用递归信息市场机制，让AI更公平地评估和获取信息价值。
Extrapolating Volition with Recursive Information Markets
- 设计递归信息市场，让大模型买家可临时查看信息并遗忘，缓解信息不对称。
- 理论证明该机制能激励信息按真实价值定价与提供。
- 适用于AI对齐研究，尤其在远期意愿推演与可扩展监督中具潜力。
信息市场的效率常受信息不对称制约，尤其因‘买家检验悖论’——买家无法通过检验信息来降低不对称性，因为检验即等于免费获得信息。以往研究提出使用大语言模型（LLM）作为买家，因其可‘遗忘’所见信息，从而克服此问题。本文通过‘信息价值’范式，正式分析这一机制的有效性，重点探讨我们提出的新型递归机制：该机制允许信息在多轮迭代中被评估与传递，且不保留历史记录。我们论证其能有效激励信息按真实价值进行定价与供给。该机制在人工智能对齐研究中具有广泛前景，特别是与外推意愿（Extrapolated Volition）及可扩展监督（Scalable Oversight）密切相关。
原文摘要 · Abstract (English)
One of the impediments to the efficiency of information markets is the inherent information asymmetry present in them, exacerbated by the "buyer's inspection paradox" (the buyer cannot mitigate the asymmetry by "inspecting" the information, because in doing so the buyer obtains the information without paying for it). Previous work has suggested that using Large Language Model (LLM) buyers to inspect and purchase information could overcome this information asymmetry, as an LLM buyer can simply "forget" the information it inspects. In this work, we analyze this mechanism formally through a "value-of-information" paradigm, i.e. whether it incentivizes information to be priced and provided in accordance with its "true value". We focus in particular on our new recursive version of the mechanism, which we believe has a range of applications including in AI alignment research, where it is related to Extrapolated Volition and Scalable Oversight.
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。