KnowGuard: Knowledge-Driven Abstention for Multi-Round Clinical Reasoning
In clinical practice, physicians refrain from making decisions when patient information is insufficient. This behavior, known as abstention, is a critical safety mechanism preventing potentially harmful misdiagnoses. Recent investigations have reported the application of large language models (LLMs) in medical scenarios. However, existing LLMs struggle with the abstentions, frequently providing overconfident responses despite incomplete information. This limitation stems from conventional abstention methods relying solely on model self-assessments, which lack systematic strategies to identify knowledge boundaries with external medical evidences. To address this, we propose \textbf{KnowGuard}, a novel \textit{investigate-before-abstain} paradigm that integrates systematic knowledge graph exploration for clinical decision-making. Our approach consists of two key stages operating on a shared contextualized evidence pool: 1) an evidence discovery stage that systematically explores the medical knowledge space through graph expansion and direct retrieval, and 2) an evidence evaluation stage that ranks evidence using multiple factors to adapt exploration based on patient context and conversation history. This two-stage approach enables systematic knowledge graph exploration, allowing models to trace structured reasoning paths and recognize insufficient medical evidence. We evaluate our abstention approach using open-ended multi-round clinical benchmarks that mimic realistic diagnostic scenarios, assessing abstention quality through accuracy-efficiency trade-offs beyond existing closed-form evaluations. Experimental evidences clearly demonstrate that KnowGuard outperforms state-of-the-art abstention approaches, improving diagnostic accuracy by 3.93\% while reducing unnecessary interaction by 7.27 turns on average.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Twin Worlds: Equivariance-Based Abstention for Evidence-Grounded Reasoning
Knowledge-intensive reasoning requires Large Language Models (LLMs) to ground answers in provided evidence. When evidence is insufficient, it is desirable that models abstain rather than confidently generating unsupporte…
Hallucinate Less by Thinking More: Aspect-Based Causal Abstention for Large Language Models
Large Language Models (LLMs) often produce fluent but factually incorrect responses, a phenomenon known as hallucination. Abstention, where the model chooses not to answer and instead outputs phrases such as "I don't kno…
Causal InferenceMASH: Modeling Abstention via Selective Help-Seeking
LLMs cannot reliably recognize their parametric knowledge boundaries and often hallucinate answers to outside-of-boundary questions. In this paper, we introduce MASH (Modeling Abstention via Selective Help-seeking), a tr…
Reinforcement LearningKARL: Mitigating Hallucinations in LLMs via Knowledge-Boundary-Aware Reinforcement Learning
Enabling large language models (LLMs) to appropriately abstain from answering questions beyond their knowledge is crucial for mitigating hallucinations. While existing reinforcement learning methods foster autonomous abs…
Reinforcement LearningActive Learning for Binary Classification with Abstention
We construct and analyze active learning algorithms for the problem of binary classification with abstention. We consider three abstention settings: \emph{fixed-cost} and two variants of \emph{bounded-rate} abstention, a…
Active LearningBinary ClassificationClassificationGeneral Classification