تقرير
CrAM: Credibility-Aware Attention Modification in LLMs for Combating Misinformation in RAG
| العنوان: | CrAM: Credibility-Aware Attention Modification in LLMs for Combating Misinformation in RAG |
|---|---|
| المؤلفون: | Deng, Boyi, Wang, Wenjie, Zhu, Fengbin, Wang, Qifan, Feng, Fuli |
| سنة النشر: | 2024 |
| المجموعة: | Computer Science |
| مصطلحات موضوعية: | Computer Science - Computation and Language |
| الوصف: | Retrieval-Augmented Generation (RAG) can alleviate hallucinations of Large Language Models (LLMs) by referencing external documents. However, the misinformation in external documents may mislead LLMs' generation. To address this issue, we explore the task of "credibility-aware RAG", in which LLMs automatically adjust the influence of retrieved documents based on their credibility scores to counteract misinformation. To this end, we introduce a plug-and-play method named $\textbf{Cr}$edibility-aware $\textbf{A}$ttention $\textbf{M}$odification (CrAM). CrAM identifies influential attention heads in LLMs and adjusts their attention weights based on the credibility of the documents, thereby reducing the impact of low-credibility documents. Experiments on Natual Questions and TriviaQA using Llama2-13B, Llama3-8B, and Qwen-7B show that CrAM improves the RAG performance of LLMs against misinformation pollution by over 20%, even surpassing supervised fine-tuning methods. Comment: Under review |
| نوع الوثيقة: | Working Paper |
| URL الوصول: | http://arxiv.org/abs/2406.11497 |
| رقم الأكسشن: | edsarx.2406.11497 |
| قاعدة البيانات: | arXiv |
| الوصف غير متاح. |