3 papers
cs.LG2026
The SuperActivator Mechanism: Transformers Concentrate Reliable Concept Signals in the Tail
Cassandra Goldberg, Chaehyeon Kim, Adam Stein +1
Concept vectors aim to enhance model interpretability by linking internal representations with human-understandable semantics, but their practical utility is often limited by noisy…
cs.CL2026
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…
cs.LG2025
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…