{"total":26,"rows":[{"id":"2506.20923","title":"KaLM-Embedding-V2: Superior Training Techniques and Data Inspire A Versatile Embedding Model","created":"2025-06-26","cited_by_count":36,"area":null},{"id":"2602.05216","title":"Semantic Search over 9 Million Mathematical Theorems","created":"2026-02-05","cited_by_count":8,"area":null},{"id":"2503.22280","title":"MultiClaimNet: A Massively Multilingual Dataset of Fact-Checked Claim Clusters","created":"2025-03-28","cited_by_count":7,"area":null},{"id":"2603.12572","title":"LMEB: Long-horizon Memory Embedding Benchmark","created":"2026-03-13","cited_by_count":7,"area":null},{"id":"2507.08983","title":"Exploiting Leaderboards for Large-Scale Distribution of Malicious Models","created":"2025-07-11","cited_by_count":5,"area":null},{"id":"2509.12340","title":"MTEB-NL and E5-NL: Embedding Benchmark and Models for Dutch","created":"2025-09-15","cited_by_count":5,"area":null},{"id":"2604.02045","title":"BidirLM: From Text to Omnimodal Bidirectional Encoders by Adapting and Composing Causal LLMs","created":"2026-04-02","cited_by_count":5,"area":null},{"id":"2507.20783","title":"On The Role of Pretrained Language Models in General-Purpose Text Embeddings: A Survey","created":"2025-07-28","cited_by_count":3,"area":null},{"id":"2605.22544","title":"One prompt is not enough: Instruction Sensitivity Undermines Embedding Model Evaluation","created":"2026-05-21","cited_by_count":3,"area":null},{"id":"2606.23959","title":"Does My Embedding Reflect That $A = B$? Evaluating Mathematical Equivalence in Embedding Models","created":"2026-06-22","cited_by_count":3,"area":null},{"id":"2506.07606","title":"PolitiSky24: U.S. Political Bluesky Dataset with User Stance Labels","created":"2025-06-09","cited_by_count":2,"area":null},{"id":"2507.05006","title":"Do We Really Need Specialization? Evaluating Generalist Text Embeddings for Zero-Shot Recommendation and Search","created":"2025-07-07","cited_by_count":2,"area":null},{"id":"2509.20645","title":"Anticipatory Evaluation of Language Models: Predicting LLM Benchmark Scores from Descriptions","created":"2025-09-25","cited_by_count":2,"area":null},{"id":"2509.24906","title":"Neural network embeddings recover value dimensions from psychometric survey items on par with human data","created":"2025-09-29","cited_by_count":2,"area":null},{"id":"2505.22118","title":"Multilingual vs Crosslingual Retrieval of Fact-Checked Claims: A Tale of Two Approaches","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2602.14492","title":"Query as Anchor: Scenario-Adaptive User Representation via Large Language Model","created":"2026-02-16","cited_by_count":1,"area":null},{"id":"2507.23386","title":"Causal2Vec: Improving Decoder-only LLMs as Embedding Models through a Contextual Token","created":"2025-07-31","cited_by_count":0,"area":null},{"id":"2509.16717","title":"Semi-Supervised Synthetic Data Generation with Fine-Grained Relevance Control for Short Video Search Relevance Modeling","created":"2025-09-20","cited_by_count":0,"area":null},{"id":"2511.08376","title":"TurkEmbed: Turkish Embedding Model on NLI & STS Tasks","created":"2025-11-11","cited_by_count":0,"area":null},{"id":"2603.04741","title":"CONE: Embeddings for Complex Numerical Data Preserving Unit and Variable Semantics","created":"2026-03-05","cited_by_count":0,"area":null},{"id":"2604.27335","title":"Iterative Definition Refinement for Zero-Shot Classification via LLM-Based Semantic Prototype Optimization","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2605.22202","title":"Structure Retention in Embedding Spaces as a Predictor of Benchmark Performance","created":"2026-05-21","cited_by_count":0,"area":null},{"id":"2605.24297","title":"Benchmarking Patent Embeddings: A Multi-Task Evaluation of 22 Models Across Retrieval, Classification, and Clustering","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2606.03027","title":"SEA-LION-Embedding: Open and Reproducible Text Embeddings for Southeast Asia","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2606.22807","title":"Lychee-Reranker: Fast but Not Late Interaction for Compressed Document Reranking","created":"2026-06-22","cited_by_count":0,"area":null},{"id":"2608.04302","title":"CLIP-CC-Bench: Evaluating Paragraph-Level Video Descriptions in Video-Language Models","created":"2026-08-05","cited_by_count":0,"area":null}],"next_cursor":null}