التفاصيل البيبلوغرافية
| العنوان: |
Welfare Diplomacy: Benchmarking Language Model Cooperation |
| المؤلفون: |
Mukobi, Gabriel, Erlebach, Hannah, Lauffer, Niklas, Hammond, Lewis, Chan, Alan, Clifton, Jesse |
| سنة النشر: |
2023 |
| المجموعة: |
Computer Science |
| مصطلحات موضوعية: |
Computer Science - Multiagent Systems, Computer Science - Artificial Intelligence, Computer Science - Computation and Language |
| الوصف: |
The growing capabilities and increasingly widespread deployment of AI systems necessitate robust benchmarks for measuring their cooperative capabilities. Unfortunately, most multi-agent benchmarks are either zero-sum or purely cooperative, providing limited opportunities for such measurements. We introduce a general-sum variant of the zero-sum board game Diplomacy -- called Welfare Diplomacy -- in which players must balance investing in military conquest and domestic welfare. We argue that Welfare Diplomacy facilitates both a clearer assessment of and stronger training incentives for cooperative capabilities. Our contributions are: (1) proposing the Welfare Diplomacy rules and implementing them via an open-source Diplomacy engine; (2) constructing baseline agents using zero-shot prompted language models; and (3) conducting experiments where we find that baselines using state-of-the-art models attain high social welfare but are exploitable. Our work aims to promote societal safety by aiding researchers in developing and assessing multi-agent AI systems. Code to evaluate Welfare Diplomacy and reproduce our experiments is available at https://github.com/mukobi/welfare-diplomacy. |
| نوع الوثيقة: |
Working Paper |
| URL الوصول: |
http://arxiv.org/abs/2310.08901 |
| رقم الانضمام: |
edsarx.2310.08901 |
| قاعدة البيانات: |
arXiv |