Gespeichert in:
Bibliographische Detailangaben
1. Verfasser: Zhang, Haotong
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2412.08317
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909424641114112
author Zhang, Haotong
author_facet Zhang, Haotong
contents We carry out a series of experiments to test large language models' multi-hop reasoning ability from three aspects: selecting and combining external knowledge, dealing with non-sequential reasoning tasks and generalising to data samples with larger numbers of hops. We test the GPT-3.5 model on four reasoning benchmarks with Chain-of-Thought prompting (and its variations). Our results reveal that despite the amazing performance achieved by large language models on various reasoning tasks, models still suffer from severe drawbacks which shows a large gap with humans.
format Preprint
id arxiv_https___arxiv_org_abs_2412_08317
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Large Language Models Still Face Challenges in Multi-Hop Reasoning with External Knowledge
Zhang, Haotong
Computation and Language
We carry out a series of experiments to test large language models' multi-hop reasoning ability from three aspects: selecting and combining external knowledge, dealing with non-sequential reasoning tasks and generalising to data samples with larger numbers of hops. We test the GPT-3.5 model on four reasoning benchmarks with Chain-of-Thought prompting (and its variations). Our results reveal that despite the amazing performance achieved by large language models on various reasoning tasks, models still suffer from severe drawbacks which shows a large gap with humans.
title Large Language Models Still Face Challenges in Multi-Hop Reasoning with External Knowledge
topic Computation and Language
url https://arxiv.org/abs/2412.08317