CoLD: Counterfactually-Guided Length Debiasing for Process Reward Models

• URL: http://arxiv.org/abs/2507.15698v1
• Date: Mon, 21 Jul 2025 15:07:59 GMT
• Title: CoLD: Counterfactually-Guided Length Debiasing for Process Reward Models
• Authors: Congmin Zheng, Jiachen Zhu, Jianghao Lin, Xinyi Dai, Yong Yu, Weinan Zhang, Mengyue Yang,
• Abstract summary: We propose a unified framework that mitigates length bias through three components.<n>CoLD consistently reduces reward-length correlation, improves accuracy in step selection, and encourages more concise, logically valid reasoning.
• Score: 29.95434387343843
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Process Reward Models (PRMs) play a central role in evaluating and guiding multi-step reasoning in large language models (LLMs), especially for mathematical problem solving. However, we identify a pervasive length bias in existing PRMs: they tend to assign higher scores to longer reasoning steps, even when the semantic content and logical validity are unchanged. This bias undermines the reliability of reward predictions and leads to overly verbose outputs during inference. To address this issue, we propose CoLD(Counterfactually-Guided Length Debiasing), a unified framework that mitigates length bias through three components: an explicit length-penalty adjustment, a learned bias estimator trained to capture spurious length-related signals, and a joint training strategy that enforces length-invariance in reward predictions. Our approach is grounded in counterfactual reasoning and informed by causal graph analysis. Extensive experiments on MATH500 and GSM-Plus show that CoLD consistently reduces reward-length correlation, improves accuracy in step selection, and encourages more concise, logically valid reasoning. These results demonstrate the effectiveness and practicality of CoLD in improving the fidelity and robustness of PRMs.

Related papers

• Accelerating LLM Reasoning via Early Rejection with Partial Reward Modeling [12.835376812101323]
  We introduce the hypothesis that PRMs are also Partial Reward Models.<n>This allows for principled early rejection based on intermediate token-level signals.<n>On math reasoning benchmarks, our method achieves up to 1.4$times$-9$times$ reduction in inference FLOPs without degrading final performance.
  arXiv  Detail & Related papers  (2025-08-04T00:58:56Z)
• AALC: Large Language Model Efficient Reasoning via Adaptive Accuracy-Length Control [18.273777938294327]
  Large reasoning models (LRMs) achieve impressive reasoning capabilities by generating lengthy chain-of-thoughts.<n>We introduce AALC, a lightweight, accuracy-aware length reward integrated into reinforcement learning.<n>We show that our approach reduces response length by over 50% while maintaining or even improving the original accuracy.
  arXiv  Detail & Related papers  (2025-06-25T06:29:18Z)
• ReCUT: Balancing Reasoning Length and Accuracy in LLMs via Stepwise Trails and Preference Optimization [16.51303604678232]
  Reasoning Compression ThroUgh Stepwise Trials (ReCUT) is a novel method aimed at balancing the accuracy and length of reasoning trajectory.<n> Experimental results across multiple math reasoning datasets and backbone models demonstrate that ReCUT significantly reduces reasoning lengths by approximately 30-50%.
  arXiv  Detail & Related papers  (2025-06-12T15:43:01Z)
• Mitigating Spurious Correlations in LLMs via Causality-Aware Post-Training [57.03005244917803]
  Large language models (LLMs) often fail on out-of-distribution (OOD) samples due to spurious correlations acquired during pre-training.<n>Here, we aim to mitigate such spurious correlations through causality-aware post-training (CAPT)<n> Experiments on the formal causal inference benchmark CLadder and the logical reasoning dataset PrOntoQA show that 3B-scale language models fine-tuned with CAPT can outperform both traditional SFT and larger LLMs on in-distribution (ID) and OOD tasks.
  arXiv  Detail & Related papers  (2025-06-11T06:30:28Z)
• What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding [84.42056293290015]
  We analyze the token-level misalignment between reasoning and non-reasoning models.<n>Motivated by the Local Misalignment Diminish, we propose FoReaL-Decoding.<n>On four popular math-reasoning benchmarks, FoReaL-Decoding reduces theoretical FLOPs by 30 to 50% and trims CoT length by up to 40%.
  arXiv  Detail & Related papers  (2025-06-08T05:08:32Z)
• Thinking Fast and Right: Balancing Accuracy and Reasoning Length with Adaptive Rewards [17.829990749622496]
  We propose an adaptive reward-shaping method for large language models.<n>Our method dynamically adjusts the trade-off between accuracy and response length based on model performance.<n> Experiments show that our approach consistently and dramatically reduces reasoning length while largely maintaining accuracy.
  arXiv  Detail & Related papers  (2025-05-23T18:44:46Z)
• Fractured Chain-of-Thought Reasoning [61.647243580650446]
  We introduce Fractured Sampling, a unified inference-time strategy that interpolates between full CoT and solution-only sampling.<n>We show that Fractured Sampling consistently achieves superior accuracy-cost trade-offs, yielding steep log-linear scaling gains in Pass@k versus token budget.
  arXiv  Detail & Related papers  (2025-05-19T11:30:41Z)
• Bias Fitting to Mitigate Length Bias of Reward Model in RLHF [81.44256822500257]
  Reinforcement Learning from Human Feedback relies on reward models to align large language models with human preferences.<n>We propose FiMi-RM, a framework that autonomously learns and corrects underlying bias patterns.<n> Experimental results demonstrate that FiMi-RM achieves a more balanced length-reward distribution.
  arXiv  Detail & Related papers  (2025-05-19T08:29:28Z)
• Disentangling Length Bias In Preference Learning Via Response-Conditioned Modeling [87.17041933863041]
  Reinforcement Learning from Human Feedback (RLHF) has achieved considerable success in aligning large language models (LLMs)<n>We introduce a $textbfR$esponse-$textbfc$onditioned $textbfB$radley-$textbfT$erry (Rc-BT) model that enhances the model's capability in length bias mitigating and length instruction following.<n>We also propose the Rc-RM and Rc-DPO algorithm to leverage the Rc-BT model for reward modeling and direct policy optimization
  arXiv  Detail & Related papers  (2025-02-02T14:50:25Z)
• Post-hoc Reward Calibration: A Case Study on Length Bias [28.266675778940133]
  Reward models (RMs) can develop biases by exploiting spurious correlations in their training data. These biases can lead to incorrect output rankings, sub-optimal model evaluations, and the amplification of undesirable behaviours. This paper addresses the challenge of correcting such biases without additional data and training.
  arXiv  Detail & Related papers  (2024-09-25T22:30:42Z)
• ODIN: Disentangled Reward Mitigates Hacking in RLHF [127.35607931337019]
  We study the issue of reward hacking on the response length, a challenge emerging in Reinforcement Learning from Human Feedback. A well-formatted, verbose but less helpful response from the LLMs can often deceive LLMs or even human evaluators to achieve high scores. Our approach almost eliminates the reward correlation with length, and improves the obtained policy by a significant margin.
  arXiv  Detail & Related papers  (2024-02-11T22:40:12Z)
• REFINER: Reasoning Feedback on Intermediate Representations [47.36251998678097]
  We introduce REFINER, a framework for finetuning language models to generate intermediate inferences. REFINER works by interacting with a critic model that provides automated feedback on the reasoning. Empirical evaluations show significant improvements over baseline LMs of comparable scale.
  arXiv  Detail & Related papers  (2023-04-04T15:57:28Z)

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.