mlsanityData to 14 Oct 2026

Wait, am I Being Fair? Characterizing Deductive Stereotyping and Mitigating It with Fair-GCG

arXiv 2606.30989 ↗First posted 30 Jun 2026cs.CL cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Warning: This paper contains several toxic and offensive statements. While reasoning generally improves fairness in recent large language models (LLMs), failures persist. In this work, we identify a failure mode, deductive stereotyping, in which models apply population-level statistical regularities to individual cases, producing logically coherent yet socially biased inferences. We provide a statistical interpretation of this phenomenon. To steer models toward fairness-aware reasoning, we propose a reasoning-time injection framework. We further introduce Fair-GCG to systematically discover effective injection phrases. Injection phrases discovered by Fair-GCG improve performance across multiple fairness benchmarks, generalize from smaller to larger LLMs, improves reasoning-level fairness, reduces bias in open-ended generation, and transfer to real-world fairness-sensitive tasks.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 54 of its 74 references that are in the map. First posted on arXiv 30 Jun 2026.

Builds on

54 of 74 references.

References · 54

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2024The Llama 3 Herd of Modelscited by 14,715
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  4. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  5. 2025Qwen3 Technical Reportcited by 8,820
  6. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  7. 2023Qwen Technical Reportcited by 3,344
  8. 2023Universal and Transferable Adversarial Attacks on Aligned Language Modelscited by 3,104
  9. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 3,050
  10. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,592
  11. 2021Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processingcited by 2,234
  12. 2024Mixtral of Expertscited by 1,823
38 more
  1. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Modelscited by 1,407
  2. 2025gpt-oss-120b & gpt-oss-20b Model Cardcited by 1,386
  3. 2016Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddingscited by 1,312
  4. 2024Qwen2.5-Coder Technical Reportcited by 1,203
  5. 2023PaLM 2 Technical Reportcited by 1,162
  6. 2020StereoSet: Measuring stereotypical bias in pretrained language modelscited by 924
  7. 2023A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivitycited by 894
  8. 2020CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Modelscited by 710
  9. 2021BBQ: A Hand-Built Bias Benchmark for Question Answeringcited by 701
  10. 2022Automatic Chain of Thought Prompting in Large Language Modelscited by 688
  11. 2022Decomposed Prompting: A Modular Approach for Solving Complex Taskscited by 558
  12. 2024Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attackscited by 486
  13. 2021DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Expertscited by 441
  14. 2021BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generationcited by 412
  15. 2017On Fairness and Calibrationcited by 406
  16. 2024Justice or Prejudice? Quantifying Biases in LLM-as-a-Judgecited by 368
  17. 2019Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Settingcited by 349
  18. 2023"Kelly is a Warm Person, Joseph is a Role Model": Gender Biases in LLM-Generated Reference Letterscited by 199
  19. 2022On Second Thought, Let's Not Think Step by Step! Bias and Toxicity in Zero-Shot Reasoningcited by 194
  20. 2018Fair Clustering Through Fairletscited by 176
  21. 2016Fairness in Learning: Classic and Contextual Banditscited by 168
  22. 2023RAIN: Your Language Models Can Align Themselves without Finetuningcited by 157
  23. 2023Black-Box Prompt Optimization: Aligning Large Language Models without Model Trainingcited by 122
  24. 2020Towards Controllable Biases in Language Generationcited by 112
  25. 2016Fairness in Reinforcement Learningcited by 95
  26. 2023Boosting Language Models Reasoning with Chain-of-Knowledge Promptingcited by 77
  27. 2023HI-TOM: A Benchmark for Evaluating Higher-Order Theory of Mind Reasoning in Large Language Modelscited by 63
  28. 2024Self-Debiasing Large Language Models: Zero-Shot Recognition and Reduction of Stereotypescited by 59
  29. 2023Bypassing the Safety Training of Open-Source LLMs with Priming Attackscited by 50
  30. 2024Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against Jailbreakscited by 48
  31. 2023WinoQueer: A Community-in-the-Loop Benchmark for Anti-LGBTQ+ Bias in Large Language Modelscited by 42
  32. 2025Test-Time Preference Optimization: On-the-Fly Alignment via Iterative Textual Feedbackcited by 41
  33. 2024Prompting Techniques for Reducing Social Bias in LLMs through System 1 and System 2 Cognitive Processescited by 39
  34. 2022Representation Bias in Data: A Survey on Identification and Resolution Techniquescited by 37
  35. 2024Bias Unveiled: Investigating Social Bias in LLM-Generated Codecited by 25
  36. 2025Does Reasoning Introduce Bias? A Study of Social Bias Evaluation and Mitigation in LLM Reasoningcited by 21
  37. 2016Quantifying and Reducing Stereotypes in Word Embeddingscited by 15
  38. 2024Evaluating Gender Bias of LLMs in Making Morality Judgementscited by 15

50 most cited of 54 All 54 (JSON)

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Reasoning Towards Fairness: Mitigating Bias in Language Models through Reasoning-Guided Fine-Tuning
  2. 2025BiasFilter: An Inference-Time Debiasing Framework for Large Language Models
  3. 2025BiasGuard: A Reasoning-enhanced Bias Detection Tool For Large Language Models
  4. 2022FairDistillation: Mitigating Stereotyping in Language Models
  5. 2025Fair-GPTQ: Bias-Aware Quantization for Large Language Models
  6. 2025Debiasing LLMs by Masking Unfairness-Driving Attention Heads
  7. 2025Silenced Biases: The Dark Side LLMs Learned to Refuse
  8. 2025Is Reasoning All You Need? Probing Bias in the Age of Reasoning Language Models