Challenge: Existing approaches for constructing PRM training data rely on human annotation or sampling-based labeling methods that require repeated LLM calls.
Approach: They propose a framework that synthesizes PRM training data by annotating step-level error labels using formal verification tools such as Z3 and Isabelle.
Outcome: The proposed framework synthesizes PRM training data from formal logic and theorem proving tasks without human annotation or additional LLM calls.

Similar Papers

An Efficient and Precise Training Data Construction Framework for Process-supervised Reward Model in Mathematical Reasoning (2025.acl-long)

Copied to clipboard

Challenge: Existing methods for constructing process supervision training data are costly or suffer from poor quality.
Approach: They propose a framework called EpicPRM which annotates each intermediate reasoning step based on its quantified contribution and uses an adaptive binary search algorithm to enhance annotation precision and efficiency.
Outcome: The proposed framework improves annotation precision and efficiency and can be used to train a high-quality training dataset with 50k annotated intermediate steps.
Process-Supervised Reward Models for Verifying Clinical Note Generation: A Scalable Approach Guided by Domain Expertise (2025.emnlp-main)

Copied to clipboard

Challenge: Currently, no automated, scalable method exists to evaluate the quality of LLM-generated clinical notes, leaving manual evaluation the gold standard.
Approach: They propose a framework for training PRMs to deliver step-level reward signals for LLM-generated clinical notes.
Outcome: The proposed framework outperforms reasoning and non-reasoning models on key evaluations and selects physician-preferred clinical notes with 56.2% accuracy.
Process Reward Models Meet Planning: Generating Precise and Scalable Datasets for Step-Level Rewards (2026.acl-long)

Copied to clipboard

Challenge: Existing PRM datasets are expensive to construct and limited to the mathematical domain.
Approach: They propose a method to generate a corpus of one million reasoning steps using the Planning Domain Definition Language.
Outcome: The proposed model generates a corpus of approximately one million reasoning steps across various PDDL domains and trains them.
Error Typing for Smarter Rewards: Improving Process Reward Models with Error-Aware Hierarchical Supervision (2025.findings-emnlp)

Copied to clipboard

Challenge: Large Language Models (LLMs) are prone to hallucination, especially during multihop tasks.
Approach: They propose a hierarchical, erroraware discriminative PRM that classifies math errors at each step and combines finegrained signals to estimate step correctness.
Outcome: The proposed model outperforms the prior best in a new stateof-theart PRMScore of 67.7 on a 400Ksample dataset .
The Lessons of Developing Process Reward Models in Mathematical Reasoning (2025.findings-acl)

Copied to clipboard

Challenge: a recent study shows that process reward models can make mistakes, leading to wrong conclusions.
Approach: They propose a consensus filtering mechanism that integrates MC estimation with LLM-as-a-judge to improve model performance and data efficiency.
Outcome: The proposed model outperforms existing open-source alternatives and provides practical guidelines for future research.
Beyond the First Error: Process Reward Models for Reflective Mathematical Reasoning (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for training effective PRMs focus on the first incorrect step and all preceding steps, assuming that all subsequent steps are incorrect.
Approach: They propose a data annotation method specifically designed to score the long CoT reasoning process by using an LLM-based judger for annotation.
Outcome: The proposed method improves PRMs' ability to identify effective self-correction behaviors and reasoning based on erroneous steps.
Enhancing Logical Reasoning in Language Models via Symbolically-Guided Monte Carlo Process Supervision (2025.emnlp-main)

Copied to clipboard

Challenge: Large language models have shown strong performance in many reasoning benchmarks, but lack robust planning or symbolic abstractions.
Approach: They propose to synthesize high-quality symbolic reasoning trajectories with stepwise pseudo-labels at scale via Monte Carlo estimation.
Outcome: The proposed method can be trained on high-quality symbolic reasoning trajectories with stepwise pseudo-labels at scale using Monte Carlo estimation.
R-PRM: Reasoning-Driven Process Reward Modeling (2025.emnlp-main)

Copied to clipboard

Challenge: Existing Process Reward Models (PRMs) output evaluation scores directly, limiting both learning efficiency and evaluation accuracy.
Approach: They propose a Reasoning-Driven Process Reward Modeling (R-PRM) which activates inherent reasoning to enhance process-level evaluation.
Outcome: The proposed model outperforms baseline models on ProcessBench and PRMBench by 13.9 and 8.5 F1 scores.
From Informal to Formal – Incorporating and Evaluating LLMs on Natural Language Requirements to Verifiable Formal Proofs (2025.acl-long)

Copied to clipboard

Challenge: Recent studies in formal mathematical reasoning have shown an unstoppable growth trend.
Approach: They constructed 18k high-quality instruction-response pairs across five mainstream formal specification languages and evaluated them against ten open-sourced LLMs.
Outcome: The proposed model compared instruction-response pairs across five formal specification languages and found that the LLMs were good at writing proof segments when given either the code, or the detailed description of proof steps.
Efficient Process Reward Modeling via Contrastive Mutual Information (2026.acl-long)

Copied to clipboard

Challenge: Existing methods to verify intermediate reasoning steps require human annotators to assign reward scores to each reasoning step, which is labor-intensive and costly.
Approach: They propose a method that leverages the model's internal probability to infer step-level supervision while significantly reducing the computational burden of annotating dataset.
Outcome: The proposed method reduces dataset construction time by 84% and token generation by 98% compared to MC estimation, while achieving higher accuracy on process-level evaluations and mathematical reasoning benchmarks.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations