Tao Peng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Tao Peng has a total of 68 co-authors. Here are the top co-authors by number of shared publications:
- Lu Liu
College of Computer Science and Technology, Jilin University, Changchun, 130012, Jilin, China; College of Software, Jilin University, Changchun, 130012, Jilin, China; Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun, 130012, Jilin, China
17 shared publications - Jiayu Han
Department of Linguistics, University of Washington, Seattle, 98195, WA, USA
11 shared publications - Ridong Han
School of Computer Science and Technology/School of Artificial Intelligence, China University of Mining and Technology, Xuzhou, 221116, Jiangsu, China; College of Computer Science and Technology, Jilin University, Changchun, 130012, Jilin, China; Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun, 130012, Jilin, China
7 shared publications - Hai Cui
Information Science and Technology College, Dalian Maritime University, Dalian, China
6 shared publications Lu Liu
6 shared publications- Haijia Bi
College of Computer Science and Technology, Jilin University, Changchun, 130012, Jilin, China
4 shared publications
Latest Publications
- Open Access
- 22 September 2026
- Published by Elsevier in SSRN Electronic Journal
Diagnosing Disagreement Observability Collapse in LLM-based Structured KnowledgeVerification: Restoring Uncertainty Signals through Task-Aligned Multi-View Verification
Large language models are increasingly used for structured knowledge verification, where reliable knowledge verification is essential for identifying potentially incorrect predictions. Existing disagreement-based uncertainty methods assume that repeated outputspreserve observable variation. However, semantically plausible false claims may produce unanimous but incorrect predictions, causing disagreement observability collapse before uncertainty computation. On a controlled stress test, SC-3 has Zero-Entropy Ratesof 83.9% on deceptive examples and 76.5% on 1,491 aligned examples. Its Wrong-Unanimity Rate (WUR) is 67.5% (326/483 errors). As a diagnostic intervention, Multi-View Conflict Aggregation (MVCA) decomposes verification into factual, semantic,and structural dimensions rather than introducing arbitrary prompt diversity. MVCA reduces the corresponding Zero-Entropy Rates to 39.1% and 55.9% and has a WUR of 39.1% (175/448 errors). It obtains AURC 0.234 with three calls, compared with 0.231 for 20 homogeneous samples. The benefit reverses on weaker backbones that do not respond differently to the assigned dimensions. Reliable LLM-based knowledge verification depends on whether diagnostically useful disagreement remains observable before uncertainty aggregation. Task-aligned verification decomposition helps only when the backbone can distinguish the relevant verification dimensions.
- 22 September 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessDiagnosing Disagreement Observability Collapse in LLM-based Structured KnowledgeVerification: Restoring Uncertainty Signals through Task-Aligned Multi-View Verification
Large language models are increasingly used for structured knowledge verification, where reliable knowledge verification is essential for identifying potentially incorrect predictions. Existing disagreement-based uncertainty methods assume that repeated outputspreserve observable variation. However, semantically plausible false claims may produce unanimous but incorrect predictions, causing disagreement observability collapse before uncertainty computation. On a controlled stress test, SC-3 has Zero-Entropy Ratesof 83.9% on deceptive examples and 76.5% on 1,491 aligned examples. Its Wrong-Unanimity Rate (WUR) is 67.5% (326/483 errors). As a diagnostic intervention, Multi-View Conflict Aggregation (MVCA) decomposes verification into factual, semantic,and structural dimensions rather than introducing arbitrary prompt diversity. MVCA reduces the corresponding Zero-Entropy Rates to 39.1% and 55.9% and has a WUR of 39.1% (175/448 errors). It obtains AURC 0.234 with three calls, compared with 0.231 for 20 homogeneous samples. The benefit reverses on weaker backbones that do not respond differently to the assigned dimensions. Reliable LLM-based knowledge verification depends on whether diagnostically useful disagreement remains observable before uncertainty aggregation. Task-aligned verification decomposition helps only when the backbone can distinguish the relevant verification dimensions.
- 12 December 2025
- Published by Elsevier in Neural Networks
- Vol. 197, 108469
Document-level relation extraction with entity type constraints
- 12 December 2025
- Published by Elsevier in Neural Networks
- Vol. 197, 108469
Document-level relation extraction with entity type constraints
- 16 November 2025
- Published by Elsevier in Knowledge-Based Systems
- Vol. 332
Rethinking structural semantics for unsupervised graph domain adaptation
- 16 November 2025
- Published by Elsevier in Knowledge-Based Systems
- Vol. 332
Rethinking structural semantics for unsupervised graph domain adaptation
- 22 September 2025
- Published by Elsevier in Neural Networks
- Vol. 194, 108124
Improving few-shot relation classification with multi-scale hierarchical prototype learning
- 22 September 2025
- Published by Elsevier in Neural Networks
- Vol. 194, 108124
Improving few-shot relation classification with multi-scale hierarchical prototype learning
- 17 July 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 296
Fine-Grained Graph Domain Adaptation via Instance Contrastive Learning
- 17 July 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 296
Fine-Grained Graph Domain Adaptation via Instance Contrastive Learning
- 19 December 2024
- Published by Elsevier in Knowledge-Based Systems
- Vol. 309
Dynamic matching-prototypical learning for noisy few-shot relation classification
- 19 December 2024
- Published by Elsevier in Knowledge-Based Systems
- Vol. 309
Dynamic matching-prototypical learning for noisy few-shot relation classification
- 7 December 2024
- Published by Elsevier in Expert Systems with Applications
- Vol. 266
DRIVE: An adjustable parallel architecture based on evidence awareness for fake news detection
- 7 December 2024
- Published by Elsevier in Expert Systems with Applications
- Vol. 266
DRIVE: An adjustable parallel architecture based on evidence awareness for fake news detection
- 10 June 2024
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 80 (14) , 21431-21446
A CUDA-based parallel optimization method for SM3 hash algorithm
- 10 June 2024
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 80 (14) , 21431-21446
A CUDA-based parallel optimization method for SM3 hash algorithm
- 30 November 2023
- Published by Elsevier in Neural Networks
- Vol. 171, 14-24
Document-level Relation Extraction with Relation Correlations
- 30 November 2023
- Published by Elsevier in Neural Networks
- Vol. 171, 14-24
Document-level Relation Extraction with Relation Correlations
- 30 June 2023
- Published by Elsevier in Knowledge-Based Systems
- Vol. 276
Path-based multi-hop reasoning over knowledge graph for answering questions via adversarial reinforcement learning
- 30 June 2023
- Published by Elsevier in Knowledge-Based Systems
- Vol. 276
Path-based multi-hop reasoning over knowledge graph for answering questions via adversarial reinforcement learning