Saved in:
Bibliographic Details
Main Authors: Mehrafarin, Houman, Eshghi, Arash, Konstas, Ioannis
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.20200
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913564858515456
author Mehrafarin, Houman
Eshghi, Arash
Konstas, Ioannis
author_facet Mehrafarin, Houman
Eshghi, Arash
Konstas, Ioannis
contents Evaluating Large Language Models (LLMs) on reasoning benchmarks demonstrates their ability to solve compositional questions. However, little is known of whether these models engage in genuine logical reasoning or simply rely on implicit cues to generate answers. In this paper, we investigate the transitive reasoning capabilities of two distinct LLM architectures, LLaMA 2 and Flan-T5, by manipulating facts within two compositional datasets: QASC and Bamboogle. We controlled for potential cues that might influence the models' performance, including (a) word/phrase overlaps across sections of test input; (b) models' inherent knowledge during pre-training or fine-tuning; and (c) Named Entities. Our findings reveal that while both models leverage (a), Flan-T5 shows more resilience to experiments (b and c), having less variance than LLaMA 2. This suggests that models may develop an understanding of transitivity through fine-tuning on knowingly relevant datasets, a hypothesis we leave to future work.
format Preprint
id arxiv_https___arxiv_org_abs_2410_20200
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Reasoning or a Semblance of it? A Diagnostic Study of Transitive Reasoning in LLMs
Mehrafarin, Houman
Eshghi, Arash
Konstas, Ioannis
Computation and Language
Evaluating Large Language Models (LLMs) on reasoning benchmarks demonstrates their ability to solve compositional questions. However, little is known of whether these models engage in genuine logical reasoning or simply rely on implicit cues to generate answers. In this paper, we investigate the transitive reasoning capabilities of two distinct LLM architectures, LLaMA 2 and Flan-T5, by manipulating facts within two compositional datasets: QASC and Bamboogle. We controlled for potential cues that might influence the models' performance, including (a) word/phrase overlaps across sections of test input; (b) models' inherent knowledge during pre-training or fine-tuning; and (c) Named Entities. Our findings reveal that while both models leverage (a), Flan-T5 shows more resilience to experiments (b and c), having less variance than LLaMA 2. This suggests that models may develop an understanding of transitivity through fine-tuning on knowingly relevant datasets, a hypothesis we leave to future work.
title Reasoning or a Semblance of it? A Diagnostic Study of Transitive Reasoning in LLMs
topic Computation and Language
url https://arxiv.org/abs/2410.20200