# Spurious Correlations and Beyond: Understanding and Mitigating Shortcut Learning in SDOH Extraction with Large Language Models

arXiv: https://arxiv.org/abs/2506.00134 · HTML: https://mlsanity.com/paper/2506.00134/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 40 references that are in the map.
- First posted on arXiv 30 May 2025.

## Builds on (most cited first, 16 of 16)

- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [Large Language Models Encode Clinical Knowledge](https://mlsanity.com/paper/2212.13138/) (2022)
- [Beyond Accuracy: Behavioral Testing of NLP models with CheckList](https://mlsanity.com/paper/2005.04118/) (2020)
- [Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference](https://mlsanity.com/paper/1902.01007/) (2019)
- [Adversarial Examples for Evaluating Reading Comprehension Systems](https://mlsanity.com/paper/1707.07328/) (2017)
- [Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints](https://mlsanity.com/paper/1707.09457/) (2017)
- [An Empirical Study on Robustness to Spurious Correlations using Pre-trained Language Models](https://mlsanity.com/paper/2007.06778/) (2020)
- [DeID-GPT: Zero-shot Medical Text De-Identification by GPT-4](https://mlsanity.com/paper/2303.11032/) (2023)
- [Large Language Model Is Not a Good Few-shot Information Extractor, but a Good Reranker for Hard Samples!](https://mlsanity.com/paper/2303.08559/) (2023)
- [Med42-v2: A Suite of Clinical LLMs](https://mlsanity.com/paper/2408.06142/) (2024)
- [Large Language Models Can be Lazy Learners: Analyze Shortcuts in In-Context Learning](https://mlsanity.com/paper/2305.17256/) (2023)
- [Detecting Shortcut Learning for Fair Medical AI using Shortcut Testing](https://mlsanity.com/paper/2207.10384/) (2022)
- [Annotating Social Determinants of Health Using Active Learning, and Characterizing Determinants Using Neural Event Extraction](https://mlsanity.com/paper/2004.05438/) (2020)
- [Deep Learning Applied to Chest X-Rays: Exploiting and Preventing Shortcuts](https://mlsanity.com/paper/2009.10132/) (2020)
- [DICE: Data-Efficient Clinical Event Extraction with Generative Models](https://mlsanity.com/paper/2208.07989/) (2022)
- [A Study of Social and Behavioral Determinants of Health in Lung Cancer Patients Using Transformers-based Natural Language Processing Models](https://mlsanity.com/paper/2108.04949/) (2021)

## Built on by (most cited first, 2 of 2)

- [Clinical Note Bloat Reduction for Efficient LLM Use](https://mlsanity.com/paper/2604.16364/) (2026)
- [Benchmarking Fairness in Spiking Neural Networks: Data Bias, Spurious Features, and Hardware Effects](https://mlsanity.com/paper/2605.27407/) (2026)

## Abstract (arXiv)

Social determinants of health (SDOH) extraction from clinical text is critical for downstream healthcare analytics. Although large language models (LLMs) have shown promise, they may rely on superficial cues leading to spurious predictions. Using the MIMIC portion of the SHAC (Social History Annotation Corpus) dataset and focusing on drug status extraction as a case study, we demonstrate that mentions of alcohol or smoking can falsely induce models to predict current/past drug use where none is present, while also uncovering concerning gender disparities in model performance. We further evaluate mitigation strategies - such as prompt engineering and chain-of-thought reasoning - to reduce these false positives, providing insights into enhancing LLM reliability in health domains.