Austria

This study explores the application of generative Large Language Models (LLMs) in DNA sequence analysis, highlighting their advantages over encoder-based models like DNABERT2 and Nucleotide Transformer. While encoder models excel in classification, they struggle to integrate external textual information. In contrast, generative LLMs can incorporate domain knowledge, such as BLASTn annotations, to improve classification accuracy even without fine-tuning. We evaluate this capability on antimicrobial resistance (AMR) gene classification, comparing generative LLMs with encoder-based baselines. Results show that LLMs significantly enhance classification when supplemented with textual information. Additionally, we demonstrate their potential in DNA sequence generation, further expanding their applicability. Our findings suggest that LLMs offer a novel paradigm for integrating biological sequences with external knowledge, bridging gaps in traditional classification methods.

ACL 2025

Can Large Language Models Classify and Generate Antimicrobial Resistance Genes?

### Welcome to The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

Message from the General Chair: 
*It is my great pleasure and honor to welcome you to the 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025), held in beautiful Vienna, Austria, from July 27 to August 1, 2025. ACL2025continues our field’s tradition of excellence in scholarship, innovation, and inclusivity, and I am deeply grateful to the many volunteers who have worked tirelessly to bring this event to life.* 
[Read more](https://drive.google.com/file/d/1GI_hvOpjswAuYdUTromfeDiPpCcqidwg/view?usp=sharing)

To access this event page, you need to log in with the **email address you registered with**. Access credentials will be sent to your email from Underline - subject line "Welcome to ACL 2025". Please be sure to check your spam email folder if you do not see an email confirmation right away.

Please log in

To access this event page, you need to log in with the **email address you registered with**. 

Welcome to The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

workshop paper

Case reports provide critical insights into rare and atypical diseases, but extracting structured knowledge remains challenging due to unstructured text and domain-specific terminology. We introduce CaseReportCollective, an LLM-extracted dataset of 85,961 open-access case reports spanning 37 years across 14 medical domains, validated through programmatic and human evaluation. Our dataset reveals key publication and demographic trends, including a significant increase in open-access case reports over the past decade, shifts in focus from oncology to COVID-19, and sex disparities in reporting across different medical conditions. Over time, the gap between male and female case reports has narrowed, suggesting greater equity in case reporting. Using \textbf{CaseReportCollective}, we further explore embedding-based retrieval for similar medical topics through accumulated similarity scores across extracted structured information. We also conducted detailed error analyses on the retrieval ranking, finding that high-reported topics dominate retrieval. Such retrieval is driven by lexical overlap rather than underlying clinical relevance, often failing to distinguish between semantically similar yet mechanistically distinct conditions. Future work should focus on clinical-aware embeddings adjusted for long-tailed case distributions to improve retrieval accuracy.

CaseReportCollective: A Large-Scale LLM-Extracted Dataset for Structured Medical Case Reports

Antibiotic resistance identification is essential for public health, medical treatment, and drug development. Traditional sequence-based models struggle with accurate resistance prediction due to the lack of biological context. To address this, we propose an NLP-based model that integrates genetic sequences with structured textual annotations, including gene family classifications and resistance mechanisms. Our approach leverages pretrained language models for both genetic sequences and biomedical text, aligning biological metadata with sequence-based embeddings. We construct a novel dataset based on the Antibiotic Resistance Ontology (ARO), consolidating gene sequences with resistance-related textual information. Experiments show that incorporating domain knowledge significantly improves classification accuracy over sequence-only models, reducing reliance on exhaustive laboratory testing. By integrating genetic sequence processing with biomedical text understanding, our approach provides a scalable and interpretable solution for antibiotic resistance prediction.

Enhancing Antimicrobial Drug Resistance Classification by Integrating Sequence-Based and Text-Based Representations

High-quality scientific article embeddings are essential for tasks like document retrieval, citation recommendation, and classification. Traditional citation-based approaches assume citations reflect semantic similarity—an assumption that introduces bias and noise. Recent models like SciNCL and SPECTER2 have attempted to refine citation-based representations but still struggle with noisy citation edges and fail to fully leverage textual information. To address these limitations, we propose a hybrid approach that combines Finding-Citation Graphs (FCG) with contrastive learning. Our method improves triplet selection by filtering out less important citations and incorporating finding similarity relations, leading to better semantic relationship capture. Evaluated on the SciRepEval benchmark, our approach consistently outperforms citation-only baselines, showing the value of text-based semantic structures. While we do not surpass state-of-the-art models in most tasks, our results reveal the limitations of purely citation-based embeddings and suggest paths for improvement through enhanced semantic integration and domain-specific adaptations.

Beyond Citations: Integrating Finding-Based Relations for Improved Biomedical Article Representations

Case Report Forms (CRFs) are largely used in medical research as they ensure accuracy, reliability, and validity of results in clinical studies. However, publicly available, well-annotated CRF datasets are scarce, limiting the development of CRF slot filling systems able to fill in a CRF from clinical notes. To mitigate the scarcity of CRF datasets, we propose to take advantage of available datasets annotated for information extraction tasks and to convert them into structured CRFs. We present a semi-automatic conversion methodology, which has been applied to the E3C dataset in two languages (English and Italian), resulting in a new, high-quality dataset for CRF slot filling. Through several experiments on the created dataset, we report that slot filling achieves 59.7% for Italian and 67.3% for English on a closed Large Language Models (zero-shot) and worse performances on three families of open-source models, showing that filling CRFs is challenging even for recent state-of-the-art LLMs.

Converting Annotated Clinical Cases into Structured Case Report Forms

Accurate prediction of drug–target interactions is critical for accelerating drug discovery. In this work, we frame drug–target prediction as a link prediction task on heterogeneous biomedical knowledge graphs (KG) that integrate drugs, proteins, diseases, pathways, and other relevant entities. Conventional KG embedding methods such as TransE and ComplEx-SE are hindered by their reliance on computationally intensive negative sampling and their limited generalization to unseen drug–target pairs. To address these challenges, we propose Multi-Context-Aware Sampling (MuCoS), a novel framework that prioritizes high-density neighbours to capture salient structural patterns and integrates these with contextual embeddings derived from BERT. By unifying structural and textual modalities and selectively sampling highly informative patterns, MuCoS circumvents the need for negative sampling, significantly reducing computational overhead while enhancing predictive accuracy for novel drug–target associations and drug targets. Extensive experiments on the KEGG50k and PharmKG-8k datasets demonstrate that MuCoS outperforms baselines, achieving up to a 13% improvement in MRR for general relation prediction on KEGG50k, a 22% improvement on PharmKG-8k, and a 6% gain in dedicated drug–target relation prediction on KEGG50k.

MuCoS: Efficient Drug–Target Discovery via Multi-Context-Aware Sampling in Knowledge Graphs

Named Entity Recognition (NER) is crucial for extracting domain-specific entities from text, particularly in biomedical and chemical fields.

Overcoming Data Scarcity in Named Entity Recognition: Synthetic Data Generation with Large Language Models

CRISPR-Cas systems enable systematic investigation of gene function, but experimental CRISPR screens are resource-intensive. Here, we investigate the potential of Large Language Models (LLMs) to predict the outcomes of CRISPR screens in silico, thereby prioritizing experiments and accelerating biological discovery. We introduce a benchmark dataset derived from BioGRID-ORCS and manually curated sources, and evaluate the performance of several LLMs across various prompting strategies, including chain-of-thought and few-shot learning. Furthermore, we develop a novel, efficient prediction framework using LLM-derived embeddings, achieving significantly improved performance and scalability compared to direct prompting. Our results demonstrate the feasibility of using LLMs to guide CRISPR screen experiments.

Virtual CRISPR: Can LLMs Predict CRISPR Screen Results?

This work presents three different approaches to address the ArchEHR-QA 2025 Shared Task on automated patient question answering. We introduce an end-to-end prompt-based baseline and two two-step methods to divide the task, without utilizing any external knowledge. Both two step approaches first extract essential sentences from the clinical text—by prompt or similarity ranking—, and then generate the final answer from these notes. Results indicate that the re-ranker based two-step system performs best, highlighting the importance of selecting the right approach for each subtask. Our best run achieved an overall score of 0.44, ranking 8th out of 30 on the leaderboard, securing the top position in overall factuality.

ArgHiTZ at ArchEHR-QA 2025: A Two-Step Divide and Conquer Approach to Patient Question Answering for Top Factuality

Biomedical texts, such as research articles and clinical reports, are often written in highly technical language, making them difficult for patients and the general public to understand. The BioLaySumm 2025 Shared Task addresses this challenge by promoting the development of models that generate lay summarisation of biomedical content. This paper focuses on Subtask 2.1: Radiology Report Generation with Layman's Terms. In this work, we evaluate two large language model (LLM) architectures, T5-large (700M parameter encoder–decoder model) and LLaMA-3.2-3B (3B parameter decoder-only model). Both models are trained under fully-supervised conditions using the task's multi-source dataset. Our results show that T5-large consistently outperforms LLaMA-3.2-3B across nine out of ten metrics, including relevance, readability, and clinical accuracy, despite having only a quarter of the parameters. Our T5-based model achieved the top rank in both the open-source and close-source tracks of the subtask 2.1.

AEHRC at BioLaySumm 2025: Leveraging T5 for Lay Summarisation of Radiology Reports

In this paper, we present our approach to the BioLaySumm 2025 Shared Task on lay summarization of biomedical research articles, which was conducted as part of the BioNLP Workshop 2025. The aim of the task is to create lay summaries from scientific articles to improve accessibility for a non-expert audience. To this end, we applied preprocessing techniques to clean and standardize the input texts, and fine-tuned Qwen2.5 and Qwen3-based language models for the summarization task. For abstract-based fine-tuning, we investigated whether we can insert salient sentences from the main article into the summary to enrich the input. We also curated a dataset of child-friendly articles with corresponding gold-standard summaries and used large language models to rewrite them into more complex scientific variants to augment our training data with more examples.

Downloads

Next from ACL 2025

CaseReportCollective: A Large-Scale LLM-Extracted Dataset for Structured Medical Case Reports

Similar lecture

Enhancing Antimicrobial Drug Resistance Classification by Integrating Sequence-Based and Text-Based Representations