3 papers
cs.LG2026
Missingness Bias Calibration in Feature Attribution Explanations
Shailesh Sridhar, Anton Xue, Eric Wong
Popular explanation methods often produce unreliable feature importance scores due to missingness bias, a systematic distortion that arises when models are probed with ablated, out…
cs.LG2025
Probabilistic Stability Guarantees for Feature Attributions
Helen Jin, Anton Xue, Weiqiu You +2
Stability guarantees have emerged as a principled way to evaluate feature attributions, but existing certification methods rely on heavily smoothed classifiers and often produce co…
cs.AI2025
Logicbreaks: A Framework for Understanding Subversion of Rule-based Inference
Anton Xue, Avishree Khare, Rajeev Alur +2
We study how to subvert large language models (LLMs) from following prompt-specified rules. We first formalize rule-following as inference in propositional Horn logic, a mathematic…