待翻譯：Woodpecker Distillation: Weak Models Diagnose Reasoning Bugs in Strong Models
AI 服務暫時不可用，以下為來源摘要，待恢復後補全翻譯：arXiv:2608.05168v1 Announce Type: new Abstract: Large language models often fail on reasoning tasks despite possessing the capability to solve them. We argue that many such failures arise from localized reasoning bugs in intermediate steps rather than from global incompetence. We show that these bugs are frequently repairable: inserting a short patch generated by a weak probe model after the same strong-model reasoning prefix can redirect the trajectory toward a correct solution. However, this corrective effect is not reliably internalized by directly fine-tuning on weak patches or repaired trajectories, suggesting that the useful signal lies not in the intervention text itself, but in how it reshapes the model's future reasoning distribution. We therefore propose Woodpecker Distillation, a weak-to-strong training framework that learns from contrastive local interventions. Our method contrasts successful and unsuccessful weak-model patches at the same prefix, constructs a corrective teacher distribution from their induced future token predictions, and distills this signal into the strong model. Experiments on mathematical reasoning benchmarks show that Woodpecker Distillation consistently improves strong-model performance and outperforms direct imitation baselines.
AI 服務暫時不可用，以下為來源正文，待恢復後補全翻譯。
--> [Submitted on 27 May 2026] Title:Woodpecker Distillation: Weak Models Diagnose Reasoning Bugs in Strong Models View a PDF of the paper titled Woodpecker Distillation: Weak Models Diagnose Reasoning Bugs in Strong Models, by Dayu Wang and 6 other authors View PDF HTML (experimental) Abstract:Large language models often fail on reasoning tasks despite possessing the capability to solve them. We argue that many such failures arise from localized reasoning bugs in intermediate steps rather than from global incompetence. We show that these bugs are frequently repairable: inserting a short patch generated by a weak probe model after the same strong-model reasoning prefix can redirect the trajectory toward a correct solution. However, this corrective effect is not reliably internalized by directly fine-tuning on weak patches or repaired trajectories, suggesting that the useful signal lies not in the intervention text itself, but in how it reshapes the model's future reasoning distribution. We therefore propose Woodpecker Distillation, a weak-to-strong training framework that learns from contrastive local interventions. Our method contrasts successful and unsuccessful weak-model patches at the same prefix, constructs a corrective teacher distribution from their induced future token predictions, and distills this signal into the strong model. Experiments on mathematical reasoning benchmarks show that Woodpecker Distillation consistently improves strong-model performance and outperforms direct imitation baselines. Subjects: Artificial Intelligence (cs.AI); Computation and Language (cs.CL) Cite as: arXiv:2608.05168 [cs.AI] (or arXiv:2608.05168v1 [cs.AI] for this version) https://doi.org/10.48550/arXiv.2608.05168 arXiv-issued DOI via DataCite Submission history From: Dayu Wang [view email] [v1] Wed, 27 May 2026 15:22:55 UTC (679 KB) Full-text links: Access Paper: View a PDF of the paper titled Woodpecker Distillation: Weak Models Diagnose Reasoning Bugs in Strong Models, by Dayu Wang and 6 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.AI new | recent | 2026-08 Change to browse by: cs cs.CL References & Citations NASA ADS Google Scholar Semantic Scholar Loading... Data provided by: Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv (What is alphaXiv?) Links to Code Toggle CatalyzeX Code Finder for Papers (What is CatalyzeX?) DagsHub Toggle DagsHub (What is DagsHub?) GotitPub Toggle Gotit.pub (What is GotitPub?) Huggingface Toggle Hugging Face (What is Huggingface?) ScienceCast Toggle ScienceCast (What is ScienceCast?) Demos Demos Replicate Toggle Replicate (What is Replicate?) Spaces Toggle Hugging Face Spaces (What is Spaces?) Spaces Toggle TXYZ.AI (What is TXYZ.AI?) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower (What are Influence Flowers?) Core recommender toggle CORE Recommender (What is CORE?) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)