Work

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

Year: 2025

Type: article

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-tuned LLMs, Retrieval-Augmented Generation (RAG), and Retrieval-Augmented Fine-Tuning (RAFT). Through a literature review, we assess their rejection accuracy, hallucination rates, computational costs, and domain adaptability. We introduce a four-dimensional framework—architecture, metrics, domain application, and dataset diversity—to organize existing studies and benchmarks for comparative analysis (Cao, 2024). Our findings show fine-tuning boosts specificity but lacks universality, RAG enhances context but suffers from retrieval noise, and RAFT balances rejection and efficiency. We recommend future LLMs embed rejection awareness in retrieval and generation. This work synthesizes current research, offering analytical insights into negative rejection strategies and guiding NLP system development.

Source: Journal of King Saud University - Computer and Information Sciences

DOI: 10.1007/s44443-025-00334-6

Authors: Li Bowen, Zhong Zhuoqing, Zhang Hengyu, Sun Xubin, Baha Ihnaini

Institution: Wenzhou-Kean University

Language: English

Topic: Topic Modeling

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: gold

Estimated APC paid: $1,990

Funder: Wenzhou-Kean University