3 papers
cs.CL2025
EvoEdit: Lifelong Free-Text Knowledge Editing through Latent Perturbation Augmentation and Knowledge-driven Parameter Fusion
Pengfei Cao, Zeao Ji, Daojian Zeng +2
Adjusting the outdated knowledge of large language models (LLMs) after deployment remains a major challenge. This difficulty has spurred the development of knowledge editing, which…
cs.CL2024
Whispers that Shake Foundations: Analyzing and Mitigating False Premise Hallucinations in Large Language Models
Hongbang Yuan, Pengfei Cao, Zhuoran Jin +4
Large Language Models (LLMs) have shown impressive capabilities but still suffer from the issue of hallucinations. A significant type of this issue is the false premise hallucinati…
cs.CL2024
Focus on Your Question! Interpreting and Mitigating Toxic CoT Problems in Commonsense Reasoning
Jiachun Li, Pengfei Cao, Chenhao Wang +5
Large language models exhibit high-level commonsense reasoning abilities, especially with enhancement methods like Chain-of-Thought (CoT). However, we find these CoT-like methods l…