Redesigning Information Markets in the Era of Language Models

Martin Weiss, Nasim Rahaman, Manuel Wuthrich, Yoshua Bengio, Li Erran Li, Bernhard Schölkopf, Christopher Pal

Research Area: Societal implications, LMs and the world, LMs and interactions, LMs on diverse modalities and novel applications

Keywords: Language Model Agents, Information Economics

TL;DR: This work proposes an information market design using language models to balance buyer inspection and seller protection.

Abstract: Information markets face many challenges leading to instability, inefficiency, and failure, ultimately reducing incentives for the creation and distribution of high-quality information. A long-standing issue for information markets is the Buyer's Inspection Paradox: buyers need to inspect information to assess its value, while sellers must limit inspection to prevent unauthorized use or theft. This paradox results from the information asymmetry present in the market, where sellers know more about the quality of their goods than buyers. This work proposes an information market design that leverages language models to mitigate the Buyer's Inspection Paradox by enabling inspection, comparison, and purchase of information, while algorithmically preventing expropriation. Our experiments (a) show methods that improve the economic rationality of language models, (b) investigate how language model behaviour changes with the price of goods, and (c) evaluate the simulated cost-efficiency of the proposed market under various conditions.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the COLM Code of Ethics on https://colmweb.org/CoE.html

Author Guide: I certify that this submission complies with the submission instructions as described on https://colmweb.org/AuthorGuide.html

Submission Number: 370