Pith. sign in

REVIEW 7 cited by

PRMBench: A Fine-grained and Challenging Benchmark for Process-Level Reward Models

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 2501.03124 v5 pith:ZGXPLEYE submitted 2025-01-06 cs.CL cs.AIcs.LG

classification cs.CLcs.AIcs.LG
keywords modelsprmsprmbenchprocess-levelreasoningbenchmarkcapabilitiescurrent
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Process-level Reward Models (PRMs) are crucial for complex reasoning and decision-making tasks, where each intermediate step plays an important role in the reasoning process. Since language models are prone to various types of errors during the reasoning process, PRMs are required to possess nuanced capabilities for detecting various implicit error types in real-world scenarios. However, current benchmarks primarily focus on step correctness, failing to evaluate PRMs' performance systematically. To address this gap, we introduce PRMBench, a process-level benchmark specifically designed to assess the fine-grained error detection capabilities of PRMs. PRMBench comprises 6,216 carefully designed problems and 83,456 step-level labels, evaluating models across multiple dimensions, including simplicity, soundness, and sensitivity. In our experiments on 15 models, spanning both open-source PRMs and closed-source large language models prompted as critic models, we uncover significant weaknesses in current PRMs. These findings underscore the challenges inherent in process-level evaluation and highlight key directions for future research. We hope PRMBench can be a robust bench for advancing research on PRM evaluation and development.

Discussion (0). Sign in to comment.

Forward citations

Cited by 7 Pith papers

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

  1. MME-SCI: A Comprehensive and Challenging Science Benchmark for Multimodal Large Language Models

    cs.CL 2025-08 conditional novelty 6.0 of 10

    A manually curated, multilingual, multimodal science benchmark shows that even top MLLMs struggle, with fine-grained knowledge-point labels revealing specific weaknesses.

  2. GM-PRM: A Generative Multimodal Process Reward Model for Multimodal Mathematical Reasoning

    cs.CL 2025-08 conditional novelty 6.0 of 10

    A generative multimodal process reward model that produces step-level critiques and corrections improves average math accuracy for six multimodal LLMs by 2.9 to 5.9 points under a refinement-based Best-of-N strategy.

  3. Self-Correction Bench: Uncovering and Addressing the Self-Correction Blind Spot in Large Language Models

    cs.CL 2025-07 conditional novelty 6.0 of 10

    Non-reasoning LLMs fail to correct their own errors (64.5% blind spot) while correcting identical external errors, and appending 'Wait' cuts the gap by 89.3%.

  4. AURA: Affordance-Understanding and Risk-aware Alignment Technique for Large Language Models

    cs.CL 2025-08 unverdicted novelty 5.0 of 10

    AURA uses step-level reward models, self-critique, and safety-aware decoding to reduce affordance-based safety failures in LLM outputs.

  5. Mitigating Think-Answer Mismatch in LLM Reasoning Through Noise-Aware Advantage Reweighting

    cs.LG 2025-08 reject novelty 5.0 of 10

    S-GRPO reweights GRPO advantages by an assumed noise level p to down-weight unbalanced groups, claiming improved and more noise-robust math reasoning training.

  6. Reward Modeling for Reinforcement Learning-Based LLM Reasoning: Design, Challenges, and Evaluation

    cs.LG 2026-02 conditional novelty 4.0 of 10

    A taxonomy-driven survey arguing that reward design is the central mechanism shaping reliable LLM reasoning, with maps of reward paradigms, reward-hacking failure modes, and benchmark pitfalls.

  7. Step-level Verifier-guided Hybrid Test-Time Scaling for Large Language Models

    cs.CL 2025-07 reject novelty 4.0 of 10

    A step-level verifier-guided hybrid of Best-of-N sampling, Monte Carlo tree search, and conditional self-refinement improves reasoning in small instruction-tuned LLMs, claiming up to 28.6-point gains.

Pith tools