Related papers: Keeping Experts in the Loop: Expert-Guided Optimiz…
Mixture of Experts (MoE) has become a key architectural paradigm for efficiently scaling Large Language Models (LLMs) by selectively activating a subset of parameters for each input token. However, standard MoE architectures face…
While pioneering deep learning methods have made great strides in analyzing electronic health record (EHR) data, they often struggle to fully capture the semantics of diverse medical codes from limited data. The integration of external…
Log analysis is crucial for ensuring the orderly and stable operation of information systems, particularly in the field of Artificial Intelligence for IT Operations (AIOps). Large Language Models (LLMs) have demonstrated significant…
Neural language models (LMs) have been extensively trained on vast corpora to store factual knowledge about various aspects of the world described in texts. Current technologies typically employ knowledge editing methods or specific prompts…
This study examines the effect of prompt engineering on the performance of Large Language Models (LLMs) in clinical note generation. We introduce an Automatic Prompt Optimization (APO) framework to refine initial prompts and compare the…
The inherent complexity of structured longitudinal Electronic Health Records (EHR) data poses a significant challenge when integrated with Large Language Models (LLMs), which are traditionally tailored for natural language processing.…
LLMs have gained immense popularity among researchers and the general public for its impressive capabilities on a variety of tasks. Notably, the efficacy of LLMs remains significantly dependent on the quality and structure of the input…
Large language models (LLMs) have shown strong performance in zero-shot summarization, but often struggle to model document structure and identify salient information in long texts. In this work, we introduce StrucSum, a training-free…
Mixture-of-Experts (MoE) has become a prevalent backbone for large vision-language models (VLMs), yet how modality-specific signals should guide expert routing remains under-explored. Existing routing strategies are either hand-crafted or…
This paper presents a novel framework for enhancing reasoning capabilities in large language models (LLMs) by leveraging iterative reasoning and feedback-driven methodologies. Building on the limitations identified in the SimpleBench…
Electronic Health Records (EHRs) are digital records of patient information, often containing unstructured clinical text. Named Entity Recognition (NER) is essential in EHRs for extracting key medical entities like problems, tests, and…
Despite strong performance in medical question-answering, the clinical adoption of Large Language Models (LLMs) is critically hampered by their opaque 'black-box' reasoning, limiting clinician trust. This challenge is compounded by the…
This paper describes our approach to the MEDIQA-CORR shared task, which involves error detection and correction in clinical notes curated by medical professionals. This task involves handling three subtasks: detecting the presence of…
Large Language Models (LLMs) have shown remarkable capabilities, with optimizing their input prompts playing a pivotal role in maximizing their performance. However, while LLM prompts consist of both the task-agnostic system prompts and…
Recent Large Language Model (LLM)-based AutoML systems demonstrate impressive capabilities but face significant limitations such as constrained exploration strategies and a severe execution bottleneck. Exploration is hindered by one-shot…
With the increasing use of large language models (LLMs) for generating answers to biomedical questions, it is crucial to evaluate the quality of the generated answers and the references provided to support the facts in the generated…
A long standing goal of the data management community is to develop general, automated systems that ingest semi-structured documents and output queryable tables without human effort or domain specific customization. Given the sheer variety…
Large language models (LLMs) exhibit remarkable capabilities across diverse tasks, yet aligning them efficiently and effectively with human expectations remains a critical challenge. This thesis advances LLM alignment by introducing novel…
Objective: This study investigates the potential of Large Language Models (LLMs) as an alternative to human expert elicitation for extracting structured causal knowledge and facilitating causal modeling in biometric and healthcare…
The field of healthcare has increasingly turned its focus towards Large Language Models (LLMs) due to their remarkable performance. However, their performance in actual clinical applications has been underexplored. Traditional evaluations…