Word-Sequence Entropy: Towards Uncertainty Estimation in Free-Form Medical Question Answering Applications and Beyond
원문 초록
Uncertainty estimation is crucial for the reliability of safety-critical human and artificial intelligence (AI) interaction systems, particularly in the domain of healthcare engineering. However, a robust and general uncertainty measure for free-form answers has not been well-established in open-ended medical question-answering (QA) tasks, where generative inequality introduces a large number of irrelevant words and sequences within the generated set for uncertainty quantification (UQ), which can lead to biases. This paper introduces Word-Sequence Entropy (WSE), a method that calibrates uncertainty at both the word and sequence levels, considering semantic relevance. WSE quantifies uncertainty in a way that is more closely aligned with the reliability of LLMs during uncertainty quantification (UQ). We compare WSE with six baseline methods on five free-form medical QA datasets, utilizing seven popular large language models (LLMs). Experimental results demonstrate that WSE exhibits superior performance in UQ under two standard criteria for correctness evaluation. Additionally, in terms of real-world medical QA applications, the performance of LLMs is significantly enhanced (e.g., a 6.36% improvement in model accuracy on the COVID-QA dataset) by employing responses with lower uncertainty that are identified by WSE as final answers, without any additional task-specific fine-tuning or architectural modifications.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Med-REFL: Medical Reasoning Enhancement via Self-Corrected Fine-grained Reflection
Instruction Tuning and CoT Prompting for Contextual Medical QA with LLMs
UProp: Investigating the Uncertainty Propagation of LLMs in Multi-Step Agentic Decision-Making
ReasonMed: A 370K Multi-Agent Generated Dataset for Advancing Medical Reasoning
COIN: Uncertainty-Guarding Selective Question Answering for Foundation Models with Provable Risk Guarantees
From RAG to Agentic: Validating Islamic-Medicine Responses with LLM Agents
토론
이 논문과 연결된 포럼 글이 아직 없습니다.