2 papers
cs.CL2026
Same Chart, Different Story: Bias in Vision-Language Chart Interpretation
Mizanur Rahman, Huan Wu, Arash Asgari +2
Vision-language models (VLMs) are increasingly used to interpret charts and generate natural-language explanations for socially consequential data. However, they may produce differ…
cs.CL2026
LLMs Silently Correct African American English: Auditing and Mitigating Dialect Bias via Activation Steering
Huan Wu, Ali Emami, Muhammad Furquan Hassan +5
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 in…