Learning from the Right Rollouts: Data Attribution for PPO-based LLM Post-Training

[2604.01597] Learning from the Right Rollouts: Data Attribution for PPO-based LLM Post-Training Skip to main content Search Submit Donate Log in Computer Science > Machine Learning arXiv:2604.01597 (cs) [Submitted on 2 Apr 2026 ( v1 ), last revised 24 Aug 2026 (this version, v2)] Title: Learning from the Right Rollouts: Data Attribution for PPO-based LLM Post-Training Authors: Dong Shu , Denghui Zhang , Jessica Hullman View PDF HTML (experimental) Abstract: Traditional RL algorithms like Proximal Policy Optimization (PPO) typically train on the entire rollout buffer, operating under the assumption that all generated episodes provide a beneficial optimization signal. However, these episodes frequently contain noisy or unfaithful reasoning, which can degrade model performance and slow down training. In this paper, we propose \textbf{Influence-Guided PPO (I-PPO)}, a novel framework that integrates data attribution into the RL post-training loop. By calculating an influence score for each episode using a gradient-based approximation, I-PPO identifies and eliminates episodes that are anti-aligned with a validation gradient. Our experiments demonstrate that I-PPO consistently outperforms SFT and PPO baselines. We show that our filtering process acts as an intrinsic early stopping mechanism, accelerating training efficiency while effectively reducing unfaithful CoT reasoning. Subjects: Machine Learning (cs.LG) Cite as: arXiv:2604.01597 [cs.LG] (or arXiv:2604.01597v2 [cs.LG] for this version) https://doi.org/10.48550/arXiv.2604.01597 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Dong Shu [ view email ] [v1] Thu, 2 Apr 2026 04:09:31 UTC (784 KB) [v2] Mon, 24 Aug 2026 19:14:01 UTC (774 KB) Full-text links: Access Paper: View PDF HTML (experimental) TeX Source view license Additional Features Audio Summary Current browse context: cs.LG < prev | next > new | recent | 2026-04 Change to browse by: cs References & Citations SciX Google Scholar Semantic Scholar export BibTeX citation Bookmark 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? ) IArxiv recommender toggle IArxiv Recommender ( What is IArxiv? ) 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? ) We gratefully acknowledge support from our major funders , member institutions , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab)

Related documents

• Learning from the Right Rollouts: Data Attribution for PPO-based LLM Post-Training#670546
• Investigating the Impact of Private Data on RAG based LLM Personalization#264922
• Temporary Authority, Permanent Effects: Commit-Time Authorization for LLM Agents#363186
• Spark Policy Toolkit: Semantic Contracts and Scalable Execution for Policy Learning in Spark#141461
• The Autonomy Tax: Defense Training Breaks LLM Agents#684389