paper-with-me

Papers

SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents

2023-10-18 · Xuhui Zhou, Hao Zhu, Leena Mathur, Ruohong Zhang, Haofei Yu, Zhengyang Qi, Louis-Philippe Morency, Yonatan Bisk, Daniel Fried, Graham Neubig, Maarten Sap

Humans are social beings; we pursue social goals in our daily interactions, which is a crucial aspect of social intelligence. Yet, AI systems' abilities in this realm remain elusive. We present SOTOPIA, an open-ended environment to simulate complex social interactions between artificial agents and evaluate their social intelligence. In our environment, agents role-play and interact under a wide variety of scenarios; they coordinate, collaborate, exchange, and compete with each other to achieve complex social goals. We simulate the role-play interaction between LLM-based agents and humans within this task space and evaluate their performance with a holistic evaluation framework called SOTOPIA-Eval. With SOTOPIA, we find significant differences between these models in terms of their social intelligence, and we identify a subset of SOTOPIA scenarios, SOTOPIA-hard, that is generally challenging for all models. We find that on this subset, GPT-4 achieves a significantly lower goal completion rate than humans and struggles to exhibit social commonsense reasoning and strategic communication skills. These findings demonstrate SOTOPIA's promise as a general platform for research on evaluating and improving social intelligence in artificial agents.

📄 PDF Abstract BibTeX arXiv:2310.11667

Code (2)

sotopia-lab/sotopia
vinid/negotiationarena

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Residual Connection 설명 없음
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Similar Papers 제목 키워드 기반

SOTOPIA-$π$: Interactive Learning of Socially Intelligent Language Agents

2024-03-13 · Ruiyi Wang, Haofei Yu, Wenxin Zhang, Zhengyang Qi 외

Humans learn social skills through both imitation and social interaction. This social learning process is largely understudied by existing research on building language agents. Motivated by this gap, we propose an intera…

Language ModelingLanguage ModellingLarge Language ModelMMLU

Sotopia-RL: Reward Design for Social Intelligence

2025-08-05 · Haofei Yu, Zhengyang Qi, Yining Zhao, Kolby Nottingham 외 arxiv

Social intelligence has become a critical capability for large language models (LLMs), enabling them to engage effectively in real-world social tasks such as collaboration and negotiation. Reinforcement learning (RL) is …

Reinforcement Learning

SOTOPIA-S4: a user-friendly system for flexible, customizable, and large-scale social simulation

2025-04-19 · Xuhui Zhou, Zhe Su, Sophie Feng, Jiaxu Zhou 외

Social simulation through large language model (LLM) agents is a promising approach to explore and validate hypotheses related to social science questions and LLM agents behavior. We present SOTOPIA-S4, a fast, flexible,…

Language ModelingLanguage ModellingLarge Language ModelManagement

Infusing Theory of Mind into Socially Intelligent LLM Agents

2025-09-26 · EunJeong Hwang, Yuwei Yin, Giuseppe Carenini, Peter West 외 arxiv

Theory of Mind (ToM)-an understanding of the mental states of others-is a key aspect of human social intelligence, yet, chatbots and LLM-based social agents do not typically integrate it. In this work, we demonstrate tha…

SOTOPIA-$Ω$: Dynamic Strategy Injection Learning and Social Instruction Following Evaluation for Social Agents

2025-02-21 · Wenyuan Zhang, Tianyun Liu, Mengxiao Song, XiaoDong Li 외

Despite the abundance of prior social strategies possessed by humans, there remains a paucity of research dedicated to their transfer and integration into social agents. Our proposed SOTOPIA-$\Omega$ framework aims to ad…

Instruction Following