A knowledge-guided agentic framework for mitigating patient-context ambiguity in health queries

Source

• Source name: arXiv
• Source kind: paper
• Authors / organization: Mahyar Abbasian, Saba A. Farahani, Arshia Ilaty, Hung Cao, Ramesh Jain, Amir M. Rahmani
• Venue: arXiv: cs.CL
• Published: 2026-08-20
• Collected: 2026-08-21
• URL: http://arxiv.org/abs/2608.19875v1
• PDF: https://arxiv.org/pdf/2608.19875v1
• DOI: UNKNOWN
• Registry group: academic_apis_and_preprints
• Evidence role: canonical_academic_index
• Language: en
• Country / region: UNKNOWN

Plain-Language Brief

The paper introduces a framework to improve the performance of healthcare chatbots by reducing patient-context ambiguity in queries. The framework uses a knowledge graph to interpret queries, create plausible hypotheses, identify missing context, ask targeted follow-up questions, and then combine the original query with the acquired context for the downstream language model.

What the Document Says

• The paper presents a knowledge-guided agentic framework designed to mitigate patient-context ambiguity in healthcare chatbots.
• The framework operates between the patient and the downstream language model.
• It interprets queries, uses a task-specific knowledge graph, constructs plausible hypotheses, identifies missing context, asks targeted follow-up questions, and combines the original query with the acquired context for the downstream model.
• The framework was evaluated using two controlled ambiguity-mitigation benchmarks: diagnosis retrieval from 1,034 symptom queries and dietary-safety classification from 487 queries.

Key Concepts Mentioned

• healthcare chatbots
• patient-context ambiguity
• knowledge graph
• plausible hypotheses
• targeted follow-up questions

Claims Made by the Document

• The framework increases overall exact Top-1 accuracy by at least 57.1 percentage points and selective exact Recall@5 by at least 77.7 percentage points in diagnosis retrieval.
• The framework improves accuracy in dietary-safety classification across all five models.

Evidence Used

• Increased overall exact Top-1 accuracy and selective exact Recall@5 in diagnosis retrieval were reported compared with direct prompting.
• Improved accuracy in dietary-safety classification was mentioned across all five models.

Methods / Approach

• The framework uses a knowledge graph, identifies missing context, asks targeted follow-up questions, and combines the original query with the acquired context for the downstream language model.

Limitations Stated by the Authors

Not stated in source

Limitations Noted by the Agent

Agent interpretation — not from the source.

The evaluation was based on two controlled benchmarks, and the framework's performance may vary in real-world scenarios.

Open Questions

• What are the specific methods used to identify missing context?
• How does the framework perform in real-world scenarios?

Notes for Future Q&A

May include interpretation. Labeled where it does.

The paper focuses on improving healthcare chatbots by reducing patient-context ambiguity. The improvements reported are based on controlled benchmarks, and the performance may vary in real-world scenarios.

Raw Abstract / Excerpt

Patients often submit short, underspecified queries to healthcare chatbots that lack the patient-specific information needed to determine an appropriate response. Although these queries may be linguistically clear, they can support multiple plausible answers depending on undisclosed factors such as symptoms, diagnoses, medications, allergies, or dietary restrictions. A language model answering such a query directly may therefore rely on unsupported assumptions about the patient. We introduce a knowledge-guided agentic framework for mitigating patient-context ambiguity before final response generation. The framework operates between the patient and an otherwise unchanged downstream language model. It interprets the initial query, uses a task-specific knowledge graph to construct a set of plausible hypotheses, identifies the missing patient-context variables needed to distinguish among them, and asks targeted follow-up questions. The original query and the acquired context are then combined into a clarified prompt for the downstream model. We evaluated the framework across five language models using two controlled ambiguity-mitigation benchmarks: diagnosis retrieval from 1,034 symptom queries with clinically relevant evidence systematically masked, and dietary-safety classification from 487 queries with decisive health context omitted. The framework was compared with direct answering of the underspecified query and with rephrasing the same query without acquiring new patient information. In diagnosis retrieval, it increased overall exact Top-1 accuracy by at least 57.1 percentage points and selective exact Recall@5 by at least 77.7 percentage points across the five evaluated models compared with direct prompting. In dietary-safety classification, it improved accuracy across all five models and achieved the highest Matthews correlation coefficient for four...