REVIEW 6 cited by
S$^2$R: Teaching LLMs to Self-verify and Self-correct via Reinforcement Learning
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
abstract
Recent studies have demonstrated the effectiveness of LLM test-time scaling. However, existing approaches to incentivize LLMs' deep thinking abilities generally require large-scale data or significant training efforts. Meanwhile, it remains unclear how to improve the thinking abilities of less powerful base models. In this work, we introduce S$^2$R, an efficient framework that enhances LLM reasoning by teaching models to self-verify and self-correct during inference. Specifically, we first initialize LLMs with iterative self-verification and self-correction behaviors through supervised fine-tuning on carefully curated data. The self-verification and self-correction skills are then further strengthened by both outcome-level and process-level reinforcement learning, with minimized resource requirements, enabling the model to adaptively refine its reasoning process during inference. Our results demonstrate that, with only 3.1k self-verifying and self-correcting behavior initialization samples, Qwen2.5-math-7B achieves an accuracy improvement from 51.0\% to 81.6\%, outperforming models trained on an equivalent amount of long-CoT distilled data. Extensive experiments and analysis based on three base models across both in-domain and out-of-domain benchmarks validate the effectiveness of S$^2$R. Our code and data are available at https://github.com/NineAbyss/S2R.
Forward citations
Cited by 6 Pith papers
-
CogDual: Enhancing Dual Cognition of LLMs via Reinforcement Learning with Implicit Rule-Based Rewards
A role-playing LLM that reasons about the scene and its own state before responding, trained with two semantic rewards, beats stronger baselines on role-play benchmarks.
-
PAG: Multi-Turn Reinforced LLM Self-Correction with Policy as Generative Verifier
A new multi-turn reinforcement learning framework trains a single LLM to both solve math problems and verify its own solutions, revising only when its verifier finds a mistake.
-
Spectral Origins of the Self-Correction Blind Spot in Autoregressive Generation
Self-correction blind spots in residual-stream autoregressive models arise iff the product of attention Jacobians has spectral radius ≥1, with a sharp marker threshold and RL coupling condition derived from that radius.
-
SVSR: A Self-Verification and Self-Rectification Paradigm for Multimodal Reasoning
SVSR trains multimodal models to verify and correct their own reasoning using a preference dataset, supervised fine-tuning, and semi-online DPO with a teacher model.
-
Towards Sparse Video Understanding and Reasoning
A video-QA agent that carries only a structured text summary between rounds beats dense-frame baselines on accuracy while using a handful of frames per video.
-
Self-Reflective Generation at Test Time
SRGen improves LLM math reasoning by detecting high-entropy tokens and injecting a small corrected vector into the hidden state at those points during decoding, without training.
Discussion (0). Sign in to comment.