6 papers
Reliability, Faithfulness, and the Limits of Post-hoc Explanations of Opaque Scientific Models
Nick Oh, Helen Jin
Post-hoc explanation methods are routinely used to interpret scientific machine learning models, with the deliverable understood to be insight into the phenomenon the model has bee…
T-FIX: Text-Based Explanations with Features Interpretable to eXperts
Shreya Havaldar, Weiqiu You, Chaehyeon Kim +12
As LLMs are deployed in knowledge-intensive settings (e.g., surgery, astronomy, therapy), users are often domain experts who expect not just answers, but explanations that mirror p…
Probabilistic Soundness Guarantees in LLM Reasoning Chains
Weiqiu You, Anton Xue, Shreya Havaldar +4
In reasoning chains generated by large language models (LLMs), initial errors often propagate and undermine the reliability of the final conclusion. Current LLM-based error detecti…
Adaptively profiling models with task elicitation
Davis Brown, Prithvi Balehannina, Helen Jin +3
Language model evaluations often fail to characterize consequential failure modes, forcing experts to inspect outputs and build new benchmarks. We introduce task elicitation, a met…
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…
The FIX Benchmark: Extracting Features Interpretable to eXperts
Helen Jin, Shreya Havaldar, Chaehyeon Kim +10
Feature-based methods are commonly used to explain model predictions, but these methods often implicitly assume that interpretable features are readily available. However, this is…