Papers
arxiv:2601.16530

Curate-Train-Refine: A Closed-Loop Agentic Framework for Zero Shot Classification

Published on Jan 23
Authors:
,

Abstract

Large language models can function as data curators to train lightweight text classifiers through an iterative process that improves accuracy while reducing computational costs.

AI-generated summary

Large language models (LLMs) and high-capacity encoders have advanced zero and few-shot classification, but their inference cost and latency limit practical deployment. We propose training lightweight text classifiers using dynamically generated supervision from an LLM. Our method employs an iterative, agentic loop in which the LLM curates training data, analyzes model successes and failures, and synthesizes targeted examples to address observed errors. This closed-loop generation and evaluation process progressively improves data quality and adapts it to the downstream classifier and task. Across four widely used benchmarks, our approach consistently outperforms standard zero and few-shot baselines. These results indicate that LLMs can serve effectively as data curators, enabling accurate and efficient classification without the operational cost of large-model deployment.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2601.16530 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2601.16530 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2601.16530 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.