MR-Align: Meta-Reasoning Informed Factuality Alignment for Large Reasoning Models

Large reasoning models (LRMs) show strong capabilities in complex reasoning, yet their marginal gains on evidence-dependent factual questions are limited. We find this limitation is partially attributable to a reasoning-answer hit gap, where the model identifies the correct facts during reasoning but fails to incorporate them into the final response, thereby reducing factual fidelity. To address this issue, we propose MR-ALIGN, a Meta-Reasoning informed alignment framework that enhances factuality without relying on external verifiers. MR-ALIGN quantifies state transition probabilities along the model's thinking process and constructs a transition-aware implicit reward that reinforces beneficial reasoning patterns while suppressing defective ones at the atomic thinking segments. This re-weighting reshapes token-level signals into probability-aware segment scores, encouraging coherent reasoning trajectories that are more conducive to factual correctness. Empirical evaluations across four factual QA datasets and one long-form factuality benchmark show that MR-ALIGN consistently improves accuracy and truthfulness while reducing misleading reasoning. These results highlight that aligning the reasoning process itself, rather than merely the outputs, is pivotal for advancing factuality in LRMs.

This is an automated message from the Librarian Bot. I found the following papers similar to this paper.

The following papers were recommended by the Semantic Scholar API

• Beyond Correctness: Rewarding Faithful Reasoning in Retrieval-Augmented Generation (2025)
• What Defines Good Reasoning in LLMs? Dissecting Reasoning Steps with Multi-Aspect Evaluation (2025)
• Knowledge-Level Consistency Reinforcement Learning: Dual-Fact Alignment for Long-Form Factuality (2025)
• ReTraceQA: Evaluating Reasoning Traces of Small Language Models in Commonsense Question Answering (2025)
• From Faithfulness to Correctness: Generative Reward Models that Think Critically (2025)
• Veri-R1: Toward Precise and Faithful Claim Verification via Online Reinforcement Learning (2025)
• When Thinking Drifts: Evidential Grounding for Robust Video Reasoning (2025)

Please give a thumbs up to this comment if you found it helpful!

If you want recommendations for any Paper on Hugging Face checkout this Space

You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: @librarian-bot recommend