Xingshen Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Xingshen Liu has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Fuxin Wang
School of Information Management, Wuhan University, Wuhan, China
3 shared publications - Haowei Wang
Wuhan University
3 shared publications Congjing Ran
2 shared publicationsFan Wang
2 shared publications- Zhixuan Jia
School of Information Management, Wuhan University, Wuhan 430072, China
2 shared publications - Fan Wang
School of Information Management, Wuhan University, Wuhan, China
1 shared publication
Latest Publications
- Open Access
- 25 June 2026
- Published by Elsevier in SSRN Electronic Journal
CoPAMoE: Cognitive Process-Aware Mixture of Experts for Bias Understanding and Mitigation
Bias handling in expert-augmented LLMs is not merely a matter of routing tasks to experts, it requires coordinating how biased cues are detected, how their social meanings are attributed, and how interventions are generated. However, existing parameter-efficient fine-tuning and mixture-of-experts approaches typically organize specialization around task labels, domains, or input-level routing signals, rather than explicitly modeling how evidence of bias should inform its interpretation and subsequent rewriting. This paper proposes CoPAMoE, a cognitive process-aware PEFT-MoE framework for bias understanding and mitigation. CoPAMoE organizes bias-related subtasks into three functional stages, Cue Perception, Attribution Reasoning, and Intervention Control. It combines stage-partitioned LoRA experts, shared experts, a task--stage routing prior, and an Adjacent Stage Gated Coordination (ASGC) module. The resulting architecture explicitly separates stage-specific adaptation from task-general bias signals and supports controlled information transfer between adjacent stages. Experiments on a unified benchmark built from CrowS-Pairs, StereoSet, and WinoBias show that CoPAMoE improves average performance over representative PEFT and MoE baselines on two backbone LLMs. Ablation, routing, representation, oracle, and efficiency analyses further suggest that the gains are associated with stage-aware specialization and cross-stage dependency transfer.
- 25 June 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessCoPAMoE: Cognitive Process-Aware Mixture of Experts for Bias Understanding and Mitigation
Bias handling in expert-augmented LLMs is not merely a matter of routing tasks to experts, it requires coordinating how biased cues are detected, how their social meanings are attributed, and how interventions are generated. However, existing parameter-efficient fine-tuning and mixture-of-experts approaches typically organize specialization around task labels, domains, or input-level routing signals, rather than explicitly modeling how evidence of bias should inform its interpretation and subsequent rewriting. This paper proposes CoPAMoE, a cognitive process-aware PEFT-MoE framework for bias understanding and mitigation. CoPAMoE organizes bias-related subtasks into three functional stages, Cue Perception, Attribution Reasoning, and Intervention Control. It combines stage-partitioned LoRA experts, shared experts, a task--stage routing prior, and an Adjacent Stage Gated Coordination (ASGC) module. The resulting architecture explicitly separates stage-specific adaptation from task-general bias signals and supports controlled information transfer between adjacent stages. Experiments on a unified benchmark built from CrowS-Pairs, StereoSet, and WinoBias show that CoPAMoE improves average performance over representative PEFT and MoE baselines on two backbone LLMs. Ablation, routing, representation, oracle, and efficiency analyses further suggest that the gains are associated with stage-aware specialization and cross-stage dependency transfer.
- Open Access
- 24 June 2026
- Published by Elsevier in SSRN Electronic Journal
CoPAMoE: Cognitive Process-Aware Mixture of Experts for Bias Understanding and Mitigation
Bias handling in expert-augmented LLMs is not merely a matter of routing tasks to experts, it requires coordinating how biased cues are detected, how their social meanings are attributed, and how interventions are generated. However, existing parameter-efficient fine-tuning and mixture-of-experts approaches typically organize specialization around task labels, domains, or input-level routing signals, rather than explicitly modeling how evidence of bias should inform its interpretation and subsequent rewriting. This paper proposes CoPAMoE, a cognitive process-aware PEFT-MoE framework for bias understanding and mitigation. CoPAMoE organizes bias-related subtasks into three functional stages, Cue Perception, Attribution Reasoning, and Intervention Control. It combines stage-partitioned LoRA experts, shared experts, a task--stage routing prior, and an Adjacent Stage Gated Coordination (ASGC) module. The resulting architecture explicitly separates stage-specific adaptation from task-general bias signals and supports controlled information transfer between adjacent stages. Experiments on a unified benchmark built from CrowS-Pairs, StereoSet, and WinoBias show that CoPAMoE improves average performance over representative PEFT and MoE baselines on two backbone LLMs. Ablation, routing, representation, oracle, and efficiency analyses further suggest that the gains are associated with stage-aware specialization and cross-stage dependency transfer.
- 24 June 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessCoPAMoE: Cognitive Process-Aware Mixture of Experts for Bias Understanding and Mitigation
Bias handling in expert-augmented LLMs is not merely a matter of routing tasks to experts, it requires coordinating how biased cues are detected, how their social meanings are attributed, and how interventions are generated. However, existing parameter-efficient fine-tuning and mixture-of-experts approaches typically organize specialization around task labels, domains, or input-level routing signals, rather than explicitly modeling how evidence of bias should inform its interpretation and subsequent rewriting. This paper proposes CoPAMoE, a cognitive process-aware PEFT-MoE framework for bias understanding and mitigation. CoPAMoE organizes bias-related subtasks into three functional stages, Cue Perception, Attribution Reasoning, and Intervention Control. It combines stage-partitioned LoRA experts, shared experts, a task--stage routing prior, and an Adjacent Stage Gated Coordination (ASGC) module. The resulting architecture explicitly separates stage-specific adaptation from task-general bias signals and supports controlled information transfer between adjacent stages. Experiments on a unified benchmark built from CrowS-Pairs, StereoSet, and WinoBias show that CoPAMoE improves average performance over representative PEFT and MoE baselines on two backbone LLMs. Ablation, routing, representation, oracle, and efficiency analyses further suggest that the gains are associated with stage-aware specialization and cross-stage dependency transfer.
- 2 January 2026
- Published by Springer Nature
- p. 88-105
RBLU: A Benchmark to Evaluate the Reverse Inference Ability of Large Language Models
- 2 January 2026
- Published by Springer Nature
- p. 88-105
RBLU: A Benchmark to Evaluate the Reverse Inference Ability of Large Language Models
- Open Access
- 16 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-9
Identification of Countries' Distance from the Global Scientific Centers: A Bibliometric Analysis Based on Physics Journal Articles
- 16 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-9
Open AccessIdentification of Countries' Distance from the Global Scientific Centers: A Bibliometric Analysis Based on Physics Journal Articles