conftrace_
← Core Methods
Machine Learning › Core Methods ›

Representation Learning

18,863 papers

Papers per year

Papers

Representation-based Broad Hallucination Detectors Fail to Generalize Out of Distribution EMNLP 2025
ET-MIER: Entity Type-guided Key Mention Identification and Evidence Retrieval for Document-level Relation Extraction EMNLP 2025
Can Role Vectors Affect LLM Behaviour? EMNLP 2025
Semantic Component Analysis: Introducing Multi-Topic Distributions to Clustering-Based Topic Modeling EMNLP 2025
Hierarchical Reward Modeling for Fault Localization in Large Code Repositories EMNLP 2025
GRAD: Generative Retrieval-Aligned Demonstration Sampler for Efficient Few-Shot Reasoning EMNLP 2025
OVFact: Measuring and Improving Open-Vocabulary Factuality for Long Caption Models EMNLP 2025
On the Versatility of Sparse Autoencoders for In-Context Learning EMNLP 2025
Out-of-Context Reasoning in Large Language Models EMNLP 2025
Length Representations in Large Language Models EMNLP 2025
Stratified Selective Sampling for Instruction Tuning with Dedicated Scoring Strategy EMNLP 2025
Entity Profile Generation and Reasoning with LLMs for Entity Alignment EMNLP 2025
Linguistically-Controlled Paraphrase Generation EMNLP 2025
Decoupled Proxy Alignment: Mitigating Language Prior Conflict for Multimodal Alignment in MLLMs EMNLP 2025
Measuring Lexical Diversity of Synthetic Data Generated through Fine-Grained Persona Prompting EMNLP 2025
PEPE: Long-context Extension for Large Language Models via Periodic Extrapolation Positional Encodings EMNLP 2025
False Friends Are Not Foes: Investigating Vocabulary Overlap in Multilingual Language Models EMNLP 2025
MV-CLAM: Multi-View Molecular Interpretation with Cross-Modal Projection via Language Model EMNLP 2025
Mind the Style Gap: Meta-Evaluation of Style and Attribute Transfer Metrics EMNLP 2025
Domain Pre-training Impact on Representations EMNLP 2025
Lost in Embeddings: Information Loss in Vision–Language Models EMNLP 2025
Looking Beyond the Pixels: Evaluating Visual Metaphor Understanding in VLMs EMNLP 2025
Enhancing Time Awareness in Generative Recommendation EMNLP 2025
Investigating Multi-layer Representations for Dense Passage Retrieval EMNLP 2025
ATHAR: A High-Quality and Diverse Dataset for Classical Arabic to English Translation EMNLP 2025