H-SAL erases latent concepts from text profiles using self-descriptions as implicit debiasing signals and shows competitive performance on a new multi-domain Stack Exchange helpfulness benchmark.
Language and Linguistics Compass , volume =
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
LLMs show minimal sociodemographic disparities in advice because they infer user demographics poorly from history; conversation topics are the main predictor and act as proxies for groups.
citing papers explorer
-
Debiasing Without Protected Attributes: Latent Concept Erasure from Textual Profiles
H-SAL erases latent concepts from text profiles using self-descriptions as implicit debiasing signals and shows competitive performance on a new multi-domain Stack Exchange helpfulness benchmark.
-
Topics as Proxies for Sociodemographics: How Conversational Context Affects LLM Answers
LLMs show minimal sociodemographic disparities in advice because they infer user demographics poorly from history; conversation topics are the main predictor and act as proxies for groups.