Structured Reasoning for Fairness: A Multi-Agent Approach to Bias Detection in Textual Data
On the map: LLM reasoning → Reasoning benchmarks and evaluation
also in 1 more
Abstract (arXiv)
From disinformation spread by AI chatbots to AI recommendations that inadvertently reinforce stereotypes, textual bias poses a significant challenge to the trustworthiness of large language models (LLMs). In this paper, we propose a multi-agent framework that systematically identifies biases by disentangling each statement as fact or opinion, assigning a bias intensity score, and providing concise, factual justifications. Evaluated on 1,500 samples from the WikiNPOV dataset, the framework achieves 84.9% accuracyunicodex2014an improvement of 13.0% over the zero-shot baselineunicodex2014demonstrating the efficacy of explicitly modeling fact versus opinion prior to quantifying bias intensity. By combining enhanced detection accuracy with interpretable explanations, this approach sets a foundation for promoting fairness and accountability in modern language models.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 19 of its 27 references that are in the map. First posted on arXiv 1 Mar 2025.
Builds on
19 of 27 references.
Closest ancestors · 1
Same direction, newest first
- 2025Explicit vs. Implicit: Investigating Social Bias in Large Language Models through Self-Reflection4 Jan
Other references · 18
- 2017Attention Is All You Needcited by 59,932
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
- 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
- 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
- 2016Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddingscited by 1,304
- 2020StereoSet: Measuring stereotypical bias in pretrained language modelscited by 911
- 2023Bias and Fairness in Large Language Models: A Surveycited by 626
- 2020Measuring and Reducing Gendered Correlations in Pre-trained Modelscited by 222
- 2019Gender Bias in Contextualized Word Embeddingscited by 203
- 2019On Measuring and Mitigating Biased Inferences of Word Embeddingscited by 112
- 2023A Survey on Fairness in Large Language Modelscited by 91
6 more
- 2020Unsupervised Discovery of Implicit Gender Biascited by 34
- 2024Bias and Volatility: A Statistical Framework for Evaluating Large Language Model's Stereotypes and the Associated Generation Inconsistencycited by 15
- 2022Mind Your Bias: A Critical Review of Bias Detection Methods for Contextual Language Modelscited by 6
- 2022It is not "accuracy vs. explainability" -- we need both for trustworthy AI systemscited by 5
- 2022Identifying and Measuring Token-Level Sentiment Bias in Pre-trained Language Models with Promptscited by 4
- 2024Exploring Subjectivity for more Human-Centric Assessment of Social Biases in Large Language Modelscited by 2
Built on by
Citing papers per year: 2025: 2.
2 papers.
Similar, not cited
Close in wording, no citation either way
- 2025BIASINSPECTOR: Detecting Bias in Structured Data through LLM Agents
- 2026MABPD: Multi-Agent Bias Probing & Detection via Structured Argument Debate
- 2025MALIBU Benchmark: Multi-Agent LLM Implicit Bias Uncovered
- 2025Debate-to-Detect: Reformulating Misinformation Detection as a Real-World Debate with Large Language Models
- 2024Mitigating Social Bias in Large Language Models: A Multi-Objective Approach within a Multi-Agent Framework
- 2026Bias Amplification in Multi-Agent Network: How Biased Agents Shape Opinions and Rhetoric
- 2025BiasFilter: An Inference-Time Debiasing Framework for Large Language Models
- 2025BiasGuard: A Reasoning-enhanced Bias Detection Tool For Large Language Models