Training-Free versus Training-Based Intent Classification in LLMs: Accuracy, Robustness, and Failure Modes

• URL: http://arxiv.org/abs/2608.02415v1
• Date: Mon, 03 Aug 2026 15:53:49 GMT
• Title: Training-Free versus Training-Based Intent Classification in LLMs: Accuracy, Robustness, and Failure Modes
• Abstract summary: We compare training-free vs training-based approaches for intent classification.<n>We find that training-free methods are more robust to mixed-intent and adversarial prompts.
• Score: 16.695022020234262
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• The Unlearning Mirage: A Dynamic Framework for Evaluating LLM Unlearning [54.67958855362658]
  We propose a dynamic framework that stress tests unlearning using complex structured queries.<n>Our approach first elicits knowledge from the target model (pre-unlearning) and constructs targeted probes, ranging from simple queries to multi-hop chains.<n>Our framework enables practical and scalable evaluation of unlearning methods without the need for manual construction of forget test sets.
  arXiv  Detail & Related papers  (2026-03-11T19:51:33Z)
• Unlearning Comparator: A Visual Analytics System for Comparative Evaluation of Machine Unlearning Methods [23.6050988823262]
  Machine Unlearning (MU) aims to remove target training data from a trained model so that the removed data no longer influences the model's behavior.<n>Yet, researchers in this rapidly emerging field face challenges in analyzing and understanding the behavior of different MU methods.<n>We introduce a visual analytics system, Unlearning Comparator, designed to facilitate the systematic evaluation of MU methods.
  arXiv  Detail & Related papers  (2025-08-18T08:53:53Z)
• GLiClass: Generalist Lightweight Model for Sequence Classification Tasks [49.2639069781367]
  We propose GLiClass, a novel method that adapts the GLiNER architecture for sequence classification tasks.<n>Our approach achieves strong accuracy and efficiency comparable to embedding-based methods, while maintaining the flexibility needed for zero-shot and few-shot learning scenarios.
  arXiv  Detail & Related papers  (2025-08-11T06:22:25Z)
• Rethinking Classifier Re-Training in Long-Tailed Recognition: A Simple Logits Retargeting Approach [102.0769560460338]
  We develop a simple logits approach (LORT) without the requirement of prior knowledge of the number of samples per class. Our method achieves state-of-the-art performance on various imbalanced datasets, including CIFAR100-LT, ImageNet-LT, and iNaturalist 2018.
  arXiv  Detail & Related papers  (2024-03-01T03:27:08Z)
• A Hard-to-Beat Baseline for Training-free CLIP-based Adaptation [121.0693322732454]
  Contrastive Language-Image Pretraining (CLIP) has gained popularity for its remarkable zero-shot capacity. Recent research has focused on developing efficient fine-tuning methods to enhance CLIP's performance in downstream tasks. We revisit a classical algorithm, Gaussian Discriminant Analysis (GDA), and apply it to the downstream classification of CLIP.
  arXiv  Detail & Related papers  (2024-02-06T15:45:27Z)
• Smooth Ranking SVM via Cutting-Plane Method [6.946903076677842]
  We develop a prototype learning approach that relies on cutting-plane method, similar to Ranking SVM, to maximize AUC. Our algorithm learns simpler models by iteratively introducing cutting planes, thus overfitting is prevented in an unconventional way. Based on the experiments conducted on 73 binary classification datasets, our method yields the best test AUC in 25 datasets among its relevant competitors.
  arXiv  Detail & Related papers  (2024-01-25T18:47:23Z)
• Efficient Training of One Class Classification-SVMs [0.0]
  This study examines the use of a highly effective training method to conduct one-class classification. In this paper, an effective algorithm for dual soft-margin one-class SVM training is presented.
  arXiv  Detail & Related papers  (2023-09-28T15:35:16Z)
• Class-Incremental Learning with Generative Classifiers [6.570917734205559]
  We propose a new strategy for class-incremental learning: generative classification. Our proposal is to learn the joint distribution p(x,y), factorized as p(x|y)p(y), and to perform classification using Bayes' rule. As a proof-of-principle, here we implement this strategy by training a variational autoencoder for each class to be learned.
  arXiv  Detail & Related papers  (2021-04-20T16:26:14Z)
• Learning and Evaluating Representations for Deep One-class Classification [59.095144932794646]
  We present a two-stage framework for deep one-class classification. We first learn self-supervised representations from one-class data, and then build one-class classifiers on learned representations. In experiments, we demonstrate state-of-the-art performance on visual domain one-class classification benchmarks.
  arXiv  Detail & Related papers  (2020-11-04T23:33:41Z)
• Towards Model-Agnostic Post-Hoc Adjustment for Balancing Ranking Fairness and Algorithm Utility [54.179859639868646]
  Bipartite ranking aims to learn a scoring function that ranks positive individuals higher than negative ones from labeled data. There have been rising concerns on whether the learned scoring function can cause systematic disparity across different protected groups. We propose a model post-processing framework for balancing them in the bipartite ranking scenario.
  arXiv  Detail & Related papers  (2020-06-15T10:08:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.