Extrapolating Volition with Recursive Information Markets

2026-04-08

AI Summary

This work addresses the buyer verification paradox in information markets, wherein buyers’ inability to credibly commit to not exploiting inspected information prevents truthful pricing and exacerbates information asymmetry. To resolve this, the paper proposes a recursive information market mechanism that leverages the controllable “forgetting” capability of large language model (LLM) buyers. By enabling LLMs to selectively erase content after inspection, the mechanism incentivizes sellers to truthfully disclose high-value information. Integrating insights from information valuation theory with the unique properties of LLMs, the approach not only theoretically mitigates information asymmetry but also offers a novel pathway for modeling extrapolation intent and enabling scalable oversight in AI alignment.

Technology Category

• Multiagent Systems: Mechanism Design
• Game Theory and Economic Paradigms: Imperfect Information
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Economics, Online Markets and Human Computation: Uses of LLMs and GenAI for marketplace design, bidding, and strategic interactions
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

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.

Problem

• information asymmetry
• buyer's inspection paradox
• value-of-information
• information markets
• Extrapolated Volition

Innovation

• Recursive Information Markets
• Information Asymmetry
• Large Language Models
• Value of Information
• Extrapolated Volition