Author name cluster

Shaobo Li

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

7 papers

1 author row

AAAI Conference 2025 Conference Paper

CDW-CoT: Clustered Distance-Weighted Chain-of-Thoughts Reasoning

Yuanheng Fang
Guoqing Chao
Wenqiang Lei
Shaobo Li
Dianhui Chu

Large Language Models (LLMs) have recently achieved impressive results in complex reasoning tasks through Chain of Thought (CoT) prompting. However, most existing CoT methods rely on using the same prompts, whether manually designed or automatically generated, to handle the entire dataset. This one-size-fits-all approach may fail to meet the specific needs arising from the diversities within a single dataset. To solve this problem, we propose the Clustered Distance-Weighted Chain of Thought (CDW-CoT) method, which dynamically constructs prompts tailored to the characteristics of each data instance by integrating clustering and prompt optimization techniques. Our method employs clustering algorithms to categorize the dataset into distinct groups, from which a candidate pool of prompts is selected to reflect the inherent diversity within the dataset. For each cluster, CDW-CoT trains the optimal prompt probability distribution tailored to their specific characteristics. Finally, it dynamically constructs a unique prompt probability distribution for each test instance, based on its proximity to cluster centers, from which prompts are selected for reasoning. CDW-CoT consistently outperforms traditional CoT methods across six datasets, including commonsense, symbolic, and mathematical reasoning tasks. Specifically, when compared to manual CoT, CDW-CoT achieves an average accuracy improvement of 25.34% on LLaMA2 (13B) and 15.72% on LLaMA3 (8B).

PDF Details DOI

EAAI Journal 2025 Journal Article

Entity-relation extraction for unmanned aerial vehicle power system assembly knowledge based on pre-trained language models and few-shot learning

Mingming Shen
Wanxing Cheng
Shiyong Tang
Shaobo Li
Liguo Yao
Jing Yang

To address the challenges of entity-relation extraction in the unmanned aerial vehicle power system assembly domains—particularly annotation scarcity and Chinese semantic complexity, this paper constructs a task-adapted dataset, AM_NER, and proposes an entity relationship extraction model—MTB_Proto, which integrates a pre-trained language model with a prototypical network. Within the pre-trained language model (the bidirectional encoder representations from the transformers) framework, the method introduces an entity position matching mechanism and a masked language model loss to enhance relation representation learning, while leveraging the prototypical network for few-shot classification. Experimental results show that MTB_Proto significantly outperforms baseline models on multiple few-shot tasks in the AM_NER dataset, achieving an F1 score as high as 76. 19 %. On the public datasets SemEval-2010 Task 8, MTB_Proto achieved an F1 score of 91. 90 % under the corresponding test setting, and reached 92. 90 % on FewRel_process. These results demonstrate that MTB_Proto excels not only on our proprietary AM_NER dataset but also exhibits strong generalization and effectiveness on public benchmarks. Overall, the model effectively addresses few-shot relation extraction challenges in unmanned aerial vehicle power system assembly and mitigates the long-tail problem in vertical-domain Chinese relation extraction.

Details DOI

EAAI Journal 2025 Journal Article

Low-cost and sparsity for continual semantic segmentation

Qing Ji
Bin Li
Shaobo Li
Hongchao An
Jing Yang

Deep neural networks have contributed to significant progress in semantic segmentation tasks. However, deep neural networks exhibit a critical drop in performance due to catastrophic forgetting when they are required to learn new tasks incrementally. The more plastic the network is, the easier it can learn new tasks. Whereas, for continual semantic segmentation, it is more reliable to preserve the knowledge it has learned from previous tasks. Here, gated 0-1 Bernoulli variable is used as a regularization method to optimize performance by enhancing network sparsity. Then, the special case of gated 0-1 Bernoulli variable is applied in the replay-based method of continual semantic segmentation. Specifically, when the value of the sub-network sampling rate reaches 0. 5, the network reaches the strongest stability. Finally, the gated 0-1 Bernoulli variable improves the network’s performance in complex scenarios and reduces cost under similar performance. Experimental results indicate that in using 100% samples for incremental training, the Mean Intersection over Union(mIoU) of the old classes improves by up to 4. 6% and 5. 5% compared to the baseline at the end of the overall training in continual semantic segmentation scenarios 10-1 and 10-2. Furthermore, in using 60% samples for incremental training, the performance for the old tasks only drops by less than a percentage, while the time cost to complete the full setup decreases by 22%.

Details DOI

EAAI Journal 2024 Journal Article

Bernstein-based oppositional-multiple learning and differential enhanced exponential distribution optimizer for real-world optimization problems

Fengbin Wu
Shaobo Li
Junxing Zhang
Rongxiang Xie
Mingbao Yang

Meta-heuristic algorithms play an essential role in solving real-world optimization problems. However, their performance is limited by the complexity and variability of the problems. Hence, various efficient algorithms are being actively explored. The exponential distribution optimizer (EDO), having attracted attention for its efficient search performance, has been extended to several applications. However, it suffers from falling into local optima and weak exploitation. Meanwhile, it cannot be directly applied to solve binary optimization problems. To address these challenges, this paper proposes an enhanced EDO called BOMLDEDO. The Bernstein-assisted oppositional-multiple learning strategy is proposed to avoid falling into local optimality. The Bernstein-based adaptive differential strategy is developed to improve exploitation capability. Moreover, by introducing a transfer function, repair method, and binary-to-real operation, BOMLDEDO is extended to a binary version. The IEEE (Institute of Electrical and Electronics Engineers) CEC (Congress on Evolutionary Computation) test functions and engineering problems are used to evaluate BOMLDEDO's optimization performance for continuous problems. Compared to its competitors, BOMLDEDO ranks first on more than 8 out of 10 IEEE CEC 2020 functions and more than 10 out of 12 IEEE CEC 2022 functions. Meanwhile, it achieves the global optimum in 91% of engineering problems. Furthermore, the 0–1 knapsack problems are applied to verify BOMLDEDO's binary optimization capabilities, and the results show that BOMLDEDO is successfully utilized in 14 knapsack instances. The above results demonstrate that incorporating multiple strategies helps improve the performance of BOMLDEDO, making it more reliable and applicable in solving continuous optimization problems and 0–1 knapsack problems.

Details DOI

EAAI Journal 2023 Journal Article

Adaptive finite-time fault-tolerant control for the full-state-constrained robotic manipulator with novel given performance

Menghan Li
Junxing Zhang
Shaobo Li
Fengbin Wu

Most robot manipulators usually operate under different nonlinearities, such as state constraints, time delays, and actuator input saturation faults. This paper proposes an adaptive finite-time fault-tolerant controller for the full-state-constrained robotic manipulator with novel prescribed performance and time-varying delays. Firstly, a novel prescribed performance function consisting of hyperbolic tangent and hyperbolic cotangent functions is constructed to the full-state performance constraints of the robotic manipulator. Such a design can circumvent the demands for accurate initial conditions of the state variables and guarantee the convergence of the state errors in a prescribed time. Then, based on the finite-time principle, a finite-time command filter and a compensation mechanism with fractional-power terms are used to bypass the “explosion of complexity” and further compensate for the filter errors within a finite time. Moreover, a proper Lyapunov–Krasovskii functional is devised within the controller design to compensate for the time-varying delays. And the radial basis function neural networks are used to estimate the other nonlinearities including actuator saturation faults, and external perturbations. Finally, simulation results exhibit that the controller designed in this paper has a faster convergence speed and minor state errors.

Details DOI

AAAI Conference 2023 Conference Paper

RPA: Reasoning Path Augmentation in Iterative Retrieving for Multi-Hop QA

Ziyi Cao
Bingquan Liu
Shaobo Li

Multi-hop questions are associated with a series of justifications, and one needs to obtain the answers by following the reasoning path (RP) that orders the justifications adequately. So reasoning path retrieval becomes a critical preliminary stage for multi-hop Question Answering (QA). Within the RP, two fundamental challenges emerge for better performance: (i) what the order of the justifications in the RP should be, and (ii) what if the wrong justification has been in the path. In this paper, we propose Reasoning Path Augmentation (RPA), which uses reasoning path reordering and augmentation to handle the above two challenges, respectively. Reasoning path reordering restructures the reasoning by targeting the easier justification first but difficult one later, in which the difficulty is determined by the overlap between query and justifications since the higher overlap means more lexical relevance and easier searchable. Reasoning path augmentation automatically generates artificial RPs, in which the distracted justifications are inserted to aid the model recover from the wrong justification. We build RPA with a naive pre-trained model and evaluate RPA on the QASC and MultiRC datasets. The evaluation results demonstrate that RPA outperforms previously published reasoning path retrieval methods, showing the effectiveness of the proposed methods. Moreover, we present detailed experiments on how the orders of justifications and the percent of augmented paths affect the question- answering performance, revealing the importance of polishing RPs and the necessity of augmentation.

PDF Details DOI

AAAI Conference 2021 Conference Paper

HopRetriever: Retrieve Hops over Wikipedia to Answer Complex Questions

Shaobo Li
Xiaoguang Li
Lifeng Shang
Xin Jiang
Qun Liu
Chengjie Sun
Zhenzhou Ji
Bingquan Liu

Collecting supporting evidence from large corpora of text (e. g. , Wikipedia) is of great challenge for open-domain Question Answering (QA). Especially, for multi-hop open-domain QA, scattered evidence pieces are required to be gathered together to support the answer extraction. In this paper, we propose a new retrieval target, hop, to collect the hidden reasoning evidence from Wikipedia for complex question answering. Specifically, the hop in this paper is defined as the combination of a hyperlink and the corresponding outbound link document. The hyperlink is encoded as the mention embedding which models the structured knowledge of how the outbound link entity is mentioned in the textual context, and the corresponding outbound link document is encoded as the document embedding representing the unstructured knowledge within it. Accordingly, we build HopRetriever which retrieves hops over Wikipedia to answer complex questions. Experiments on the HotpotQA dataset demonstrate that HopRetriever outperforms previously published evidence retrieval methods by large margins. Moreover, our approach also yields quantifiable interpretations of the evidence collection process.

PDF Details