Our paper “Automatically Correcting Large Language Models: Surveying the Landscape of Diverse Automated Correction Strategies”, published in TACL 2024, was covered by Communications of the ACM (CACM) in the news article Self-Correction in Large Language Models.
About the Paper
Techniques leveraging automated feedback, either produced by the LLM itself (self-correction) or some external system, are of particular interest as they make LLM-based solutions more practical and deployable with minimal human intervention. Our survey paper provides an exhaustive review of the recent advances in correcting LLMs with automated feedback, categorizing them into training-time, generation-time, and post-hoc approaches. We also identify potential challenges and future directions in this emerging field.
About CACM
Communications of the ACM is the monthly journal of the Association for Computing Machinery (ACM). According to the Journal Citation Reports, the journal has a 2023 impact factor of 11.1. It is widely read by researchers and practitioners across computing.