Six state-of-the-art LLMs systematically prefer Standard American English over AAE continuations, and a training-free activation steering method reduces this bias 5-20x more than prompting while preserving fluency.
Linguistic Bias in C hat GPT : Language Models Reinforce Dialect Discrimination
3 Pith papers cite this work, alongside 43 external citations. Polarity classification is still indexing.
3
Pith papers citing it
43
external citations · OpenAlex
years
2026 3representative citing papers
A RAG method with a curated lexicon enables controlled Singlish generation from standard English through sparse substitutions, matching zero-shot prompting in perceived naturalness while achieving higher semantic preservation and edit minimality.
citing papers explorer
-
LLMs Silently Correct African American English: Auditing and Mitigating Dialect Bias via Activation Steering
Six state-of-the-art LLMs systematically prefer Standard American English over AAE continuations, and a training-free activation steering method reduces this bias 5-20x more than prompting while preserving fluency.
-
From Standard English to Singlish: A Retrieval-Augmented Approach for Code-Switched Creole Generation in Large Language Models
A RAG method with a curated lexicon enables controlled Singlish generation from standard English through sparse substitutions, matching zero-shot prompting in perceived naturalness while achieving higher semantic preservation and edit minimality.
- Topics as Proxies for Sociodemographics: How Conversational Context Affects LLM Answers