arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2407.07845cs.GT
收藏

基于基础模型自解析的自然语言机制

Natural Language Mechanisms via Self-Resolution with Foundation Models

Nicolas Della Penna

AI总结:

针对传统机制限制智能体报告格式的问题,提出基于自然语言的新型机制,利用大语言模型的世界建模能力选结果、分收益,明确其激励相容与高效的充分条件,验证其在预测市场失效场景下的信息聚合能力。

摘要:

实用机制通常将智能体的报告限制为交易、排序等受限格式,可能会限制智能体能表达的信息。我们提出一类新型机制,以自然语言获取智能体报告,并利用大语言模型(LLMs)的世界建模能力选择结果、分配收益。我们明确了这类机制具备激励相容性与效率的充分条件:LLM是足够优秀的世界模型,且满足强智能体间信息超定条件。我们展示了在预测市场失效的信号结构中,这类基于语言模型的机制可成功聚合信息的场景。

英文摘要:

Practical mechanisms often limit agent reports to constrained formats like trades or orderings, potentially limiting the information agents can express. We propose a novel class of mechanisms that elicit agent reports in natural language and leverage the world-modeling capabilities of large language models (LLMs) to select outcomes and assign payoffs. We identify sufficient conditions for these mechanisms to be incentive-compatible and efficient as the LLM being a good enough world model and a strong inter-agent information over-determination condition. We show situations where these LM-based mechanisms can successfully aggregate information in signal structures on which prediction markets fail.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑