发表机构
Johns Hopkins University（约翰斯·霍普金斯大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究系统对比LLMs中无训练与基于训练的意图分类方法，发现两类方法在简单基准上性能饱和，基于训练的方法在难分类任务占优，无训练方法对混合与对抗性提示更鲁棒。
AI 中文摘要
大语言模型（LLMs）的意图分类是将用户提示归入预定义类别的任务，例如给定用户提示后，系统需判断其主要涉及数学、编程还是通用文本处理，该分类可将提示路由至针对特定领域优化的专用模型，提升准确性与计算效率。本研究系统对比无训练与基于训练的意图分类方法，选取两种基于内部表示统计的轻量无训练方法，与MLP分类器、线性探针进行对比。综合实证评估显示：1）无训练与基于训练的方法在简单基准（数学vs编程vs自然语言）上均达到饱和性能；2）基于训练的分类器在更难的分类任务（如Java vs Python）上具有优势；3）无训练方法通常对混合意图提示与对抗性提示更具鲁棒性。
英文摘要
Intent classification in Large Language Models (LLMs) involves categorizing user prompts into predefined classes. For instance, given a user prompt, the system must determine whether it primarily concerns mathematics, coding, or general text processing. Such classification enables routing prompts to specialized models optimized for specific domains, improving both accuracy and computational efficiency. In this work, we conduct a systematic study comparing training-free vs training-based approaches for intent classification. For this purpose, we consider two lightweight, training-free methods based on statistics of internal representations and compare them against MLP classifiers and linear probes. Our comprehensive empirical evaluation reveals that 1) Both training-free and training-based methods saturate easy benchmarks (mathematics vs. coding vs. natural language), 2) Training-based classifiers have an advantage on harder classification tasks (e.g. Java vs Python), and 3) Training-free methods are generally more robust to mixed-intent and adversarial prompts.
CommentsAccepted at the Conference on Language Modeling (COLM 2026)
