Biomedical reasoning often requires traversing interconnected relationships across entities such as drugs, diseases, and proteins. Despite the increasing prominence of large language models (LLMs), existing benchmarks lack the ability to evaluate multi-hop reasoning in the biomedical domain, particularly for queries involving one-to-many and many-to-many relationships. This gap leaves the critical challenges of biomedical multi-hop reasoning underexplored. To address this, we introduce BioHopR, a novel benchmark designed to evaluate multi-hop, multi-answer reasoning in structured biomedical knowledge graphs. Built from the comprehensive PrimeKG, BioHopR includes 1-hop and 2-hop reasoning tasks that reflect real-world biomedical complexities.Evaluations of state-of-the-art models reveal that O3-mini, a proprietary reasoning-focused model, achieves 37.93% precision on 1-hop tasks and 14.57% on 2-hop tasks, outperforming proprietary models such as GPT4O and open-source biomedical models including HuatuoGPT-o1-70B and Llama-3.3-70B. However, all models exhibit significant declines in multi-hop performance, underscoring the challenges of resolving implicit reasoning steps in the biomedical domain. By addressing the lack of benchmarks for multi-hop reasoning in biomedical domain, BioHopR sets a new standard for evaluating reasoning capabilities and highlights critical gaps between proprietary and open-source models while paving the way for future advancements in biomedical LLMs. BioHopR is available at https://huggingface.co/datasets/knowlab-research/BioHopR.

Recent advancements in multimodal Large Language Models (LLMs) have significantly enhanced the automation of medical image analysis, particularly in generating radiology reports from chest X-rays (CXR). However, these models still suffer from hallucinations and clinically significant errors, limiting their reliability in real-world applications. In this study, we propose Look & Mark (L&M), a novel grounding fixation strategy that integrates radiologist eye fixations (Look) and bounding box annotations (Mark) into the LLM prompting framework. Unlike conventional fine-tuning, L&M leverages in-context learning to achieve substantial performance gains without retraining. When evaluated across multiple domain-specific and general-purpose models, L&M demonstrates significant gains, including a 1.2% improvement in overall metrics (A.AVG) for CXR-LLaVA compared to baseline prompting and a remarkable 9.2% boost for LLaVA-Med. General-purpose models also benefit from L&M combined with in-context learning, with LLaVA-OV achieving an 87.3% clinical average performance (C.AVG)—the highest among all models, even surpassing those explicitly trained for CXR report generation. Expert evaluations further confirm that L&M reduces clinically significant errors (by 0.43 average errors per report), such as false predictions and omissions, enhancing both accuracy and reliability. These findings highlight L&M’s potential as a scalable and efficient solution for AI-assisted radiology, paving the way for improved diagnostic workflows in low-resource clinical settings.

Transformer model has been a de-facto standard in natural language processing. Its adaptations in other fields such as computer vision showed promising results that this architecture is a powerful neural network in representation learning regardless of the data type. This recent success has led to research in multimodal Large Language Model (LLM), which enabled us to new types of tasks and applications with multiple data types. However, multimodal LLM in the biomedical domain is primarily limited to images, text, and/or sequence data. Here I propose to work on multimodal LLM architecture for biomedical graphs such as protein structure and chemical molecules. The research hypothesis is based on the fact that clinicians and researchers in computational biology and clinical research take advantage of various information for their decision-making process. Therefore, an AI model being able to handle multiple data types should boost its ability to use diverse knowledge for improved performances in clinical applications.

This paper introduces MedExQA, a novel benchmark in medical question-answering, to evaluate large language models’ (LLMs) understanding of medical knowledge through explanations. By constructing datasets across five distinct medical specialties that are underrepresented in current datasets and further incorporating multiple explanations for each question-answer pair, we address a major gap in current medical QA benchmarks which is the absence of comprehensive assessments of LLMs’ ability to generate nuanced medical explanations. Our work highlights the importance of explainability in medical LLMs, proposes an effective methodology for evaluating models beyond classification accuracy, and sheds light on one specific domain, speech language pathology, where current LLMs including GPT4 lack good understanding. Our results show generation evaluation with multiple explanations aligns better with human assessment, highlighting an opportunity for a more robust automated comprehension assessment for LLMs. To diversify open-source medical LLMs (currently mostly based on Llama2), this work also proposes a new medical model, MedPhi-2, based on Phi-2 (2.7B). The model outperformed medical LLMs based on Llama2-70B in generating explanations, showing its effectiveness in the resource-constrained medical domain. We will share our benchmark datasets and the trained model.

This paper describes our submission to the MEDIQA-CORR 2024 shared task for automatically detecting and correcting medical errors in clinical notes. We report results for three methods of few-shot In-Context Learning (ICL) augmented with Chain-of-Thought (CoT) and reason prompts using a large language model (LLM). In the first method, we manually analyse a subset of train and validation dataset to infer three CoT prompts by examining error types in the clinical notes. In the second method, we utilise the training dataset to prompt the LLM to deduce reasons about their correctness or incorrectness. The constructed CoTs and reasons are then augmented with ICL examples to solve the tasks of error detection, span identification, and error correction. Finally, we combine the two methods using a rule-based ensemble method. Across the three sub-tasks, our ensemble method achieves a ranking of 3rd for both sub-task 1 and 2, while securing 7th place in sub-task 3 among all submissions.

This paper presents our submission to the L+M-24 shared task, focused on translating molecular structures into natural language descriptions, known as the molecule captioning task. We selected a small language model (SLM), Phi-3-mini-4k, to evaluate the impact of continued pretraining and instruction tuning for domain-specific chemical knowledge. The Phi-3 model was continued pretrained with 90M chemistry textbooks and abstracts, followed by instruction tuning on 150K question answering sets of SMILES and general chemistry knowledge. Despite the continued pretraining phase not including direct exposure to SMILES representations, it significantly enhanced the Phi-3 model’s performance, a 300% increase for the BLEU scores, in the molecule captioning task. The code and model are released at https://github.com/bluesky333/Phi3KnowChem to facilitate research in chemical small language modeling.

In this paper, we introduce the benchmark datasets named CLUB (Chemical Language Understanding Benchmark) to facilitate NLP research in the chemical industry. We have 4 datasets consisted of text and token classification tasks. As far as we have recognized, it is one of the first examples of chemical language understanding benchmark datasets consisted of tasks for both patent and literature articles provided by industrial organization. All the datasets are internally made by chemists from scratch. Finally, we evaluate the datasets on the various language models based on BERT and RoBERTa, and demonstrate the model performs better when the domain of the pretrained models are closer to chemistry domain. We provide baselines for our benchmark as 0.8054 in average, and we hope this benchmark is used by many researchers in both industry and academia.