How Temperature Shapes Ideological Discourse in Retrieval-Augmented Generation?
Retrieval-Augmented Generation (RAG) has been increasingly adopted to reduce hallucinations and strengthen the factual grounding of large language models (LLMs). While robustness to errors in the retrieval process has been explored, the impact of ideological bias on LLM outputs has been overlooked. For instance, if the retrieved material contains ideological positions, the RAG may transmit, amplify, or suppress such ideological discourses in its outputs. In this study, we address this issue by examining the influence of the RAG framework, comprising ideological discourses, in LLM-generated ans
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 51%amscotti/local-LLM-with-RAG →
- PossiblePossibly related (embedding) · 49%Evaluating J-space entropy as an error predictor across 7 datasets on Qwen3-4B [R] →
- PossiblePossibly related (embedding) · 45%Knowledge Distillation of Black-Box Large Language Models →
- LinkedLinked via arxiv author · 85%Elmira Salari →
“How Temperature Shapes Ideological Discourse in Retrieval-Augmented Generation?”
- LinkedLinked via arxiv author · 85%Hazem Amamou →
“How Temperature Shapes Ideological Discourse in Retrieval-Augmented Generation?”
- LinkedLinked via arxiv author · 85%José Victor de Souza →
“How Temperature Shapes Ideological Discourse in Retrieval-Augmented Generation?”
- LinkedLinked via arxiv author · 85%Shruti Kshirsagar →
“How Temperature Shapes Ideological Discourse in Retrieval-Augmented Generation?”
- LinkedLinked via arxiv author · 85%Maria Nunes Delfino →
“How Temperature Shapes Ideological Discourse in Retrieval-Augmented Generation?”