Skip to content
conftrace_
2026 EMNLP EMNLP 2026

Gradient-Free Test-Time Adaptation for Few-Shot Online Clustering with Large Language Models

AbstractWe study few-shot online clustering (FSOC), where an unlabelled stream must be assigned to a dynamically growing cluster inventory using only a few labelled support examples for currently observed classes. We propose a two-component test-time gradient-free framework. First, we adapt Wasserstein Generative Flow Networks (wGFN) as an amortised LLM-based policy for in-distribution assignment and out-of-distribution (OOD) rejection. Unlike prior work that trains separate policies for each evaluation class set, we show that a single policy trained on a few classes generalises to novel support classes at test time without parameter updates and further replace fixed rejection thresholds with a Dirichlet evidence model over candidate class assignments. Second, rejected OOD examples enter an oracle-mediated cluster-formation stage. Under shuffled stream orderings, this stage can create noisy provisional support sets that corrupt later assignments. To address this, we introduce a von Mises–Fisher Dirichlet Process Mixture Model warm start to provide oracle-independent cluster structure over unit-normalised text embeddings before oracle-mediated formation. This improves clustering quality, in some settings by ∼ 2×, even with small LLMs (<1B parameters). To our knowledge, this is the first FSOC framework to couple amortised LLM-based assignment with Bayesian non-parametric warm-starting, enabling growing cluster inventories without data augmentation, novel-class parameter updates or predefined cluster counts.

More from EMNLP 2026

All EMNLP 2026 papers →