Temporal Consistency for LLM Reasoning Process Error Identification
Verification is crucial for effective mathematical reasoning. We present a new temporal consistency method where verifiers iteratively refine their judgments based on the previous assessment. Unlike one-round verification or multi-model debate approaches, our method leverages consistency in a sequence of self-reflection actions to improve verification accuracy. Empirical evaluations across diverse mathematical process error identification benchmarks (Mathcheck, ProcessBench, and PRM800K) show consistent performance improvements over baseline methods. When applied to the recent DeepSeek R1 distilled models, our method demonstrates strong performance, enabling 7B/8B distilled models to outperform all 70B/72B models and GPT-4o on ProcessBench. Notably, the distilled 14B model with our method achieves performance comparable to Deepseek-R1. Our codes are available at https://github.com/jcguo123/Temporal-Consistency
Code (1)
Tasks
Mathematical ReasoningSimilar Papers 제목 키워드 기반
Table-Critic: A Multi-Agent Framework for Collaborative Criticism and Refinement in Table Reasoning
Despite the remarkable capabilities of large language models (LLMs) in various reasoning tasks, they still struggle with table reasoning tasks, particularly in maintaining consistency throughout multi-step reasoning proc…
Computational EfficiencyThink Step by Step: Chain-of-Gesture Prompting for Error Detection in Robotic Surgical Videos
Despite significant advancements in robotic systems and surgical data science, ensuring safe and optimal execution in robot-assisted minimally invasive surgery (RMIS) remains a complex challenge. Current surgical error d…
Temporal Information ExtractionVisual ReasoningExplainable Chain-of-Thought Reasoning: An Empirical Analysis on State-Aware Reasoning Dynamics
Recent advances in chain-of-thought (CoT) prompting have enabled large language models (LLMs) to perform multi-step reasoning. However, the explainability of such reasoning remains limited, with prior work primarily focu…
NeSTR: A Neuro-Symbolic Abductive Framework for Temporal Reasoning in Large Language Models
Large Language Models (LLMs) have demonstrated remarkable performance across a wide range of natural language processing tasks. However, temporal reasoning, particularly under complex temporal constraints, remains a majo…
Question AnsweringDiffCoT: Diffusion-styled Chain-of-Thought Reasoning in LLMs
Chain-of-Thought (CoT) reasoning improves multi-step mathematical problem solving in large language models but remains vulnerable to exposure bias and error accumulation, as early mistakes propagate irreversibly through …