AI Paper Atlas

Research map / Label-efficient and robust learning / Semi-supervised learning

LLM-Guided Probabilistic Fusion for Label-Efficient Document Layout Analysis

Ibne Farabi Shihab, Sanjeda Akter, Anuj Sharma

CVPR 2026 · Label-efficient and robust learning › Semi-supervised learning · approach: Pseudo-labeling for specialized tasks · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add LLM structural priors via fusion to teacher pseudo-labels (ablation)SwiftFormer-DETR semi-supervised · PubLayNet (5% labels)AP: 82.3 -> 87.3Improved
remove LLM guidance (ablation)Full method · PubLayNet (5% labels)AP: 84.3 vs 87.3 (-3.0)Improved
add probabilistic fusion (ablation)Teacher+LLM pseudo-labels · PubLayNet (5% labels)AP: 85.9 -> 86.7Improved
add cross-modal consistency loss (ablation)Fusion framework · PubLayNet (5% labels)AP: 86.7 -> 87.3Improved
use learned instance-adaptive gating instead of fixed weights (ablation)Lightweight SwiftFormer · PubLayNet (5% labels)AP: 87.3 -> 88.2Improved
use learned gating instead of fixed weights (ablation)LayoutLMv3 variant · PubLayNet (5% labels)AP: 89.4 -> 89.7Improved
add LLM fusion to LayoutLMv3 semi-supervised learningLayoutLMv3 · PubLayNet (5% labels)AP: 89.1 -> 89.7Improved
use MLP fusion instead of inverse-variance plus gate (ablation)Fusion · PubLayNet (5% labels)AP: 88.2 -> 87.6Hurt
use open-source Llama-3-70B instead of GPT-4o-mini (ablation)LLM component · PubLayNet (5% labels, LayoutLMv3)AP: 89.7 -> 89.4No clear effect
use regex text patterns instead of LLM (ablation)Text prior · PubLayNet (5% labels)AP: 88.2 vs 84.9 for regexHurt
add LLM guidance to semi-supervised baseline on rare classesSoftTeacher · DocLayNet (5% labels)Caption AP: 70.1 -> 76.8Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy