Tracing Pharmacological Knowledge In Large Language Models

• URL: http://arxiv.org/abs/2603.03407v1
• Date: Tue, 03 Mar 2026 17:04:08 GMT
• Title: Tracing Pharmacological Knowledge In Large Language Models
• Abstract summary: We investigate how drug-group semantics are represented and retrieved within large language models.<n>Early layers play a key role in encoding drug-group knowledge.<n>Drug-group semantics are distributed across tokens and are already present in the embedding space.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) have shown strong empirical performance across pharmacology and drug discovery tasks, yet the internal mechanisms by which they encode pharmacological knowledge remain poorly understood. In this work, we investigate how drug-group semantics are represented and retrieved within Llama-based biomedical language models using causal and probing-based interpretability methods. We apply activation patching to localize where drug-group information is stored across model layers and token positions, and complement this analysis with linear probes trained on token-level and sum-pooled activations. Our results demonstrate that early layers play a key role in encoding drug-group knowledge, with the strongest causal effects arising from intermediate tokens within the drug-group span rather than the final drug-group token. Linear probing further reveals that pharmacological semantics are distributed across tokens and are already present in the embedding space, with token-level probes performing near chance while sum-pooled representations achieve maximal accuracy. Together, these findings suggest that drug-group semantics in LLMs are not localized to single tokens but instead arise from distributed representations. This study provides the first systematic mechanistic analysis of pharmacological knowledge in LLMs, offering insights into how biomedical semantics are encoded in large language models.

Related papers

• DrugReason: Dynamic Multi-View Reasoning over Knowledge Graph and Language Evidence for Drug Repurposing [55.45112712244231]
  DrugReason is a multi-view reasoning framework that integrates grounded KG reasoning with LLM-generated mechanistic inference for drug repurposing.<n> Experiments on PharmaDB, DDInter, and DrugBank show that DrugReason improves average performance over strong single-view reasoning baselines.
  arXiv  Detail & Related papers  (2026-09-06T18:54:26Z)
• Lost in Tokenization: Context as the Key to Unlocking Biomolecular Understanding in Scientific LLMs [78.18336140706471]
  Sci-LLMs have emerged as a promising frontier for accelerating biological discovery.<n>Current strategies limit Sci-LLMs' reasoning capacity when processing raw biomolecular sequences.<n>We show that a more effective strategy is to provide Sci-LLMs with high-level structured context.
  arXiv  Detail & Related papers  (2025-10-27T09:03:21Z)
• How do Large Language Models Understand Relevance? A Mechanistic Interpretability Perspective [64.00022624183781]
  Large language models (LLMs) can assess relevance and support information retrieval (IR) tasks.<n>We investigate how different LLM modules contribute to relevance judgment through the lens of mechanistic interpretability.
  arXiv  Detail & Related papers  (2025-04-10T16:14:55Z)
• Causal Representation Learning from Multimodal Biomedical Observations [57.00712157758845]
  We develop flexible identification conditions for multimodal data and principled methods to facilitate the understanding of biomedical datasets.<n>Key theoretical contribution is the structural sparsity of causal connections between modalities.<n>Results on a real-world human phenotype dataset are consistent with established biomedical research.
  arXiv  Detail & Related papers  (2024-11-10T16:40:27Z)
• Y-Mol: A Multiscale Biomedical Knowledge-Guided Large Language Model for Drug Development [24.5979645373074]
  Y-Mol is a knowledge-guided LLM designed to accomplish tasks across lead compound discovery, pre-clinic, and clinic prediction. It learns from a corpus of publications, knowledge graphs, and expert-designed synthetic data. Y-Mol significantly outperforms general-purpose LLMs in discovering lead compounds, predicting molecular properties, and identifying drug interaction events.
  arXiv  Detail & Related papers  (2024-10-15T12:39:20Z)
• Large Language Models in Drug Discovery and Development: From Disease Mechanisms to Clinical Trials [49.19897427783105]
  The integration of Large Language Models (LLMs) into the drug discovery and development field marks a significant paradigm shift. We investigate how these advanced computational models can uncover target-disease linkage, interpret complex biomedical data, enhance drug molecule design, predict drug efficacy and safety profiles, and facilitate clinical trial processes.
  arXiv  Detail & Related papers  (2024-09-06T02:03:38Z)
• Explainable Biomedical Hypothesis Generation via Retrieval Augmented Generation enabled Large Language Models [46.05020842978823]
  Large Language Models (LLMs) have emerged as powerful tools to navigate this complex data landscape. RAGGED is a comprehensive workflow designed to support investigators with knowledge integration and hypothesis generation.
  arXiv  Detail & Related papers  (2024-07-17T07:44:18Z)
• UMLS-KGI-BERT: Data-Centric Knowledge Integration in Transformers for Biomedical Entity Recognition [3.5555176462255824]
  This work contributes a data-centric paradigm for enriching the language representations of biomedical transformer-encoder LMs by extracting text sequences from the UMLS.<n>Preliminary results from experiments in the extension of pre-trained LMs as well as training from scratch show that this framework improves downstream performance on multiple biomedical and clinical Named Entity Recognition (NER) tasks.
  arXiv  Detail & Related papers  (2023-07-20T18:08:34Z)
• Interpretable Medical Diagnostics with Structured Data Extraction by Large Language Models [59.89454513692417]
  Tabular data is often hidden in text, particularly in medical diagnostic reports. We propose a novel, simple, and effective methodology for extracting structured tabular data from textual medical reports, called TEMED-LLM. We demonstrate that our approach significantly outperforms state-of-the-art text classification models in medical diagnostics.
  arXiv  Detail & Related papers  (2023-06-08T09:12:28Z)
• HiPrompt: Few-Shot Biomedical Knowledge Fusion via Hierarchy-Oriented Prompting [33.1455954220194]
  HiPrompt is a supervision-efficient knowledge fusion framework. It elicits the few-shot reasoning ability of large language models through hierarchy-oriented prompts. Empirical results on the collected KG-Hi-BKF benchmark datasets demonstrate the effectiveness of HiPrompt.
  arXiv  Detail & Related papers  (2023-04-12T16:54:26Z)
• Interpretability from a new lens: Integrating Stratification and Domain knowledge for Biomedical Applications [0.0]
  This paper proposes a novel computational strategy for the stratification of biomedical problem datasets into k-fold cross-validation (CVs) This approach can improve model stability, establish trust, and provide explanations for outcomes generated by trained IML models.
  arXiv  Detail & Related papers  (2023-03-15T12:02:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.