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.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
A pipeline using SBERT/UMAP/HDBSCAN clustering on 339 repositories identifies 692k recurring Gherkin slices, labels 200 of them, and trains an XGBoost model that achieves F1 0.891 for extraction-worthiness, outperforming rule and LLM baselines, with prevalence statistics released.
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.