作者位次 #6/9ACL 2026Poster· Natural Language Processing
F act C orrector: A Graph-Inspired Approach to Long-Form Factuality Correction of Large Language Models
Javier Carnerero-Cano · Massimiliano Pronesti · Radu Marinescu · Tigran T. Tchrakian · James Barry · Jasmina Gajcin · Yufang Hou · Alessandra Pascale · Elizabeth M. Daly
摘要
Large language models (LLMs) are widely used in knowledge-intensive applications but often generate factually incorrect responses. A promising approach to rectify these flaws is correcting LLMs using feedback. Therefore, in this paper, we introduce FactCorrector, a new post-hoc correction method...