# Coupling Symbolic Reasoning with Language Modeling for Efficient Longitudinal Understanding of Unstructured Electronic Medical Records

arXiv: https://arxiv.org/abs/2308.03360 · HTML: https://mlsanity.com/paper/2308.03360/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning.
- Builds on 8 of its 43 references that are in the map.
- First posted on arXiv 7 Aug 2023.

## Placed in

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

## Builds on (most cited first, 8 of 8)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [PaLM 2 Technical Report](https://mlsanity.com/paper/2305.10403/) (2023)
- [Faith and Fate: Limits of Transformers on Compositionality](https://mlsanity.com/paper/2305.18654/) (2023)
- [PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning about Change](https://mlsanity.com/paper/2206.10498/) (2022)
- [One Embedder, Any Task: Instruction-Finetuned Text Embeddings](https://mlsanity.com/paper/2212.09741/) (2022)
- [SGPT: GPT Sentence Embeddings for Semantic Search](https://mlsanity.com/paper/2202.08904/) (2022)
- [Faithful Reasoning Using Large Language Models](https://mlsanity.com/paper/2208.14271/) (2022)
- [Neural Natural Language Processing for Unstructured Data in Electronic Health Records: a Review](https://mlsanity.com/paper/2107.02975/) (2021)

## Built on by (most cited first, 1 of 1)

- [ACR: A Benchmark for Automatic Cohort Retrieval](https://mlsanity.com/paper/2406.14780/) (2024)

## Abstract (arXiv)

The application of Artificial Intelligence (AI) in healthcare has been revolutionary, especially with the recent advancements in transformer-based Large Language Models (LLMs). However, the task of understanding unstructured electronic medical records remains a challenge given the nature of the records (e.g., disorganization, inconsistency, and redundancy) and the inability of LLMs to derive reasoning paradigms that allow for comprehensive understanding of medical variables. In this work, we examine the power of coupling symbolic reasoning with language modeling toward improved understanding of unstructured clinical texts. We show that such a combination improves the extraction of several medical variables from unstructured records. In addition, we show that the state-of-the-art commercially-free LLMs enjoy retrieval capabilities comparable to those provided by their commercial counterparts. Finally, we elaborate on the need for LLM steering through the application of symbolic reasoning as the exclusive use of LLMs results in the lowest performance.