Retrieval Sensitivity to Identity Signals in Queries
cs.CL, cs.CY, cs.IR
Submitted: 2026-09-29
Updated: 2026-09-29
Comments: EMNLP 2026 camera-ready, with a correction to Fig. 4
Code: https://github.com/Andrewtcr/bias-ret
License: http://creativecommons.org/licenses/by/4.0/
The gist: Dense retrievers decide which documents reach users and the language models that use them, yet they are typically evaluated with neutral queries.
Terminology
Abstract
Dense retrievers decide which documents reach users and the language models that use them, yet they are typically evaluated with neutral queries. We ask whether the identity signals that real users express in their queries---political ideology and dialect---bias what a retriever returns. We design evaluations in two domains, political news and consumer-health questions, each pairing a controlled synthetic set that varies only the identity signal with naturalistic queries. Across five dense retrievers and a sparse baseline, every retriever (i) retrieves articles that align with the query's own political lean and (ii) performs worse for questions written in African American Language (AAL) than in White Mainstream English (WME). Two analyses tie these gaps to queries' identity signals beyond surface vocabulary: partialling out an aggregate lexical-asymmetry score leaves the synthetic gaps largely intact, and linear probes recover lean and dialect from the retrievers' query embeddings beyond token-level features. Left unaddressed, such retrieval biases risk contributing to polarization and reinforcing the health disparities already faced by AAL speakers. Code is available at https://github.com/Andrewtcr/bias-ret.
Sources
- Llama-Embed-Nemotron-8B: A Universal Text Embedding Model for Multilingual and Cross-Lingual Tasks
- BM25S: Orders of magnitude faster lexical search via eager sparse scoring
- Evaluating Social Bias in RAG Systems: When External Context Helps and Reasoning Hurts
- Different Demographic Cues Yield Inconsistent Conclusions About LLM Personalization and Bias
- Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering