MR-Ben: A Meta-Reasoning Benchmark for Evaluating System-2 Thinking in LLMs
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929641546055680 |
|---|---|
| author | Zeng, Zhongshen Liu, Yinhong Wan, Yingjia Li, Jingyao Chen, Pengguang Dai, Jianbo Yao, Yuxuan Xu, Rongwu Qi, Zehan Zhao, Wanru Shen, Linling Lu, Jianqiao Tan, Haochen Chen, Yukang Zhang, Hao Shi, Zhan Wang, Bailin Guo, Zhijiang Jia, Jiaya |
| author_facet | Zeng, Zhongshen Liu, Yinhong Wan, Yingjia Li, Jingyao Chen, Pengguang Dai, Jianbo Yao, Yuxuan Xu, Rongwu Qi, Zehan Zhao, Wanru Shen, Linling Lu, Jianqiao Tan, Haochen Chen, Yukang Zhang, Hao Shi, Zhan Wang, Bailin Guo, Zhijiang Jia, Jiaya |
| contents | Large language models (LLMs) have shown increasing capability in problem-solving and decision-making, largely based on the step-by-step chain-of-thought reasoning processes. However, evaluating these reasoning abilities has become increasingly challenging. Existing outcome-based benchmarks are beginning to saturate, becoming less effective in tracking meaningful progress. To address this, we present a process-based benchmark MR-Ben that demands a meta-reasoning skill, where LMs are asked to locate and analyse potential errors in automatically generated reasoning steps. Our meta-reasoning paradigm is especially suited for system-2 slow thinking, mirroring the human cognitive process of carefully examining assumptions, conditions, calculations, and logic to identify mistakes.MR-Ben comprises 5,975 questions curated by human experts across a wide range of subjects, including physics, chemistry, logic, coding, and more. Through our designed metrics for assessing meta-reasoning on this benchmark, we identify interesting limitations and weaknesses of current LLMs (open-source and closed-source models). For example, with models like the o1 series from OpenAI demonstrating strong performance by effectively scrutinizing the solution space, many other state-of-the-art models fall significantly behind on MR-Ben, exposing potential shortcomings in their training strategies and inference methodologies. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_13975 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MR-Ben: A Meta-Reasoning Benchmark for Evaluating System-2 Thinking in LLMs Zeng, Zhongshen Liu, Yinhong Wan, Yingjia Li, Jingyao Chen, Pengguang Dai, Jianbo Yao, Yuxuan Xu, Rongwu Qi, Zehan Zhao, Wanru Shen, Linling Lu, Jianqiao Tan, Haochen Chen, Yukang Zhang, Hao Shi, Zhan Wang, Bailin Guo, Zhijiang Jia, Jiaya Computation and Language Artificial Intelligence Large language models (LLMs) have shown increasing capability in problem-solving and decision-making, largely based on the step-by-step chain-of-thought reasoning processes. However, evaluating these reasoning abilities has become increasingly challenging. Existing outcome-based benchmarks are beginning to saturate, becoming less effective in tracking meaningful progress. To address this, we present a process-based benchmark MR-Ben that demands a meta-reasoning skill, where LMs are asked to locate and analyse potential errors in automatically generated reasoning steps. Our meta-reasoning paradigm is especially suited for system-2 slow thinking, mirroring the human cognitive process of carefully examining assumptions, conditions, calculations, and logic to identify mistakes.MR-Ben comprises 5,975 questions curated by human experts across a wide range of subjects, including physics, chemistry, logic, coding, and more. Through our designed metrics for assessing meta-reasoning on this benchmark, we identify interesting limitations and weaknesses of current LLMs (open-source and closed-source models). For example, with models like the o1 series from OpenAI demonstrating strong performance by effectively scrutinizing the solution space, many other state-of-the-art models fall significantly behind on MR-Ben, exposing potential shortcomings in their training strategies and inference methodologies. |
| title | MR-Ben: A Meta-Reasoning Benchmark for Evaluating System-2 Thinking in LLMs |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2406.13975 |