Answering real-world clinical questions using large language model based systems
Atropos Health（阿特罗波斯健康公司）；University of California, Los Angeles（加州大学洛杉矶分校）；The Hospital for Sick Children（病童医院）；University of California, San Diego（加州大学圣地亚哥分校）；University of Michigan（密歇根大学）；Columbia University（哥伦比亚大学）；Stanford University（斯坦福大学）
Yen Sia Low, Michael L. Jackson, Rebecca J. Hyde, Robert E. Brown, Neil M. Sanghavi, Julian D. Baldwin, C. William Pike, Jananee Muralidharan, Gavin Hui, Natash… 展开作者
Yen Sia Low, Michael L. Jackson, Rebecca J. Hyde, Robert E. Brown, Neil M. Sanghavi, Julian D. Baldwin, C. William Pike, Jananee Muralidharan, Gavin Hui, Natasha Alexander, Hadeel Hassan, Rahul V. Nene, Morgan Pike, Courtney J. Pokrzywa, Shivam Vedak, Adam Paul Yan, Dong-han Yao, Amy R. Zipursky, Christina Dinh, Philip Ballentine, Dan C. Derieg, Vladimir Polony, Rehan N. Chawdry, Jordan Davies, Brigham B. Hyde, Nigam H. Shah, Saurabh Gombar
备注：
28 pages (2 figures, 3 tables) inclusive of 8 pages of supplemental materials (4 supplemental figures and 4 supplemental tables)
Evidence to guide healthcare decisions is often limited by a lack of relevant and trustworthy literature as well as difficulty in contextualizing existing research for a specific patient. Large language models (LLMs) could potentially address both challenges by either summarizing published literature or generating new studies based on real-world data (RWD). We evaluated the ability of five LLM-based systems in answering 50 clinical questions and had nine independent physicians review the responses for relevance, reliability, and actionability. As it stands, general-purpose LLMs (ChatGPT-4, Claude 3 Opus, Gemini Pro 1.5) rarely produced answers that were deemed relevant and evidence-based (2% - 10%). In contrast, retrieval augmented generation (RAG)-based and agentic LLM systems produced relevant and evidence-based answers for 24% (OpenEvidence) to 58% (ChatRWD) of questions. Only the agentic ChatRWD was able to answer novel questions compared to other LLMs (65% vs. 0-9%). These results suggest that while general-purpose LLMs should not be used as-is, a purpose-built system for evidence summarization based on RAG and one for generating novel evidence working synergistically would improve availability of pertinent evidence for patient care.
HealthBranches: Synthesizing Clinically-Grounded Question Answering Datasets via Decision Pathways
University of Calabria（卡拉布里亚大学）；University of Catanzaro（卡坦扎罗大学）；University of Eastern Piedmont（东皮埃蒙特大学）；University of Pisa（比萨大学）；University of Cambridge（剑桥大学）
East China University of Science and Technology（华东理工大学）；Ruijin Hospital, School of Medicine, Shanghai Jiao Tong University（上海交通大学医学院附属瑞金医院）
Clinical text structuring is a critical and fundamental task for clinical research. Traditional methods such as taskspecific end-to-end models and pipeline models usually suffer from the lack of dataset and error propagation. In this paper, we present a question answering based clinical text structuring (QA-CTS) task to unify different specific tasks and make dataset shareable. A novel model that aims to introduce domain-specific features (e.g., clinical named entity information) into pre-trained language model is also proposed for QA-CTS task. Experimental results on Chinese pathology reports…
EHRNote-ChatQA: A Benchmark for Evidence-Grounded Multi-Turn Clinical Question Answering over Longitudinal Discharge Summaries
KAIST（韩国科学技术院）；Seoul National University（首尔大学）；Seoul National University Bundang Hospital（首尔大学盆唐医院）；SAIHST, Sungkyunkwan University（成均馆大学）；Yonsei University College of Medicine（延世大学医学院）；Gangnam Severance Hospital（江南塞弗伦斯医院）；Severance Hospital（塞弗伦斯医院）；Seoul Medical Center（首尔医疗中心）；Seoul National University Hospital（首尔大学医院）；National Cancer Center（国立癌症中心）；Icahn School of Medicine at Mount Sinai（西奈山伊坎医学院）；Samsung Medical Center（三星医疗中心）
The amount of publicly available biomedical literature has been growing rapidly in recent years, yet question answering systems still struggle to exploit the full potential of this source of data. In a preliminary processing step, many question answering systems rely on retrieval models for identifying relevant documents and passages. This paper proposes a weighted cosine distance retrieval scheme based on neural network word embeddings. Our experiments are based on publicly available data and tasks from the BioASQ biomedical question answering challenge and demonstrate significant performance…
UMass-Amherst（马萨诸塞大学阿默斯特分校）；MIT CSAIL（麻省理工学院计算机科学与人工智能实验室）；MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）；IBM Research, Cambridge（IBM剑桥研究院）
We explore state-of-the-art neural models for question answering on electronic medical records and improve their ability to generalize better on previously unseen (paraphrased) questions at test time. We enable this by learning to predict logical forms as an auxiliary task along with the main task of answer span detection. The predicted logical forms also serve as a rationale for the answer. Further, we also incorporate medical entity information in these models via the ERNIE architecture. We train our models on the large-scale emrQA dataset and observe that our multi-task entity-enriched mode…
With the rapid development of knowledge base,question answering based on knowledge base has been a hot research issue. In this paper, we focus on answering singlerelation factoid questions based on knowledge base. We build a question answering system and study the effect of context information on fact selection, such as entity's notable type,outdegree. Experimental results show that context information can improve the result of simple question answering.
!MSA at AraHealthQA 2025 Shared Task: Enhancing LLM Performance for Arabic Clinical Question Answering through Prompt Engineering and Ensemble Learning
Faculty of Computer Science, MSA University（计算机科学学院，MSA大学）
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；University of Science and Technology of China（中国科学技术大学）；Bytedance Inc（字节跳动公司）
Answering complex questions involving multiple entities and relations is a challenging task. Logically, the answer to a complex question should be derived by decomposing the complex question into multiple simple sub-questions and then answering those sub-questions. Existing work has followed this strategy but has not attempted to optimize the order of how those sub-questions are answered. As a result, the sub-questions are answered in an arbitrary order, leading to larger search space and a higher risk of missing an answer. In this paper, we propose a novel reinforcement learning(RL) approach …
Question answering systems may find the answers to users' questions from either unstructured texts or structured data such as knowledge graphs. Answering questions using supervised learning approaches including deep learning models need large training datasets. In recent years, some datasets have been presented for the task of Question answering over knowledge graphs, which is the focus of this paper. Although many datasets in English were proposed, there have been a few question-answering datasets in Persian. This paper introduces \textit{PeCoQ}, a dataset for Persian question answering. This…
Universität Koblenz-Landau（科布伦茨-兰道大学）；Harz University of Applied Sciences（哈尔茨应用科学大学）
This paper briefly characterizes the field of cognitive computing. As an exemplification, the field of natural language question answering is introduced together with its specific challenges. A possibility to master these challenges is illustrated by a detailed presentation of the LogAnswer system, which is a successful representative of the field of natural language question answering.
Sluice resolution is a problem where a system needs to output the corresponding antecedents of wh-ellipses. The antecedents are elided contents behind the wh-words but are implicitly referred to using contexts. Previous work frames sluice resolution as question answering where this setting outperforms all its preceding works by large margins. Ellipsis and questions are referentially dependent expressions (anaphoras) and retrieving the corresponding antecedents are like answering questions to output pieces of clarifying information. However, the task is not fully solved. Therefore, we want to f…
In this paper, we study the problem of geometric reasoning in the context of question-answering. We introduce Dynamic Spatial Memory Network (DSMN), a new deep network architecture designed for answering questions that admit latent visual representations. DSMN learns to generate and reason over such representations. Further, we propose two synthetic benchmarks, FloorPlanQA and ShapeIntersection, to evaluate the geometric reasoning capability of QA systems. Experimental results validate the effectiveness of our proposed DSMN for visual thinking tasks.
Sri Lanka Institute of Information Technology（斯里兰卡信息技术学院）；College of Science, Health, Engineering and Education（科学、健康、工程与教育学院）
Question Answering has recently received high attention from artificial intelligence communities due to the advancements in learning technologies. Early question answering models used rule-based approaches and moved to the statistical approach to address the vastly available information. However, statistical approaches are shown to underperform in handling the dynamic nature and the variation of language. Therefore, learning models have shown the capability of handling the dynamic nature and variations in language. Many deep learning methods have been introduced to question answering. Most of …
University of California Santa Barbara（加州大学圣巴巴拉分校）
As an important part of Artificial Intelligence (AI), Question Answering (QA) aims at generating answers to questions phrased in natural language. While there has been substantial progress in open-domain question answering, QA systems are still struggling to answer questions which involve geographic entities or concepts and that require spatial operations. In this paper, we discuss the problem of geographic question answering (GeoQA). We first investigate the reasons why geographic questions are difficult to answer by analyzing challenges of geographic questions. We discuss the uniqueness of g…
The design or simulation analysis of special equipment products must follow the national standards, and hence it may be necessary to repeatedly consult the contents of the standards in the design process. However, it is difficult for the traditional question answering system based on keyword retrieval to give accurate answers to technical questions. Therefore, we use natural language processing techniques to design a question answering system for the decision-making process in pressure vessel design. To solve the problem of insufficient training data for the technology question answering syste…
Video Question Answering is a challenging problem in visual information retrieval, which provides the answer to the referenced video content according to the question. However, the existing visual question answering approaches mainly tackle the problem of static image question, which may be ineffectively for video question answering due to the insufficiency of modeling the temporal dynamics of video contents. In this paper, we study the problem of video question answering by modeling its temporal dynamics with frame-level attention mechanism. We propose the attribute-augmented attention networ…
Research on open-domain question answering (QA) has a long tradition. A challenge in this domain is answering complex questions (CQA) that require complex inference methods and large amounts of knowledge. In low resource languages, such as Persian, there are not many datasets for open-domain complex questions and also the language processing toolkits are not very accurate. In this paper, we propose a knowledge-based approach for answering Persian complex questions using Farsbase; the Persian knowledge graph, exploiting PeCoQ; the newly created complex Persian question dataset. In this work, we…
Several deep learning models have been proposed for question answering. However, due to their single-pass nature, they have no way to recover from local maxima corresponding to incorrect answers. To address this problem, we introduce the Dynamic Coattention Network (DCN) for question answering. The DCN first fuses co-dependent representations of the question and the document in order to focus on relevant parts of both. Then a dynamic pointing decoder iterates over potential answer spans. This iterative procedure enables the model to recover from initial local maxima corresponding to incorrect …
Bar-Ilan University（巴伊兰大学）；Allen Institute for AI（艾伦人工智能研究所）；University of Washington（华盛顿大学）
Long-context question answering (QA) tasks require reasoning over a long document or multiple documents. Addressing these tasks often benefits from identifying a set of evidence spans (e.g., sentences), which provide supporting evidence for answering the question. In this work, we propose a novel method for equipping long-context QA models with an additional sequence-level objective for better identification of the supporting evidence. We achieve this via an additional contrastive supervision signal in finetuning, where the model is encouraged to explicitly discriminate supporting evidence sen…
Complex knowledge base question answering can be achieved by converting questions into sequences of predefined actions. However, there is a significant semantic and structural gap between natural language and action sequences, which makes this conversion difficult. In this paper, we introduce an alignment-enhanced complex question answering framework, called ALCQA, which mitigates this gap through question-to-action alignment and question-to-question alignment. We train a question rewriting model to align the question and each action, and utilize a pretrained language model to implicitly align…
University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；School of Information Sciences（信息科学学院）
Question answering (QA) has demonstrated impressive progress in answering questions from customized domains. Nevertheless, domain adaptation remains one of the most elusive challenges for QA systems, especially when QA systems are trained in a source domain but deployed in a different target domain. In this work, we investigate the potential benefits of question classification for QA domain adaptation. We propose a novel framework: Question Classification for Question Answering (QC4QA). Specifically, a question classifier is adopted to assign question classes to both the source and target data…
University of Maryland（马里兰大学）；Google Research（谷歌研究院）
In addition to the traditional task of getting machines to answer questions, a major research question in question answering is to create interesting, challenging questions that can help systems learn how to answer questions and also reveal which systems are the best at answering questions. We argue that creating a question answering dataset -- and the ubiquitous leaderboard that goes with it -- closely resembles running a trivia tournament: you write questions, have agents (either humans or machines) answer the questions, and declare a winner. However, the research community has ignored the d…
We analyze the language learned by an agent trained with reinforcement learning as a component of the ActiveQA system [Buck et al., 2017]. In ActiveQA, question answering is framed as a reinforcement learning task in which an agent sits between the user and a black box question-answering system. The agent learns to reformulate the user's questions to elicit the optimal answers. It probes the system with many versions of a question that are generated via a sequence-to-sequence question reformulation model, then aggregates the returned evidence to find the best answer. This process is an instanc…
Multi-hop question answering (QA) requires a model to retrieve and integrate information from different parts of a long text to answer a question. Humans answer this kind of complex questions via a divide-and-conquer approach. In this paper, we investigate whether top-performing models for multi-hop questions understand the underlying sub-questions like humans. We adopt a neural decomposition model to generate sub-questions for a multi-hop complex question, followed by extracting the corresponding sub-answers. We show that multiple state-of-the-art multi-hop QA models fail to correctly answer …
The task of Outside Knowledge Visual Question Answering (OKVQA) requires an automatic system to answer natural language questions about pictures and images using external knowledge. We observe that many visual questions, which contain deictic referential phrases referring to entities in the image, can be rewritten as "non-grounded" questions and can be answered by existing text-based question answering systems. This allows for the reuse of existing text-based Open Domain Question Answering (QA) Systems for visual question answering. In this work, we propose a potentially data-efficient approac…
MAC Net is a compositional attention network designed for Visual Question Answering. We propose a modified MAC net architecture for Natural Language Question Answering. Question Answering typically requires Language Understanding and multi-step Reasoning. MAC net's unique architecture - the separation between memory and control, facilitates data-driven iterative reasoning. This makes it an ideal candidate for solving tasks that involve logical reasoning. Our experiments with 20 bAbI tasks demonstrate the value of MAC net as a data-efficient and interpretable architecture for Natural Language Q…
This paper presents a new video question answering task on screencast tutorials. We introduce a dataset including question, answer and context triples from the tutorial videos for a software. Unlike other video question answering works, all the answers in our dataset are grounded to the domain knowledge base. An one-shot recognition algorithm is designed to extract the visual cues, which helps enhance the performance of video question answering. We also propose several baseline neural network architectures based on various aspects of video contexts from the dataset. The experimental results de…
Question-Answering System Extracts Information on Injection Drug Use from Clinical Notes
Oak Ridge National Laboratory（橡树岭国家实验室）；Vanderbilt University（范德堡大学）；Department of Veterans Affairs（美国退伍军人事务部）；Stanford University School of Medicine（斯坦福大学医学院）；Veterans Affairs Great Lakes Health Care System（退伍军人事务部大湖区医疗系统）
University of Bonn（波恩大学）；Ruhr University Bochum（波鸿鲁尔大学）；Fraunhofer IAIS（弗劳恩霍夫应用信息技术研究所）
Answering simple questions over knowledge graphs is a well-studied problem in question answering. Previous approaches for this task built on recurrent and convolutional neural network based architectures that use pretrained word embeddings. It was recently shown that finetuning pretrained transformer networks (e.g. BERT) can outperform previous approaches on various natural language processing tasks. In this work, we investigate how well BERT performs on SimpleQuestions and provide an evaluation of both BERT and BiLSTM-based models in datasparse scenarios.
Imperial College London（帝国理工学院）；University of Sheffield（谢菲尔德大学）；Department of Computing, Imperial College London（帝国理工学院计算机系）；Department of Computer Science, University of Sheffield（谢菲尔德大学计算机科学系）
Current work on Visual Question Answering (VQA) explore deterministic approaches conditioned on various types of image and question features. We posit that, in addition to image and question pairs, other modalities are useful for teaching machine to carry out question answering. Hence in this paper, we propose latent variable models for VQA where extra information (e.g. captions and answer categories) are incorporated as latent variables, which are observed during training but in turn benefit question-answering performance at test time. Experiments on the VQA v2.0 benchmarking dataset demonstr…
Question Answering (QA) is a task in which a machine understands a given document and a question to find an answer. Despite impressive progress in the NLP area, QA is still a challenging problem, especially for non-English languages due to the lack of annotated datasets. In this paper, we present the Japanese Question Answering Dataset, JaQuAD, which is annotated by humans. JaQuAD consists of 39,696 extractive question-answer pairs on Japanese Wikipedia articles. We finetuned a baseline model which achieves 78.92% for F1 score and 63.38% for EM on test set. The dataset and our experiments are …
Tel-Aviv University（特拉维夫大学）；Allen Institute for Artificial Intelligence（艾伦人工智能研究所）
When answering a question, people often draw upon their rich world knowledge in addition to the particular context. Recent work has focused primarily on answering questions given some relevant document or context, and required very little general background. To investigate question answering with prior knowledge, we present CommonsenseQA: a challenging new dataset for commonsense question answering. To capture common sense beyond associations, we extract from ConceptNet (Speer et al., 2017) multiple target concepts that have the same semantic relation to a single source concept. Crowd-workers …
Understanding visual question answering is going to be crucial for numerous human activities. However, it presents major challenges at the heart of the artificial intelligence endeavor. This paper presents an update on the rapid advancements in visual question answering using images that have occurred in the last couple of years. Tremendous growth in research on improving visual question answering system architecture has been published recently, showing the importance of multimodal architectures. Several points on the benefits of visual question answering are mentioned in the review paper by M…
University of Washington（华盛顿大学）；Microsoft Research（微软研究院）
We show that a character-level encoder-decoder framework can be successfully applied to question answering with a structured knowledge base. We use our model for single-relation question answering and demonstrate the effectiveness of our approach on the SimpleQuestions dataset (Bordes et al., 2015), where we improve state-of-the-art accuracy from 63.9% to 70.9%, without use of ensembles. Importantly, our character-level model has 16x fewer parameters than an equivalent word-level model, can be learned with significantly less data compared to previous work, which relies on data augmentation, an…
University of Rochester（罗切斯特大学）；Adobe Research（Adobe研究院）
Answering open-ended questions is an essential capability for any intelligent agent. One of the most interesting recent open-ended question answering challenges is Visual Question Answering (VQA) which attempts to evaluate a system's visual understanding through its answers to natural language questions about images. There exist many approaches to VQA, the majority of which do not exhibit deeper semantic understanding of the candidate answers they produce. We study the importance of generating plausible answers to a given question by introducing the novel task of `Answer Proposal': for a given…
Video question answering has recently received a lot of attention from multimodal video researchers. Most video question answering datasets are usually in the form of multiple-choice. But, the model for the multiple-choice task does not infer the answer. Rather it compares the answer candidates for picking the correct answer. Furthermore, it makes it difficult to extend to other tasks. In this paper, we challenge the existing multiple-choice video question answering by changing it to open-ended video question answering. To tackle open-ended question answering, we use the pretrained GPT2 model.…
Standard accuracy metrics indicate that modern reading comprehension systems have achieved strong performance in many question answering datasets. However, the extent these systems truly understand language remains unknown, and existing systems are not good at distinguishing distractor sentences, which look related but do not actually answer the question. To address this problem, we propose QAInfomax as a regularizer in reading comprehension systems by maximizing mutual information among passages, a question, and its answer. QAInfomax helps regularize the model to not simply learn the superfic…
