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

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.