Back to search

Cornell University

Evaluating and Improving LLM reasoning with Externalized Value Signals

Abstract

dc:description.abstract

The rapid progress of large language models (LLMs) has been driven primarily by scaling model size, data, and compute. While this paradigm has enabled remarkable advances in reasoning, it is increasingly constrained by physical, economic, and data limitations. At the same time, evaluating and improving reasoning systems has itself become a bottleneck: as models approach or surpass human-level performance, reliable assessment and supervision become increasingly costly, ambiguous, and fragile. This thesis investigates a complementary paradigm for advancing LLM reasoning that shifts emphasis from scaling models to scaling

Degree

thesis:*
Name thesis:degree_name
Ph. D., Computer Science
Level thesis:degree_level
Doctor of Philosophy
Discipline thesis:degree_discipline
Computer Science
Grantor
Cornell University
Year dc:date.issued
2026

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Zhou, Jin Peng
Chair dc:contributor.chair
  • Weinberger, Kilian
Committee members dc:contributor.committeemember
  • Chattopadhyay, Eshan
  • Sun, Wen

Subjects

dc:subject × 5

Rights

dc:rights
Statement dc:rights
  • Attribution 4.0 International
Language dc:language.iso
en

Identifiers

dc:identifier.*
Dc Identifier Other
Zhou_cornellgrad_0058F_15445
https://www.proquest.com/LegacyDocView/DISSNUM/32445847

Chain of custody

source
Harvested from
Cornell University
Base URL
ecommons.cornell.edu/server/oai/request
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Zhou, Jin Peng. Evaluating and Improving LLM reasoning with Externalized Value Signals. Doctor of Philosophy thesis, Cornell University, 2026. https://hdl.handle.net/1813/126481