[2310.10826] Mechanism Design for Large Language Models
-->
Computer Science > Computer Science and Game Theory
arXiv:2310.10826 (cs)
[Submitted on 16 Oct 2023 (v1), last revised 2 Jul 2024 (this version, v3)]
Title:Mechanism Design for Large Language Models
Authors:Paul Duetting, Vahab Mirrokni, Renato Paes Leme, Haifeng Xu, Song Zuo<br>View a PDF of the paper titled Mechanism Design for Large Language Models, by Paul Duetting and 4 other authors
View PDF<br>HTML (experimental)
Abstract:We investigate auction mechanisms for AI-generated content, focusing on applications like ad creative generation. In our model, agents' preferences over stochastically generated content are encoded as large language models (LLMs). We propose an auction format that operates on a token-by-token basis, and allows LLM agents to influence content creation through single dimensional bids. We formulate two desirable incentive properties and prove their equivalence to a monotonicity condition on output aggregation. This equivalence enables a second-price rule design, even absent explicit agent valuation functions. Our design is supported by demonstrations on a publicly available LLM.
Comments:<br>WWW'24 Best Paper
Subjects:
Computer Science and Game Theory (cs.GT); Theoretical Economics (econ.TH)
Cite as:<br>arXiv:2310.10826 [cs.GT]
(or<br>arXiv:2310.10826v3 [cs.GT] for this version)
https://doi.org/10.48550/arXiv.2310.10826
Focus to learn more
arXiv-issued DOI via DataCite
Submission history<br>From: Song Zuo [view email]<br>[v1]<br>Mon, 16 Oct 2023 21:01:12 UTC (50 KB)
[v2]<br>Fri, 14 Jun 2024 19:59:11 UTC (64 KB)
[v3]<br>Tue, 2 Jul 2024 14:34:11 UTC (38 KB)
Full-text links:<br>Access Paper:
View a PDF of the paper titled Mechanism Design for Large Language Models, by Paul Duetting and 4 other authors<br>View PDF<br>HTML (experimental)<br>TeX Source
view license
Current browse context: cs.GT
next >
new<br>recent<br>| 2023-10
Change to browse by:
cs<br>econ<br>econ.TH
References & Citations
NASA ADS<br>Google Scholar
Semantic Scholar
export BibTeX citation<br>Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
Links to Code Toggle
Papers with Code (What is Papers with Code?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs .
Which authors of this paper are endorsers? |<br>Disable MathJax (What is MathJax?)