Generalizable Process Reward Models via Formally Verified Training Data

• URL: http://arxiv.org/abs/2505.15960v2
• Date: Sat, 27 Sep 2025 21:15:03 GMT
• Title: Generalizable Process Reward Models via Formally Verified Training Data
• Authors: Ryo Kamoi, Yusen Zhang, Nan Zhang, Sarkar Snigdha Sarathi Das, Rui Zhang,
• Abstract summary: FoVer is an approach to synthesize PRM training data with accurate step-level error labels automatically annotated by formal verification tools.<n>Experiments show that PRMs trained with FoVer exhibit cross-task generalization, enabling a single PRM to effectively perform verification across diverse reasoning tasks.
• Score: 13.781401358802462
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Process Reward Models (PRMs), which provide step-level feedback on reasoning traces generated by Large Language Models (LLMs), are receiving increasing attention. However, two key research gaps remain: creating PRM training data requires costly human annotation to label accurate step-level errors, and existing PRMs are limited to math reasoning domains. In response to these gaps, this paper aims to enable automatic synthesis of accurate PRM training data and the generalization of PRMs to diverse reasoning tasks beyond math reasoning. We propose FoVer, an approach to synthesize PRM training data with accurate step-level error labels automatically annotated by formal verification tools, such as Z3 and Isabelle. To show the practical effectiveness of FoVer, we synthesize a training dataset by annotating step-level error labels on LLM responses to formal logic and theorem proving tasks, without relying on human annotation. While FoVer creates training data with symbolic tasks compatible with formal verification, our experiments show that PRMs trained on our dataset exhibit cross-task generalization, enabling a single PRM to effectively perform verification across diverse reasoning tasks. Specifically, LLM-based PRMs trained with FoVer significantly outperform PRMs based on the original LLMs and achieve competitive or superior results compared to state-of-the-art PRMs, as measured by step-level verification on ProcessBench and Best-of-K performance across 12 reasoning benchmarks, including MATH, AIME, ANLI, MMLU, and BBH. The dataset and code are in the supplementary material and will be made public. The datasets, models, and code are provided at https://github.com/psunlpgroup/FoVer.

Related papers

• Adversarial Training for Process Reward Models [47.92183495904245]
  We introduce Adversarially Trained PRMs (textttAPRM), where a Generator ($G$) learns to produce reasoning errors to deceive a PRM ($R$)<n>This interaction yields progressively harder negatives for $R$, improving its robustness and generalization to novel errors without requiring manual step-level labels.
  arXiv  Detail & Related papers  (2025-11-28T05:32:01Z)
• Exploring Generative Process Reward Modeling for Semi-Structured Data: A Case Study of Table Question Answering [14.119525003137356]
  Process reward models (PRMs) improve complex reasoning in large language models (LLMs) by grading candidate solutions step-by-step and selecting answers via aggregated step scores.<n>This work presents the first systematic study of PRMs for table question answering (TQA)<n>We evaluate state-of-the-art generative PRMs on TQA from both answer and step perspectives.
  arXiv  Detail & Related papers  (2025-10-23T07:49:39Z)
• Your Reward Function for RL is Your Best PRM for Search: Unifying RL and Search-Based TTS [62.22644307952087]
  We introduce AIRL-S, the first natural unification of RL-based and search-based TTS.<n>We leverage adversarial inverse reinforcement learning (AIRL) combined with group relative policy optimization (GRPO) to learn a dense, dynamic PRM directly from correct reasoning traces.<n>Our results show that our unified approach improves performance by 9 % on average over the base model, matching GPT-4o.
  arXiv  Detail & Related papers  (2025-08-19T23:41:15Z)
• Uncertainty-Based Methods for Automated Process Reward Data Construction and Output Aggregation in Mathematical Reasoning [10.227089771963943]
  We propose an uncertainty-driven framework for automated process reward data construction.<n>We introduce two generic uncertainty-aware output aggregation methods: Hybrid Majority Reward Vote and weighted Reward Frequency Vote.<n>Experiments on ProcessBench, MATH, and GSMPlus show the effectiveness and efficiency of the proposed PRM data construction framework.
  arXiv  Detail & Related papers  (2025-08-03T14:14:13Z)
• Discriminative Policy Optimization for Token-Level Reward Models [55.98642069903191]
  Process reward models (PRMs) provide more nuanced supervision compared to outcome reward models (ORMs)<n>Q-RM explicitly learns token-level Q-functions from preference data without relying on fine-grained annotations.<n>Reinforcement learning with Q-RM significantly enhances training efficiency, achieving convergence 12 times faster than ORM on GSM8K and 11 times faster than step-level PRM on MATH.
  arXiv  Detail & Related papers  (2025-05-29T11:40:34Z)
• Beyond the First Error: Process Reward Models for Reflective Mathematical Reasoning [49.21525229904197]
  We propose a novel data annotation method for PRMs specifically designed to score the long CoT reasoning process.<n>We introduce the concepts of Error Propagation and Error Cessation, enhancing PRMs' ability to identify both effective self-correction behaviors and reasoning based on erroneous steps.<n>Our PRM achieves superior performance across various metrics, including search guidance, BoN, and F1 scores.
  arXiv  Detail & Related papers  (2025-05-20T14:12:05Z)
• Accurate and Diverse LLM Mathematical Reasoning via Automated PRM-Guided GFlowNets [6.001837672951086]
  We introduce a novel Process Reward Model (PRM) trained automatically using Monte Carlo Tree Search.<n>We then adapt Generative Flow Networks (GFlowNets) to operate at the reasoning step level.<n> Empirical evaluation shows strong improvements in both accuracy and solution diversity on challenging mathematical benchmarks.
  arXiv  Detail & Related papers  (2025-04-28T16:56:41Z)
• Process Reward Models That Think [86.88809596842428]
  Step-by-step verifiers -- also known as process reward models (PRMs) -- are a key ingredient for test-time scaling.<n>This work aims to build data-efficient PRMs as verbalized step-wise reward models that verify every step in the solution by generating a verification chain-of-thought (CoT)<n>We propose ThinkPRM, a long CoT verifier fine-tuned on orders of magnitude fewer process labels than those required by discriminative PRMs.
  arXiv  Detail & Related papers  (2025-04-23T15:44:54Z)
• Efficient Process Reward Model Training via Active Learning [27.846449143217704]
  Process Reward Models (PRMs) provide step-level supervision to large language models (LLMs)<n>We propose an active learning approach, ActPRM, which proactively selects the most uncertain samples for training.<n>A capable yet costly reasoning model then labels this data.<n>A subsequent training on this selected dataset yields a new state-of-the-art (SOTA) PRM on ProcessBench (75.0%) and PRMBench (65.5%) compared with same sized models.
  arXiv  Detail & Related papers  (2025-04-14T14:53:56Z)
• GenPRM: Scaling Test-Time Compute of Process Reward Models via Generative Reasoning [35.429904556288996]
  We introduce GenPRM, a generative process reward model that performs explicit Chain-of-Thought (CoT) reasoning with code verification.<n> Experimental results show that GenPRM significantly outperforms prior PRMs with only 23K training data from MATH dataset.
  arXiv  Detail & Related papers  (2025-04-01T15:21:05Z)
• The First Few Tokens Are All You Need: An Efficient and Effective Unsupervised Prefix Fine-Tuning Method for Reasoning Models [69.798277882245]
  We introduce Unsupervised Prefix Fine-Tuning (UPFT) to enhance large language models' reasoning efficiency.<n>UPFT removes the need for labeled data or exhaustive sampling.<n> Experiments show that UPFT matches the performance of supervised methods.
  arXiv  Detail & Related papers  (2025-03-04T18:56:03Z)
• Free Process Rewards without Process Labels [55.14044050782222]
  We show that an textitimplicit PRM can be obtained at no additional cost, by simply training an ORM on the cheaper response-level labels.<n>We show that our implicit PRM, when instantiated with the cross-entropy (CE) loss, is more data-efficient and can keep improving generation models even when trained with only one response per instruction.
  arXiv  Detail & Related papers  (2024-12-02T21:20:02Z)
• InfiMM-Eval: Complex Open-Ended Reasoning Evaluation For Multi-Modal Large Language Models [50.03163753638256]
  Multi-modal Large Language Models (MLLMs) are increasingly prominent in the field of artificial intelligence. Our benchmark comprises three key reasoning categories: deductive, abductive, and analogical reasoning. We evaluate a selection of representative MLLMs using this rigorously developed open-ended multi-step elaborate reasoning benchmark.
  arXiv  Detail & Related papers  (2023-11-20T07:06:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.