Improving reasoning capabilities of large language models

Large Language Models (LLMs) have succeeded at solving several wide range of tasks like mathematical problem solving, code generation, common-sense reasoning, etc. The recent success of these models is largely attributed to scaling in both model size and training data, which often includes massive amounts of web-scale and synthetic data — raising important questions about their true generalization capabilities. Several studies have highlighted critical failure cases in the reasoning abilities of LLMs, such as token biases in logical problem-solving and sensitivity to the order of premises, indicating a reliance on surface-level cues rather than true logical understanding. Additionally, these reasoning abilities ares hown to emerge only when models are trained on extremely large datasets. This technique of learning to reason deviates from how humans learn to reason and think. Humans learn to solve problems by first understanding and acquiring the fundamental principles involved in reasoning, and then learn to apply these principles to new tasks, rather than directly learning to solve hundreds of complex problems. Inspired by this, we aim to train LLMs to learn to reason with the help of axioms - fundamental principles of reasoning, in particular causal axioms. Causal axioms lay the crucks of causal inference which humans use in making decisions or inferences in several scenarios. The influence of causal axioms on the reasoning abilities of LLMs remains underexplored; in this work, we demonstrate that causal axiomatic training can enhance LLM performance across a broad range of reasoning tasks, even those not directly related to causality. Our extensive evaluation results across 16 benchmarks, shows that LLMs fine-tuned using our axiomatic data show stronger gains compared to baseline approaches on most tasks.

Name thesis:degree_name

M.S.

Level thesis:degree_level

Thesis

Discipline thesis:degree_discipline

Computer Science

Grantor

University of Illinois Urbana-Champaign

Year dc:date

2025

Author dc:creator

• Dixit, Tanay

Contributors dc:contributor

• Han, Jiawei

• Natural Language Processing
• Large Language Models

Statement dc:rights

• Copyright 2025 Tanay Dixit

Language dc:language

en, eng

Handle dc:identifier

https://hdl.handle.net/2142/129521

OAI record oai:identifier

https://www.ideals.illinois.edu/oai-pmh?verb=GetRecord&metadataPrefix=etdms&identifier=oai%3Awww.ideals.illinois.edu%3A2142%2F129521