CORE-Acu: Structured Reasoning Traces and Knowledge Graph Safety Verification for Acupuncture Clinical Decision Support

Liuyi Xu; Yun Guo; Ming Chen; Zihan Dun; Yining Qian; An-Yang Lu; Shuang Li; Lijun Liu

cs.AIMar 9, 2026

CORE-Acu: Structured Reasoning Traces and Knowledge Graph Safety Verification for Acupuncture Clinical Decision Support

Authors: Liuyi Xu, Yun Guo, Ming Chen, Zihan Dun, Yining Qian, An-Yang Lu, Shuang Li, Lijun Liu

Organizations: College of Information Science and Engineering, Northeastern University, Shenyang 110819, China · School of Information Science and Engineering, Yanshan University, Qinhuangdao, Hebei 066000, China · School of Computer Science and Engineering, Northeastern University, Shenyang 110819, China · School of Artificial Intelligence, Beihang University, Beijing 100000, China ·

Abstract

Large language models (LLMs) show significant potential for clinical decision support (CDS), yet their black-box nature -- characterized by untraceable reasoning and probabilistic hallucinations -- poses severe challenges in acupuncture, a field demanding rigorous interpretability and safety. To address this, we propose CORE-Acu, a neuro-symbolic framework for acupuncture clinical decision support that integrates Structured Chain-of-Thought (S-CoT) with knowledge graph (KG) safety verification. First, we construct the first acupuncture Structured Reasoning Trace dataset and a schema-constrained fine-tuning framework. By enforcing an explicit causal chain from pattern identification to treatment principles, treatment plans, and acupoint selection, we transform implicit Traditional Chinese Medicine (TCM) reasoning into interpretable generation constraints, mitigating the opacity of LLM-based CDS. Furthermore, we construct a TCM safety knowledge graph and establish a ``Generate--Verify--Revise'' closed-loop inference system based on a Symbolic Veto Mechanism, employing deterministic rules to intercept hallucinations and enforce hard safety boundaries. Finally, we introduce the Lexicon-Matched Entity-Reweighted Loss (LMERL), which corrects terminology drift caused by the frequency--importance mismatch in general optimization by adaptively amplifying gradient contributions of high-risk entities during fine-tuning. Experiments on 1,000 held-out cases demonstrate CORE-Acu's superior entity fidelity and reasoning quality. Crucially, CORE-Acu achieved 0/1,000 observed safety violations (95% CI: 0--0.37%), whereas GPT-4o exhibited an 8.5% violation rate under identical rules. These results establish CORE-Acu as a robust neuro-symbolic framework for acupuncture clinical decision support, guaranteeing both reasoning auditability and strict safety compliance.

Figures & tables

Figure 1: Overall architecture of the CORE-Acu framework. The framework operates in two phases: (1) Phase I (Offline Training): Module 1 constructs the S-CoT corpus to model the clinical causal chain, while Module 2 builds the TCM KG. These inputs guide Module 3 to fine-tune the LLM via LMERL, focusing on safety-critical entities. (2) Phase II (Online Inference): Module 4 implements a neuro-symbolic closed-loop mechanism, leveraging KG constraints from Module 2 to verify prescriptions and trigger bounded self-correction for guaranteed safety.

Figure 2: The Triangulated Neuro-Symbolic Validation Framework of CORE-Acu. The protocol begins with a Symbolic Veto Mechanism that utilizes the TCM KG to deterministically intercept hard safety violations, effectively reducing the Safety Violation Rate. Validated outputs then undergo multidimensional adjudication and expert cognitive verification, which scrutinize the causal reasoning chain to distinguish authentic clinical logic from black-box memorization traps.

Category	Node Entity	Semantics Description	Count
Basic Info	AcuCode	Standard alphanumeric code (e.g., LI4).	361
	AcuName	Standard Romanized/Pinyin name.	361
	Category	The Meridian or Channel attribution.	14
	CategoryType	Functional classification.	28
Clinical	Disease	Western or Traditional disease names.	520
	Symptom	Discrete clinical symptoms or complaints.	1,240

Table 1: Schema Definition and Statistics of the Proposed TCM-KG. The graph integrates standardized acupoint attributes with expert-verified clinical reasoning logic.

Parameter	Value / Specification
Hardware Infrastructure
CPU	16 vCPU on AMD EPYC 9654
GPU	NVIDIA GeForce RTX 4090 (24GB)
LoRA Fine-tuning Setup
Base Model	Qwen3-8B
Fine-tuning Type	LoRA

Table 2: Implementation Details of Experimental Setup.

Configuration Item	Value / Specification
Judge Model	GPT-5.2 (via OpenAI API)
Call Date	December 2025
Temperature	0.1
Top_p	1.0
Max Tokens	2048
Scoring Scale	0–50 Total Score (5 dimensions, 0–10 each)

Table 3: Detailed Configuration of the LLM-as-a-Judge Evaluation.

Model	BLEU-4	ROUGE-L	Entity-F1
CORE-Acu (Ours)	0.1898	0.3334	0.4612
GLM-4.6	0.0697	0.1970	0.3511
HuatuoGPT-o1-7B	0.0059	0.1209	0.2161
Qwen3-8B (Base)	0.0814	0.1883	0.3062
Qwen-Max (General)	0.0865	0.1988	0.3087
GPT-4o	0.0722	0.1985	0.2906

Table 4: Automated Evaluation Results on the Held-out Test Set. CORE-Acu achieves the best performance among the evaluated baselines across all metrics. Note: Entity-F1 measures the strict overlap of key medical entities (Acupoints, Syndromes) against the ground truth.

Figure 3: Comparative performance across five clinical dimensions.

Figure 4: Distribution of total scores across 1,000 test cases. The comparison includes CORE-Acu, Qwen-Max, Qwen3-8B, GPT-4o, GLM-4.6, and HuatuoGPT-o1-7B.

$\alpha$	BLEU-4	ROUGE-L	Entity-P	Entity-R	Entity-F1
1.0 (Baseline)	0.3728	0.4452	0.5492	0.5245	0.5350
1.02	0.3715	0.4453	0.5495	0.5284	0.5368
1.5 (Ours)	0.3879	0.4573	0.5667	0.5425	0.5521
2.0	0.3485	0.4225	0.5430	0.4937	0.5139
3.0	0.3455	0.4206	0.5332	0.4806	0.5034

Table 5: Sensitivity analysis of the keyword weight factor

\alpha

on the internal validation set.

Model	Reasoning	Diagnosis	Pathology Logic	Prescription	Explicability
CORE-Acu (Ours)	9.53	9.33	8.00	8.00	10.00
GPT-4o	6.00	2.00	2.00	10.00	7.00
GLM-4.6	6.33	6.00	6.00	6.33	7.87
HuatuoGPT	4.00	3.00	3.33	7.00	5.67
Qwen-Max	6.00	6.00	2.00	8.00	2.00
Qwen3-8B	5.00	2.00	2.00	8.00	7.00

Table 6: Qualitative clinical expert evaluation (consensus scores, 0–10;

n=4

complex cases). Three senior TCM practitioners assessed each model along five criteria. GPT-4o attains the highest Prescription score, whereas CORE-Acu achieves substantially stronger Pathology Logic and Explicability , indicating better alignment between clinical reasoning and the final prescription.

Model	Total Score	Reasoning	Dialectical	Pathology Logic	Prescription	Explicability
GPT-4o	36.73 $\pm$ 2.49	7.54 $\pm$ 0.56	7.20 $\pm$ 0.65	7.09 $\pm$ 0.58	7.24 $\pm$ 0.63	7.66 $\pm$ 0.47
Qwen-Max	36.88 $\pm$ 2.10	7.52 $\pm$ 0.54	7.16 $\pm$ 0.58	6.99 $\pm$ 0.59	7.30 $\pm$ 0.56	7.91 $\pm$ 0.32
Qwen3-8B	29.06 $\pm$ 3.56	5.93 $\pm$ 0.79	5.75 $\pm$ 0.77	5.62 $\pm$ 0.72	5.34 $\pm$ 1.14	6.43 $\pm$ 0.59
GLM-4.6	42.26 $\pm$ 2.12	8.77 $\pm$ 0.44	8.34 $\pm$ 0.60	8.51 $\pm$ 0.62	9.04 $\pm$ 0.34	7.60 $\pm$ 0.58
HuatuoGPT	20.00 $\pm$ 3.15	3.99 $\pm$ 0.76	3.92 $\pm$ 0.67	3.77 $\pm$ 0.69	3.64 $\pm$ 0.83	4.68 $\pm$ 0.73
CORE-Acu	42.96 $\pm$ 2.47	8.93 $\pm$ 0.59	8.28 $\pm$ 0.65	8.74 $\pm$ 0.52	8.16 $\pm$ 0.72	8.85 $\pm$ 0.55

Table 7: Quantitative scale validation on 1,000 clinical cases. Scores are reported as mean

\pm

SD over 1,000 cases using the LLM-as-a-Judge protocol (GPT-5.2). CORE-Acu attains the best overall performance and maintains consistent gains on reasoning-centric dimensions.

Figure 5: Safety Violation Rate across models (lower is better).

Method	Mech.	SVR (%)	Repair (fix/det)	FB (#)
Qwen3-8B (base)	–	30.0	–	–
CORE-Acu (SFT)	–	4.0	–	–
CORE-Acu (full)	veto + rw	0 (0/1,000)	100% (40/40)	0

Table 8: Ablation of KG veto (1,000 test cases).

Appendix figures & tables9 assets

Supplementary material from the paper’s appendix.

Appendix

Role	Content
System	You are a TCM acupuncture expert. Follow the required output schema strictly.
Instruction	Based on the patient’s symptoms, generate a S-CoT response. Your output must be a single valid JSON object and contain no additional text.

Appendix

Table A.1: System and Instruction Template.

Field	Model Output Content
Complaint	Unilateral temporal (lateral) headache, migraine-like, accompanied by nausea and photophobia.
Diagnosis	$\bullet$ Shaoyang Headache (Migraine): Unilateral temporal pain linked to the Gallbladder channel. $\bullet$ Hyperactivity of Liver-Yang: Underlying root cause (to be differentiated from Phlegm-Turbidity).
Pathology	Dysfunction of the Shaoyang pivot causing Qi stagnation; Liver Qi rebellion transforming into Fire and disturbing the clear orifices; potentially accompanied by phlegm-turbidity blocking the collaterals.
Principle	$\bullet$ Soothe Shaoyang: Unblock the pivot mechanism. $\bullet$ Calm Liver & Extinguish Wind: Address the root cause of rising Yang. $\bullet$ Unblock Collaterals: Relieve local pain.
Acupoints	• SJ5 (Waiguan) + GB41 (Zulinqi): [Main, Bilateral] Mechanism: The Shaoyang pair. SJ5 dredges the pivot mechanism and clears the head/eyes; GB41 opens the Dai Mai . Together they specifically target lateral migraines and reduce sensitivity to external stimuli. • LR3 (Taichong): [Main, Bilateral] Mechanism: Targeting the Root. Courses Liver Qi and pacifies Liver Yang to treat the underlying hyperactivity and reduce the frequency of emotional triggers. • GB20 (Fengchi): [Assist, Bilateral] Mechanism: Dispels wind and unblocks collaterals; pacifies ascending wind-fire to relieve neck tension and head distension. • GB8 (Shuaigu): [Assist, Affected Side] Mechanism: Local Point. Directly enters the temporal collaterals to course wind and stop pain; specifically improves throbbing sensation and photophobia.

Appendix

Table A.3: A concrete S-CoT output example formatted for readability. This example demonstrates how the model explicates the specific mechanism for each acupoint selection, linking back to the diagnosis.

Model	BLEU Scores				ROUGE Scores			Entity Metrics
Model	B-1	B-2	B-3	B-4	R-1	R-2	R-L	Prec.	Rec.	F1
GPT-4o	0.3470	0.1991	0.1205	0.0722	0.2753	0.0961	0.1985	0.3812	0.2368	0.2906
Qwen-Max	0.3788	0.2259	0.1401	0.0865	0.2949	0.1054	0.1988	0.3678	0.2679	0.3087
Qwen3-8B	0.3735	0.2159	0.1343	0.0814	0.2865	0.1025	0.1883	0.3182	0.2970	0.3062
GLM-4.6	0.3655	0.2061	0.1193	0.0697	0.3257	0.1137	0.1970	0.3480	0.3702	0.3511
HuatuoGPT	0.0331	0.0188	0.0107	0.0059	0.2054	0.0443	0.1209	0.4569	0.1431	0.2161

Appendix

Table B.1: Comprehensive breakdown of automated metrics on the held-out test set.

Component	Content / Specification
Trigger Context	Given generated acupoints $\mathcal{A}$ and a detected conflicting tuple $(x,r,y)$ where $r\in\mathcal{R}_{\text{unsafe}}$ .
System Alert	Safety Verifier Alert: Detected unsafe violation under <RULE_TYPE> .
Evidence Injection	Conflict evidence: <EVIDENCE> ( e.g., { SJ5, GB41 } is Incompatible )
Task Instruction	Your task: Revise acupoints to eliminate conflict while keeping others unchanged.
Hard Constraints	(1) Output only a valid JSON object; (2) No text outside JSON; (3) No conflicting pairs.
Fallback Policy	If unresolved within $T_{\max}$ retries, terminate and request human confirmation.

Appendix

Table B.2: Template Specification for Violation-Aware Rewriting.

Field	Content
Instruction	Perform syndrome differentiation using TCM acupuncture theory and provide structured S-CoT.
Input	Unilateral temporal (lateral) headache, migraine-like
Output	Target S-CoT Response: [complaint :] Unilateral temporal (lateral) headache, migraine-like [diagnosis :] Shaoyang (lateral/temporal) headache / Migraine; Hyperactivity of liver-yang (to be differentiated). [pathology :] Dysfunction of the Shaoyang pivot, stagnation of liver and gallbladder Qi transforming into fire. [principle :] Soothe Shaoyang; Calm the liver and suppress yang; Unblock collaterals to relieve pain. [acupoints :] SJ5, GB41 : main ; GB20, GB8 : assist .

Appendix

Table B.3: Example of a Training Instance in Alpaca Format (SFT Data Record).

Dimension	Assessment Criteria
Reasoning Validity	Assess if the reasoning chain is coherent and free of internal contradictions.
Dialectical Accuracy	Evaluate whether the TCM syndrome (diagnosis) is correct and reflects the precise nature/location of the condition.
Pathological Logic	Verify if the pathological mechanism explanation aligns with TCM theory.
Prescription Rationality	Assess whether selected acupoints align with therapeutic principles and include critical main points.
Explicability	Evaluate transparency, structural clarity, and professional standardization of the output.

Appendix

Table C.1: Definition of the five clinical evaluation dimensions (Scale: 0–10 per dimension).

Component	Content / Specification
System Role	You are a senior TCM acupuncture expert and professor. You need to compare the answers of multiple candidates and score each candidate based on five specific dimensions.
Scoring Criteria	(Detailed rubric as defined in Section C.1 )
Input Data	The prompt receives a formatted block of answers: === Candidate Answer List === {candidates_text_block}
Output Req.	1) Compare all candidates to ensure scoring consistency; 2) Output JSON only (no Markdown); 3) Keys must match the input names exactly.

Appendix

Table C.2: Structure of the Judge Prompt used for evaluation.

Model	Reas.	Dial.	Path.	Pres.	Expl.	Total	Judge’s Rationale (Translated)
CORE-Acu	10	9	10	9	10	48	The reasoning chain is highly coherent, accurately capturing the root-branch relationship. The combination of main points is rigorous and principles-based.
GLM-4.6	9	9	9	9	8	44	Demonstrates a complete chain from etiology to treatment. Syndrome differentiation is precise, though expanded therapies are slightly generalized.
GPT-4o	8	8	8	8	8	40	The differentiation of phlegm-qi binding is accurate with smooth logic. The prescription aligns well, though additions appear somewhat formulaic.
Qwen-Max	8	7	7	7	8	37	Overall structure is clear, but syndrome boundaries are slightly overlapping. The point significance explanation lacks depth for certain key acupoints.
HuatuoGPT	6	5	5	5	6	27	Syndrome differentiation is overly coarse. The prescription is brief with insufficient justification for specific point selection.
Qwen3-8B	4	4	4	3	5	20	Internal logic is loose. Multiple significant errors in acupoint meridian attributes and anatomical locations were detected.

Appendix

Table C.3: Detailed Evaluation Output from Judge LLM (Sample Case 001). Scores represent five key TCM dimensions (0–10).

Field Key	Data Type	Description
complaint	String	Free-text description of patient symptoms.
diagnosis	List[String]	TCM syndrome differentiation (Bian-Zheng).
pathology	String	Mechanism explanation of the illness.
principle	List[String]	Treatment principles guiding the prescription.
acupoints	List[Object]	Structured acupoint prescription. Each object contains: $\bullet$ code: acupoint ID $\bullet$ name: Pinyin name $\bullet$ side: Specific side $\bullet$ role: Therapeutic role

Appendix

Table C.4: Data Schema of the Proposed Dataset

Structured CoT Reasoning

See all 15 papers

From Answers to Arguments: Toward Trustworthy Clinical Diagnostic Reasoning with Toulmin-Guided Curriculum Goal-Conditioned Learning
Apr 13, 2026Chen Zhan, Xiaoyu Tan, Gengchen Ma +3Clinical Reasoning LLM Reliability
School of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai, 201620, China. · Tencent Youtu Lab, Shanghai, 200232, China.
TCMClinicalReason-Bench: Can Language Models Reason from Pathogenesis to Prescription over Real-World Clinical Cases?
Oct 3, 2026Jirui Dai, Chenkai Zhang, Yan Jia +4Traditional Chinese Medicine Clinical Language Model Evaluation
the Department of Computer Science, Johns Hopkins University, Baltimore, USA · the School of Pharmacy, Nanjing University of Chinese Medicine, Nanjing, China · the School of Information Engineering, Huzhou University, Huzhou, China +3
Lingdan-V2: Large language models for clinically grounded reasoning in traditional Chinese medicine
Oct 10, 2026Rui Hua, Yu Wei, Ziri Jin +15Traditional Chinese Medicine Medical LLMs
School of Computer Science & Technology, Beijing Jiaotong University, Beijing, 100044, China · Tianjin Tasly Digital Chinese Medicine Technology Co., Ltd., Tianjin, 300410, China · Tasly Biopharmaceuticals Co., Ltd., Tianjin, 300410, China +8

Apr 13, 2026J/K move · Enter open · S save

From Answers to Arguments: Toward Trustworthy Clinical Diagnostic Reasoning with Toulmin-Guided Curriculum Goal-Conditioned Learning

Chen Zhan, Xiaoyu Tan, Gengchen Ma, Yu-Jie Xiong+2

School of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai, 201620, China. · Tencent Youtu Lab, Shanghai, 200232, China.

Clinical Reasoning LLM Reliability Clinical Decision Support Curriculum Learning

Open paper AskPDF arXiv

The integration of Large Language Models (LLMs) into clinical decision support is critically obstructed by their opaque and often unreliable reasoning. In the high-stakes domain of healthcare, correct answers alone are insufficient; clinical practice demands full transparency to ensure patient safety and enable professional accountability. A pervasive and dangerous weakness of current LLMs is their tendency to produce "correct answers through flawed reasoning." This issue is far more than a minor academic flaw; such process errors signal a fundamental lack of robust understanding, making the model prone to broader hallucinations and unpredictable failures when faced with real-world clinical complexity. In this paper, we establish a framework for trustworthy clinical argumentation by adapting the Toulmin model to the diagnostic process. We propose a novel training pipeline: Curriculum Goal-Conditioned Learning (CGCL), designed to progressively train LLM to generate diagnostic arguments that explicitly follow this Toulmin structure. CGCL's progressive three-stage curriculum systematically builds a solid clinical argument: (1) extracting facts and generating differential diagnoses; (2) justifying a core hypothesis while rebutting alternatives; and (3) synthesizing the analysis into a final, qualified conclusion. We validate CGCL using T-Eval, a quantitative framework measuring the integrity of the diagnosis reasoning. Experiments show that our method achieves diagnostic accuracy and reasoning quality comparable to resource-intensive Reinforcement Learning (RL) methods, while offering a more stable and efficient training pipeline.

Abstract

Structured CoT Reasoning

Explore similar work

From Answers to Arguments: Toward Trustworthy Clinical Diagnostic Reasoning with Toulmin-Guided Curriculum Goal-Conditioned Learning

TCMClinicalReason-Bench: Can Language Models Reason from Pathogenesis to Prescription over Real-World Clinical Cases?

Lingdan-V2: Large language models for clinically grounded reasoning in traditional Chinese medicine