MEDIQ: Question-Asking LLMs for Adaptive and Reliable Clinical Reasoning

• URL: http://arxiv.org/abs/2406.00922v2
• Date: Tue, 4 Jun 2024 13:55:05 GMT
• Title: MEDIQ: Question-Asking LLMs for Adaptive and Reliable Clinical Reasoning
• Authors: Shuyue Stella Li, Vidhisha Balachandran, Shangbin Feng, Jonathan Ilgen, Emma Pierson, Pang Wei Koh, Yulia Tsvetkov,
• Abstract summary: In high-stakes domains like clinical reasoning, AI assistants powered by large language models (LLMs) are yet to be reliable and safe. We propose to develop more careful LLMs that ask follow-up questions to gather necessary and sufficient information and respond reliably. We introduce MEDIQ, a framework to simulate realistic clinical interactions.
• Score: 36.400896909161006
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In high-stakes domains like clinical reasoning, AI assistants powered by large language models (LLMs) are yet to be reliable and safe. We identify a key obstacle towards reliability: existing LLMs are trained to answer any question, even with incomplete context in the prompt or insufficient parametric knowledge. We propose to change this paradigm to develop more careful LLMs that ask follow-up questions to gather necessary and sufficient information and respond reliably. We introduce MEDIQ, a framework to simulate realistic clinical interactions, which incorporates a Patient System and an adaptive Expert System. The Patient may provide incomplete information in the beginning; the Expert refrains from making diagnostic decisions when unconfident, and instead elicits missing details from the Patient via follow-up questions. To evaluate MEDIQ, we convert MEDQA and CRAFT-MD -- medical benchmarks for diagnostic question answering -- into an interactive setup. We develop a reliable Patient system and prototype several Expert systems, first showing that directly prompting state-of-the-art LLMs to ask questions degrades the quality of clinical reasoning, indicating that adapting LLMs to interactive information-seeking settings is nontrivial. We then augment the Expert with a novel abstention module to better estimate model confidence and decide whether to ask more questions, thereby improving diagnostic accuracy by 20.3%; however, performance still lags compared to an (unrealistic in practice) upper bound when full information is given upfront. Further analyses reveal that interactive performance can be improved by filtering irrelevant contexts and reformatting conversations. Overall, our paper introduces a novel problem towards LLM reliability, a novel MEDIQ framework, and highlights important future directions to extend the information-seeking abilities of LLM assistants in critical domains.

Related papers

• Accommodate Knowledge Conflicts in Retrieval-augmented LLMs: Towards Reliable Response Generation in the Wild [11.058848731627233]
  Large language models (LLMs) have advanced information retrieval systems. LLMs often face knowledge conflicts between internal memory and retrievaled external information. We propose Swin-VIB, a novel framework that integrates a pipeline of variational information bottleneck models into adaptive augmentation of retrieved information.
  arXiv  Detail & Related papers  (2025-04-17T14:40:31Z)
• Structured Outputs Enable General-Purpose LLMs to be Medical Experts [50.02627258858336]
  Large language models (LLMs) often struggle with open-ended medical questions. We propose a novel approach utilizing structured medical reasoning. Our approach achieves the highest Factuality Score of 85.8, surpassing fine-tuned models.
  arXiv  Detail & Related papers  (2025-03-05T05:24:55Z)
• Aligning LLMs to Ask Good Questions A Case Study in Clinical Reasoning [39.750234944933666]
  Large language models (LLMs) often fail to ask effective questions under uncertainty. We present ALFA, a framework that improves LLM question-asking by decomposing the notion of a "good" question into a set of theory-grounded attributes.
  arXiv  Detail & Related papers  (2025-02-20T18:59:31Z)
• LLM-as-an-Interviewer: Beyond Static Testing Through Dynamic LLM Evaluation [24.103034843158717]
  We introduce LLM-as-an-Interviewer, a novel paradigm for evaluating large language models (LLMs) This approach leverages multi-turn interactions where the interviewer actively provides feedback on responses and poses follow-up questions to the evaluated LLM. We apply the framework to evaluate six models on the MATH and DepthQA tasks.
  arXiv  Detail & Related papers  (2024-12-10T15:00:32Z)
• Information Anxiety in Large Language Models [21.574677910096735]
  Large Language Models (LLMs) have demonstrated strong performance as knowledge repositories. We take the investigation further by conducting a comprehensive analysis of the internal reasoning and retrieval mechanisms of LLMs. Our work focuses on three critical dimensions - the impact of entity popularity, the models' sensitivity to lexical variations in query formulation, and the progression of hidden state representations.
  arXiv  Detail & Related papers  (2024-11-16T14:28:33Z)
• AGENT-CQ: Automatic Generation and Evaluation of Clarifying Questions for Conversational Search with LLMs [53.6200736559742]
  AGENT-CQ consists of two stages: a generation stage and an evaluation stage. CrowdLLM simulates human crowdsourcing judgments to assess generated questions and answers. Experiments on the ClariQ dataset demonstrate CrowdLLM's effectiveness in evaluating question and answer quality.
  arXiv  Detail & Related papers  (2024-10-25T17:06:27Z)
• ELOQ: Resources for Enhancing LLM Detection of Out-of-Scope Questions [52.33835101586687]
  Large Language Models (LLMs) are widely used in Conversational AI systems to generate responses to user inquiries. We propose a guided hallucination-based method to efficiently generate a diverse set of out-of-scope questions from a given document corpus.
  arXiv  Detail & Related papers  (2024-10-18T16:11:29Z)
• Beyond Binary: Towards Fine-Grained LLM-Generated Text Detection via Role Recognition and Involvement Measurement [51.601916604301685]
  Large language models (LLMs) generate content that can undermine trust in online discourse. Current methods often focus on binary classification, failing to address the complexities of real-world scenarios like human-AI collaboration. To move beyond binary classification and address these challenges, we propose a new paradigm for detecting LLM-generated content.
  arXiv  Detail & Related papers  (2024-10-18T08:14:10Z)
• Boosting Healthcare LLMs Through Retrieved Context [0.6144680854063939]
  This study explores the boundaries of context retrieval methods within the healthcare domain. Our findings reveal how open LLMs can achieve performance comparable to the biggest private solutions on established healthcare benchmarks. In particular, we propose OpenMedPrompt to improve the generation of more reliable open-ended answers.
  arXiv  Detail & Related papers  (2024-09-23T15:33:38Z)
• Understanding the Relationship between Prompts and Response Uncertainty in Large Language Models [55.332004960574004]
  Large language models (LLMs) are widely used in decision-making, but their reliability, especially in critical tasks like healthcare, is not well-established. This paper investigates how the uncertainty of responses generated by LLMs relates to the information provided in the input prompt. We propose a prompt-response concept model that explains how LLMs generate responses and helps understand the relationship between prompts and response uncertainty.
  arXiv  Detail & Related papers  (2024-07-20T11:19:58Z)
• UBENCH: Benchmarking Uncertainty in Large Language Models with Multiple Choice Questions [10.28688988951815]
  UBENCH is a benchmark for evaluating large language models. It includes 3,978 multiple-choice questions covering knowledge, language, understanding, and reasoning abilities. We also evaluate the reliability of 15 popular LLMs, finding GLM4 to be the most outstanding.
  arXiv  Detail & Related papers  (2024-06-18T16:50:38Z)
• ReEval: Automatic Hallucination Evaluation for Retrieval-Augmented Large Language Models via Transferable Adversarial Attacks [91.55895047448249]
  This paper presents ReEval, an LLM-based framework using prompt chaining to perturb the original evidence for generating new test cases. We implement ReEval using ChatGPT and evaluate the resulting variants of two popular open-domain QA datasets. Our generated data is human-readable and useful to trigger hallucination in large language models.
  arXiv  Detail & Related papers  (2023-10-19T06:37:32Z)
• Retrieving Evidence from EHRs with LLMs: Possibilities and Challenges [18.56314471146199]
  Large volume of notes often associated with patients together with time constraints renders manually identifying relevant evidence practically infeasible. We propose and evaluate a zero-shot strategy for using LLMs as a mechanism to efficiently retrieve and summarize unstructured evidence in patient EHR.
  arXiv  Detail & Related papers  (2023-09-08T18:44:47Z)
• Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedback [127.75419038610455]
  Large language models (LLMs) are able to generate human-like, fluent responses for many downstream tasks. This paper proposes a LLM-Augmenter system, which augments a black-box LLM with a set of plug-and-play modules.
  arXiv  Detail & Related papers  (2023-02-24T18:48:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.