LLM Critics Help Catch Bugs in Mathematics: Towards a Better Mathematical Verifier with Natural Language Feedback (2025.findings-acl)
Copied to clipboard
Bofei Gao, Zefan Cai, Runxin Xu, Peiyi Wang, Ce Zheng, Runji Lin, Keming Lu, Dayiheng Liu, Chang Zhou, Wen Xiao, Tianyu Liu, Baobao Chang
| Challenge: | Existing mathematical verifiers are trained with binary classification labels, which are not informative enough for the model to accurately assess the solutions. |
| Approach: | They propose a natural language feedback-enhanced verifier that can validate the correctness of response generated by policy models by constructing automatically generated training data and a two-stage training paradigm. |
| Outcome: | The proposed verifier significantly improves in verification and reinforcement learning and alleviates data-demanding problems of the reward model. |
Similar Papers
LLM2: Let Large Language Models Harness System 2 Reasoning (2025.naacl-short)
Copied to clipboard
| Challenge: | Empirical results on mathematical reasoning benchmarks substantiate the efficacy of Large language models (LLMs). |
| Approach: | They propose a framework that combines an LLM with a process-based verifier to generate plausible candidates and provide timely process-driven feedback to distinguish desirable and undesirable outputs. |
| Outcome: | Empirical results show that LLM2 improves accuracy on GSM8K and self-consistency increases major@20 accuracy. |
Exposing the Achilles’ Heel: Evaluating LLMs Ability to Handle Mistakes in Mathematical Reasoning (2025.acl-long)
Copied to clipboard
| Challenge: | Existing evaluations focus on final accuracy, neglecting the critical aspect of reasoning capabilities. |
| Approach: | They propose to evaluate LLMs’ abilities to detect and correct reasoning mistakes by using rule-based methods and smaller language models. |
| Outcome: | The proposed model outperforms existing models such as GPT-4o and GPT4 in both accuracy and accuracy, but lacks data contamination and memorization concerns. |
Enhancing Mathematical Reasoning in LLMs by Stepwise Correction (2025.acl-long)
Copied to clipboard
| Challenge: | Existing Best-of-N decoding methods often lead to incorrect solutions . a novel method is proposed to help large language models identify and revise incorrect steps in their generated reasoning paths. |
| Approach: | They propose a method that helps large language models identify and revise incorrect steps in their generated reasoning paths. |
| Outcome: | The proposed method outperforms the state-of-the-art Best-ofN decoding method by +2.4 and reduces token consumption by 77.8%. |
LLMs for Mathematical Modeling: Towards Bridging the Gap between Natural and Mathematical Languages (2025.findings-naacl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have demonstrated strong performance across various natural language processing tasks, but their proficiency in mathematical reasoning remains a key challenge. |
| Approach: | They propose a process-oriented framework to evaluate LLMs' ability to construct mathematical models, using solvers to compare outputs with ground truth. |
| Outcome: | The proposed framework evaluates LLMs' ability to construct mathematical models, using solvers to compare outputs with ground truth. |
Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations (2024.acl-long)
Copied to clipboard
| Challenge: | Existing methods for process-oriented math reward models rely on manual annotation. |
| Approach: | They propose a process-oriented math process reward model called Math-shepherd which assigns a reward score to each step of math problem solutions. |
| Outcome: | The proposed model breaks the bottleneck of manual supervision in two scenarios. |
Small Language Models Need Strong Verifiers to Self-Correct Reasoning (2024.findings-acl)
Copied to clipboard
Yunxiang Zhang, Muhammad Khalifa, Lajanugen Logeswaran, Jaekyeom Kim, Moontae Lee, Honglak Lee, Lu Wang
| Challenge: | Existing studies show that large language models can self-correct their outputs by generating a critique and revising it based on the critique. |
| Approach: | They propose a pipeline that prompts small language models to collect self-correction data that supports the training of self-refinement abilities. |
| Outcome: | The proposed pipeline improves the self-correction abilities of two models on five datasets spanning math and commonsense reasoning. |
Step Guided Reasoning: Improving Mathematical Reasoning using Guidance Generation and Step Reasoning (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to improve mathematical reasoning require extensive datasets for training or depend on few-shot methods that compromise computational accuracy. |
| Approach: | They propose a training-free adaptation framework that efficiently equips general-purpose pre-trained language models with enhanced mathematical reasoning capabilities. |
| Outcome: | The proposed framework outperforms Qwen2.5-72B-Math-Instruct on MMLU-STEM with a score of 90.9%, compared to 87.3%. |
CHAMP: A Competition-level Dataset for Fine-Grained Analyses of LLMs’ Mathematical Reasoning Capabilities (2024.findings-acl)
Copied to clipboard
| Challenge: | Recent large language models have shown indications of mathematical reasoning ability on competition-level problems. |
| Approach: | They propose a benchmark dataset to enable such analyses using large language models. |
| Outcome: | The proposed model performs better with concepts and hints than with the best model, but it is difficult to verify. |
MARIO: MAth Reasoning with code Interpreter Output - A Reproducible Pipeline (2024.findings-acl)
Copied to clipboard
| Challenge: | Large language models lack mathematical reasoning, a hurdle on the path to true artificial general intelligence. |
| Approach: | They propose a protocol for fine-tuning large language models with a Python code interpreter to enhance the text analysis of the LLMs. |
| Outcome: | The proposed protocol improves the performance of a 7B-parameter LLM on the GSM8K and MATH datasets while allowing for an outlier-free value model-based inference method. |
ClozeMath: Improving Mathematical Reasoning in Language Models by Learning to Fill Equations (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to train large language models do not capture how humans learn to think. |
| Approach: | They propose a method to fine-tune large language models for mathematical reasoning by using a text-infilling task that predicts masked equations from a given solution. |
| Outcome: | Experiments on GSM8K, MATH, and GSM-Symbolic show that ClozeMath surpasses baseline Masked Thought in performance and robustness with two test-time scaling decoding algorithms, Beam Search and Chain-of-Thought decoding. |