LLMs Silently Correct African American English: Auditing and Mitigating Dialect Bias via Activation Steering

Overview

arXiv:2607.06845v1 Announce Type: new Abstract: African American English (AAE), a rule-governed dialect spoken by over 30 million people, is routinely misinterpreted and "corrected" by large language models (LLMs). Across six instruction-tuned LLMs (14B to 70B), we show that state-of-the-art models systematically prefer Standard American English (SAE) continuations even when the preceding context is in AAE, effectively rewriting AAE into SAE. We present an end-to-end framework to audit and mitig

SpinGraph analysis pending — check back after processing.