# TT-XAI: Trustworthy Clinical Text Explanations via Keyword Distillation and LLM Reasoning

arXiv: https://arxiv.org/abs/2508.08273 · HTML: https://mlsanity.com/paper/2508.08273/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning.
- Builds on 20 of its 27 references that are in the map.
- First posted on arXiv 30 Jul 2025.

## Placed in

- LLM reasoning / [Clinical and biomedical applications](https://mlsanity.com/lr/clinical-and-biomedical-applications/)

## Builds on (most cited first, 20 of 20)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization](https://mlsanity.com/paper/1912.08777/) (2019)
- [Attention is not Explanation](https://mlsanity.com/paper/1902.10186/) (2019)
- [Capabilities of GPT-4 on Medical Challenge Problems](https://mlsanity.com/paper/2303.13375/) (2023)
- [Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?](https://mlsanity.com/paper/2004.03685/) (2020)
- [Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference](https://mlsanity.com/paper/2412.13663/) (2024)
- [Evaluating the visualization of what a Deep Neural Network has learned](https://mlsanity.com/paper/1509.06321/) (2015)
- [Explain Yourself! Leveraging Language Models for Commonsense Reasoning](https://mlsanity.com/paper/1906.02361/) (2019)
- [RETAIN: An Interpretable Predictive Model for Healthcare using Reverse Time Attention Mechanism](https://mlsanity.com/paper/1608.05745/) (2016)
- [Neural Additive Models: Interpretable Machine Learning with Neural Nets](https://mlsanity.com/paper/2004.13912/) (2020)
- [Counterfactual Visual Explanations](https://mlsanity.com/paper/1904.07451/) (2019)
- [Can language models learn from explanations in context?](https://mlsanity.com/paper/2204.02329/) (2022)
- [Explainable Machine Learning in Deployment](https://mlsanity.com/paper/1909.06342/) (2019)
- [Visualizing and Understanding Neural Models in NLP](https://mlsanity.com/paper/1506.01066/) (2015)
- [Usable XAI: 10 Strategies Towards Exploiting Explainability in the LLM Era](https://mlsanity.com/paper/2403.08946/) (2024)
- [Med7: a transferable clinical natural language processing model for electronic health records](https://mlsanity.com/paper/2003.01271/) (2020)
- [RaKUn: Rank-based Keyword extraction via Unsupervised learning and Meta vertex aggregation](https://mlsanity.com/paper/1907.06458/) (2019)

## Abstract (arXiv)

Clinical language models often struggle to provide trustworthy predictions and explanations when applied to lengthy, unstructured electronic health records (EHRs). This work introduces TT-XAI, a lightweight and effective framework that improves both classification performance and interpretability through domain-aware keyword distillation and reasoning with large language models (LLMs). First, we demonstrate that distilling raw discharge notes into concise keyword representations significantly enhances BERT classifier performance and improves local explanation fidelity via a focused variant of LIME. Second, we generate chain-of-thought clinical explanations using keyword-guided prompts to steer LLMs, producing more concise and clinically relevant reasoning. We evaluate explanation quality using deletion-based fidelity metrics, self-assessment via LLaMA-3 scoring, and a blinded human study with domain experts. All evaluation modalities consistently favor the keyword-augmented method, confirming that distillation enhances both machine and human interpretability. TT-XAI offers a scalable pathway toward trustworthy, auditable AI in clinical decision support.