Knowledge Boundary and Persona Dynamic Shape A Better Social Media Agent (2403.19275v2)
Abstract: Constructing personalized and anthropomorphic agents holds significant importance in the simulation of social networks. However, there are still two key problems in existing works: the agent possesses world knowledge that does not belong to its personas, and it cannot eliminate the interference of diverse persona information on current actions, which reduces the personalization and anthropomorphism of the agent. To solve the above problems, we construct the social media agent based on personalized knowledge and dynamic persona information. For personalized knowledge, we add external knowledge sources and match them with the persona information of agents, thereby giving the agent personalized world knowledge. For dynamic persona information, we use current action information to internally retrieve the persona information of the agent, thereby reducing the interference of diverse persona information on the current action. To make the agent suitable for social media, we design five basic modules for it: persona, planning, action, memory and reflection. To provide an interaction and verification environment for the agent, we build a social media simulation sandbox. In the experimental verification, automatic and human evaluations demonstrated the effectiveness of the agent we constructed.
- The role of social networks in information diffusion. In Proceedings of the 21st international conference on World Wide Web, pages 519–528.
- Language models are few-shot learners. Advances in neural information processing systems, 33:1877–1901.
- Agentverse: Facilitating multi-agent collaboration and exploring emergent behaviors in agents. arXiv preprint arXiv:2308.10848.
- Pearson correlation coefficient. Noise reduction in speech processing, pages 1–4.
- Roles in social networks: Methodologies and research issues. Web Intelligence and Agent Systems: An international Journal, 10(1):117–133.
- s3superscript𝑠3s^{3}italic_s start_POSTSUPERSCRIPT 3 end_POSTSUPERSCRIPT: Social-network simulation system with large language model-empowered agents. arXiv preprint arXiv:2307.14984.
- Metagpt: Meta programming for multi-agent collaborative framework. arXiv preprint arXiv:2308.00352.
- Matthew O Jackson. 2014. Networks in the understanding of economic behaviors. Journal of Economic Perspectives, 28(4):3–22.
- Camel: Communicative agents for" mind" exploration of large scale language model society. arXiv preprint arXiv:2303.17760.
- A diversity-promoting objective function for neural conversation models. In Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 110–119, San Diego, California. Association for Computational Linguistics.
- Roberta: A robustly optimized BERT pretraining approach. CoRR, abs/1907.11692.
- Personalizing dialogue agents via meta-learning. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 5454–5459, Florence, Italy. Association for Computational Linguistics.
- OpenAI. 2022. Chatgpt: Optimizing language models for dialogue.
- OpenAI. 2023. Gpt-4 technical report.
- On the prospects of incorporating large language models (llms) in automated planning and scheduling (aps). arXiv preprint arXiv:2401.02500.
- Generative agents: Interactive simulacra of human behavior. In Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology, pages 1–22.
- Social simulacra: Creating populated prototypes for social computing systems.
- Communicative agents for software development. arXiv preprint arXiv:2307.07924.
- Gerard Salton and Christopher Buckley. 1988. Term-weighting approaches in automatic text retrieval. Information processing & management, 24(5):513–523.
- Colbertv2: Effective and efficient retrieval via lightweight late interaction.
- Hugginggpt: Solving ai tasks with chatgpt and its friends in huggingface. arXiv preprint arXiv:2303.17580.
- Reflexion: Language agents with verbal reinforcement learning. In Thirty-seventh Conference on Neural Information Processing Systems.
- Veronica L Thomas and Gema Vinuales. 2017. Understanding the role of social influence in piquing curiosity and influencing attitudes and behaviors in a social network environment. Psychology & Marketing, 34(9):884–893.
- Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971.
- Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288.
- Voyager: An open-ended embodied agent with large language models. arXiv preprint arXiv:2305.16291.
- When large language model based agent meets user behavior analysis: A novel user simulation paradigm.
- Dialogue natural language inference. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 3731–3741, Florence, Italy. Association for Computational Linguistics.
- Simulating public administration crisis: A novel generative agent-based simulation system to lower technology barriers in social science research. arXiv preprint arXiv:2311.06957.
- Hotpotqa: A dataset for diverse, explainable multi-hop question answering. arXiv preprint arXiv:1809.09600.
- Personalizing dialogue agents: I have a dog, do you have pets too? In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2204–2213, Melbourne, Australia. Association for Computational Linguistics.
- Bertscore: Evaluating text generation with bert. arXiv preprint arXiv:1904.09675.