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

Mahyar Abbasian; Saba A. Farahani; Arshia Ilaty; Hung Cao; Ramesh Jain; Amir M. Rahmani

cs.CLAug 20, 2026

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

Authors: Mahyar Abbasian, Saba A. Farahani, Arshia Ilaty, Hung Cao, Ramesh Jain, Amir M. Rahmani

Abstract

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...

Figures & tables

Patient query	Patient-specific context	Implication for the response
What should I take for a headache?	Not provided	Several common options may appear plausible, but the information needed to distinguish among them is absent.
What should I take for a headache?	Pregnancy	The response must account for pregnancy-related medication constraints and may differ from general over-the-counter guidance.
What should I take for a headache?	Use of an anticoagulant	The response must consider medication interactions and bleeding risk before suggesting an option.
What should I take for a headache?	Liver disease	The response must consider whether common medications are appropriate given impaired liver function.
What should I take for a headache?	Multiple relevant conditions or warning signs	A specific medication recommendation may be inappropriate, and the response may instead require escalation or professional assessment.

Table 1: Illustrative effect of patient-specific context on an otherwise unchanged health query. The examples are conceptual and show why the same linguistically clear query may require different response strategies as additional patient context becomes available. They are not intended as treatment recommendations or as outputs from the evaluated models.

Figure 1: Mitigating patient-context ambiguity before downstream language-model generation. a , In direct interaction with a healthcare chatbot, the downstream large language model (LLM) can use knowledge encoded during training and, when available, external evidence. However, decision-relevant patient-specific context may remain unavailable because it has not been elicited. The response is therefore generated from incomplete patient context. b , The knowledge-graph-guided ambiguity-mitigation framework operates between the patient-facing interface and an otherwise unchanged downstream LLM. The framework grounds the query in a task-specific knowledge graph, retrieves graph-supported hypotheses and selects the most informative clarification question. The patient’s answer is used to update the active hypotheses, and the cycle repeats until a stopping condition is met. The resulting clarified record is then passed to the downstream LLM, which generates a response informed by the elicited context.

	Symptom-based diagnosis retrieval	Dietary safety classification
Data source	Curated synthetic patient records	Curated food and health-condition resources
Evaluation instances	1,034	487
Output space	32 diagnosis labels	OK or Not OK
Information initially provided	Partial symptom profile	Food-related question without complete health context
Information initially withheld	Approximately 49.5% of the symptoms recorded in the complete case	Patient-specific health conditions relevant to the queried food
Information initially visible	Approximately 50.5% of the symptoms recorded in the complete case	Queried food and the user’s stated request

Table 2: Overview of the two ambiguity-mitigation evaluation sets. Both evaluation sets were curated so that the intended output could not be uniquely determined from the information initially provided. Missing patient-specific information was subsequently made available through the clarification process.

			Top-1, selective			Recall@5, selective			Top-1, overall			Recall@5, overall
Model	Configuration	Abstain	Category	ICD	Exact	Category	ICD	Exact	Category	ICD	Exact	Category	ICD	Exact
GPT-5.5	Agent	3.4	92.1	82.2	64.3	96.9	95.1	94.1	89.0	79.4	62.1	93.6	91.9	90.9
GPT-5.5	RaR	0.0	80.3	27.5	1.7	95.6	60.5	2.2	80.3	27.5	1.7	95.6	60.5	2.2
GPT-5.5	Basic	0.0	80.9	27.2	1.6	95.6	60.1	2.0	80.9	27.2	1.6	95.6	60.1	2.0
Claude Opus 4.8	Agent	3.4	94.0	81.6	72.6	96.7	94.9	93.9	90.8	78.8	70.1	93.4	91.7	90.7
Claude Opus 4.8	RaR	0.0	79.2	33.3	4.5	94.8	63.4	10.9	79.2	33.3	4.5	94.8	63.4	10.9

Table 3: Symptom-based diagnosis retrieval on the curated evaluation set (

n=1{,}034

). Performance was evaluated at three levels of specificity: broad diagnostic category, ICD-level grouping, and exact diagnosis name. Selective results include only cases for which the framework returned an answer. Overall results include all evaluation cases, with abstentions counted as incorrect. Because the Basic and RaR configurations did not abstain, their selective and overall values are identical. Bold values indicate the best configuration within each downstream model and metric column. Underlined values indicate the highest value in the corresponding column across all models and configurations. Category and ICD values rely on reference mappings that were not independently clinician-adjudicated, whereas exact-name matching does not require these mappings. All values are percentages.

Model	Configuration	Accuracy	MCC	F1	Recall	Precision	FN rate	FP rate	FN ( $n$ )
GPT-5.5	Agent $\star$	89.3	0.783	0.869	92.5	81.9	7.5	12.6	14
GPT-5.5	RaR	83.2	0.640	0.747	65.1	87.7	34.9	5.6	65
GPT-5.5	Basic	88.3	0.757	0.852	88.2	82.4	11.8	11.6	22
Claude Opus 4.8	Agent $\star$	91.8	0.837	0.900	96.8	84.1	3.2	11.3	6
Claude Opus 4.8	RaR	83.4	0.650	0.741	62.4	91.3	37.6	3.7	70
Claude Opus 4.8	Basic	81.3	0.607	0.760	77.4	74.6	22.6	16.3	42

Table 4: Dietary safety classification on 487 queries. The positive class is Not OK . A false negative denotes an unsafe food classified as safe, whereas a false positive denotes an unnecessary restriction. MCC is reported because the dataset contains 301 OK and 186 Not OK queries. Bold values indicate the best result within each downstream-model block and metric column;

\star

marks the best configuration for each model, ranked by MCC. Higher values are better for accuracy, MCC, F1, recall, and precision, whereas lower values are better for false-negative rate, false-positive rate, and false-negative count. Accuracy, recall, precision, and error rates are percentages.

Figure 2: Between-model performance and variation under each configuration. Markers denote the mean across the five evaluated downstream language models, and horizontal error bars denote

\pm 1

population standard deviation across the five model-specific values. Diagnosis metrics were computed over all 1,034 cases, with abstentions counted as incorrect, and dietary metrics were computed over all 487 queries. Higher values indicate better performance for category Top-1 accuracy, ICD Top-1 accuracy, exact Recall@5, and dietary MCC, whereas a lower value indicates better performance for the dietary false-negative rate, as shown by the arrows above each panel. For every displayed metric, the Agent attained both a better mean and a smaller between-model standard deviation than either baseline, indicating stronger average performance and less dependence on the selected downstream model. MCC is unitless; all other quantities are expressed in percentage points. Exact Top-1 diagnosis accuracy was omitted because its near-zero baseline means made dispersion alone misleading.

		Item 0: acute viral pharyngitis			Item 98: ischemic heart disease
Model	Configuration	$K$	$H_{\mathrm{exact}}$	$H_{\mathrm{cat}}$	$K$	$H_{\mathrm{exact}}$	$H_{\mathrm{cat}}$
GPT-5.5	Agent $\star$	1	0.000	0.000	1	0.000	0.000
GPT-5.5	RaR	1	0.000	0.000	6	1.006	0.988
GPT-5.5	Basic	1	0.000	0.000	5	1.232	1.128
Claude Opus 4.8	Agent $\star$	1	0.000	0.000	2	0.335	0.000
Claude Opus 4.8	RaR	11	2.092	0.000	9	2.044	0.511

Table 5: Diagnosis-output uncertainty under repeated sampling. Two randomly selected diagnosis queries were evaluated using 500 independent repetitions for each model and configuration.

K

denotes the number of distinct exact diagnosis strings returned,

H_{\mathrm{exact}}

denotes predictive entropy over exact diagnosis strings, and

H_{\mathrm{cat}}

denotes entropy after mapping outputs to their clinical categories. Item 0 had the reference diagnosis acute viral pharyngitis, and Item 98 had the reference diagnosis ischemic heart disease. In the Agent condition, the symbolic clarification trajectory and terminal hypothesis were held fixed, so the repetitions resampled only downstream language generation. Outputs that could not be mapped to a clinical category were retained as distinct categories rather than excluded. Bold values identify the lowest-uncertainty configuration within each model block, and

\star

marks that configuration. Lower values indicate less variation across repeated outputs. Entropy measures the dispersion of the generated answers and does not, by itself, indicate whether the resulting diagnosis was correct. Entropy is reported in bits.

		Classification over 1,000 repetitions					Predictive entropy (bits)
Model	Configuration	Accuracy	MCC	Recall	Precision	FP rate	$H_{\mathrm{unsafe}}$	$H_{\mathrm{safe}}$	Mean $H$
GPT-5.5	Agent $\star$	100.0	1.000	100.0	100.0	0.0	0.000	0.000	0.000
GPT-5.5	RaR	96.8	0.938	93.6	100.0	0.0	0.343	0.000	0.172
GPT-5.5	Basic $\star$	100.0	1.000	100.0	100.0	0.0	0.000	0.000	0.000
Claude Opus 4.8	Agent $\star$	100.0	1.000	100.0	100.0	0.0	0.000	0.000	0.000
Claude Opus 4.8	RaR	99.2	0.984	98.4	100.0	0.0	0.118	0.000	0.059

Table 6: Dietary-safety uncertainty under repeated sampling. One Not OK -labeled query and one OK -labeled query were each evaluated using 500 independent repetitions per model and configuration, producing 1,000 binary decisions per row. The positive class was Not OK .

H_{\mathrm{unsafe}}

and

H_{\mathrm{safe}}

denote predictive entropy for the Not OK - and OK -labeled queries, respectively. Zero bits indicates a fully consistent output, while one bit indicates an approximately even split between the two labels. In the Agent condition, the confirmed patient context and final safety decision were held fixed across repetitions, so the repetitions resampled only downstream language generation. Bold values indicate the best result within each model block and metric column. The

\star

symbol marks the best-performing configuration for each model, ranked first by MCC, then by accuracy and mean entropy. Exact ties are marked for both configurations. Low entropy indicates consistency, not necessarily correctness. Accuracy, recall, precision, and false-positive rate are percentages; MCC is unitless.

Figure 3: Knowledge-graph-guided ambiguity-mitigation framework. a , The framework operates between the user-facing Interface and an unchanged downstream large language model (LLM). The Interface exchanges the initial query, clarification questions and user answers. The Orchestrator combines an inner LLM with a deterministic controller and accesses a task-specific knowledge graph implemented in Neo4j. After clarification, the Orchestrator passes the clarified query and retained graph evidence to the downstream LLM for response generation. b , The inner LLM interprets the query, and graph grounding retrieves the supported candidate hypotheses. When the available context is insufficient, the controller selects the eligible question with the greatest expected information gain. The inner LLM expresses the selected variable as a user-facing question, and the controller uses the answer to remove incompatible hypotheses. The cycle repeats until the remaining evidence supports a task output, no informative question remains or the interaction limit is reached. Orange denotes inner-LLM operations, blue denotes deterministic-controller operations, green denotes knowledge-graph operations and purple denotes the clarified output.

Appendix figures & tables6 assets

Supplementary material from the paper’s appendix.

Appendix

Stage or partition	Patients	Instances
Generated by Synthea	4,884	–
Excluded: no retained benchmark instance	366	–
Included in the frozen benchmark	4,518	10,374
Training partition	3,163	7,258
Validation partition	904	2,082
Test partition	451	1,034

Appendix

Supplementary Table 1: Flow of synthetic patients and case–diagnosis instances into the diagnosis benchmark.

Component	Count
Diagnosis nodes	129,815
Symptom nodes	340,842
HAS_SYMPTOM relations	82,813
IS_A relations	1,400

Appendix

Supplementary Table 2: DxSxKG artifact used in the reported evaluation.

Component	Count
USDA food-item nodes	2,085,340
Nutrient nodes	477
Food-phrase nodes	298
Ingredient nodes	130
Food-property nodes	60
Condition nodes	67

Appendix

Supplementary Table 3: FoodSafetyKG components used in the reported evaluation.

Display label	Developer	API provider	Requested identifier
GPT-5.5	OpenAI	OpenAI	gpt-5.5
Claude Opus 4.8	Anthropic	Anthropic	claude-opus-4-8
Gemini 3.1 Pro	Google	OpenRouter	google/gemini-3.1-pro-preview
Llama 3.3 70B Instruct	Meta	OpenRouter	meta-llama/llama-3.3-70b-instruct
Mistral Large	Mistral AI	Mistral	mistral-large-2512

Appendix

Supplementary Table 4: Model routing used for the frozen evaluation.

Mechanism	Seed (specific)	Surface after AIM	Latent
Severity masking	I’m feeling extremely anxious and having panic attacks for 2 weeks. I don’t know what to do.	I’m feeling anxious and having panic attacks for 2 weeks. I don’t know what to do.	full seed
Temporal masking	I’ve been depressed for 2 weeks .	I’ve been depressed for a while.	full seed
Euphemism mapping (risk-preserving vagueness)	I’ve been having thoughts of hurting myself .	I’ve been having thoughts. a	full seed
Diagnostic phrase removal	I was diagnosed with major depressive disorder .	I was diagnosed with. b	full seed
Ontological generalization (domain map + WordNet)	After masking: … and having panic attacks …	… and having mental condition … (domain hypernym map where applicable)	masked intermediate
LLM persona rewrite (illustrative)	(same seed as row 1, after rule-based steps)	“I’ve been kind of on edge and my body does that thing where it freaks out, it’s been going on for a bit.”	full seed + strategy tags

Appendix

Supplementary Table 5: Mental-health domain: example transformations produced by AIM masking, lexical generalization, and one illustrative vague user paraphrase. Latent indicates what is retained as hidden structure and is not shown to the user at inference time.

Mechanism	Seed (specific)	Surface after AIM	Latent
Disease/condition masking	Can I eat white rice with chicken curry? I have type 2 diabetes.	Can I eat white rice with chicken curry?	condition + safety label
Allergen masking	I need a recipe with 2 cups flour and chicken, but I have a peanut allergy.	I need a recipe with 2 cups flour and chicken, but.	allergen + full seed
Quantity removal	Add 2 cups of flour to the bowl.	Add some of flour to the bowl.	quantities + full seed
Ingredient omission	I need chicken, onions, and garlic for the stir-fry.	I need onions, and garlic for the stir-fry. (one ingredient dropped)	omitted slots + full seed
Generalization only	I want grilled salmon for dinner.	I want grilled fish for dinner.	full seed
LLM persona rewrite (illustrative)	(masked recipe-style request)	“I want to make that creamy spicy thing, maybe with some meat? I can’t remember what I bought.”	full seed + variables

Appendix

Supplementary Table 6: Food/dietary domain: examples of omission, abstraction, and generalization that force clarification of health context (e.g., diabetes, allergy), amounts, or ingredients. The Latent column names the hidden structure that must be recovered before a safety decision.

Medical QA

Medical question answering develops and evaluates AI systems that answer clinical, patient-facing, and health-information questions.

See all 84 papers

Knowing but Not Showing: LLMs Recognize Ambiguity but Rarely Ask Clarifying Questions
May 24, 2026Jinyan Su, Claire CardieLLM Evaluation Clarification Question Generation
1Cornell University
MedClarify: An information-seeking AI agent for medical diagnosis with case-specific follow-up questions
Feb 19, 2026Hui Min Wong, Philip Heesen, Pascal Janetzky +2Information Gain Medical LLMs
LMU Munich, Munich, Germany · Munich Center for Machine Learning, Germany · Department of Neuroradiology, Heidelberg University, Heidelberg, Germany
Query Disambiguation via Answer-Free Context: Doubling Performance on Humanity's Last Exam
Feb 27, 2026Michael Majurski, Cynthia MatuszekQuery Reformulation LLM Grounding
National Institute of Standards and Technology · University of Maryland Baltimore County

May 24, 2026J/K move · Enter open · S save

Knowing but Not Showing: LLMs Recognize Ambiguity but Rarely Ask Clarifying Questions

Jinyan Su, Claire Cardie

1Cornell University

LLM Evaluation Clarification Question Generation LLM Decision-Making

Open paper AskPDF arXiv

User queries are often underspecified and may admit multiple valid interpretations. Rather than silently making assumptions about the user's intent, a helpful assistant should surface such ambiguity by asking a clarifying question. Doing so requires two abilities: recognizing that a query is ambiguous, and acting on that recognition by seeking clarification instead of answering directly. To study these abilities, we evaluate models on ambiguous, unambiguous, and disambiguated questions in three settings: standard question answering, explicit ambiguity judgment, and behavioral analysis, where a judge model classifies responses as direct answers, refusals, or clarifying questions. We find a clear gap between recognition and behavior: models often identify ambiguity when explicitly asked to judge it, yet in the QA setting they overwhelmingly default to direct answers. Retrieved context further widens this gap by improving answerability while making models even less likely to ask clarifying questions.

Abstract

Medical QA

Explore similar work

Knowing but Not Showing: LLMs Recognize Ambiguity but Rarely Ask Clarifying Questions

MedClarify: An information-seeking AI agent for medical diagnosis with case-specific follow-up questions

Query Disambiguation via Answer-Free Context: Doubling Performance on Humanity's Last Exam