arXiv 2603.148382026-03-16cs.CL

检索增强生成中意识形态话语的影响：以新冠治疗方案为例

The Impact of Ideological Discourses in RAG: A Case Study with COVID-19 Treatments

Wichita State University（威斯康星州立大学）；Pontifícia Universidade Católica de São Paulo（圣保罗天主教大学）；Institut national de la recherche scientifique（国家科学研究中心）；Université du Québec en Outaouais（魁北克大学Outaouais）

Elmira Salari, Maria Claudia Nunes Delfino, Hazem Amamou, José Victor de Souza, Shruti Kshirsagar, Alan Davoust, Anderson Avila

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文研究检索到的意识形态文本对大语言模型输出的影响，通过新冠治疗方案案例，探讨意识形态在RAG框架中的识别与影响，揭示意识形态偏见与潜在风险。

摘要：

本文研究检索到的意识形态文本对大语言模型（LLMs）输出的影响。尽管近年来对LLMs中意识形态的理解兴趣有所增加，但在检索增强生成（RAG）背景下对此问题的关注却较少。为填补这一空白，我们设计了一个基于关于新冠治疗方案的意识形态负载文本的外部知识库。我们的语料库基于1,117篇学术文章，代表了对争议性和认可性治疗方案的讨论。我们提出了一种基于词汇多维分析（LMDA）的语料库语言学框架，以识别语料库中的意识形态。LLMs被要求回答从三个识别出的意识形态维度衍生出的问题，并采用两种类型的上下文提示：第一种包含用户问题和意识形态文本；第二种包含问题、意识形态文本和LMDA描述。通过余弦相似度评估参考意识形态文本与LLMs响应之间的意识形态一致性，用于词法和语义表示。结果表明，基于意识形态检索文本的LLMs响应更符合外部知识中的意识形态，增强提示进一步影响LLMs的输出。我们的发现强调了在RAG框架内识别意识形态话语的重要性，以减轻不仅意外意识形态偏见，还有此类模型被恶意操纵的风险。

英文摘要：

This paper studies the impact of retrieved ideological texts on the outputs of large language models (LLMs). While interest in understanding ideology in LLMs has recently increased, little attention has been given to this issue in the context of Retrieval-Augmented Generation (RAG). To fill this gap, we design an external knowledge source based on ideological loaded texts about COVID-19 treatments. Our corpus is based on 1,117 academic articles representing discourses about controversial and endorsed treatments for the disease. We propose a corpus linguistics framework, based on Lexical Multidimensional Analysis (LMDA), to identify the ideologies within the corpus. LLMs are tasked to answer questions derived from three identified ideological dimensions, and two types of contextual prompts are adopted: the first comprises the user question and ideological texts; and the second contains the question, ideological texts, and LMDA descriptions. Ideological alignment between reference ideological texts and LLMs' responses is assessed using cosine similarity for lexical and semantic representations. Results demonstrate that LLMs' responses based on ideological retrieved texts are more aligned with the ideology encountered in the external knowledge, with the enhanced prompt further influencing LLMs' outputs. Our findings highlight the importance of identifying ideological discourses within the RAG framework in order to mitigate not just unintended ideological bias, but also the risks of malicious manipulation of such models.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。