Analysis of Prompt Engineering for Drug Toxicity Prediction

• URL: http://arxiv.org/abs/2609.03635v1
• Date: Thu, 03 Sep 2026 10:28:55 GMT
• Title: Analysis of Prompt Engineering for Drug Toxicity Prediction
• Abstract summary: This paper proposes a method to analyse prompt engineering for drug toxicity prediction.<n>The aim of the paper is to investigate the importance of prompt phrasing for drug toxicity prediction.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Clinical trials in the UK can cost up to £1.3 million, with approximately 90% drug failure rate. Toxicity is a major contributing factor in drug failure. Testing is time and cost intensive. In recent years, the use of artificial intelligence has been increasingly explored to aid in the prediction of drug toxicity, with extensive use of large language models (LLMs). However, LLMs can show considerable variation when minor changes are made to prompts, which raises concerns about their sensitivity to prompt engineering. Prompt engineering is used to optimise a prompt given to an LLM to generate the desired output. This paper proposes a method to analyse prompt engineering for drug toxicity prediction. The aim of the paper is to investigate the importance of prompt phrasing for drug toxicity prediction. LLMs were prompted to identify chemical properties of significance when predicting drug toxicity. Prompts were constructed to investigate; job role, prompt structuring, and rule interpretation. LLMs were then used to generate datasets, using the identified features from initial prompting, which were then passed to machine learning algorithms. The experiments show that the natural variance which occurs in LLMs outweighs any fine-tuning of prompts. There were, however, substantial improvements in model performance when using chemoinformatic code to extract features instead of using LLM-generated values. The proposed analysis methodology is applicable to a wide range of prompt types across different areas of bioinformatics.

Related papers

• Predicting LLM Performance from Prompt Linguistic Features: An Empirical Study in Requirements Engineering [5.806534256425491]
  Linguistic features significantly predict prompt performance across all targets.<n>Cross-LLM predictors include compound dependency distribution, conjunction density, and word/sentence length.
  arXiv  Detail & Related papers  (2026-08-27T19:02:09Z)
• DrugPlayGround: Benchmarking Large Language Models and Embeddings for Drug Discovery [11.058244885471169]
  Large language models (LLMs) are in the ascendancy for research in drug discovery.<n>DrugPlayGround is a framework to evaluate and benchmark LLM performance.
  arXiv  Detail & Related papers  (2026-02-11T19:16:33Z)
• CoTox: Chain-of-Thought-Based Molecular Toxicity Reasoning and Prediction [20.143495021407166]
  Large language models (LLMs) offer a promising alternative through step-by-step reasoning and integration of textual data.<n>We propose CoTox, a novel framework that integrates LLM with chain-of-thought (CoT) reasoning for multi-toxicity prediction.<n>Using GPT-4o, we show that CoTox outperforms both traditional machine learning and deep learning model.
  arXiv  Detail & Related papers  (2025-08-05T07:04:44Z)
• ChemActor: Enhancing Automated Extraction of Chemical Synthesis Actions with LLM-Generated Data [53.78763789036172]
  We present ChemActor, a fully fine-tuned large language model (LLM) as a chemical executor to convert between unstructured experimental procedures and structured action sequences.<n>This framework integrates a data selection module that selects data based on distribution divergence, with a general-purpose LLM, to generate machine-executable actions from a single molecule input.<n>Experiments on reaction-to-description (R2D) and description-to-action (D2A) tasks demonstrate that ChemActor achieves state-of-the-art performance, outperforming the baseline model by 10%.
  arXiv  Detail & Related papers  (2025-06-30T05:11:19Z)
• Do "New Snow Tablets" Contain Snow? Large Language Models Over-Rely on Names to Identify Ingredients of Chinese Drugs [79.00288739947406]
  Traditional Chinese Medicine (TCM) has seen increasing adoption in healthcare, with specialized Large Language Models (LLMs) emerging to support clinical applications.<n>A fundamental requirement for these models is accurate identification of TCM drug ingredients.<n>Our systematic analysis reveals consistent failure patterns: models often interpret drug names literally, overuse common herbs regardless of relevance, and exhibit erratic behaviors when faced with unfamiliar formulations.
  arXiv  Detail & Related papers  (2025-04-03T17:43:45Z)
• Detoxifying Large Language Models via Knowledge Editing [57.0669577257301]
  This paper investigates using knowledge editing techniques to detoxify Large Language Models (LLMs) We construct a benchmark, SafeEdit, which covers nine unsafe categories with various powerful attack prompts. We conduct experiments with several knowledge editing approaches, indicating that knowledge editing has the potential to detoxify LLMs with a limited impact on general performance efficiently.
  arXiv  Detail & Related papers  (2024-03-21T15:18:30Z)
• Emerging Opportunities of Using Large Language Models for Translation Between Drug Molecules and Indications [6.832024637226738]
  We propose a new task, which is the translation between drug molecules and corresponding indications. The creation of molecules from indications, or vice versa, will allow for more efficient targeting of diseases.
  arXiv  Detail & Related papers  (2024-02-14T21:33:13Z)
• Large Language Model Distilling Medication Recommendation Model [58.94186280631342]
  We harness the powerful semantic comprehension and input-agnostic characteristics of Large Language Models (LLMs)<n>Our research aims to transform existing medication recommendation methodologies using LLMs.<n>To mitigate this, we have developed a feature-level knowledge distillation technique, which transfers the LLM's proficiency to a more compact model.
  arXiv  Detail & Related papers  (2024-02-05T08:25:22Z)
• Self-Verification Improves Few-Shot Clinical Information Extraction [73.6905567014859]
  Large language models (LLMs) have shown the potential to accelerate clinical curation via few-shot in-context learning. They still struggle with issues regarding accuracy and interpretability, especially in mission-critical domains such as health. Here, we explore a general mitigation framework using self-verification, which leverages the LLM to provide provenance for its own extraction and check its own outputs.
  arXiv  Detail & Related papers  (2023-05-30T22:05:11Z)
• RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models [93.151822563361]
  Pretrained neural language models (LMs) are prone to generating racist, sexist, or otherwise toxic language which hinders their safe deployment. We investigate the extent to which pretrained LMs can be prompted to generate toxic language, and the effectiveness of controllable text generation algorithms at preventing such toxic degeneration.
  arXiv  Detail & Related papers  (2020-09-24T03:17:19Z)

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.