mlsanityData to 14 Oct 2026

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

arXiv 2603.14838 ↗First posted 16 Mar 2026cs.CLcited by 1

On the map: Retrieval-augmented generation → Medical and biomedical RAG

Abstract (arXiv)

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.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Medical and biomedical RAG, one of 15 directions in Retrieval-augmented generation. Builds on 8 of its 31 references that are in the map. First posted on arXiv 16 Mar 2026.

Builds on

8 of 31 references.

References · 8

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2024The Power of Noise: Redefining Retrieval for RAG Systemscited by 281
  3. 2023Why So Gullible? Enhancing the Robustness of Retrieval-Augmented Models against Counterfactual Noisecited by 54
  4. 2024Social Bias Evaluation for Large Language Models Requires Prompt Variationscited by 40
  5. 2024How Susceptible are Large Language Models to Ideological Manipulation?cited by 26
  6. 2024Does RAG Introduce Unfairness in LLMs? Evaluating Fairness in Retrieval-Augmented Generation Systemscited by 26
  7. 2025Mitigating Bias in RAG: Controlling the Embeddercited by 6
  8. 2025Decoding the Mind of Large Language Models: A Quantitative Evaluation of Ideology and Biasescited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Towards Trustworthy Audio Deepfake Detection: A Systematic Framework for Diagnosing and Mitigating Gender Biascited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2026How Temperature Shapes Ideological Discourse in Retrieval-Augmented Generation?
  2. 2024Extracting Affect Aggregates from Longitudinal Social Media Data with Temporal Adapters for Large Language Models
  3. 2025Demo: Guide-RAG: Evidence-Driven Corpus Curation for Retrieval-Augmented Generation in Long COVID
  4. 2024Evaluating Students' Open-ended Written Responses with LLMs: Using the RAG Framework for GPT-3.5, GPT-4, Claude-3, and Mistral-Large
  5. 2025Contradictions in Context: Challenges for Retrieval-Augmented Generation in Healthcare
  6. 2025Use of Retrieval-Augmented Large Language Model Agent for Long-Form COVID-19 Fact-Checking
  7. 2024Evaluating ChatGPT on Nuclear Domain-Specific Data
  8. 2025Better Aligned with Survey Respondents or Training Data? Unveiling Political Leanings of LLMs on U.S. Supreme Court Cases