Critic-CoT: Boosting the reasoning abilities of large language model via Chain-of-thoughts Critic
- URL: http://arxiv.org/abs/2408.16326v2
- Date: Thu, 10 Oct 2024 06:42:16 GMT
- Title: Critic-CoT: Boosting the reasoning abilities of large language model via Chain-of-thoughts Critic
- Authors: Xin Zheng, Jie Lou, Boxi Cao, Xueru Wen, Yuqiu Ji, Hongyu Lin, Yaojie Lu, Xianpei Han, Debing Zhang, Le Sun,
- Abstract summary: Critic-CoT is a framework that pushes LLMs toward System-2-like critic capability.
CoT reasoning paradigm and the automatic construction of distant-supervision data without human annotation.
Experiments on GSM8K and MATH demonstrate that our enhanced model significantly boosts task-solving performance.
- Score: 48.94340387130627
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Self-critic has become a crucial mechanism for enhancing the reasoning performance of LLMs. However, current approaches mainly involve basic prompts for intuitive instance-level feedback, which resembles System-1 processes and limits the reasoning capabilities. Moreover, there is a lack of in-depth investigations into the relationship between LLM's ability to criticize and its task-solving performance. To address these issues, we propose Critic-CoT, a novel framework that pushes LLMs toward System-2-like critic capability. Through a step-wise CoT reasoning paradigm and the automatic construction of distant-supervision data without human annotation, Critic-CoT enables LLMs to engage in slow, analytic self-critique and refinement, thereby improving their reasoning abilities. Experiments on GSM8K and MATH demonstrate that our enhanced model significantly boosts task-solving performance by filtering out invalid solutions or iterative refinement. Furthermore, we investigate the intrinsic correlation between critique and task-solving abilities within LLMs, discovering that these abilities can mutually reinforce each other rather than conflict.
Related papers
- Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search [57.28671084993782]
Large language models (LLMs) have demonstrated remarkable reasoning capabilities across diverse domains.
Recent studies have shown that increasing test-time computation enhances LLMs' reasoning capabilities.
We propose a two-stage training paradigm: 1) a small-scale format tuning stage to internalize the COAT reasoning format and 2) a large-scale self-improvement stage leveraging reinforcement learning.
arXiv Detail & Related papers (2025-02-04T17:26:58Z) - RealCritic: Towards Effectiveness-Driven Evaluation of Language Model Critiques [59.861013614500024]
We introduce a new benchmark designed to assess the critique capabilities of Large Language Models (LLMs)
Unlike existing benchmarks, which typically function in an open-loop fashion, our approach employs a closed-loop methodology that evaluates the quality of corrections generated from critiques.
arXiv Detail & Related papers (2025-01-24T13:48:10Z) - Enabling Scalable Oversight via Self-Evolving Critic [59.861013614500024]
SCRIT (Self-evolving CRITic) is a framework that enables genuine self-evolution of critique abilities.
It self-improves by training on synthetic data, generated by a contrastive-based self-critic.
It achieves up to a 10.3% improvement on critique-correction and error identification benchmarks.
arXiv Detail & Related papers (2025-01-10T05:51:52Z) - VISCO: Benchmarking Fine-Grained Critique and Correction Towards Self-Improvement in Visual Reasoning [112.35483894933904]
We propose VISCO, the first benchmark to extensively analyze the fine-grained critique and correction capabilities of LVLMs.
VISCO features dense and fine-grained critique, requiring LVLMs to evaluate the correctness of each step in the chain-of-thought.
LookBack significantly improves critique and correction performance by up to 13.5%.
arXiv Detail & Related papers (2024-12-03T05:04:49Z) - Critic-V: VLM Critics Help Catch VLM Errors in Multimodal Reasoning [46.411313304605564]
Critic-V is a framework inspired by the Actor-Critic paradigm to boost the reasoning capability of vision-language models (VLMs)
The Reasoner generates reasoning paths based on visual and textual inputs, and the Critic provides constructive critique to refine these paths.
evaluation results show that the Critic-V framework significantly outperforms existing methods, including GPT-4V, on 5 out of 8 benchmarks.
arXiv Detail & Related papers (2024-11-27T10:28:57Z) - CriticBench: Benchmarking LLMs for Critique-Correct Reasoning [26.45110574463893]
CriticBench is a benchmark designed to assess Large Language Models' abilities to critique and rectify their reasoning.
We evaluate and dissect the performance of 17 LLMs in generation, critique, and correction reasoning.
arXiv Detail & Related papers (2024-02-22T18:59:02Z) - Critique Ability of Large Language Models [38.34144195927209]
This study explores the ability of large language models (LLMs) to deliver accurate critiques across various tasks.
We develop a benchmark called CriticBench, which comprises 3K high-quality natural language queries and corresponding model responses.
arXiv Detail & Related papers (2023-10-07T14:12:15Z) - Measuring and Improving Chain-of-Thought Reasoning in Vision-Language Models [61.28463542324576]
Vision-language models (VLMs) have recently demonstrated strong efficacy as visual assistants that can generate human-like outputs.
We evaluate existing state-of-the-art VLMs and find that even the best-performing model is unable to demonstrate strong visual reasoning capabilities and consistency.
We propose a two-stage training framework aimed at improving both the reasoning performance and consistency of VLMs.
arXiv Detail & Related papers (2023-09-08T17:49:44Z)
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.