In-Context Learning in Large Language Models (LLMs): Mechanisms, Capabilities, and Implications for Advanced Knowledge Representation and Reasoning

The rapid growth of Large Language Models (LLMs) and their in-context learning (ICL) capabilities has significantly transformed paradigms in artificial intelligence (AI) and natural language processing. Notable models, such as OpenAI’s GPT series, have demonstrated previously unprecedente...

Full description

Saved in:
Bibliographic Details
Main Authors: Azza Mohamed, Mohamed El Rashid, Khaled Shaalan
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11018434/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850132640843169792
author Azza Mohamed
Mohamed El Rashid
Khaled Shaalan
author_facet Azza Mohamed
Mohamed El Rashid
Khaled Shaalan
author_sort Azza Mohamed
collection DOAJ
description The rapid growth of Large Language Models (LLMs) and their in-context learning (ICL) capabilities has significantly transformed paradigms in artificial intelligence (AI) and natural language processing. Notable models, such as OpenAI’s GPT series, have demonstrated previously unprecedented advancements in verbal comprehension and adaptability, dynamically responding to new tasks offered via contextual prompts. This study provides a detailed survey of recent advances in theoretical research on LLMs and ICL. The search was conducted across several scholarly databases including Google Scholar, arXiv, IEEE Xplore, ACM Digital Library, and SpringerLink, covering publications from January 2019 to March 2024. We investigate how LLMs encode and use knowledge via ICL, the evolving reasoning skills that result from this process, and the considerable impact of prompt design on LLM reasoning performance, particularly in symbolic reasoning tasks. Furthermore, we investigate the theoretical frameworks that explain or challenge LLM behaviors in ICL contexts and address the significance of these findings for the development of complex knowledge representation and reasoning systems. Using a systematic methodology consistent with accepted research criteria, this review synthesizes significant observations, highlights existing gaps and obstacles, and discusses implications for future research and practice. Our goal is to connect theoretical ideas with actual advances in Artificial Intelligence, ultimately contributing to the continuing discussion about the capabilities and applications of LLMs in knowledge representation and reasoning.
format Article
id doaj-art-2891e3eb43fc4a2eae19ad91a53dcdc3
institution OA Journals
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-2891e3eb43fc4a2eae19ad91a53dcdc32025-08-20T02:32:10ZengIEEEIEEE Access2169-35362025-01-0113955749559310.1109/ACCESS.2025.357530311018434In-Context Learning in Large Language Models (LLMs): Mechanisms, Capabilities, and Implications for Advanced Knowledge Representation and ReasoningAzza Mohamed0https://orcid.org/0000-0002-1244-4448Mohamed El Rashid1https://orcid.org/0009-0002-7106-1938Khaled Shaalan2https://orcid.org/0000-0003-0823-8390Faculty of Engineering and Computing, Liwa University, Al Ain, United Arab EmiratesImam Malik College, Dubai, United Arab EmiratesFaculty of Engineering and IT, The British University in Dubai, Dubai, United Arab EmiratesThe rapid growth of Large Language Models (LLMs) and their in-context learning (ICL) capabilities has significantly transformed paradigms in artificial intelligence (AI) and natural language processing. Notable models, such as OpenAI’s GPT series, have demonstrated previously unprecedented advancements in verbal comprehension and adaptability, dynamically responding to new tasks offered via contextual prompts. This study provides a detailed survey of recent advances in theoretical research on LLMs and ICL. The search was conducted across several scholarly databases including Google Scholar, arXiv, IEEE Xplore, ACM Digital Library, and SpringerLink, covering publications from January 2019 to March 2024. We investigate how LLMs encode and use knowledge via ICL, the evolving reasoning skills that result from this process, and the considerable impact of prompt design on LLM reasoning performance, particularly in symbolic reasoning tasks. Furthermore, we investigate the theoretical frameworks that explain or challenge LLM behaviors in ICL contexts and address the significance of these findings for the development of complex knowledge representation and reasoning systems. Using a systematic methodology consistent with accepted research criteria, this review synthesizes significant observations, highlights existing gaps and obstacles, and discusses implications for future research and practice. Our goal is to connect theoretical ideas with actual advances in Artificial Intelligence, ultimately contributing to the continuing discussion about the capabilities and applications of LLMs in knowledge representation and reasoning.https://ieeexplore.ieee.org/document/11018434/Artificial intelligencein-context learninglarge language models (LLMs)knowledge representation reasoningadvanced AI modelsnatural language processing (NLP)
spellingShingle Azza Mohamed
Mohamed El Rashid
Khaled Shaalan
In-Context Learning in Large Language Models (LLMs): Mechanisms, Capabilities, and Implications for Advanced Knowledge Representation and Reasoning
IEEE Access
Artificial intelligence
in-context learning
large language models (LLMs)
knowledge representation reasoning
advanced AI models
natural language processing (NLP)
title In-Context Learning in Large Language Models (LLMs): Mechanisms, Capabilities, and Implications for Advanced Knowledge Representation and Reasoning
title_full In-Context Learning in Large Language Models (LLMs): Mechanisms, Capabilities, and Implications for Advanced Knowledge Representation and Reasoning
title_fullStr In-Context Learning in Large Language Models (LLMs): Mechanisms, Capabilities, and Implications for Advanced Knowledge Representation and Reasoning
title_full_unstemmed In-Context Learning in Large Language Models (LLMs): Mechanisms, Capabilities, and Implications for Advanced Knowledge Representation and Reasoning
title_short In-Context Learning in Large Language Models (LLMs): Mechanisms, Capabilities, and Implications for Advanced Knowledge Representation and Reasoning
title_sort in context learning in large language models llms mechanisms capabilities and implications for advanced knowledge representation and reasoning
topic Artificial intelligence
in-context learning
large language models (LLMs)
knowledge representation reasoning
advanced AI models
natural language processing (NLP)
url https://ieeexplore.ieee.org/document/11018434/
work_keys_str_mv AT azzamohamed incontextlearninginlargelanguagemodelsllmsmechanismscapabilitiesandimplicationsforadvancedknowledgerepresentationandreasoning
AT mohamedelrashid incontextlearninginlargelanguagemodelsllmsmechanismscapabilitiesandimplicationsforadvancedknowledgerepresentationandreasoning
AT khaledshaalan incontextlearninginlargelanguagemodelsllmsmechanismscapabilitiesandimplicationsforadvancedknowledgerepresentationandreasoning