Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

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

Abstract

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.

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

Abstract

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.
Paper Structure (22 sections, 7 figures, 4 tables)

This paper contains 22 sections, 7 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Bias in RAG
  4. Ideology in LLMs
  5. Prompt Effect on Bias
  6. Methodology
  7. Lexical Multidimensional Analysis
  8. Corpus Design
  9. Pre-processing
  10. Factor Analysis
  11. LMDA Description
  12. Discourse-Augmented Generation
  13. Retriever
  14. Generator
  15. Experimental Setup
  16. ...and 7 more sections

Figures (7)

  • Figure 1: Illustration of our experimental framework where LMDA is used to identify the underlying ideology in scientific texts, which are used as an external source of knowledge by the RAG framework.
  • Figure 2: Corpus size with the number of texts and words for endorsed and controversial documents.
  • Figure 3: Factor scores after applying LMDA to the COVID-19 scientific articles.
  • Figure 4: Regular Prompt template used in RAG Configuration without LMDA descriptions.
  • Figure 5: Enhanced prompt template based on ideological texts and LMDA descriptions.
  • ...and 2 more figures