REVIEW 5 cited by
ReVISE: Learning to Refine at Test-Time via Intrinsic Self-Verification
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
read the original abstract
Self-awareness, i.e., the ability to assess and correct one's own generation, is a fundamental aspect of human intelligence, making its replication in large language models (LLMs) an important yet challenging task. Previous works tackle this by employing extensive reinforcement learning or rather relying on large external verifiers. In this work, we propose Refine via Intrinsic Self-Verification (ReVISE), an efficient and effective framework that enables LLMs to self-correct their outputs through self-verification. The core idea of ReVISE is to enable LLMs to verify their reasoning processes and continually rethink reasoning trajectories based on its verification. We introduce a structured curriculum based upon online preference learning to implement this efficiently. Specifically, as ReVISE involves two challenging tasks (i.e., self-verification and reasoning correction), we tackle each task sequentially using curriculum learning, collecting both failed and successful reasoning paths to construct preference pairs for efficient training. During inference, our approach enjoys natural test-time scaling by integrating self-verification and correction capabilities, further enhanced by our proposed confidence-aware decoding mechanism. Our experiments on various reasoning tasks demonstrate that ReVISE achieves efficient self-correction and significantly improves reasoning performance.
Forward citations
Cited by 5 Pith papers
-
ReGUIDE: Data Efficient GUI Grounding via Spatial Reasoning and Search
ReGUIDE reaches state-of-the-art GUI grounding accuracy using 0.2% of the usual training data by adding self-generated reasoning, spatial-consistency training, and test-time KDE coordinate search.
-
ThinkRetrieve: Retrieval-Augmented Reasoning Traces for Test-Time Scaling
Per-step retrieval of solved exemplars injected into the reasoning trace improves test-time scaling accuracy, with up to 13.4 absolute points gained on AIME 2025.
-
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.
-
Refining Over Resampling: Test-Time Self-Correction for LLM Reasoning
Sampling multiple reasoning paths, refining each with self-critique and self-correction, then majority voting improves math reasoning accuracy over width-only or verifier-based test-time scaling on several open-weight LLMs.
-
Self-Correcting Code Generation Using Small Language Models
CoCoS, an online RL method with accumulated and fine-grained unit-test rewards, enables 1B-parameter language models to self-correct generated code and outperforms existing self-correction baselines on MBPP, HumanEval...
Discussion (0). Continue with ORCID to comment.