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.
Representation Engineering: A Top-Down Approach to
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
FishBack derives a closed-form minimum-distortion steering direction from the pullback Fisher metric of the softmax layer, outperforming Euclidean baselines on GPT-2 verb-morphology tasks with lower off-target KL divergence.
Benchmark construction artifacts in hallucination detection corpora allow naive text-similarity baselines to achieve near-perfect scores, and controlled evaluations show most methods perform near chance except SAPLMA and the new DRIFT probe.
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.
-
FishBack: Pullback Fisher Geometry for Optimal Activation Steering in Transformers
FishBack derives a closed-form minimum-distortion steering direction from the pullback Fisher metric of the softmax layer, outperforming Euclidean baselines on GPT-2 verb-morphology tasks with lower off-target KL divergence.
-
PARALLAX: Separating Genuine Hallucination Detection from Benchmark Construction Artifacts
Benchmark construction artifacts in hallucination detection corpora allow naive text-similarity baselines to achieve near-perfect scores, and controlled evaluations show most methods perform near chance except SAPLMA and the new DRIFT probe.