# Multi-Label Classification

2 related articles

Subscribe to updates

aclanthology.org Oct 31, 2026
Autoregressive training drops strict left-to-right targets: Max(MI(S;t)) reorders by mutual information and lifts arithmetic accuracy to 94.96%
Autoregressive language models normally learn next-token prediction in a fixed left-to-right order; Max(MI(S;t)) instead ranks target tokens by their mutual information with the source and already-selected targets before training, exposing informative targets earlier. On GPT-style models it reaches 94.96% average accuracy across arithmetic tasks, against 74.84% for next-token prediction and 86.29% for reverse order, close to the 97.33% upper bound from exhaustively testing 24 orders; on WikiText-2 it lowers average perplexity from 13.58 to 10.77. Only the training-target organization changes; architecture and autoregressive decoding stay the same.
Autoregressive language models normally learn next-token prediction in a fixed left-to-right order; Max(MI(S;t)) instead ranks target tokens by their mutual information with the source and already-selected targets before training, exposing informative targets earlier. On GPT-style models it reaches 94.96% average accuracy across arithmetic tasks, against 74.84% for next-token prediction and 86.29% for reverse order, close to the 97.33% upper bound from exhaustively testing 24 orders; on WikiText-2 it lowers average perplexity from 13.58 to 10.77. Only the training-target organization changes; architecture and autoregressive decoding stay the same.
National Taiwan University
Max(MI(S;t))Next-Token Prediction Multi-Label Classification Text Generation Large language models
arXiv Sep 25, 2026
Fact-Flow uses LLM-bootstrapped multi-label fact guidance to raise factual accuracy of MLLM medical reports on tuberculosis and ophthalmology data
The work introduces Fact-Flow, a framework that decouples visual fact identification from report generation: an LLM automatically extracts and merges clinical finding labels from training reports (7 labels for tuberculosis, 42 for ophthalmology), a multi-label classifier predicts findings, and the predicted labels are serialized into a prompt to guide an MLLM; on the tuberculosis chest X-ray dataset MedGemma + Fact-Flow reaches RadFact F1 0.3055 versus 0.2266 for MedGemma alone, and on the ophthalmology dataset Qwen2.5-VL + Fact-Flow is best on most NLG metrics.
The work introduces Fact-Flow, a framework that decouples visual fact identification from report generation: an LLM automatically extracts and merges clinical finding labels from training reports (7 labels for tuberculosis, 42 for ophthalmology), a multi-label classifier predicts findings, and the predicted labels are serialized into a prompt to guide an MLLM; on the tuberculosis chest X-ray dataset MedGemma + Fact-Flow reaches RadFact F1 0.3055 versus 0.2266 for MedGemma alone, and on the ophthalmology dataset Qwen2.5-VL + Fact-Flow is best on most NLG metrics.
Zhejiang University Zhejiang University of Technology Second Affiliated Hospital of Zhejiang University
Cunyuan Yang（First author）Haishuai Wang（Corresponding author）Qianqian Shen（Corresponding author）
Fact-Flow Medical Report Generation LLM-Bootstrapped Multi-Label Dataset Construction Multi-Label Classification Multimodal Large Language Model

You’re all caught up

Autoregressive training drops strict left-to-right targets: Max(MI(S;t)) reorders by mutual information and lifts arithmetic accuracy to 94.96%

Fact-Flow uses LLM-bootstrapped multi-label fact guidance to raise factual accuracy of MLLM medical reports on tuberculosis and ophthalmology data