Large Language Models Have Intrinsic Meta-Cognition, but Need a Good Lens
Previous research has primarily focused on the cognitive error detection capabilities of Large Language Models (LLMs), often prompting them to analyze mistakes in reasoning chains. However, few studies have examined the meta-cognitive abilities of LLMs (e.g., their self-awareness of step errors), which are crucial for their reliability. While studies on LLM self-evaluation present some measures, such as perplexity, which can reflect the answer correctness and be viewed as the lens of meta-cognition, they lack step-level analysis and adaptation. This paper studies the evaluation of LLM meta-cognition using the current lenses and how to improve these lenses. Specifically, we propose AutoMeco, an Automated Meta-cognition Evaluation framework for benchmarking the existing lenses. Furthermore, a training-free Markovian Intrinsic Reward Adjustment strategy, MIRA, is proposed to boost current meta-cognition lenses. Experimental results on three mathematical reasoning datasets and three LLMs show the reasonableness of AutoMeco by comparing it with Best-of-N verification. Moreover, the meta-cognition ability of LLMs can be better evaluated using MIRA.
Code (0)
등록된 구현이 없습니다.
Tasks
BenchmarkingMathematical ReasoningSimilar Papers 제목 키워드 기반
Truly Self-Improving Agents Require Intrinsic Metacognitive Learning
Self-improving agents aim to continuously acquire new capabilities with minimal supervision. However, current approaches face two key limitations: their self-improvement processes are often rigid, fail to generalize acro…
Human Cognition in Machines: A Unified Perspective of World Models
This report of world models distinguishes prior works by the cognitive functions they innovate. Many works claim an almost human-like cognitive capability in their world models. To evaluate these claims requires a proper…
MetaFaith: Faithful Natural Language Uncertainty Expression in LLMs
A critical component in the trustworthiness of LLMs is reliable uncertainty communication, yet LLMs often use assertive language when conveying false claims, leading to over-reliance and eroded trust. We present the firs…
BenchmarkingJudgment of Learning: A Human Ability Beyond Generative Artificial Intelligence
Large language models (LLMs) increasingly mimic human cognition in various language-based tasks. However, their capacity for metacognition - particularly in predicting memory performance - remains unexplored. Here, we in…
SentenceBenchmarking Meta-embeddings: What Works and What Does Not
In the last few years, several methods have been proposed to build meta-embeddings. The general aim was to obtain new representations integrating complementary knowledge from different source pre-trained embeddings there…
BenchmarkingEmbeddings Evaluation