Integrating chemistry knowledge in large language models via prompt engineering.
Ontology highlight
ABSTRACT:
SUBMITTER: Liu H
PROVIDER: S-EPMC11350497 | biostudies-literature | 2025
REPOSITORIES: biostudies-literature
Publications
Integrating chemistry knowledge in large language models via prompt engineering.
Liu Hongxuan H Yin Haoyu H Luo Zhiyao Z Wang Xiaonan X
Synthetic and systems biotechnology 20240724 1
This paper presents a study on the integration of domain-specific knowledge in prompt engineering to enhance the performance of large language models (LLMs) in scientific domains. The proposed domain-knowledge embedded prompt engineering method outperforms traditional prompt engineering strategies on various metrics, including capability, accuracy, F1 score, and hallucination drop. The effectiveness of the method is demonstrated through case studies on complex materials including the MacMillan c ...[more]
Similar Datasets
Project description:ImportanceThe study highlights the potential of large language models, specifically GPT-3.5 and GPT-4, in processing complex clinical data and extracting meaningful information with minimal training data. By developing and refining prompt-based strategies, we can significantly enhance the models' performance, making them viable tools for clinical NER tasks and possibly reducing the reliance on extensive annotated datasets.ObjectivesThis study quantifies the capabilities of GPT-3.5 and GPT-4 for clinical named entity recognition (NER) tasks and proposes task-specific prompts to improve their performance.Materials and methodsWe evaluated these models on 2 clinical NER tasks: (1) to extract medical problems, treatments, and tests from clinical notes in the MTSamples corpus, following the 2010 i2b2 concept extraction shared task, and (2) to identify nervous system disorder-related adverse events from safety reports in the vaccine adverse event reporting system (VAERS). To improve the GPT models' performance, we developed a clinical task-specific prompt framework that includes (1) baseline prompts with task description and format specification, (2) annotation guideline-based prompts, (3) error analysis-based instructions, and (4) annotated samples for few-shot learning. We assessed each prompt's effectiveness and compared the models to BioClinicalBERT.ResultsUsing baseline prompts, GPT-3.5 and GPT-4 achieved relaxed F1 scores of 0.634, 0.804 for MTSamples and 0.301, 0.593 for VAERS. Additional prompt components consistently improved model performance. When all 4 components were used, GPT-3.5 and GPT-4 achieved relaxed F1 socres of 0.794, 0.861 for MTSamples and 0.676, 0.736 for VAERS, demonstrating the effectiveness of our prompt framework. Although these results trail BioClinicalBERT (F1 of 0.901 for the MTSamples dataset and 0.802 for the VAERS), it is very promising considering few training samples are needed.DiscussionThe study's findings suggest a promising direction in leveraging LLMs for clinical NER tasks. However, while the performance of GPT models improved with task-specific prompts, there's a need for further development and refinement. LLMs like GPT-4 show potential in achieving close performance to state-of-the-art models like BioClinicalBERT, but they still require careful prompt engineering and understanding of task-specific knowledge. The study also underscores the importance of evaluation schemas that accurately reflect the capabilities and performance of LLMs in clinical settings.ConclusionWhile direct application of GPT models to clinical NER tasks falls short of optimal performance, our task-specific prompt framework, incorporating medical knowledge and training samples, significantly enhances GPT models' feasibility for potential clinical applications.
| S-EPMC11339492 | biostudies-literature
Project description:Spatial reasoning in Large Language Models (LLMs) serves as a foundation for embodied intelligence. However, even in simple maze environments, LLMs often struggle to plan correct paths due to hallucination issues. To address this, we propose S2ERS, an LLM-based technique that integrates entity and relation extraction with the on-policy reinforcement learning algorithm Sarsa for optimal path planning. We introduce three key improvements: (1) To tackle the hallucination of spatial, we extract a graph structure of entities and relations from the text-based maze description, aiding LLMs in accurately comprehending spatial relationships. (2) To prevent LLMs from getting trapped in dead ends due to context inconsistency hallucination by long-term reasoning, we insert the state-action value function Q into the prompts, guiding the LLM's path planning. (3) To reduce the token consumption of LLMs, we utilize multi-step reasoning, dynamically inserting local Q-tables into the prompt to assist the LLM in outputting multiple steps of actions at once. Our comprehensive experimental evaluation, conducted using closed-source LLMs ChatGPT 3.5, ERNIE-Bot 4.0 and open-source LLM ChatGLM-6B, demonstrates that S2ERS significantly mitigates the spatial hallucination issues in LLMs, and improves the success rate and optimal rate by approximately 29% and 19%, respectively, in comparison to the SOTA CoT methods.
| S-EPMC11909242 | biostudies-literature
Project description:ObjectivesLarge Language Models (LLMs) have been proposed as a solution to address high volumes of Patient Medical Advice Requests (PMARs). This study addresses whether LLMs can generate high quality draft responses to PMARs that satisfies both patients and clinicians with prompt engineering.Materials and methodsWe designed a novel human-involved iterative processes to train and validate prompts to LLM in creating appropriate responses to PMARs. GPT-4 was used to generate response to the messages. We updated the prompts, and evaluated both clinician and patient acceptance of LLM-generated draft responses at each iteration, and tested the optimized prompt on independent validation data sets. The optimized prompt was implemented in the electronic health record production environment and tested by 69 primary care clinicians.ResultsAfter 3 iterations of prompt engineering, physician acceptance of draft suitability increased from 62% to 84% (P <.001) in the validation dataset (N = 200), and 74% of drafts in the test dataset were rated as "helpful." Patients also noted significantly increased favorability of message tone (78%) and overall quality (80%) for the optimized prompt compared to the original prompt in the training dataset, patients were unable to differentiate human and LLM-generated draft PMAR responses for 76% of the messages, in contrast to the earlier preference for human-generated responses. Majority (72%) of clinicians believed it can reduce cognitive load in dealing with InBasket messages.Discussion and conclusionInformed by clinician and patient feedback synergistically, tuning in LLM prompt alone can be effective in creating clinically relevant and useful draft responses to PMARs.
| S-EPMC11413421 | biostudies-literature
Project description:In this work, we investigate the question: do code-generating large language models know chemistry? Our results indicate, mostly yes. To evaluate this, we introduce an expandable framework for evaluating chemistry knowledge in these models, through prompting models to solve chemistry problems posed as coding tasks. To do so, we produce a benchmark set of problems, and evaluate these models based on correctness of code by automated testing and evaluation by experts. We find that recent LLMs are able to write correct code across a variety of topics in chemistry and their accuracy can be increased by 30 percentage points via prompt engineering strategies, like putting copyright notices at the top of files. Our dataset and evaluation tools are open source which can be contributed to or built upon by future researchers, and will serve as a community resource for evaluating the performance of new models as they emerge. We also describe some good practices for employing LLMs in chemistry. The general success of these models demonstrates that their impact on chemistry teaching and research is poised to be enormous.
| S-EPMC10087057 | biostudies-literature
Project description:Large language models (LLMs) have demonstrated impressive capabilities, but the bar for clinical applications is high. Attempts to assess the clinical knowledge of models typically rely on automated evaluations based on limited benchmarks. Here, to address these limitations, we present MultiMedQA, a benchmark combining six existing medical question answering datasets spanning professional medicine, research and consumer queries and a new dataset of medical questions searched online, HealthSearchQA. We propose a human evaluation framework for model answers along multiple axes including factuality, comprehension, reasoning, possible harm and bias. In addition, we evaluate Pathways Language Model1 (PaLM, a 540-billion parameter LLM) and its instruction-tuned variant, Flan-PaLM2 on MultiMedQA. Using a combination of prompting strategies, Flan-PaLM achieves state-of-the-art accuracy on every MultiMedQA multiple-choice dataset (MedQA3, MedMCQA4, PubMedQA5 and Measuring Massive Multitask Language Understanding (MMLU) clinical topics6), including 67.6% accuracy on MedQA (US Medical Licensing Exam-style questions), surpassing the prior state of the art by more than 17%. However, human evaluation reveals key gaps. To resolve this, we introduce instruction prompt tuning, a parameter-efficient approach for aligning LLMs to new domains using a few exemplars. The resulting model, Med-PaLM, performs encouragingly, but remains inferior to clinicians. We show that comprehension, knowledge recall and reasoning improve with model scale and instruction prompt tuning, suggesting the potential utility of LLMs in medicine. Our human evaluations reveal limitations of today's models, reinforcing the importance of both evaluation frameworks and method development in creating safe, helpful LLMs for clinical applications.
| S-EPMC10396962 | biostudies-literature
Project description:There has been a growing effort to replace manual extraction of data from research papers with automated data extraction based on natural language processing, language models, and recently, large language models (LLMs). Although these methods enable efficient extraction of data from large sets of research papers, they require a significant amount of up-front effort, expertise, and coding. In this work, we propose the ChatExtract method that can fully automate very accurate data extraction with minimal initial effort and background, using an advanced conversational LLM. ChatExtract consists of a set of engineered prompts applied to a conversational LLM that both identify sentences with data, extract that data, and assure the data's correctness through a series of follow-up questions. These follow-up questions largely overcome known issues with LLMs providing factually inaccurate responses. ChatExtract can be applied with any conversational LLMs and yields very high quality data extraction. In tests on materials data, we find precision and recall both close to 90% from the best conversational LLMs, like GPT-4. We demonstrate that the exceptional performance is enabled by the information retention in a conversational model combined with purposeful redundancy and introducing uncertainty through follow-up prompts. These results suggest that approaches similar to ChatExtract, due to their simplicity, transferability, and accuracy are likely to become powerful tools for data extraction in the near future. Finally, databases for critical cooling rates of metallic glasses and yield strengths of high entropy alloys are developed using ChatExtract.
| S-EPMC10882009 | biostudies-literature
Project description:Drug repurposing is a promising approach in the field of drug discovery owing to its efficiency and cost-effectiveness. Most current drug repurposing models rely on specific datasets for training, which limits their predictive accuracy and scope. The number of both market-approved and experimental drugs is vast, forming an extensive molecular space. Due to limitations in parameter size and data volume, traditional drug-target interaction (DTI) prediction models struggle to generalize well within such a broad space. In contrast, large language models (LLMs), with their vast parameter sizes and extensive training data, demonstrate certain advantages in drug repurposing tasks. In our research, we introduce a novel drug repurposing framework, DrugReAlign, based on LLMs and multi-source prompt techniques, designed to fully exploit the potential of existing drugs efficiently. Leveraging LLMs, the DrugReAlign framework acquires general knowledge about targets and drugs from extensive human knowledge bases, overcoming the data availability limitations of traditional approaches. Furthermore, we collected target summaries and target-drug space interaction data from databases as multi-source prompts, substantially improving LLM performance in drug repurposing. We validated the efficiency and reliability of the proposed framework through molecular docking and DTI datasets. Significantly, our findings suggest a direct correlation between the accuracy of LLMs' target analysis and the quality of prediction outcomes. These findings signify that the proposed framework holds the promise of inaugurating a new paradigm in drug repurposing.
| S-EPMC11463036 | biostudies-literature
Project description:The performance of deep learning-based natural language processing systems is based on large amounts of labeled training data which, in the clinical domain, are not easily available or affordable. Weak supervision and in-context learning offer partial solutions to this issue, particularly using large language models (LLMs), but their performance still trails traditional supervised methods with moderate amounts of gold-standard data. In particular, inferencing with LLMs is computationally heavy. We propose an approach leveraging fine-tuning LLMs and weak supervision with virtually no domain knowledge that still achieves consistently dominant performance. Using a prompt-based approach, the LLM is used to generate weakly-labeled data for training a downstream BERT model. The weakly supervised model is then further fine-tuned on small amounts of gold standard data. We evaluate this approach using Llama2 on three different i2b2/ n2c2 datasets for clinical named entity recognition. With no more than 10 gold standard notes, our final BERT models weakly supervised by fine-tuned Llama2-13B consistently outperformed out-of-the-box PubMedBERT by 4.7-47.9% in F1 scores. With only 50 gold standard notes, our models achieved close performance to fully fine-tuned systems.
| S-EPMC11893743 | biostudies-literature
Project description:Vision-language artificial intelligence models (VLMs) possess medical knowledge and can be employed in healthcare in numerous ways, including as image interpreters, virtual scribes, and general decision support systems. However, here, we demonstrate that current VLMs applied to medical tasks exhibit a fundamental security flaw: they can be compromised by prompt injection attacks. These can be used to output harmful information just by interacting with the VLM, without any access to its parameters. We perform a quantitative study to evaluate the vulnerabilities to these attacks in four state of the art VLMs: Claude-3 Opus, Claude-3.5 Sonnet, Reka Core, and GPT-4o. Using a set of N = 594 attacks, we show that all of these models are susceptible. Specifically, we show that embedding sub-visual prompts in manifold medical imaging data can cause the model to provide harmful output, and that these prompts are non-obvious to human observers. Thus, our study demonstrates a key vulnerability in medical VLMs which should be mitigated before widespread clinical adoption.
| S-EPMC11785991 | biostudies-literature
Project description:Knowledge about the interactions between dietary and biomedical factors is scattered throughout uncountable research articles in an unstructured form (e.g., text, images, etc.) and requires automatic structuring so that it can be provided to medical professionals in a suitable format. Various biomedical knowledge graphs exist, however, they require further extension with relations between food and biomedical entities. In this study, we evaluate the performance of three state-of-the-art relation-mining pipelines (FooDis, FoodChem and ChemDis) which extract relations between food, chemical and disease entities from textual data. We perform two case studies, where relations were automatically extracted by the pipelines and validated by domain experts. The results show that the pipelines can extract relations with an average precision around 70%, making new discoveries available to domain experts with reduced human effort, since the domain experts should only evaluate the results, instead of finding, and reading all new scientific papers.
| S-EPMC10185525 | biostudies-literature