Pith. sign in

REVIEW 19 cited by

V-STaR: Training Verifiers for Self-Taught Reasoners

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

arxiv 2402.06457 v2 pith:ZSECQMXW submitted 2024-02-09 cs.LG cs.AIcs.CL

classification cs.LGcs.AIcs.CL
keywords solutionsapproachesself-improvementv-starcommonduringgeneratedincorrect
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Common self-improvement approaches for large language models (LLMs), such as STaR, iteratively fine-tune LLMs on self-generated solutions to improve their problem-solving ability. However, these approaches discard the large amounts of incorrect solutions generated during this process, potentially neglecting valuable information in such solutions. To address this shortcoming, we propose V-STaR that utilizes both the correct and incorrect solutions generated during the self-improvement process to train a verifier using DPO that judges correctness of model-generated solutions. This verifier is used at inference time to select one solution among many candidate solutions. Running V-STaR for multiple iterations results in progressively better reasoners and verifiers, delivering a 4% to 17% test accuracy improvement over existing self-improvement and verification approaches on common code generation and math reasoning benchmarks with LLaMA2 models.

Discussion (0). Sign in to comment.

Forward citations

Cited by 19 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. The Verifier is the Curriculum: Execution-Gated Self-Distillation for Cross-Family Game Generation

    cs.AI 2026-06 conditional novelty 6.5 of 10

    Strict-launch-gated rejection-sampling self-distillation compounds cross-family clean Godot generation from 8.8% to 42.2% and full best-of-K coverage, while gold duplication and a lenient BUILD filter erase the gain.

  2. Cybersecurity Detection Classification with Reasoning-enabled Language Models

    cs.LG 2026-07 conditional novelty 6.0 of 10

    CoT-trained triage plus a separate reasoning calibrator reaches 82.6% accuracy and large high-confidence recall gains over direct-label LLM classifiers on real SOC detections.

  3. LeAct: Learning to Reason from Expert Actions

    cs.LG 2026-07 conditional novelty 6.0 of 10

    An AI can learn to reason by sampling explanations for an expert's actions and keeping only the ones that help it predict those actions.

  4. Test-Time Scaling via Error Localization

    cs.LG 2026-07 conditional novelty 6.0 of 10

    TTEL uses feedback-induced token probability drops to localize the first error in a failed reasoning trace and branch a new generation from that prefix, improving pass@k per token on coding and math benchmarks.

  5. Post-Training Shifts Confidence: A Three-Stage Analysis of How SFT, RL, and OPD Shape CoT Calibration

    cs.CL 2026-07 conditional novelty 6.0 of 10

    Post-training changes where confidence is trustworthy in reasoning traces: OPD best gauges difficulty before thinking, SFT best supports early stopping, RL best selects final answers, and confidence should be read onl...

  6. LookWise: Knowing When and Where to Look for Fine-Grained Visual Reasoning in Multimodal Large Language Models

    cs.CV 2026-02 conditional novelty 6.0 of 10

    A confidence-based when-to-look gate plus semantic-guided attention where-to-look module improves training-free fine-grained visual reasoning accuracy and reduces inference cost versus search-based baselines.

  7. CAViAR: Critic-Augmented Video Agentic Reasoning

    cs.CV 2025-09 conditional novelty 6.0 of 10

    CAViAR, an agent-plus-critic system for long video reasoning, improves on direct video LLM inference across LVBench, Neptune, and ActivityNet-RTL.

  8. Revolutionizing Reinforcement Learning Framework for Diffusion Large Language Models

    cs.CL 2025-09 conditional novelty 6.0 of 10

    TraceRL aligns the RL objective with the DLM's actual step-by-step decoding, producing TraDo-4B/8B models that beat autoregressive baselines on math reasoning.

  9. Learn from What We HAVE: History-Aware VErifier that Reasons about Past Interactions Online

    cs.RO 2025-08 conditional novelty 6.0 of 10

    A history-aware verifier that scores candidate actions using past interactions cuts failure rates in ambiguous robot manipulation tasks compared to using the generator alone.

  10. VL-GenRM: Enhancing Vision-Language Verification via Vision Experts and Iterative Training

    cs.CL 2025-06 conditional novelty 6.0 of 10

    A vision-expert-filtered, chain-of-thought-guided, iteratively fine-tuned reward model boosts a compact 7B model's ability to judge vision-language responses, especially detecting hallucinations.

  11. Multi-Step Visual Reasoning with Visual Tokens Scaling and Verification

    cs.CV 2025-06 conditional novelty 6.0 of 10

    An iterative, verifier-guided visual token scaling framework improves multi-step visual reasoning in both closed and open multimodal models on BLINK and related benchmarks.

  12. Sample More, Reflect Less: Self-Refine and Reflexion Lose to Repeated Sampling at Equal Token Cost, from 1.5B to 7B

    cs.CL 2026-07 accept novelty 5.5 of 10

    Self-inspection methods (Self-Refine, Reflexion, Best-of-N self-verify) lose to equal-token repeated sampling on math from 1.5B to 7B; no tested method reliably wins.

  13. Reasoning in machine vision by learning fast and slow thinking

    cs.CV 2025-06 conditional novelty 5.0 of 10

    A dual-process vision system improves segmentation accuracy by spending more inference-time compute, using a fast predictor and a slow self-play refiner, reporting gains on cancer localisation with only 8-16 labels.

  14. See, Think, Learn: A Self-Taught Multimodal Reasoner

    cs.CV 2025-12 conditional novelty 4.0 of 10

    A self-training loop that structures model rationales into image-caption, reasoning, and conclusion, and adds negative rationales, improves VLM accuracy on M3CoT over answer-only and STaR baselines.

  15. TaoSR-AGRL: Adaptive Guided Reinforcement Learning Framework for E-commerce Search Relevance

    cs.IR 2025-10 conditional novelty 4.0 of 10

    TaoSR-AGRL improves e-commerce search relevance by combining dense rule-aware reward shaping with adaptive ground-truth-guided replay in GRPO, reporting gains on Taobao's private offline and online evaluations.

  16. Logit Arithmetic Elicits Long Reasoning Capabilities Without Training

    cs.CL 2025-07 conditional novelty 4.0 of 10

    ThinkLogit blends logits from a small reasoning guider into a frozen 32B model, improving math pass@1 by up to 29% without training the large model.

  17. DiMo-GUI: Advancing Test-time Scaling in GUI Grounding via Modality-Aware Visual Reasoning

    cs.AI 2025-06 conditional novelty 4.0 of 10

    Separating text and icon grounding with iterative zooming improves GUI-element localization accuracy of existing vision-language models without retraining.

  18. The Hitchhiker's Guide to Agentic AI: From Foundations to Systems

    cs.AI 2026-06 unverdicted novelty 2.0 of 10

    A survey-style reference book mapping the full agentic-AI stack from transformer internals to production deployment, with no new research result.

  19. A Survey on Large Language Models for Mathematical Reasoning

    cs.AI 2025-06 conditional novelty 1.0 of 10

    Recent advances in LLM mathematical reasoning are organized into comprehension and generation phases, covering methods from prompting to test-time scaling.

Pith tools