paper
Beyond Third-Person Audits: Situated Interaction Auditing for User-Centered LLM Bias Research
paperactiveprovisional
beyond-third-person-audits-situated-interaction-auditing-for-user-centered-llm-bias-research-c382796f·1 events·first seen 6d agoAliases: Beyond Third-Person Audits: Situated Interaction Auditing for User-Centered LLM Bias Research
Co-occurring entities
More like this (12)
Situated Interaction AuditingRevising Context, Shifting Simulated Stance: Auditing LLM-Based Stance Simulation in Online DiscussionsSecurity and Privacy Prompts in the Wild: What Users Ask LLMs and How LLMs RespondThe Masked Advantage: Uncovering Local-Language Access to Cultural Knowledge in LLMsFrom Self to Other: Evaluating Demographic Perspective-Taking in LLM Hate Speech AnnotationFrom Observation to Intervention: A Causal Audit of Expert Importance in Mixture-of-Experts ModelsPhantoms and Disclosures: a Causal Framework for Auditing Synthetic DataClinically Grounded Privacy Evaluation of Medical LMsBe My Tutor: On-Policy Co-Distillation for Mutual LLM Improvement via Peer FeedbackWhich Models Are Our Models Built On? Auditing Invisible Dependencies in Modern LLMsFlaws in the LLM Automation Narrativehuman-LLM collaborative annotation
Recent events (1)
Situated Interaction Auditing: A user-centered framework for LLM bias research
Researchers propose Situated Interaction Auditing (SIA), a new framework for studying LLM bias from the perspective of the user rather than third-party demographic representation. The core insight is that bias can manifest in how a model treats its interlocutor — varying response quality, content, and tone based on implicit sociodemographic signals, writing style, or stated identity — rather than only in how it describes external groups. The paper demonstrates SIA through a case study intersecting gender and socioeconomic status signals across multiple task domains and outlines a research agenda for the approach.