# Additive Large Language Models for Semi-Structured Text

arXiv: https://arxiv.org/abs/2511.11922 · HTML: https://mlsanity.com/paper/2511.11922/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 32 of its 65 references that are in the map.
- First posted on arXiv 14 Nov 2025.

## Builds on (most cited first, 30 of 32)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [Sanity Checks for Saliency Maps](https://mlsanity.com/paper/1810.03292/) (2018)
- [Attention is not Explanation](https://mlsanity.com/paper/1902.10186/) (2019)
- [Interpretable Explanations of Black Boxes by Meaningful Perturbation](https://mlsanity.com/paper/1704.03296/) (2017)
- [Estimating Training Data Influence by Tracing Gradient Descent](https://mlsanity.com/paper/2002.08484/) (2020)
- [A Benchmark for Interpretability Methods in Deep Neural Networks](https://mlsanity.com/paper/1806.10758/) (2018)
- [Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methods](https://mlsanity.com/paper/1911.02508/) (2019)
- [Neural Additive Models: Interpretable Machine Learning with Neural Nets](https://mlsanity.com/paper/2004.13912/) (2020)
- [A Multiscale Visualization of Attention in the Transformer Model](https://mlsanity.com/paper/1906.05714/) (2019)
- [Influence Functions in Deep Learning Are Fragile](https://mlsanity.com/paper/2006.14651/) (2020)
- [InterpretML: A Unified Framework for Machine Learning Interpretability](https://mlsanity.com/paper/1909.09223/) (2019)
- [Deep k-Nearest Neighbors: Towards Confident, Interpretable and Robust Deep Learning](https://mlsanity.com/paper/1803.04765/) (2018)
- [NODE-GAM: Neural Generalized Additive Model for Interpretable Deep Learning](https://mlsanity.com/paper/2106.01613/) (2021)
- [GAMI-Net: An Explainable Neural Network based on Generalized Additive Models with Structured Interactions](https://mlsanity.com/paper/2003.07132/) (2020)
- [Framework for Evaluating Faithfulness of Local Explanations](https://mlsanity.com/paper/2202.00734/) (2022)
- [Learning Certifiably Optimal Rule Lists for Categorical Data](https://mlsanity.com/paper/1704.01701/) (2017)
- [Clinical Outcome Prediction from Admission Notes using Self-Supervised Knowledge Integration](https://mlsanity.com/paper/2102.04110/) (2021)
- [Revisiting Methods for Finding Influential Examples](https://mlsanity.com/paper/2111.04683/) (2021)
- [Sparse Interaction Additive Networks via Feature Interaction Detection and Sparse Selection](https://mlsanity.com/paper/2209.09326/) (2022)
- [Sparse Neural Additive Model: Interpretable Deep Learning with Feature Selection via Group Sparsity](https://mlsanity.com/paper/2202.12482/) (2022)
- [A Modular Approach for Clinical SLMs Driven by Synthetic Data with Pre-Instruction Tuning, Model Merging, and Clinical-Tasks Alignment](https://mlsanity.com/paper/2505.10717/) (2025)
- [Assessing Fidelity in XAI post-hoc techniques: A Comparative Study with Ground Truth Explanations Datasets](https://mlsanity.com/paper/2311.01961/) (2023)
- [Discriminative Feature Attributions: Bridging Post Hoc Explainability and Inherent Interpretability](https://mlsanity.com/paper/2307.15007/) (2023)
- [Supersparse Linear Integer Models for Interpretable Classification](https://mlsanity.com/paper/1306.6677/) (2013)
- [Extending the Neural Additive Model for Survival Analysis with EHR Data](https://mlsanity.com/paper/2211.07814/) (2022)

## Abstract (arXiv)

Large Language Models have advanced clinical text classification, but their opaque predictions remain a critical barrier to practical adoption in research and clinical settings where investigators and physicians need to understand which parts of a patient's record drive risk signals. To address this challenge, we introduce CALM, short for Classification with Additive Large Language Models, an interpretable framework for semi-structured text where inputs are composed of semantically meaningful components, such as sections of an admission note or question-answer fields from an intake form. CALM predicts outcomes as the additive sum of each component's contribution, making these contributions part of the forward computation itself and enabling faithful explanations at both the patient and population level. The additive structure also enables clear visualizations, such as component-level risk curves similar to those used in generalized additive models, making the learned relationships easier to inspect and communicate. Although CALM expects semi-structured inputs, many clinical documents already have this form, and similar structure can often be automatically extracted from free-text notes. CALM achieves performance comparable to conventional LLM classifiers while improving trust, supporting quality-assurance checks, and revealing clinically meaningful patterns during model development and auditing.