":"An Exploration of Self-Supervised Mutual Information Alignment for Multi-Task Settings","date":"2024-10-02","arxiv_id":"2410.01704","n_code_links":1,"syntology":null},{"paper":"/paper/flashmask-efficient-and-rich-mask-extension","slug":"flashmask-efficient-and-rich-mask-extension","title":"FlashMask: Efficient and Rich Mask Extension of FlashAttention","date":"2024-10-02","arxiv_id":"2410.01359","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["PaddlePaddle/Paddle"],"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"]}}},{"paper":"/paper/locret-enhancing-eviction-in-long-context-llm","slug":"locret-enhancing-eviction-in-long-context-llm","title":"Locret: Enhancing Eviction in Long-Context LLM Inference with Trained Retaining Heads on Consumer-Grade Devices","date":"2024-10-02","arxiv_id":"2410.01805","n_code_links":1,"syntology":null},{"paper":"/paper/openmathinstruct-2-accelerating-ai-for-math","slug":"openmathinstruct-2-accelerating-ai-for-math","title":"OpenMathInstruct-2: Accelerating AI for Math with Massive Open-Source Instruction Data","date":"2024-10-02","arxiv_id":"2410.01560","n_code_links":1,"syntology":{"ran":12,"of":15,"n_ran_checked":12,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":null}},{"paper":null,"slug":"mitigating-training-imbalance-in-llm-fine","title":"Mitigating Training Imbalance in LLM Fine-Tuning via Selective Parameter Merging","date":"2024-10-01","arxiv_id":"2410.03743","n_code_links":0,"syntology":null},{"paper":null,"slug":"modulated-intervention-preference","title":"Modulated Intervention Preference Optimization (MIPO): Keep the Easy, Refine the Difficult","date":"2024-09-26","arxiv_id":"2409.17545","n_code_links":0,"syntology":null},{"paper":null,"slug":"empirical-insights-on-fine-tuning-large","title":"60 Data Points are Sufficient to Fine-Tune LLMs for Question-Answering","date":"2024-09-24","arxiv_id":"2409.15825","n_code_links":0,"syntology":null},{"paper":null,"slug":"supervised-fine-tuning-an-activation-pattern","title":"Supervised Fine-Tuning Achieve Rapid Task Adaption Via Alternating Attention Head Activation Patterns","date":"2024-09-24","arxiv_id":"2409.15820","n_code_links":0,"syntology":null},{"paper":null,"slug":"backtracking-improves-generation-safety","title":"Backtracking Improves Generation Safety","date":"2024-09-22","arxiv_id":"2409.14586","n_code_links":0,"syntology":null},{"paper":"/paper/a-case-study-of-web-app-coding-with-openai","slug":"a-case-study-of-web-app-coding-with-openai","title":"A Case Study of Web App Coding with OpenAI Reasoning Models","date":"2024-09-19","arxiv_id":"2409.13773","n_code_links":1,"syntology":null},{"paper":null,"slug":"fine-tuning-large-language-models-for-4","title":"Fine Tuning Large Language Models for Medicine: The Role and Importance of Direct Preference Optimization","date":"2024-09-19","arxiv_id":"2409.12741","n_code_links":0,"syntology":null},{"paper":"/paper/training-language-models-to-self-correct-via","slug":"training-language-models-to-self-correct-via","title":"Training Language Models to Self-Correct via Reinforcement Learning","date":"2024-09-19","arxiv_id":"2409.12917","n_code_links":2,"syntology":null},{"paper":"/paper/qwen2-5-math-technical-report-toward","slug":"qwen2-5-math-technical-report-toward","title":"Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement","date":"2024-09-18","arxiv_id":"2409.12122","n_code_links":0,"syntology":null},{"paper":null,"slug":"generated-data-with-fake-privacy-hidden","title":"Generated Data with Fake Privacy: Hidden Dangers of Fine-tuning Large Language Models on Generated Data","date":"2024-09-12","arxiv_id":"2409.11423","n_code_links":0,"syntology":null},{"paper":null,"slug":"beyond-iid-optimizing-instruction-learning","title":"Beyond IID: Optimizing Instruction Learning from the Perspective of Instruction Interaction and Dependency","date":"2024-09-11","arxiv_id":"2409.07045","n_code_links":0,"syntology":null},{"paper":null,"slug":"selective-self-rehearsal-a-fine-tuning","title":"Selective Self-Rehearsal: A Fine-Tuning Approach to Improve Generalization in Large Language Models","date":"2024-09-07","arxiv_id":"2409.04787","n_code_links":0,"syntology":null},{"paper":"/paper/the-representation-landscape-of-few-shot","slug":"the-representation-landscape-of-few-shot","title":"The representation landscape of few-shot learning and fine-tuning in large language models","date":"2024-09-05","arxiv_id":"2409.03662","n_code_links":1,"syntology":{"ran":11,"of":13,"n_ran_checked":11,"n_instrument":0,"unverified":2,"pointer_only":13,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["diegodoimo/geometry_icl_finetuning"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/longcite-enabling-llms-to-generate-fine","slug":"longcite-enabling-llms-to-generate-fine","title":"LongCite: Enabling LLMs to Generate Fine-grained Citations in Long-context QA","date":"2024-09-04","arxiv_id":"2409.02897","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":["THUDM/LongCite"],"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":"surface-flux-transport-modelling-using","title":"Surface Flux Transport Modeling using Physics Informed Neural Networks","date":"2024-09-03","arxiv_id":"2409.01744","n_code_links":0,"syntology":null},{"paper":null,"slug":"imitating-language-via-scalable-inverse","title":"Imitating Language via Scalable Inverse Reinforcement Learning","date":"2024-09-02","arxiv_id":"2409.01369","n_code_links":0,"syntology":null},{"paper":null,"slug":"entropic-distribution-matching-in-supervised","title":"Entropic Distribution Matching in Supervised Fine-tuning of LLMs: Less Overfitting and Better Diversity","date":"2024-08-29","arxiv_id":"2408.16673","n_code_links":0,"syntology":null},{"paper":"/paper/scilitllm-how-to-adapt-llms-for-scientific","slug":"scilitllm-how-to-adapt-llms-for-scientific","title":"SciLitLLM: How to Adapt LLMs for Scientific Literature Understanding","date":"2024-08-28","arxiv_id":"2408.15545","n_code_links":1,"syntology":{"ran":13,"of":13,"n_ran_checked":11,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["dptech-corp/Uni-SMART"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/instruct-skillmix-a-powerful-pipeline-for-llm","slug":"instruct-skillmix-a-powerful-pipeline-for-llm","title":"Instruct-SkillMix: A Powerful Pipeline for LLM Instruction Tuning","date":"2024-08-27","arxiv_id":"2408.14774","n_code_links":1,"syntology":{"ran":7,"of":8,"n_ran_checked":6,"n_instrument":1,"unverified":1,"pointer_only":8,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["princeton-pli/Instruct-SkillMix"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"quality-or-quantity-on-data-scale-and","title":"Quality or Quantity? On Data Scale and Diversity in Adapting Large Language Models for Low-Resource Translation","date":"2024-08-23","arxiv_id":"2408.12780","n_code_links":0,"syntology":null},{"paper":null,"slug":"minor-sft-loss-for-llm-fine-tune-to-increase","title":"Minor SFT loss for LLM fine-tune to increase performance and reduce model deviation","date":"2024-08-20","arxiv_id":"2408.10642","n_code_links":0,"syntology":null},{"paper":null,"slug":"threshold-filtering-packing-for-supervised","title":"Threshold Filtering Packing for Supervised Fine-Tuning: Training Related Samples within Packs","date":"2024-08-18","arxiv_id":"2408.09327","n_code_links":0,"syntology":null},{"paper":null,"slug":"api-guided-dataset-synthesis-to-finetune","title":"API-guided Dataset Synthesis to Finetune Large Code Models","date":"2024-08-15","arxiv_id":"2408.08343","n_code_links":0,"syntology":null},{"paper":"/paper/longwriter-unleashing-10000-word-generation","slug":"longwriter-unleashing-10000-word-generation","title":"LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs","date":"2024-08-13","arxiv_id":"2408.07055","n_code_links":3,"syntology":null},{"paper":null,"slug":"sampling-foundational-transformer-a","title":"Sampling Foundational Transformer: A Theoretical Perspective","date":"2024-08-11","arxiv_id":"2408.05822","n_code_links":0,"syntology":null},{"paper":null,"slug":"2408-02923","title":"Intermediate direct preference optimization","date":"2024-08-06","arxiv_id":"2408.02923","n_code_links":0,"syntology":null},{"paper":null,"slug":"2408-02861","title":"A Framework for Fine-Tuning LLMs using Heterogeneous Feedback","date":"2024-08-05","arxiv_id":"2408.02861","n_code_links":0,"syntology":null},{"paper":"/paper/large-language-models-for-anomaly-detection","slug":"large-language-models-for-anomaly-detection","title":"Large Language Models for Anomaly Detection in Computational Workflows: from Supervised Fine-Tuning to In-Context Learning","date":"2024-07-24","arxiv_id":"2407.17545","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-hitchhiker-s-guide-to-human-alignment","title":"The Hitchhiker's Guide to Human Alignment with *PO","date":"2024-07-21","arxiv_id":"2407.15229","n_code_links":0,"syntology":null},{"paper":"/paper/does-refusal-training-in-llms-generalize-to","slug":"does-refusal-training-in-llms-generalize-to","title":"Does Refusal Training in LLMs Generalize to the Past Tense?","date":"2024-07-16","arxiv_id":"2407.11969","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["tml-epfl/llm-past-tense"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"enhancing-training-efficiency-using-packing","title":"Enhancing Training Efficiency Using Packing with Flash Attention","date":"2024-07-12","arxiv_id":"2407.09105","n_code_links":0,"syntology":null},{"paper":"/paper/model-surgery-modulating-llm-s-behavior-via","slug":"model-surgery-modulating-llm-s-behavior-via","title":"Model Surgery: Modulating LLM's Behavior Via Simple Parameter Editing","date":"2024-07-11","arxiv_id":"2407.08770","n_code_links":1,"syntology":{"ran":13,"of":13,"n_ran_checked":13,"n_instrument":0,"unverified":0,"pointer_only":13,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["lucywang720/model-surgery"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"skywork-math-data-scaling-laws-for","title":"Skywork-Math: Data Scaling Laws for Mathematical Reasoning in Large Language Models -- The Story Goes On","date":"2024-07-11","arxiv_id":"2407.08348","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-and-accurate-memorable-conversation","title":"Efficient and Accurate Memorable Conversation Model using DPO based on sLLM","date":"2024-07-09","arxiv_id":"2407.06537","n_code_links":0,"syntology":null},{"paper":"/paper/lions-an-empirically-optimized-approach-to","slug":"lions-an-empirically-optimized-approach-to","title":"LIONs: An Empirically Optimized Approach to Align Language Models","date":"2024-07-09","arxiv_id":"2407.06542","n_code_links":1,"syntology":null},{"paper":null,"slug":"unlocking-the-potential-of-model-merging-for","title":"Unlocking the Potential of Model Merging for Low-Resource Languages","date":"2024-07-04","arxiv_id":"2407.03994","n_code_links":0,"syntology":null},{"paper":null,"slug":"52b-to-1t-lessons-learned-via-tele-flm-series","title":"52B to 1T: Lessons Learned via Tele-FLM Series","date":"2024-07-03","arxiv_id":"2407.02783","n_code_links":0,"syntology":null},{"paper":null,"slug":"raw-text-is-all-you-need-knowledge-intensive","title":"Raw Text is All you Need: Knowledge-intensive Multi-turn Instruction Tuning for Large Language Model","date":"2024-07-03","arxiv_id":"2407.03040","n_code_links":0,"syntology":null},{"paper":null,"slug":"iterative-nash-policy-optimization-aligning","title":"Iterative Nash Policy Optimization: Aligning LLMs with General Preferences via No-Regret Learning","date":"2024-06-30","arxiv_id":"2407.00617","n_code_links":0,"syntology":null},{"paper":"/paper/step-controlled-dpo-leveraging-stepwise-error","slug":"step-controlled-dpo-leveraging-stepwise-error","title":"Step-Controlled DPO: Leveraging Stepwise Error for Enhanced Mathematical Reasoning","date":"2024-06-30","arxiv_id":"2407.00782","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":5,"n_instrument":1,"unverified":0,"pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["mathllm/Step-Controlled_DPO"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/understanding-and-mitigating-language","slug":"understanding-and-mitigating-language","title":"Understanding and Mitigating Language Confusion in LLMs","date":"2024-06-28","arxiv_id":"2406.20052","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["for-ai/language-confusion"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/suri-multi-constraint-instruction-following","slug":"suri-multi-constraint-instruction-following","title":"Suri: Multi-constraint Instruction Following for Long-form Text Generation","date":"2024-06-27","arxiv_id":"2406.19371","n_code_links":1,"syntology":{"ran":12,"of":15,"n_ran_checked":12,"n_instrument":0,"unverified":3,"pointer_only":15,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 1 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["chtmp223/suri"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"open-vocabulary-mobile-manipulation-in-unseen","title":"Open-vocabulary Mobile Manipulation in Unseen Dynamic Environments with 3D Semantic Maps","date":"2024-06-26","arxiv_id":"2406.18115","n_code_links":0,"syntology":null},{"paper":"/paper/ares-alternating-reinforcement-learning-and","slug":"ares-alternating-reinforcement-learning-and","title":"ARES: Alternating Reinforcement Learning and Supervised Fine-Tuning for Enhanced Multi-Modal Chain-of-Thought Reasoning Through Diverse AI Feedback","date":"2024-06-25","arxiv_id":"2407.00087","n_code_links":1,"syntology":null},{"paper":null,"slug":"paft-a-parallel-training-paradigm-for","title":"PAFT: A Parallel Training Paradigm for Effective LLM Fine-Tuning","date":"2024-06-25","arxiv_id":"2406.17923","n_code_links":0,"syntology":null},{"paper":null,"slug":"does-cross-cultural-alignment-change-the","title":"Does Cross-Cultural Alignment Change the Commonsense Morality of Language Models?","date":"2024-06-24","arxiv_id":"2406.16316","n_code_links":0,"syntology":null},{"paper":"/paper/ruler-improving-llm-controllability-by-rule","slug":"ruler-improving-llm-controllability-by-rule","title":"RuleR: Improving LLM Controllability by Rule-based Data Recycling","date":"2024-06-22","arxiv_id":"2406.15938","n_code_links":3,"syntology":null},{"paper":null,"slug":"gradient-mask-tuning-elevates-the-upper","title":"Gradient-Mask Tuning Elevates the Upper Limits of LLM Performance","date":"2024-06-21","arxiv_id":"2406.15330","n_code_links":0,"syntology":null},{"paper":null,"slug":"secokd-aligning-large-language-models-for-in","title":"SeCoKD: Aligning Large Language Models for In-Context Learning with Fewer Shots","date":"2024-06-20","arxiv_id":"2406.14208","n_code_links":0,"syntology":null},{"paper":"/paper/self-play-with-execution-feedback-improving","slug":"self-play-with-execution-feedback-improving","title":"Self-play with Execution Feedback: Improving Instruction-following Capabilities of Large Language Models","date":"2024-06-19","arxiv_id":"2406.13542","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["QwenLM/AutoIF"],"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"]}}},{"paper":null,"slug":"aqulia-med-llm-pioneering-full-process-open","title":"Aqulia-Med LLM: Pioneering Full-Process Open-Source Medical Language Models","date":"2024-06-18","arxiv_id":"2406.12182","n_code_links":0,"syntology":null},{"paper":null,"slug":"recognition-of-dynamic-hand-gestures-in-long","title":"Recognition of Dynamic Hand Gestures in Long Distance using a Web-Camera for Robot Guidance","date":"2024-06-18","arxiv_id":"2406.12424","n_code_links":0,"syntology":null},{"paper":"/paper/a-systematic-analysis-of-large-language","slug":"a-systematic-analysis-of-large-language","title":"A Systematic Analysis of Large Language Models as Soft Reasoners: The Case of Syllogistic Inferences","date":"2024-06-17","arxiv_id":"2406.11341","n_code_links":1,"syntology":null},{"paper":null,"slug":"preserving-knowledge-in-large-language-model","title":"Preserving Knowledge in Large Language Model with Model-Agnostic Self-Decompression","date":"2024-06-17","arxiv_id":"2406.11354","n_code_links":0,"syntology":null},{"paper":null,"slug":"self-evolution-fine-tuning-for-policy","title":"Self-Evolution Fine-Tuning for Policy Optimization","date":"2024-06-16","arxiv_id":"2406.10813","n_code_links":0,"syntology":null},{"paper":"/paper/synthet2c-generating-synthetic-data-for-fine","slug":"synthet2c-generating-synthetic-data-for-fine","title":"SyntheT2C: Generating Synthetic Data for Fine-Tuning Large Language Models on the Text2Cypher Task","date":"2024-06-15","arxiv_id":"2406.10710","n_code_links":1,"syntology":null},{"paper":null,"slug":"unlock-the-correlation-between-supervised","title":"Unlock the Correlation between Supervised Fine-Tuning and Reinforcement Learning in Training Code Large Language Models","date":"2024-06-14","arxiv_id":"2406.10305","n_code_links":0,"syntology":null},{"paper":"/paper/magpie-alignment-data-synthesis-from-scratch","slug":"magpie-alignment-data-synthesis-from-scratch","title":"Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing","date":"2024-06-12","arxiv_id":"2406.08464","n_code_links":2,"syntology":{"ran":6,"of":7,"n_ran_checked":6,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["magpie-align/magpie"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"plum-preference-learning-plus-test-cases","title":"$\\textbf{PLUM}$: Improving Code LMs with Execution-Guided On-Policy Preference Learning Driven By Synthetic Test Cases","date":"2024-06-11","arxiv_id":"2406.06887","n_code_links":0,"syntology":null}],"record_sha256":"abdea970c190c538ec8f6a1e542d67687f119abec5e47909d4ec0d1160a846fe","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}