SERC: LDPC-Inspired Semantic Error Correction for Retrieval-Augmented Generation 事件

SERC: LDPC-Inspired Semantic Error Correction for Retrieval-Augmented Generation arXiv:2605.28837v1 Announce Type: new Abstract: While Large Language Models (LLMs) have demonstrated remarkable capabilities, their reliability is significantly compromised by hallucinations. Existing intrinsic self-correction methods attempt to address this, but often fail due to self-bias, where models struggle to identify errors in their own outputs without external verification. To overcome these limitations, w