Search Results for author:
Found 33 papers, 19 papers with code
The impact of preprint servers in the formation of novel ideas
We study whether novel ideas in biomedical literature appear first in preprints or traditional journals.
RARE: Retrieval-Augmented Reasoning Enhancement for Large Language Models
This work introduces RARE (Retrieval-Augmented Reasoning Enhancement), a versatile extension to the mutual reasoning framework (rStar), aimed at enhancing reasoning accuracy and factual integrity across large language models (LLMs) for complex, knowledge-intensive tasks such as commonsense and medical reasoning.
RiTeK: A Dataset for Large Language Models Complex Reasoning over Textual Knowledge Graphs
To tackle these challenges, we first develop a Dataset for LLMs Complex Reasoning over Textual Knowledge Graphs (RiTeK) with a broad topological structure coverage. We synthesize realistic user queries that integrate diverse topological structures, relational information, and complex textual descriptions.
MCQG-SRefine: Multiple Choice Question Generation and Evaluation with Iterative Self-Critique, Correction, and Comparison Feedback
Automatic question generation (QG) is essential for AI and NLP, particularly in intelligent tutoring, dialogue systems, and fact verification.
Blocks Architecture (BloArk): Efficient, Cost-Effective, and Incremental Dataset Architecture for Wikipedia Revision History
Wikipedia (Wiki) is one of the most widely used and publicly available resources for natural language processing (NLP) applications.
CS4: Measuring the Creativity of Large Language Models Automatically by Controlling the Number of Story-Writing Constraints
Additionally, our experiments on OLMo suggest that Learning from Human Feedback (LHF) can help LLMs select better stories from their training data but has limited influence in boosting LLMs' ability to produce creative stories that are unseen in the training corpora.
MedQA-CS: Benchmarking Large Language Models Clinical Skills Using an AI-SCE Framework
Combined with existing benchmarks, MedQA-CS enables a more comprehensive evaluation of LLMs' clinical capabilities for both open- and closed-source LLMs.
Large Language Model-based Role-Playing for Personalized Medical Jargon Extraction
Previous studies reveal that Electronic Health Records (EHR), which have been widely adopted in the U. S. to allow patients to access their personal medical information, do not have high readability to patients due to the prevalence of medical jargon.
ReadCtrl: Personalizing text generation with readability-controlled instruction learning
In an era of large language models (LLMs), readability-controlled text generation based on LLMs has become increasingly important.
UMass-BioNLP at MEDIQA-M3G 2024: DermPrompt -- A Systematic Exploration of Prompt Engineering with GPT-4V for Dermatological Diagnosis
This paper presents our team's participation in the MEDIQA-ClinicalNLP2024 shared task B.
JMLR: Joint Medical LLM and Retrieval Training for Enhancing Reasoning and Professional Question Answering Capability
Through this work, we provide a new and efficient knowledge enhancement method for healthcare, demonstrating the potential of integrating retrieval and LLM training for medical question-answering systems.
LocalTweets to LocalHealth: A Mental Health Surveillance Framework Based on Twitter Data
Prior research on Twitter (now X) data has provided positive evidence of its utility in developing supplementary health surveillance systems.
SYNFAC-EDIT: Synthetic Imitation Edit Feedback for Factual Alignment in Clinical Summarization
Large Language Models (LLMs) such as GPT & Llama have demonstrated significant achievements in summarization tasks but struggle with factual inaccuracies, a critical issue in clinical NLP applications where errors could lead to serious consequences.
EHR Interaction Between Patients and AI: NoteAid EHR Interaction
Through a comprehensive evaluation of the entire dataset using LLM assessment and a rigorous manual evaluation of 64 instances, we showcase the potential of LLMs in patient education.
README: Bridging Medical Jargon and Lay Understanding for Patient Education through Data-Centric NLP
The advancement in healthcare has shifted focus toward patient-centric approaches, particularly in self-care and patient education, facilitated by access to Electronic Health Records (EHR).
Do Physicians Know How to Prompt? The Need for Automatic Prompt Optimization Help in Clinical Note Generation
We recommend a two-phase optimization process, leveraging APO-GPT4 for consistency and expert input for personalization.
Large Language Models are In-context Teachers for Knowledge Reasoning
Furthermore, we reveal that for ICT, rationales from different teacher LLMs or human experts that more resemble the student LLM's self-explanations are better in-context demonstrations.
EHRTutor: Enhancing Patient Understanding of Discharge Instructions
This paper presents EHRTutor, an innovative multi-component framework leveraging the Large Language Model (LLM) for patient education through conversational question-answering.
BioInstruct: Instruction Tuning of Large Language Models for Biomedical Natural Language Processing
We also examined whether categories(e. g., QA, IE, and generation) of instructions impact model performance.
Synthetic Imitation Edit Feedback for Factual Alignment in Clinical Summarization
In this work, we propose a new pipeline using ChatGPT instead of human experts to generate high-quality feedback data for improving factual consistency in the clinical note summarization task.
NoteChat: A Dataset of Synthetic Doctor-Patient Conversations Conditioned on Clinical Notes
We introduce NoteChat, a novel cooperative multi-agent framework leveraging Large Language Models (LLMs) to generate patient-physician dialogues.
Improving Summarization with Human Edits
Existing works use human feedback to train large language models (LLMs) in general domain abstractive summarization and have obtained summary quality exceeding traditional likelihood training.
PaniniQA: Enhancing Patient Education Through Interactive Question Answering
Patient portal allows discharged patients to access their personalized discharge instructions in electronic health records (EHRs).
UMASS_BioNLP at MEDIQA-Chat 2023: Can LLMs generate high-quality synthetic note-oriented doctor-patient conversations?
This paper presents UMASS_BioNLP team participation in the MEDIQA-Chat 2023 shared task for Task-A and Task-C. We focus especially on Task-C and propose a novel LLMs cooperation system named a doctor-patient loop to generate high-quality conversation data sets.
Revisiting the Architectures like Pointer Networks to Efficiently Improve the Next Word Distribution, Summarization Factuality, and Beyond
Is the output softmax layer, which is adopted by most language models (LMs), always the best way to compute the next word probability?
Controllable Video Generation by Learning the Underlying Dynamical System with Neural ODE
Videos depict the change of complex dynamical systems over time in the form of discrete image sequences.
Automated Identification of Eviction Status from Electronic Health Record Notes
Materials and Methods: We first defined eviction status (eviction presence and eviction period) and then annotated eviction status in 5000 EHR notes from the Veterans Health Administration (VHA).
Multi-label Few-shot ICD Coding as Autoregressive Generation with Prompt
This task is challenging due to the high-dimensional space of multi-label assignment (155, 000+ ICD code candidates) and the long-tail challenge - Many ICD codes are infrequently assigned yet infrequent ICD codes are important clinically.
Context Variance Evaluation of Pretrained Language Models for Prompt-based Biomedical Knowledge Probing
Different from the previous known-unknown evaluation criteria, we propose the concept of "Misunderstand" in LAMA for the first time.
MedJEx: A Medical Jargon Extraction Model with Wiki's Hyperlink Span and Contextualized Masked Language Model Score
We first present a novel and publicly available dataset with expert-annotated medical jargon terms from 18K+ EHR note sentences ($MedJ$).
Extracting Biomedical Factual Knowledge Using Pretrained Language Model and Electronic Health Record Context
In order to make LMs as KBs more in line with the actual application scenarios of the biomedical domain, we specifically add EHR notes as context to the prompt to improve the low bound in the biomedical domain.
Improving Formality Style Transfer with Context-Aware Rule Injection
Models pre-trained on large-scale regular text corpora often do not work well for user-generated data where the language styles differ significantly from the mainstream text.
Zero-shot Entity Linking with Efficient Long Range Sequence Modeling
This paper considers the problem of zero-shot entity linking, in which a link in the test time may not present in training.
