2 papers
cs.CL2026
CORTEX: Token-Level Hallucination Detection in RAG via Comparative Internal Representations
Kazuaki Furumai, Shuichiro Haruta, Kazunori Matsumoto +1
In this paper, we propose CORTEX, a token-level hallucination detection method for Retrieval-Augmented Generation (RAG). In long-form RAG outputs, hallucinations often arise in loc…
cs.CL2026
RCPU: Rotation-Constrained Error Compensation for Structured Pruning of Large Language Models
Shuichiro Haruta, Kazunori Matsumoto, Zhi Li +2
In this paper, we propose a rotation-constrained compensation method to address the errors introduced by structured pruning of large language models (LLMs). LLMs are trained on mas…