AIOct 21, 2024

Reflection-Bench: Evaluating Epistemic Agency in Large Language Models

arXiv:2410.16270v35 citationsh-index: 9Has CodeICML
Originality Incremental advance
AI Analysis

This addresses the need for reliable AI agents by providing a foundational benchmark to assess epistemic agency, though it is incremental as it builds on existing cognitive psychology concepts.

The paper tackled the problem of evaluating epistemic agency in large language models (LLMs) by proposing Reflection-Bench, a benchmark with seven tasks, and found that current LLMs show a three-tier performance hierarchy with significant limitations, especially in meta-reflection.

With large language models (LLMs) increasingly deployed as cognitive engines for AI agents, the reliability and effectiveness critically hinge on their intrinsic epistemic agency, which remains understudied. Epistemic agency, the ability to flexibly construct, adapt, and monitor beliefs about dynamic environments, represents a base-model-level capacity independent of specific tools, modules, or applications. We characterize the holistic process underlying epistemic agency, which unfolds in seven interrelated dimensions: prediction, decision-making, perception, memory, counterfactual thinking, belief updating, and meta-reflection. Correspondingly, we propose Reflection-Bench, a cognitive-psychology-inspired benchmark consisting of seven tasks with long-term relevance and minimization of data leakage. Through a comprehensive evaluation of 16 models using three prompting strategies, we identify a clear three-tier performance hierarchy and significant limitations of current LLMs, particularly in meta-reflection capabilities. While state-of-the-art LLMs demonstrate rudimentary signs of epistemic agency, our findings suggest several promising research directions, including enhancing core cognitive functions, improving cross-functional coordination, and developing adaptive processing mechanisms. Our code and data are available at https://github.com/AI45Lab/ReflectionBench.

Code Implementations2 repos
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes