中国计算机学会通讯2024年第11期专题聚焦“大模型时代下的人机交互”,深度剖析了这一时代下人机交互领域的最新研究成果与前沿趋势。该专题邀请了该领域的杰出学者,精心撰写了五篇学术力作,全方位多维度探讨了大模型对人机交互的深远影响与促进作用。《以人为中心的大模型Agent社会交互模拟——以推荐系统为例》是其中一个关键议题,它旨在分析和理解用户与大模型Agent之间的复杂交互关系,构建与人类价值对齐、公平无偏、可解释、可信可靠的大模型Agent模拟器,并着重探讨这一模拟器如何解释和评估其对用户期望价值目标的影响、塑造以及潜在风险。这一前沿探索不仅为理解用户与大模型Agent之间的交互机制提供了新的视角和方法,更为构建更加健康、公平且可持续的数字社会环境提供了有力支持,引领大模型智能体技术迈向真正以人为本的新篇章。
作者信息
如果您对本文内容感兴趣的话,可以与作者联系:
张鹏 复旦大学计算机科学技术学院副教授、硕士生导师
联系方式:zhangpeng_@fudan.edu.cn
实验室相关论文
[1] Guangping Zhang, Dongsheng Li, Hansu Gu, Tun Lu, Li Shang, Ning Gu. Simulating News Recommendation Ecosystems for Insights and Implications. In IEEE Transactions on Computational Social Systems, vol. 11, no. 5, pp. 5699-5713, Oct. 2024.
[2] Yubo Shu, Haonan Zhang, Hansu Gu, Peng Zhang, Tun Lu, Dongsheng Li, Ning Gu. RAH! RecSys-Assistant-Human: A Human-Centered Recommendation Framework with LLM Agents. In IEEE Transactions on Computational Social Systems, vol. 11, no. 5, pp. 6759-6770, Oct. 2024.
[3] Yaqiong Li, Peng Zhang, Hansu Gu, Tun Lu, Siyuan Qiao, Yubo Shu, Yiyang Shao, Ning Gu. DeMod: A Holistic Tool with Explainable Detection and Personalized Modification for Toxicity Censorship. In Proceedings of the ACM on Human-Computer Interaction, 2025.
[4] Shitong Duan, Xiaoyuan Yi, Peng Zhang, Tun Lu, Xing Xie, and Ning Gu. 2024. Denevil: Towards Deciphering and Navigating the Ethical Values of Large Language Models via Instruction Learning. In the Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024.
[5] Shitong Duan, Xiaoyuan Yi, Peng Zhang, Tun Lu, Xing Xie, and Ning Gu. 2024. Negating Negatives: Alignment without Human Positive Samples via Distributional Dispreference Optimization. In Findings of the Association for Computational Linguistics: EMNLP 2024, Miami, Florida, November 12-16, 2024.