Qinghua Zhao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Qinghua Zhao has a total of 38 co-authors. Here are the top co-authors by number of shared publications:
- Junfeng Liu
Department of Optoelectronic Information and Optical Fiber Communication, Pengcheng Laboratory, Shenzhen, China
4 shared publications - Zenghui Zhou
School of Automation Science and Electrical Engineering, Beihang University, Beijing, China
4 shared publications - Zhongfeng Kang
Lanzhou University
4 shared publications - Lei Li
Department of Computer Science, University of Copenhagen, Copenhagen, Denmark
3 shared publications - Kaiyuan Zheng
Beijing Normal University
2 shared publications - Shantian Yang
School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, Sichuan 611731, China
2 shared publications
Latest Publications
- 1 July 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. 75 (7) , 2548-2562
Bounded Dynamic Level Maintenance for Efficient Logic Optimization
- 1 July 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. 75 (7) , 2548-2562
Bounded Dynamic Level Maintenance for Efficient Logic Optimization
- 19 May 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 346
MSK-Net: Multi-scale spatial KANs enhanced U-shaped network for explainable 3D brain tumor segmentation
- 19 May 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 346
MSK-Net: Multi-scale spatial KANs enhanced U-shaped network for explainable 3D brain tumor segmentation
- 2 May 2026
- Published by Elsevier in Neurocomputing
- Vol. 691
HMP-Net: A hierarchical multi-prior network for brain tumor segmentation integrating physics, topology, and tumor dynamics
- 2 May 2026
- Published by Elsevier in Neurocomputing
- Vol. 691
HMP-Net: A hierarchical multi-prior network for brain tumor segmentation integrating physics, topology, and tumor dynamics
- 24 July 2025
- Published by Springer Nature
- p. 89-100
Reassessing the Role of Chain-of-Thought in Sentiment Analysis: Insights and Limitations
- 24 July 2025
- Published by Springer Nature
- p. 89-100
Reassessing the Role of Chain-of-Thought in Sentiment Analysis: Insights and Limitations
- 31 March 2025
- Published by Springer Nature in Software Quality Journal
- Vol. 33 (2) , 1-25
Evaluating the effectiveness of neuron coverage metrics: a metamorphic-testing approach
- 31 March 2025
- Published by Springer Nature in Software Quality Journal
- Vol. 33 (2) , 1-25
Evaluating the effectiveness of neuron coverage metrics: a metamorphic-testing approach
- Open Access
Reassessing the Role of Chain-of-Thought in Sentiment Analysis: Insights and Limitations
The relationship between language and thought remains an unresolved philosophical issue. Existing viewpoints can be broadly categorized into two schools: one asserting their independence, and another arguing that language constrains thought. In the context of large language models, this debate raises a crucial question: Does a language model's grasp of semantic meaning depend on thought processes? To explore this issue, we investigate whether reasoning techniques can facilitate semantic understanding. Specifically, we conceptualize thought as reasoning, employ chain-of-thought prompting as a reasoning technique, and examine its impact on sentiment analysis tasks. The experiments show that chain-of-thought has a minimal impact on sentiment analysis tasks. Both the standard and chain-of-thought prompts focus on aspect terms rather than sentiment in the generated content. Furthermore, counterfactual experiments reveal that the model's handling of sentiment tasks primarily depends on information from demonstrations. The experimental results support the first viewpoint.
Open AccessReassessing the Role of Chain-of-Thought in Sentiment Analysis: Insights and Limitations
The relationship between language and thought remains an unresolved philosophical issue. Existing viewpoints can be broadly categorized into two schools: one asserting their independence, and another arguing that language constrains thought. In the context of large language models, this debate raises a crucial question: Does a language model's grasp of semantic meaning depend on thought processes? To explore this issue, we investigate whether reasoning techniques can facilitate semantic understanding. Specifically, we conceptualize thought as reasoning, employ chain-of-thought prompting as a reasoning technique, and examine its impact on sentiment analysis tasks. The experiments show that chain-of-thought has a minimal impact on sentiment analysis tasks. Both the standard and chain-of-thought prompts focus on aspect terms rather than sentiment in the generated content. Furthermore, counterfactual experiments reveal that the model's handling of sentiment tasks primarily depends on information from demonstrations. The experimental results support the first viewpoint.
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 20422-20436
SynapticRAG: Enhancing Temporal Memory Retrieval in Large Language Models through Synaptic Mechanisms
Yuki Hou, Haruki Tamoto, Qinghua Zhao, Homei Miyashita. Findings of the Association for Computational Linguistics: ACL 2025. 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 20422-20436
Open AccessSynapticRAG: Enhancing Temporal Memory Retrieval in Large Language Models through Synaptic Mechanisms
Yuki Hou, Haruki Tamoto, Qinghua Zhao, Homei Miyashita. Findings of the Association for Computational Linguistics: ACL 2025. 2025.
- Open Access
- 11 September 2024
- Published by MDPI AG in Electronics
- Vol. 13 (18) , 3614
AiMap+: Guiding Technology Mapping for ASICs via Learning Delay Prediction
Technology mapping is an essential process in the Electronic Design Automation (EDA) flow which aims to find an optimal implementation of a logic network from a technology library. In application-specific integrated circuit (ASIC) designs, the non-linear delay behaviors of cells in the library essentially guide the search direction of technology mappers. Existing methods for cell delay estimation, however, rely on approximate simplifications that significantly compromise accuracy, thereby limiting the achievement of better Quality-of-Result (QoR). To address this challenge, we propose formulating cell delay estimation as a regression learning task by incorporating multiple perspective features, such as the structure of logic networks and non-linear cell delays, to guide the mapper search. We design a learning model that incorporates a customized attention mechanism to be aware of the pin delay and jointly learns the hierarchy between the logic network and library through a Neural Tensor Network, with the help of proposed parameterizable strategies to generate learning labels. Experimental results show that (i) our proposed method noticeably improves area by 9.3% and delay by 1.5%, and (ii) improves area by 12.0% for delay-oriented mapping, compared with the well-known mapper.
- 11 September 2024
- Published by MDPI AG in Electronics
- Vol. 13 (18) , 3614
Open AccessAiMap+: Guiding Technology Mapping for ASICs via Learning Delay Prediction
Technology mapping is an essential process in the Electronic Design Automation (EDA) flow which aims to find an optimal implementation of a logic network from a technology library. In application-specific integrated circuit (ASIC) designs, the non-linear delay behaviors of cells in the library essentially guide the search direction of technology mappers. Existing methods for cell delay estimation, however, rely on approximate simplifications that significantly compromise accuracy, thereby limiting the achievement of better Quality-of-Result (QoR). To address this challenge, we propose formulating cell delay estimation as a regression learning task by incorporating multiple perspective features, such as the structure of logic networks and non-linear cell delays, to guide the mapper search. We design a learning model that incorporates a customized attention mechanism to be aware of the pin delay and jointly learns the hierarchy between the logic network and library through a Neural Tensor Network, with the help of proposed parameterizable strategies to generate learning labels. Experimental results show that (i) our proposed method noticeably improves area by 9.3% and delay by 1.5%, and (ii) improves area by 12.0% for delay-oriented mapping, compared with the well-known mapper.
- 11 July 2024
- Published by Elsevier in Expert Systems with Applications
- Vol. 255
Dynamic Hierarchical Attention Network for news recommendation
- 11 July 2024
- Published by Elsevier in Expert Systems with Applications
- Vol. 255
Dynamic Hierarchical Attention Network for news recommendation
- Open Access
Word Order's Impacts: Insights from Reordering and Generation Analysis
Existing works have studied the impacts of the order of words within natural text. They usually analyze it by destroying the original order of words to create a scrambled sequence, and then comparing the models' performance between the original and scrambled sequences. The experimental results demonstrate marginal drops. Considering this findings, different hypothesis about word order is proposed, including ``the order of words is redundant with lexical semantics'', and ``models do not rely on word order''. In this paper, we revisit the aforementioned hypotheses by adding a order reconstruction perspective, and selecting datasets of different spectrum. Specifically, we first select four different datasets, and then design order reconstruction and continuing generation tasks. Empirical findings support that ChatGPT relies on word order to infer, but cannot support or negate the redundancy relations between word order lexical semantics.
Open AccessWord Order's Impacts: Insights from Reordering and Generation Analysis
Existing works have studied the impacts of the order of words within natural text. They usually analyze it by destroying the original order of words to create a scrambled sequence, and then comparing the models' performance between the original and scrambled sequences. The experimental results demonstrate marginal drops. Considering this findings, different hypothesis about word order is proposed, including ``the order of words is redundant with lexical semantics'', and ``models do not rely on word order''. In this paper, we revisit the aforementioned hypotheses by adding a order reconstruction perspective, and selecting datasets of different spectrum. Specifically, we first select four different datasets, and then design order reconstruction and continuing generation tasks. Empirical findings support that ChatGPT relies on word order to infer, but cannot support or negate the redundancy relations between word order lexical semantics.