Leveraging Agentic RAG toReduce Hallucinations inLarge Language Models

Title

Leveraging Agentic RAG toReduce Hallucinations inLarge Language Models

Creator

Sudhir, Pratul; Suresh, Sreya; Thontadari, C.

Description

Large Language Models (LLMs) have revolutionized language generation and comprehension. However, a notable issue remains, which is their sensitivity to hallucination, which may lead them to generate inaccurate or irrelevant content. Context dependency, or the capacity to use and understand ones environment, is crucial for surviving hallucinations. The agentic RAG framework offers a feasible solution, leveraging intelligent agents to strengthen contextual knowledge. Through the evaluation of entity roles and relationships, agentic RAG aids LLMs in understanding the variation of context, spotting inconsistencies and generating more precise and balanced replies. This research explores the establishment of Agentic RAG into LLMs to refine their reliability and efficiency by overcasting hallucinations and lifting contextual awareness. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

Source

Lecture Notes in Networks and Systems;Volume;1355 LNNS;pp.31-42

Date

01-01-2025

Publisher

Springer Science and Business Media Deutschland GmbH

Subject

Large language models; LLM Hallucinations; RAG Systems

Coverage

Sudhir P., Department of Computer Science, Christ University, Bangalore, India; Suresh S., Department of Computer Science, Christ University, Bangalore, India; Thontadari C., Department of Computer Science, Christ University, Bangalore, India

Rights

Restricted Access; Hardcopy may be available in the library

Relation

ISSN: 23673370; ISBN: 978-981964882-5;

Format

online

Language

English

Type

Conference paper

Identifier

https://doi.org/10.1007/978-981-96-4883-2_4

https://www.scopus.com/pages/publications/105010631290?origin=resultslist