让大模型通过对话练习形成高效沟通习惯，缩短表达且更易懂。
Success and Cost Elicit Convention Formation for Efficient Communication
- 用模拟对话游戏训练模型，无需人工标注数据
- 消息长度减少41%，成功率提升15%，人听懂更快
- 既要追求成功又要控制成本，才能促成语言习惯形成
人类通过共享对话背景，随时间推移沟通越来越高效。这种现象表现为临时语言惯例的形成，使人们能用简短、低成本的表达达成理解。我们提出一种方法，训练大型多模态模型自发形成此类惯例，实现高效沟通。该方法基于模型间的模拟指称游戏，在照片和七巧板图像任务中无需额外人工数据即可实现。经过多次交互后，模型与人类沟通时消息长度最多减少41%，成功率提升15%；人类听众反应速度也显著加快。实验还表明，仅优化成功率或仅降低通信成本均不足以引发惯例形成，二者必须协同作用。
原文摘要 · Abstract (English)
Humans leverage shared conversational context to become increasingly successful and efficient at communicating over time. One manifestation of this is the formation of ad hoc linguistic conventions, which allow people to coordinate on short, less costly utterances that are understood using shared conversational context. We present a method to train large multimodal models to form conventions, enabling efficient communication. Our approach uses simulated reference games between models, and requires no additional human-produced data. In repeated reference games involving photographs and tangram images, our method enables models to communicate efficiently with people: reducing the message length by up to 41% while increasing success by 15% over the course of the interaction. Human listeners respond faster when interacting with our model that forms conventions. We also show that training based on success or cost alone is insufficient - both are necessary to elicit convention formation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。