arXiv subjects

Alan Davoust

Publications and source records attributed to Alan Davoust.

4 recordsLinked to original sources

arXiv2026

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

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.

cs.CL↗

arXiv2026

Towards Robust Retrieval-Augmented Generation Based on Knowledge Graph: A Comparative Analysis

Retrieval-Augmented Generation (RAG) was introduced to enhance the capabilities of Large Language Models (LLMs) beyond their encoded prior knowledge. This is achieved by providing LLMs with an external source of knowledge, which helps reduce factual hallucinations and enables access to new information not available during pretraining. However, inconsistent retrieved information can negatively affect LLM responses. The Retrieval-Augmented Generation Benchmark (RGB) was introduced to evaluate the robustness of RAG systems under such conditions. In this work, we use the RGB corpus to evaluate LLMs in four scenarios: noise robustness, information integration, negative rejection, and counterfactual robustness. We perform a comparative analysis between the RGB RAG baseline and GraphRAG, a knowledge graph based retrieval system. We test three GraphRAG customizations to improve robustness. Results show improvements over the RGB baseline and provide insights for designing more reliable RAG systems for real world scenarios.

cs.CL↗

arXiv2023

Fairness in Socio-technical Systems: a Case Study of Wikipedia

Problems broadly known as algorithmic bias frequently occur in the context of complex socio-technical systems (STS), where observed biases may not be directly attributable to a single automated decision algorithm. As a first investigation of fairness in STS, we focus on the case of Wikipedia. We systematically review 75 papers describing different types of bias in Wikipedia, which we classify and relate to established notions of harm from algorithmic fairness research. By analysing causal relationships between the observed phenomena, we demonstrate the complexity of the socio-technical processes causing harm. Finally, we identify the normative expectations of fairness associated with the different problems and discuss the applicability of existing criteria proposed for machine learning-driven decision systems.

cs.CY↗

arXiv2015

Processing Regular Path Queries on Arbitrarily Distributed Data

Regular Path Queries (RPQs) are a type of graph query where answers are pairs of nodes connected by a sequence of edges matching a regular expression. We study the techniques to process such queries on a distributed graph of data. While many techniques assume the location of each data element (node or edge) is known, when the components of the distributed system are autonomous, the data will be arbitrarily distributed. As the different query processing strategies are equivalently costly in the worst case, we isolate query-dependent cost factors and present a method to choose between strategies, using new query cost estimation techniques. We evaluate our techniques using meaningful queries on biomedical data.

cs.DC↗