From the 1 of 3 linked papers with an AI index.
3 papers
Metacognition in LLMs: Foundations, Progress, and Opportunities
Gabrielle Kaili-May Liu, Areeb Gani, Jacqueline Lu +3
The paper surveys recent work on metacognition in large language models, reviewing methods, benchmarks, and applications for measuring and improving models' self‑reflective abiliti…
Reinforcement Learning with Metacognitive Feedback Elicits Faithful Uncertainty Expression in LLMs
Gabrielle Kaili-May Liu, Avi Caciularu, Gal Yona +2
Metacognition is a critical component of intelligence that describes the ability to monitor and regulate one's own cognitive processes. Yet LLMs exhibit systemic deficiencies in ke…
MDCure: A Scalable Pipeline for Multi-Document Instruction-Following
Gabrielle Kaili-May Liu, Bowen Shi, Avi Caciularu +2
Multi-document (MD) processing is crucial for LLMs to handle real-world tasks such as summarization and question-answering across large sets of documents. While LLMs have improved…