mlsanityData to 14 Oct 2026

When RAG Fails to Equalize: Geo-bias in Factual Question Answering over Public Companies

arXiv 2608.25717 ↗First posted 26 Aug 2026cs.CL cs.AIcited by 0

On the map: Retrieval-augmented generation → RAG robustness and adaptive retrieval

Abstract (arXiv)

Retrieval-augmented generation (RAG) is widely assumed to mitigate factual errors in large language models (LLMs), but it remains unclear whether retrieval uniformly compensates for missing knowledge. We study this question in a controlled factual QA setting over public companies, constructing a benchmark of approximately 2,000 firms across global equity indices. We evaluate six LLMs on four atomic attributes under four conditions: no-context, perfect context, misleading context, and distraction context. We find strong geographic disparities in no-context accuracy, indicating uneven parametric knowledge. While perfect context improves performance, it does not eliminate these gaps: gains are correlated with baseline accuracy, suggesting retrieval effectiveness is coupled to internal representations. Under misleading context, models frequently copy incorrect information. Larger models improve overall performance but do not remove these structural effects. These results challenge the view of RAG as a universal corrective and highlight the interaction between model knowledge, context quality, and entity representation.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation. Builds on 24 of its 32 references that are in the map. First posted on arXiv 26 Aug 2026.

Builds on

24 of 32 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024ClashEval: Quantifying the tug-of-war between an LLM's internal prior and external evidence16 Apr

Other references · 23

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  3. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,141
  4. 2019Language Models as Knowledge Bases?cited by 1,936
  5. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,601
  6. 2018FEVER: a large-scale dataset for Fact Extraction and VERificationcited by 1,375
  7. 2021Improving language models by retrieving from trillions of tokenscited by 1,293
  8. 2023FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generationcited by 1,282
  9. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,210
  10. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,128
  11. 2020Language (Technology) is Power: A Critical Survey of "Bias" in NLPcited by 956
  12. 2020How Much Knowledge Can You Pack Into the Parameters of a Language Model?cited by 719
11 more
  1. 2020KILT: a Benchmark for Knowledge Intensive Language Taskscited by 573
  2. 2021FinQA: A Dataset of Numerical Reasoning over Financial Datacited by 562
  3. 2022Large Language Models Struggle to Learn Long-Tail Knowledgecited by 458
  4. 2021TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Financecited by 408
  5. 2021Measuring and Improving Consistency in Pretrained Language Modelscited by 364
  6. 2022RARR: Researching and Revising What Language Models Say, Using Language Modelscited by 287
  7. 2022Internet-augmented language models through few-shot prompting for open-domain question answeringcited by 131
  8. 2020Entities as Experts: Sparse Memory Access with Entity Supervisioncited by 100
  9. 2024A Survey of Large Language Models in Finance (FinLLMs)cited by 79
  10. 2024Toward Robust RALMs: Revealing the Impact of Imperfect Retrieval on Retrieval-Augmented Language Modelscited by 8
  11. 2024Evaluation of Geographical Distortions in Language Modelscited by 6

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Evaluating RAG Reliability under Clean, Misleading, and Mixed Retrieval
  2. 2024Fact, Fetch, and Reason: A Unified Evaluation of Retrieval-Augmented Generation
  3. 2025Improving Factuality in LLMs via Inference-Time Knowledge Graph Construction
  4. 2024Deploying Large Language Models With Retrieval Augmented Generation
  5. 2025FinDER: Financial Dataset for Question Answering and Evaluating Retrieval-Augmented Generation
  6. 2025On the Influence of Context Size and Model Choice in Retrieval-Augmented Generation Systems
  7. 2024LLMs are Biased Evaluators But Not Biased for Retrieval Augmented Generation
  8. 2024Do You Know What You Are Talking About? Characterizing Query-Knowledge Relevance For Reliable Retrieval Augmented Generation