Papers for
ml model auditors
Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.
Model size and compression affect bias and abstention in question answering
Effects of Model Scale and Quantization on Social Bias and Abstention in Question Answering
Abstract: The deployment of small and quantized language models in resource-constrained settings raises an important fairness question: when a compressed model produces fewer biased responses, does this reflect fairer behavior or greater abstention? We study this problem in Question Answering (QA) using the BBQ benchmark across multiple model sizes and quantization settings from Qwen3, Gemma-3, and SmolLM2. We also examine whether the observed trends remain stable across alternative prompt formulations and when the ``Unknown'' option is removed in a forced-choice setting. Our results show that larger models achieved higher QA accuracy, but bias showed no simple scaling trend and quantization effects varied across configurations. Notably, 20 of the 26 configurations with fewer biased responses also show increased over-abstention, indicating that lower observed bias can partly reflect greater abstention. These findings show that lower observed bias can partly reflect greater abstention, and that fairness evaluation should consider biased responses, abstention, prompt formulation, and answer-option design jointly.
Language model outputs traced to key internal components
Matryoshka attribution: Learning to attribute language model outputs to representations and weights
Abstract: Attributing language model outputs to their internal computations is an open problem in interpretability. Existing methods, which use causal interventions, gradients, or learnable masks, either are infeasibly expensive or struggle to identify actual causally-important internal computations. We propose framing attribution as the problem of identifying nested subsets of internal components which minimise a downstream loss. To learn this task, we introduce Matryoshka Attribution (MAttr), a mask learning method that parametrises the mask with a simple differentiable sigmoid top-$k$ operator. We supervise training over all sparsities simultaneously by randomising $k$ over training, resulting in a learned ordering of components by attribution score. MAttr achieves number 1 on the official leaderboard of the Mechanistic Interpretability Benchmark (Mueller et al., 2025); our method identifies sparse and task-transferrable circuits across varying circuit bases. As a practical application, we show that MAttr can be trained with reinforcement learning to identify weight changes responsible for downstream behaviours in LLM finetuning. We train MAttr on refusal judge scores and find that restoring $1\%$ of Llama 3.1 8B Instruct's weights to their base model state is sufficient to remove refusals while maintaining capabilities. We view MAttr as a successful formulation of interpretability into a learnable objective that we can tackle with gradient descent, and encourage future work along these lines.