MIT Libraries logoDSpace@MIT

MIT
View Item 
  • DSpace@MIT Home
  • MIT Libraries
  • MIT Theses
  • Graduate Theses
  • View Item
  • DSpace@MIT Home
  • MIT Libraries
  • MIT Theses
  • Graduate Theses
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

Searching with Intuition: Exploring (the bounds of) LLM-guided Search with Unknown Objectives

Author(s)
Kaashoek, Justin H.
Thumbnail
DownloadThesis PDF (6.698Mb)
Advisor
Raghavan, Manish
Terms of use
In Copyright - Educational Use Permitted Copyright retained by author(s) https://rightsstatements.org/page/InC-EDU/1.0/
Metadata
Show full item record
Abstract
Large language models (LLMs) can perform a wide range of search and optimization tasks over discrete spaces. This work seeks to explore the limits of LLM-guided search. We construct a set of text optimization tasks with different levels of "intuitiveness'' and evaluate whether LLMs can effectively optimize objectives. We show that the LLM's performance depends not only on its intuition for the objective, but also on the alignment between the objective and its priors. We also find that the LLM can successfully optimize an objective even without an explicit description of the objective. Our results largely focus on greedy search strategies; we develop a theoretical characterization of conditions under which greedy search is optimal, meaning the LLM's failures result from a fundamental inability to take gradient-like steps, not suboptimal search.
Date issued
2025-05
URI
https://hdl.handle.net/1721.1/163276
Department
Sloan School of Management
Publisher
Massachusetts Institute of Technology

Collections
  • Graduate Theses

Browse

All of DSpaceCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

My Account

Login

Statistics

OA StatisticsStatistics by CountryStatistics by Department
MIT Libraries
PrivacyPermissionsAccessibilityContact us
MIT
Content created by the MIT Libraries, CC BY-NC unless otherwise noted. Notify us about copyright concerns.