支持LLM对话中基础响应的因素：一项快速回顾
Factors That Support Grounded Responses in LLM Conversations: A Rapid Review
AI总结：
本文通过快速回顾识别了支持LLM对话中基础响应的因素，重点分析了推理时间、训练后及强化学习方法，旨在提升LLM响应的准确性和可靠性。
摘要：
大型语言模型（LLMs）可能生成与用户意图不一致、缺乏上下文支撑或在对话中出现幻觉的输出，这会削弱基于LLM的应用可靠性。本回顾旨在识别和分析能够使LLM响应与对话目标一致、确保支撑性以及减少幻觉和主题漂移的技术。我们依据PRISMA框架和PICO策略进行了快速回顾，以结构化搜索、过滤和选择过程。识别出的对齐策略根据LLM生命周期阶段进行分类：推理时间、训练后以及基于强化学习的方法。其中，推理时间的方法尤为高效，能够在不重新训练的情况下对齐输出，同时支持用户意图、上下文支撑和幻觉缓解。所审查的技术提供了改进LLM响应质量和可靠性的结构化机制，覆盖关键对齐目标。
英文摘要：
Large language models (LLMs) may generate outputs that are misaligned with user intent, lack contextual grounding, or exhibit hallucinations during conversation, which compromises the reliability of LLM-based applications. This review aimed to identify and analyze techniques that align LLM responses with conversational goals, ensure grounding, and reduce hallucination and topic drift. We conducted a Rapid Review guided by the PRISMA framework and the PICO strategy to structure the search, filtering, and selection processes. The alignment strategies identified were categorized according to the LLM lifecycle phase in which they operate: inference-time, post-training, and reinforcement learning-based methods. Among these, inference-time approaches emerged as particularly efficient, aligning outputs without retraining while supporting user intent, contextual grounding, and hallucination mitigation. The reviewed techniques provided structured mechanisms for improving the quality and reliability of LLM responses across key alignment objectives.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
