# Evaluating Social Bias in RAG Systems: When External Context Helps and Reasoning Hurts

arXiv: https://arxiv.org/abs/2602.09442 · HTML: https://mlsanity.com/paper/2602.09442/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 25 of its 28 references that are in the map.
- First posted on arXiv 10 Feb 2026.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)
- Retrieval-augmented generation / [RAG robustness and adaptive retrieval](https://mlsanity.com/rag/rag-robustness-and-adaptive-retrieval/)

## Builds on (most cited first, 25 of 25)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting](https://mlsanity.com/paper/2305.04388/) (2023)
- [StereoSet: Measuring stereotypical bias in pretrained language models](https://mlsanity.com/paper/2004.09456/) (2020)
- [CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models](https://mlsanity.com/paper/2010.00133/) (2020)
- [Measuring Faithfulness in Chain-of-Thought Reasoning](https://mlsanity.com/paper/2307.13702/) (2023)
- [Retrieval Augmentation Reduces Hallucination in Conversation](https://mlsanity.com/paper/2104.07567/) (2021)
- [GoEmotions: A Dataset of Fine-Grained Emotions](https://mlsanity.com/paper/2005.00547/) (2020)
- [BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generation](https://mlsanity.com/paper/2101.11718/) (2021)
- [Towards Revealing the Mystery behind Chain of Thought: A Theoretical Perspective](https://mlsanity.com/paper/2305.15408/) (2023)
- [Societal Biases in Language Generation: Progress and Challenges](https://mlsanity.com/paper/2105.04054/) (2021)
- [FlashRAG: A Modular Toolkit for Efficient Retrieval-Augmented Generation Research](https://mlsanity.com/paper/2405.13576/) (2024)
- ["I'm sorry to hear that": Finding New Biases in Language Models with a Holistic Descriptor Dataset](https://mlsanity.com/paper/2205.09209/) (2022)
- [SafeChain: Safety of Language Models with Long Chain-of-Thought Reasoning Capabilities](https://mlsanity.com/paper/2502.12025/) (2025)
- [Reducing hallucination in structured outputs via Retrieval-Augmented Generation](https://mlsanity.com/paper/2404.08189/) (2024)
- [Igniting Language Intelligence: The Hitchhiker's Guide From Chain-of-Thought Reasoning to Language Agents](https://mlsanity.com/paper/2311.11797/) (2023)
- [Dialogue Chain-of-Thought Distillation for Commonsense-aware Conversational Agents](https://mlsanity.com/paper/2310.09343/) (2023)
- [Controlling Style in Generated Dialogue](https://mlsanity.com/paper/2009.10855/) (2020)
- [Does RAG Introduce Unfairness in LLMs? Evaluating Fairness in Retrieval-Augmented Generation Systems](https://mlsanity.com/paper/2409.19804/) (2024)
- [Enhancing Retrieval-Augmented Generation: A Study of Best Practices](https://mlsanity.com/paper/2501.07391/) (2025)
- [Evaluating the Effect of Retrieval Augmentation on Social Biases](https://mlsanity.com/paper/2502.17611/) (2025)

## Built on by (most cited first, 1 of 1)

- [Retrieval Sensitivity to Identity Signals in Queries](https://mlsanity.com/paper/2609.36534/) (2026)

## Abstract (arXiv)

Social biases inherent in large language models (LLMs) raise significant fairness concerns. Retrieval-Augmented Generation (RAG) architectures, which retrieve external knowledge sources to enhance the generative capabilities of LLMs, remain susceptible to the same bias-related challenges. This work focuses on evaluating and understanding the social bias implications of RAG. Through extensive experiments across various retrieval corpora, LLMs, and bias evaluation datasets, encompassing more than 13 different bias types, we surprisingly observe a reduction in bias in RAG. This suggests that the inclusion of external context can help counteract stereotype-driven predictions, potentially improving fairness by diversifying the contextual grounding of the model's outputs. To better understand this phenomenon, we then explore the model's reasoning process by integrating Chain-of-Thought (CoT) prompting into RAG while assessing the faithfulness of the model's CoT. Our experiments reveal that the model's bias inclinations shift between stereotype and anti-stereotype responses as more contextual information is incorporated from the retrieved documents. Interestingly, we find that while CoT enhances accuracy, contrary to the bias reduction observed with RAG, it increases overall bias across datasets, highlighting the need for bias-aware reasoning frameworks that can mitigate this trade-off.