mlsanityData to 14 Oct 2026

Beyond Third-Person Audits: Situated Interaction Auditing for User-Centered LLM Bias Research

arXiv 2606.12247 ↗First posted 10 Jun 2026cs.CY cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Research on bias in large language models (LLMs) has predominantly focused on third-person audits, which study how models represent or evaluate demographic groups as external subjects. However, this paradigm overlooks a structural blind spot because the user is absent from the audit. In practice, LLMs are used in open-ended, personal interactions, during which the model implicitly represents the user and adjusts its responses accordingly. When identical requests yield different responses depending on who is asking, bias manifests not in how the model describes others but in how it treats its interlocutor. We propose Situated Interaction Auditing (SIA), a user-centered framework for studying how user profile signals -- implicit sociodemographic markers, writing style, and stated identity -- systematically shape LLM response quality, content, and tone. We demonstrate the framework through a case study that intersects gender and socioeconomic status signals across multiple task domains and outline a research agenda for SIA as a new mission for natural language processing.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 30 of its 54 references that are in the map. First posted on arXiv 10 Jun 2026.

Builds on

30 of 54 references.

References · 30

  1. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  2. 2023A Survey on Evaluation of Large Language Modelscited by 1,242
  3. 2023Towards Understanding Sycophancy in Language Modelscited by 1,040
  4. 2022Red Teaming Language Models with Language Modelscited by 1,026
  5. 2020Language (Technology) is Power: A Critical Survey of "Bias" in NLPcited by 956
  6. 2016Fair prediction with disparate impact: A study of bias in recidivism prediction instrumentscited by 672
  7. 2023Bias and Fairness in Large Language Models: A Surveycited by 639
  8. 2024WildChat: 1M ChatGPT Interaction Logs in the Wildcited by 629
  9. 2023LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Datasetcited by 461
  10. 2018AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Biascited by 319
  11. 2023"Kelly is a Warm Person, Joseph is a Role Model": Gender Biases in LLM-Generated Reference Letterscited by 199
  12. 2018Aequitas: A Bias and Fairness Audit Toolkitcited by 147
18 more
  1. 2025ELEPHANT: Measuring and understanding social sycophancy in LLMscited by 129
  2. 2024SafetyPrompts: a Systematic Review of Open Datasets for Evaluating and Improving Large Language Model Safetycited by 77
  3. 2023Rethinking Model Evaluation as Narrowing the Socio-Technical Gapcited by 56
  4. 2024Linguistic Bias in ChatGPT: Language Models Reinforce Dialect Discriminationcited by 56
  5. 2024What's in a Name? Auditing Large Language Models for Race and Gender Biascited by 51
  6. 2023The Shifted and The Overlooked: A Task-oriented Investigation of User-GPT Interactionscited by 45
  7. 2024AI auditing: The Broken Bus on the Road to AI Accountabilitycited by 43
  8. 2025Linear Representations of Political Perspective Emerge in Large Language Modelscited by 32
  9. 2024Towards interactive evaluations for interaction harms in human-AI systemscited by 29
  10. 2025Presumed Cultural Identity: How Names Shape LLM Responsescited by 21
  11. 2024First-Person Fairness in Chatbotscited by 20
  12. 2025WeAudit: Scaffolding User Auditors and AI Practitioners in Auditing Generative AIcited by 14
  13. 2025The Inadequacy of Offline LLM Evaluations: A Need to Account for Personalization in Model Behaviorcited by 8
  14. 2025Invisible Filters: Cultural Bias in Hiring Evaluations Using Large Language Modelscited by 6
  15. 2025A Framework for Auditing Chatbots for Dialect-Based Quality-of-Service Harmscited by 5
  16. 2025Bias Association Discovery Framework for Open-Ended LLM Generationscited by 4
  17. 2023Surname affinity in Santiago, Chile: A network-based approach that uncovers urban segregationcited by 3
  18. 2026Representational Harms in LLM-Generated Narratives Against Global Majority Nationalitiescited by 2

Built on by

Not cited yet.