← Learning Types
Machine Learning › Learning Types ›

Weakly Supervised Learning

3895 directly classified papers

Papers per year

Papers

Categorical Attention: Fine-grained Language-guided Noise Filtering Network for Occluded Person Re-Identification IJCAI 2025
Weakly-Supervised Movie Trailer Generation Driven by Multi-Modal Semantic Consistency IJCAI 2025
Ask-Before-Detection: Identifying and Mitigating Conformity Bias in LLM-Powered Error Detector for Math Word Problem Solutions ACL 2025
Crowd Comparative Reasoning: Unlocking Comprehensive Evaluations for LLM-as-a-Judge ACL 2025
Pattern Recognition or Medical Knowledge? The Problem with Multiple-Choice Questions in Medicine ACL 2025
Self-Taught Agentic Long Context Understanding ACL 2025
Disentangling Biased Knowledge from Reasoning in Large Language Models via Machine Unlearning ACL 2025
Instance-Selection-Inspired Undersampling Strategies for Bias Reduction in Small and Large Language Models for Binary Text Classification ACL 2025
Mitigating Confounding in Speech-Based Dementia Detection through Weight Masking ACL 2025
Lost in Literalism: How Supervised Training Shapes Translationese in LLMs ACL 2025
Improving Medical Large Vision-Language Models with Abnormal-Aware Feedback ACL 2025
QAEval: Mixture of Evaluators for Question-Answering Task Evaluation ACL 2025
Can External Validation Tools Improve Annotation Quality for LLM-as-a-Judge? ACL 2025
How to Mitigate Overfitting in Weak-to-strong Generalization? ACL 2025
Can’t See the Forest for the Trees: Benchmarking Multimodal Safety Awareness for Multimodal LLMs ACL 2025
Revealing the Deceptiveness of Knowledge Editing: A Mechanistic Analysis of Superficial Editing ACL 2025
OmniAlign-V: Towards Enhanced Alignment of MLLMs with Human Preference ACL 2025
Synergistic Weak-Strong Collaboration by Aligning Preferences ACL 2025
Efficient Ensemble for Fine-tuning Language Models on Multiple Datasets ACL 2025
Safety Alignment via Constrained Knowledge Unlearning ACL 2025
CheXalign: Preference fine-tuning in chest X-ray interpretation models without human feedback ACL 2025
Are the Values of LLMs Structurally Aligned with Humans? A Causal Perspective ACL 2025
RAEmoLLM: Retrieval Augmented LLMs for Cross-Domain Misinformation Detection Using In-Context Learning Based on Emotional Information ACL 2025
Graphically Speaking: Unmasking Abuse in Social Media with Conversation Insights ACL 2025
Hard Negatives, Hard Lessons: Revisiting Training Data Quality for Robust Information Retrieval with LLMs EMNLP 2025