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

TL;DR

T-FIX is a unified, automatic evaluation framework for assessing how well LLM explanations align with domain experts' reasoning across multiple scientific tasks, reducing reliance on costly annotations.

Contribution

It introduces a scalable, domain-grounded evaluation method for expert-aligned explanations applicable to unseen data, with a unified framework across diverse scientific fields.

Findings

Evaluated across seven scientific tasks in three domains.

Enables automatic and personalized assessment of expert alignment.

Generalizes to unseen explanations without ongoing expert input.

Abstract

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 professional reasoning. Yet evaluating whether an LLM "thinks like an expert" remains difficult: existing approaches rely on per-example expert annotation, making them costly, hard to scale, and tied to a single notion of correct reasoning within each domain. To address this gap, we introduce T-FIX, a unified evaluation framework that operationalizes expert alignment as a desired attribute of LLM-generated explanations. T-FIX spans seven scientific tasks across three domains, with each task evaluated against expert-defined criteria that capture domain-grounded reasoning rather than generic explanation quality. Our framework enables automatic, personalizable evaluation of expert alignment that generalizes to unseen explanations without ongoing expert involvement. Code is available at https://github.com/BrachioLab/FIX-2/.