Language Models Can Reduce Asymmetry in Information Markets
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917619064373248 |
|---|---|
| author | Rahaman, Nasim Weiss, Martin Wüthrich, Manuel Bengio, Yoshua Li, Li Erran Pal, Chris Schölkopf, Bernhard |
| author_facet | Rahaman, Nasim Weiss, Martin Wüthrich, Manuel Bengio, Yoshua Li, Li Erran Pal, Chris Schölkopf, Bernhard |
| contents | This work addresses the buyer's inspection paradox for information markets. The paradox is that buyers need to access information to determine its value, while sellers need to limit access to prevent theft. To study this, we introduce an open-source simulated digital marketplace where intelligent agents, powered by language models, buy and sell information on behalf of external participants. The central mechanism enabling this marketplace is the agents' dual capabilities: they not only have the capacity to assess the quality of privileged information but also come equipped with the ability to forget. This ability to induce amnesia allows vendors to grant temporary access to proprietary information, significantly reducing the risk of unauthorized retention while enabling agents to accurately gauge the information's relevance to specific queries or tasks. To perform well, agents must make rational decisions, strategically explore the marketplace through generated sub-queries, and synthesize answers from purchased information. Concretely, our experiments (a) uncover biases in language models leading to irrational behavior and evaluate techniques to mitigate these biases, (b) investigate how price affects demand in the context of informational goods, and (c) show that inspection and higher budgets both lead to higher quality outcomes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_14443 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Language Models Can Reduce Asymmetry in Information Markets Rahaman, Nasim Weiss, Martin Wüthrich, Manuel Bengio, Yoshua Li, Li Erran Pal, Chris Schölkopf, Bernhard Artificial Intelligence Computation and Language Computer Science and Game Theory Machine Learning Multiagent Systems Social and Information Networks This work addresses the buyer's inspection paradox for information markets. The paradox is that buyers need to access information to determine its value, while sellers need to limit access to prevent theft. To study this, we introduce an open-source simulated digital marketplace where intelligent agents, powered by language models, buy and sell information on behalf of external participants. The central mechanism enabling this marketplace is the agents' dual capabilities: they not only have the capacity to assess the quality of privileged information but also come equipped with the ability to forget. This ability to induce amnesia allows vendors to grant temporary access to proprietary information, significantly reducing the risk of unauthorized retention while enabling agents to accurately gauge the information's relevance to specific queries or tasks. To perform well, agents must make rational decisions, strategically explore the marketplace through generated sub-queries, and synthesize answers from purchased information. Concretely, our experiments (a) uncover biases in language models leading to irrational behavior and evaluate techniques to mitigate these biases, (b) investigate how price affects demand in the context of informational goods, and (c) show that inspection and higher budgets both lead to higher quality outcomes. |
| title | Language Models Can Reduce Asymmetry in Information Markets |
| topic | Artificial Intelligence Computation and Language Computer Science and Game Theory Machine Learning Multiagent Systems Social and Information Networks |
| url | https://arxiv.org/abs/2403.14443 |