Transformer language models are increasingly used as software components, yet biased outputs remain difficult to localize and repair inside the model. Existing fairness testing and repair methods largely operate at the input-output or retraining level, while recent work suggests that bias-related behavior can concentrate in a small set of attention heads.
arXiv:2606. 27449v1 Announce Type: new Abstract: Multi-head attention conventionally partitions the hidden dimension equally across all heads at every layer, enforcing an identical representational subspace dimension (dh = dmodel/h) throughout the models depth.
By Shubham Aggarwal
arXiv:2608. 19203v1 Announce Type: cross Abstract: Standard multi-head attention (MHA) gives every head the same full causal context span, although heads can serve different contextual roles.
By Zimu Zhao
arXiv:2502. 08363v3 Announce Type: replace-cross Abstract: We present Top-Theta (Top-$\theta$) Attention, a training-free method for sparsifying transformer attention during inference.
By Konstantin Berestizshevsky, Renzo Andri, Lukas Cavigelli
BiasGym is a cost‑effective, generalizable framework that injects specific biases into large language models via token‑based fine‑tuning while keeping the model frozen. It then uses two debiasing methods—Scope and Steer—to identify and suppress or redirect the components responsible for biased behavior. The framework enables consistent bias elicitation, precise localization of bias associations, and targeted debiasing without harming downstream performance, and it has been shown to reduce real‑world stereotypes such as labeling Italians as reckless drivers.
By Sekh Mainul Islam, Nadav Borenstein, Siddhesh Milind Pawar, Haeun Yu, Arnav Arora, Isabelle Augenstein
The paper introduces an influence score that measures how much each attention head contributes to classification decisions in Transformer models, specifically for prompt injection detection. The score blends directional effects on logits with structural impact within the residual stream, allowing analysis at head, layer, and network scales. When applied to a DeBERTa model, the framework uncovers different decision patterns for correct versus incorrect predictions, offering a balanced approach between detailed circuit analysis and global output methods.
By Lisa Bouger, Yannick Teglia, Philippe Loubet Moundi