LLM Critics Help Catch Bugs in Mathematics: Towards a Better Mathematical Verifier with Natural Language Feedback

• URL: http://arxiv.org/abs/2406.14024v4
• Date: Fri, 18 Oct 2024 06:59:24 GMT
• Title: LLM Critics Help Catch Bugs in Mathematics: Towards a Better Mathematical Verifier with Natural Language Feedback
• Authors: Bofei Gao, Zefan Cai, Runxin Xu, Peiyi Wang, Ce Zheng, Runji Lin, Keming Lu, Dayiheng Liu, Chang Zhou, Wen Xiao, Junjie Hu, Tianyu Liu, Baobao Chang,
• Abstract summary: We propose Math-Minos, a natural language feedback-enhanced verifier. Our experiments reveal that a small set of natural language feedback can significantly boost the performance of the verifier.
• Score: 71.95402654982095
• License:
• Abstract: In recent progress, mathematical verifiers have achieved success in mathematical reasoning tasks by validating the correctness of solutions generated by policy models. However, existing verifiers are trained with binary classification labels, which are not informative enough for the model to accurately assess the solutions. To mitigate the aforementioned insufficiency of binary labels, we introduce step-wise natural language feedback as rationale labels, that is, the correctness of each step and the detailed explanations. In this paper, we propose Math-Minos, a natural language feedback-enhanced verifier by constructing automatically generated training data and a two-stage training paradigm for effective training and efficient inference. Our experiments reveal that a small set of natural language feedback can significantly boost the performance of the verifier in both verification and reinforcement learning. We have released the code and data for further exploration.

Related papers

• Subtle Errors Matter: Preference Learning via Error-injected Self-editing [59.405145971637204]
  We propose a novel preference learning framework called eRror-Injected Self-Editing (RISE) RISE injects predefined subtle errors into partial tokens of correct solutions to construct hard pairs for error mitigation. Experiments validate the effectiveness of RISE, with preference learning on Qwen2-7B-Instruct yielding notable improvements of 3.0% on GSM8K and 7.9% on MATH.
  arXiv  Detail & Related papers  (2024-10-09T07:43:38Z)
• Improving LLM Reasoning through Scaling Inference Computation with Collaborative Verification [52.095460362197336]
  Large language models (LLMs) struggle with consistent and accurate reasoning. LLMs are trained primarily on correct solutions, reducing their ability to detect and learn from errors. We propose a novel collaborative method integrating Chain-of-Thought (CoT) and Program-of-Thought (PoT) solutions for verification.
  arXiv  Detail & Related papers  (2024-10-05T05:21:48Z)
• SIaM: Self-Improving Code-Assisted Mathematical Reasoning of Large Language Models [54.78329741186446]
  We propose a novel paradigm that uses a code-based critic model to guide steps including question-code data construction, quality control, and complementary evaluation. Experiments across both in-domain and out-of-domain benchmarks in English and Chinese demonstrate the effectiveness of the proposed paradigm.
  arXiv  Detail & Related papers  (2024-08-28T06:33:03Z)
• Prover-Verifier Games improve legibility of LLM outputs [12.532113917099885]
  We study legibility in the context of solving grade-school math problems. We propose a training algorithm inspired by Prover-Verifier Game from Anil et al. We show that legibility training transfers to time-constrained humans tasked with verifying solution correctness.
  arXiv  Detail & Related papers  (2024-07-18T16:58:18Z)
• Token-Supervised Value Models for Enhancing Mathematical Reasoning Capabilities of Large Language Models [35.29961848648335]
  Large Language Models (LLMs) have demonstrated impressive problem-solving capabilities in mathematics through step-by-step reasoning chains. They are susceptible to reasoning errors that impact the quality of subsequent reasoning chains and the final answer due to their autoregressive token-by-token generating nature. Recent works have proposed adopting external verifiers to guide the generation of reasoning paths, but existing works utilize models that have been trained with step-by-step labels.
  arXiv  Detail & Related papers  (2024-07-12T13:16:50Z)
• Evaluating Mathematical Reasoning Beyond Accuracy [50.09931172314218]
  We introduce ReasonEval, a new methodology for evaluating the quality of reasoning steps. We show that ReasonEval achieves state-of-the-art performance on human-labeled datasets. We observe that ReasonEval can play a significant role in data selection.
  arXiv  Detail & Related papers  (2024-04-08T17:18:04Z)
• XAL: EXplainable Active Learning Makes Classifiers Better Low-resource Learners [71.8257151788923]
  We propose a novel Explainable Active Learning framework (XAL) for low-resource text classification. XAL encourages classifiers to justify their inferences and delve into unlabeled data for which they cannot provide reasonable explanations. Experiments on six datasets show that XAL achieves consistent improvement over 9 strong baselines.
  arXiv  Detail & Related papers  (2023-10-09T08:07:04Z)
• Entailment as Robust Self-Learner [14.86757876218415]
  We design a prompting strategy that formulates a number of different NLU tasks as contextual entailment. We propose the Simple Pseudo-Label Editing (SimPLE) algorithm for better pseudo-labeling quality in self-training.
  arXiv  Detail & Related papers  (2023-05-26T18:41:23Z)
• Label-Descriptive Patterns and their Application to Characterizing Classification Errors [31.272875287136426]
  State-of-the-art deep learning methods achieve human-like performance on many tasks, but make errors nevertheless. Characterizing these errors in easily interpretable terms gives insight into whether a model is prone to making systematic errors, but also gives a way to act and improve the model. In this paper we propose a method that allows us to do so for arbitrary classifiers by mining a small set of patterns that together succinctly describe the input data that is partitioned according to correctness of prediction.
  arXiv  Detail & Related papers  (2021-10-18T19:42:21Z)

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.