T-FIX: Text-Based Explanations with Features Interpretable to eXperts
By: Shreya Havaldar , Helen Jin , Chaehyeon Kim and more
Potential Business Impact:
Makes AI give smart answers experts trust.
As LLMs are deployed in knowledge-intensive settings (e.g., surgery, astronomy, therapy), users expect not just answers, but also meaningful explanations for those answers. In these settings, users are often domain experts (e.g., doctors, astrophysicists, psychologists) who require explanations that reflect expert-level reasoning. However, current evaluation schemes primarily emphasize plausibility or internal faithfulness of the explanation, which fail to capture whether the content of the explanation truly aligns with expert intuition. We formalize expert alignment as a criterion for evaluating explanations with T-FIX, a benchmark spanning seven knowledge-intensive domains. In collaboration with domain experts, we develop novel metrics to measure the alignment of LLM explanations with expert judgment.
Similar Papers
On the Factual Consistency of Text-based Explainable Recommendation Models
Information Retrieval
Checks if computer recommendations tell the truth.
LExT: Towards Evaluating Trustworthiness of Natural Language Explanations
Computation and Language
Checks if AI explanations are true and believable.
FLEx: Language Modeling with Few-shot Language Explanations
Computation and Language
Teaches computers to fix their own mistakes.