Skip to main navigation
Skip to search
Skip to main content
University of Edinburgh Research Explorer Home
Help & FAQ
Link opens in a new tab
Search content at University of Edinburgh Research Explorer
Home
Research output
Profiles
Research units
Projects
Datasets
Prizes
Activities
Press/Media
Equipment
In LLM reasoning, there is irrationality on top of value misalignment
Kejiang Qian
,
Fengxiang He
*
*
Corresponding author for this work
EPSRC CDT in Machine Learning Systems
School of Informatics
Artificial Intelligence and its Applications Institute
Research output
:
Working paper
›
Preprint
Overview
Fingerprint
Fingerprint
Dive into the research topics of 'In LLM reasoning, there is irrationality on top of value misalignment'. Together they form a unique fingerprint.
Sort by
Weight
Alphabetically
Computer Science
Reasoning Strategy
100%
Large Language Model
100%
Reasoning LLM
100%
Estimation Error
50%
Mathematics
Irrationality
100%
Large Language Model
100%
Diminishing Return
33%
Economics, Econometrics and Finance
Law of Diminishing Returns
100%