LLM-Enhanced Dual-Branch Learning for Large-Scale Multi-Label Text Classification

2026-09-11

AI Summary

为解决大规模多标签文本分类问题，提出DualMLC框架，通过自回归解码器语言模型和双向编码器双分支独立处理文档并融合得分，提升预测准确性。

Abstract

Large-scale multi-label text classification assigns a small subset of relevant labels to each document from a vocabulary containing thousands or tens of thousands of candidate labels. Although pretrained language models have improved semantic text representations, most representation-based approaches center their prediction pipelines on a primary encoder or combine auxiliary features within a single ranker. The complementarity between heterogeneous language models therefore remains insufficiently explored. We propose DualMLC, a dual-branch framework that processes the same document through an autoregressive decoder-only language model and a bidirectional encoder. Each branch maintains its own representation pathway and independently estimates relevance scores over the shared label space. DualMLC combines the two score vectors through late logit fusion, allowing shared evidence to reinforce relevant labels and branch-specific evidence to compensate for limitations in the other branch's representation. DualMLC achieves state-of-the-art results on three widely used large-scale multi-label text classification benchmarks. Ablation results further confirm that integrating the heterogeneous predictors produces stronger rankings than either branch alone. The source code is publicly available at https://github.com/huiyegit/DualMLC.

Problem

• large-scale multi-label text classification
• pretrained language models
• heterogeneous language models
• complementarity

Innovation

• Dual-Branch Framework
• Autoregressive Decoder-Only Language Model
• Bidirectional Encoder
• Late Logit Fusion
• Large-Scale Multi-Label Text Classification