Improving negative rejection ability in language models: A review of fine-tuned LLMs, RAG, and RAFT

Abstract Large Language Models (LLMs) excel in text understanding and generation but struggle to reject irrelevant, ambiguous, or misleading queries, termed negative rejection, impacting reliability in high-stakes contexts. This paper reviews negative rejection, analyzing three approaches: fine-tune...

Volledige beschrijving

Bibliografische gegevens

Hoofdauteurs:	Li Bowen, Zhong Zhuoqing, Zhang Hengyu, Sun Xubin, Baha Ihnaini
Formaat:	Artigo
Taal:	Inglês
Gepubliceerd in:	Springer 2025-12-01
Reeks:	Journal of King Saud University: Computer and Information Sciences
Onderwerpen:	Negative rejection LLM safety Fine-tuning RAG RAFT Hallucination mitigation
Online toegang:	https://doi.org/10.1007/s44443-025-00334-6
Tags:	Voeg label toe Geen labels, Wees de eerste die dit record labelt!