相关论文: Strong Reasoning Isn't Enough: Evaluating Evidence…

Radiological imaging is central to diagnosis, treatment planning, and clinical decision-making. Vision-language foundation models have spurred interest in automated radiology report generation (RRG), but safe deployment requires reliable…

Accurate document retrieval is crucial for the success of retrieval-augmented generation (RAG) applications, including open-domain question answering and code completion. While large language models (LLMs) have been employed as dense…

Document-level relation extraction (DocRE) aims to extract semantic relations among entity pairs in a document. Typical DocRE methods blindly take the full document as input, while a subset of the sentences in the document, noted as the…

With the continuous advancement of Large Language Models (LLMs), intelligent agents are becoming increasingly vital. However, these agents often fail in environments governed by implicit rules--hidden constraints that cannot be observed…

Recent advances in large language models (LLMs) have shown promising results in medical diagnosis, with some studies indicating superior performance compared to human physicians in specific scenarios. However, the diagnostic capabilities of…

Multi-page Document Visual Question Answering requires reasoning over semantics, layouts, and visual elements in long, visually dense documents. Existing OCR-free methods face a trade-off between capacity and precision: end-to-end models…

Multi-agent large language model frameworks are promising for complex multi step reasoning, yet existing systems remain weak for scientific and knowledge intensive domains due to static prompts and agent roles, rigid workflows, and…

When explaining the decisions of deep neural networks, simple stories are tempting but dangerous. Especially in computer vision, the most popular explanation approaches give a false sense of comprehension to its users and provide an overly…

Electronic health records (EHR) consist of longitudinal clinical observations portrayed with sparsity, irregularity, and high-dimensionality, which become major obstacles in drawing reliable downstream clinical outcomes. Although there…

The exponential growth of scientific literature in PDF format necessitates advanced tools for efficient and accurate document understanding, summarization, and content optimization. Traditional methods fall short in handling complex layouts…

We present M-Reason, a demonstration system for transparent, agent-based reasoning and evidence integration in the biomedical domain, with a focus on cancer research. M-Reason leverages recent advances in large language models (LLMs) and…

Knowledge editing (KE) provides a scalable approach for updating factual knowledge in large language models without full retraining. While previous studies have demonstrated effectiveness in general domains and medical QA tasks, little…

Current IR evaluation is based on relevance judgments, created either manually or automatically, with decisions outsourced to Large Language Models (LLMs). We offer an alternative paradigm, that never relies on relevance judgments in any…

Assessing the quality of outputs generated by generative models, such as large language models and vision language models, presents notable challenges. Traditional methods for evaluation typically rely on either human assessments, which are…

Data consistency between unstructured clinical notes and structured tables in Electronic Health Records (EHRs) is essential for patient safety and clinical decision-making. However, existing work on note-table consistency verification…

Assessing the veracity of online content has become increasingly critical. Large language models (LLMs) have recently enabled substantial progress in automated veracity assessment, including automated fact-checking and claim verification…

Large Language Models (LLMs) offer promising opportunities to support mental healthcare workflows, yet they often lack the structured clinical reasoning needed for reliable diagnosis and may struggle to provide the emotionally attuned…

Many benchmarks for automated causal inference evaluate a system's performance based on a single numerical output, such as an Average Treatment Effect (ATE). This approach conflates two distinct steps in causal analysis: identification -…

Existing medical RAG systems mainly leverage knowledge from medical knowledge bases, neglecting the crucial role of experiential knowledge derived from similar patient cases -- a key component of human clinical reasoning. To bridge this…

Determining whether a provided context contains sufficient information to answer a question is a critical challenge for building reliable question-answering systems. While simple prompting strategies have shown success on factual questions,…