# Beyond Label Attention: Transparency in Language Models for Automated Medical Coding via Dictionary Learning

arXiv: https://arxiv.org/abs/2411.00173 · HTML: https://mlsanity.com/paper/2411.00173/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Interpreting biomedical and science models, one of 13 directions in Mechanistic interpretability.
- Builds on 25 of its 58 references that are in the map.
- First posted on arXiv 31 Oct 2024.

## Placed in

- Mechanistic interpretability / [Interpreting biomedical and science models](https://mlsanity.com/mechinterp/interpreting-biomedical-and-science-models/)

## Builds on (most cited first, 25 of 25)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [Sparse Autoencoders Find Highly Interpretable Features in Language Models](https://mlsanity.com/paper/2309.08600/) (2023)
- [Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks](https://mlsanity.com/paper/1710.11063/) (2017)
- [ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks](https://mlsanity.com/paper/2303.15056/) (2023)
- [Quantifying Attention Flow in Transformers](https://mlsanity.com/paper/2005.00928/) (2020)
- [Towards Automated Circuit Discovery for Mechanistic Interpretability](https://mlsanity.com/paper/2304.14997/) (2023)
- [ERASER: A Benchmark to Evaluate Rationalized NLP Models](https://mlsanity.com/paper/1911.03429/) (2019)
- [Evaluating the visualization of what a Deep Neural Network has learned](https://mlsanity.com/paper/1509.06321/) (2015)
- [Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers](https://mlsanity.com/paper/2103.15679/) (2021)
- [A Survey on Neural Network Interpretability](https://mlsanity.com/paper/2012.14261/) (2020)
- [Explainable Prediction of Medical Codes from Clinical Text](https://mlsanity.com/paper/1802.05695/) (2018)
- [Towards Causal Representation Learning](https://mlsanity.com/paper/2102.11107/) (2021)
- [Is ChatGPT better than Human Annotators? Potential and Limitations of ChatGPT in Explaining Implicit Hate Speech](https://mlsanity.com/paper/2302.07736/) (2023)
- [Transformer visualization via dictionary learning: contextualized embedding as a linear superposition of transformer factors](https://mlsanity.com/paper/2103.15949/) (2021)
- [A survey of sparse representation: algorithms and applications](https://mlsanity.com/paper/1602.07017/) (2016)
- [SPINE: SParse Interpretable Neural Embeddings](https://mlsanity.com/paper/1711.08792/) (2017)
- [Automated Medical Coding on MIMIC-III and MIMIC-IV: A Critical Review and Replicability Study](https://mlsanity.com/paper/2304.10909/) (2023)
- [A Comparative Study of Faithfulness Metrics for Model Interpretability Methods](https://mlsanity.com/paper/2204.05514/) (2022)
- [Explaining a Series of Models by Propagating Shapley Values](https://mlsanity.com/paper/2105.00108/) (2021)
- [A Systematic Literature Review of Automated ICD Coding and Classification Systems using Discharge Summaries](https://mlsanity.com/paper/2107.10652/) (2021)
- [On the Interpretability of Attention Networks](https://mlsanity.com/paper/2212.14776/) (2022)
- [Examining Structure of Word Embeddings with PCA](https://mlsanity.com/paper/1906.00114/) (2019)
- [Dictionary Learning under Symmetries via Group Representations](https://mlsanity.com/paper/2305.19557/) (2023)

## Built on by (most cited first, 5 of 5)

- [Explainable ICD Coding via Entity Linking](https://mlsanity.com/paper/2503.20508/) (2025)
- [Exploring Accurate and Transparent Domain Adaptation in Predictive Healthcare via Concept-Grounded Orthogonal Inference](https://mlsanity.com/paper/2602.12542/) (2026)
- [From Documents to Spans: Span-Centric Learning for LLM-based Explainable Medical Coding](https://mlsanity.com/paper/2603.15270/) (2026)
- [Bridging the Version Gap: Multi-version Training Improves ICD Code Prediction, Especially for Rare Codes](https://mlsanity.com/paper/2605.17755/) (2026)
- [Making Clinical Language Models Auditable: Concept-Guided Fine-Tuning for Robust Prediction](https://mlsanity.com/paper/2608.27397/) (2026)

## Abstract (arXiv)

Medical coding, the translation of unstructured clinical text into standardized medical codes, is a crucial but time-consuming healthcare practice. Though large language models (LLM) could automate the coding process and improve the efficiency of such tasks, interpretability remains paramount for maintaining patient trust. Current efforts in interpretability of medical coding applications rely heavily on label attention mechanisms, which often leads to the highlighting of extraneous tokens irrelevant to the ICD code. To facilitate accurate interpretability in medical language models, this paper leverages dictionary learning that can efficiently extract sparsely activated representations from dense language model embeddings in superposition. Compared with common label attention mechanisms, our model goes beyond token-level representations by building an interpretable dictionary which enhances the mechanistic-based explanations for each ICD code prediction, even when the highlighted tokens are medically irrelevant. We show that dictionary features can steer model behavior, elucidate the hidden meanings of upwards of 90% of medically irrelevant tokens, and are human interpretable.