Graham Neubig, Yonatan Bisk, Hao Zhu, Maarten Sap, Haofei Yu, Ruiyi Wang, Zhengyang Qi, Wenxin Zhang
We lifted 2 functions out of this paper's own repositories and ran 1 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| sotopia-lab/sotopia-pi | canonical | 1 of 2 |
| Function | Status | Where it lives |
|---|---|---|
| sample_prompt_by_source | Ran | sotopia-lab/sotopia-pi/data_generate/generate_new_envs.py code served (permissive licence) · get_code("efb4336be7e7526a") |
| delete_sotopia_data | Not yet run | sotopia-lab/sotopia-pi/data_generate/generate_inspirational_prompts.py code served (permissive licence) · get_code("f4a6c9b92be727d9") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
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 interactive learning method, SOTOPIA-π, improving the social intelligence of language agents. This method leverages behavior cloning and self-reinforcement training on filtered social interaction data according to large language model (LLM) ratings. We show that our training method allows a 7B LLM to reach the social goal completion ability of an expert model (GPT-4-based agent), while improving the safety of language agents and maintaining general QA ability on the MMLU benchmark. We also find that this training paradigm uncovers some difficulties in LLM-based evaluation of social intelligence: LLM-based evaluators overestimate the abilities of the language agents trained specifically for social interaction.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2403.08715")
get_code_for_paper("2403.08715")
have("2403.08715")
Connect an agent — have() is free.