T-FIX: Text-Based Explanations with Features Interpretable to eXperts

2025-11-06

AI Summary

Knowledge-intensive domains (e.g., surgery, astronomy, psychotherapy) demand that large language model explanations not only be logically coherent but also align with domain experts’ cognitive intuitions—yet existing evaluation methods emphasize superficial plausibility and lack quantitative measures of expert alignment. Method: We introduce T-FIX, the first benchmark to formalize “expert alignment” as a core interpretability metric, co-developed with domain experts across seven disciplines; it integrates textual explanations with feature-level interpretability analysis and defines quantifiable expert consistency metrics grounded in real-world clinical and research scenarios. Contribution/Results: T-FIX significantly enhances the credibility and practical utility of model explanations in professional contexts, establishing a novel paradigm for trustworthy AI by bridging the gap between algorithmic interpretability and domain-specific epistemic standards.

Technology Category

• Computer Vision: Interpretability, Explainability, and Transparency
• Machine Learning: Transparent, Interpretable, Explainable ML
• Humans and AI: Explainable AI (XAI) for Human Understanding

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization

Abstract

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.

Problem

• Evaluating expert alignment of LLM explanations in knowledge-intensive domains
• Developing metrics to measure explanation alignment with expert judgment
• Creating benchmark for explanations matching expert intuition across domains

Innovation

• T-FIX benchmark spans seven knowledge-intensive domains
• Develops novel metrics to measure expert alignment
• Evaluates explanations using expert intuition as criterion