← Core Methods
Machine Learning › Core Methods ›

Embedding Learning

3751 directly classified papers

Papers per year

Papers

SCV: Light and Effective Multi-Vector Retrieval with Sequence Compressive Vectors COLING 2025
MedEureka: A Medical Domain Benchmark for Multi-Granularity and Multi-Data-Type Embedding-Based Retrieval NAACL 2025
Lightweight Contrastive Distilled Hashing for Online Cross-modal Retrieval AAAI 2025
HEISIR: Hierarchical Expansion of Inverted Semantic Indexing for Training-free Retrieval of Conversational Data using LLMs NAACL 2025
TriEmbed: Bridge the Gap between Text and Token Indices with Embedding Reparameterization ACL 2025
Steering into New Embedding Spaces: Analyzing Cross-Lingual Alignment Induced by Model Interventions in Multilingual Language Models ACL 2025
Hierarchical Level-Wise News Article Clustering via Multilingual Matryoshka Embeddings ACL 2025
Direct Prompt Optimization with Continuous Representations ACL 2025
LADM: Long-context Training Data Selection with Attention-based Dependency Measurement for LLMs ACL 2025
Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs ACL 2025
Contrastive Prompting Enhances Sentence Embeddings in LLMs through Inference-Time Steering ACL 2025
Enhancing Character-Level Understanding in LLMs through Token Internal Structure Learning ACL 2025
TokAlign: Efficient Vocabulary Adaptation via Token Alignment ACL 2025
Optimizing Question Semantic Space for Dynamic Retrieval-Augmented Multi-hop Question Answering ACL 2025
Enhancing Lexicon-Based Text Embeddings with Large Language Models ACL 2025
Look Both Ways and No Sink: Converting LLMs into Text Encoders without Training ACL 2025
Learning to Look at the Other Side: A Semantic Probing Study of Word Embeddings in LLMs with Enabled Bidirectional Attention ACL 2025
ALGEN: Few-shot Inversion Attacks on Textual Embeddings via Cross-Model Alignment and Generation ACL 2025
RefreshKV: Updating Small KV Cache During Long-form Generation ACL 2025
Parameter-Aware Contrastive Knowledge Editing: Tracing and Rectifying based on Critical Transmission Paths ACL 2025
MIR: Methodology Inspiration Retrieval for Scientific Research Problems ACL 2025
Negative Matters: Multi-Granularity Hard-Negative Synthesis and Anchor-Token-Aware Pooling for Enhanced Text Embeddings ACL 2025
WET: Overcoming Paraphrasing Vulnerabilities in Embeddings-as-a-Service with Linear Transformation Watermarks ACL 2025
Sticking to the Mean: Detecting Sticky Tokens in Text Embedding Models ACL 2025
GLoCIM: Global-view Long Chain Interest Modeling for news recommendation COLING 2025