Open-world Multi-label Text Classification with Extremely Weak Supervision

TL;DR

This paper introduces X-MLClass, a novel approach for open-world multi-label text classification under extremely weak supervision, leveraging large language models and iterative label space expansion to improve coverage and accuracy.

Contribution

The paper proposes a new iterative method, X-MLClass, that effectively discovers comprehensive label spaces and enhances multi-label classification performance with minimal supervision.

Findings

40% improvement in label space coverage on AAPD dataset

Achieves state-of-the-art end-to-end classification accuracy

Effective discovery of long-tail labels through iterative refinement

Abstract

We study open-world multi-label text classification under extremely weak supervision (XWS), where the user only provides a brief description for classification objectives without any labels or ground-truth label space. Similar single-label XWS settings have been explored recently, however, these methods cannot be easily adapted for multi-label. We observe that (1) most documents have a dominant class covering the majority of content and (2) long-tail labels would appear in some documents as a dominant class. Therefore, we first utilize the user description to prompt a large language model (LLM) for dominant keyphrases of a subset of raw documents, and then construct a (initial) label space via clustering. We further apply a zero-shot multi-label classifier to locate the documents with small top predicted scores, so we can revisit their dominant keyphrases for more long-tail labels. We iterate this process to discover a comprehensive label space and construct a multi-label classifier as a novel method, X-MLClass. X-MLClass exhibits a remarkable increase in ground-truth label space coverage on various datasets, for example, a 40% improvement on the AAPD dataset over topic modeling and keyword extraction methods. Moreover, X-MLClass achieves the best end-to-end multi-label classification accuracy.