{"total":99,"rows":[{"id":"2312.10997","title":"Retrieval-Augmented Generation for Large Language Models: A Survey","created":"2023-12-18","cited_by_count":2212,"area":"lr"},{"id":"2405.17428","title":"NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models","created":"2024-05-27","cited_by_count":472,"area":null},{"id":"2401.00368","title":"Improving Text Embeddings with Large Language Models","created":"2023-12-31","cited_by_count":303,"area":null},{"id":"2402.07867","title":"PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models","created":"2024-02-12","cited_by_count":267,"area":"rag"},{"id":"2402.09906","title":"Generative Representational Instruction Tuning","created":"2024-02-15","cited_by_count":233,"area":null},{"id":"2311.05112","title":"A Survey of Large Language Models in Medicine: Progress, Application, and Challenge","created":"2023-11-09","cited_by_count":124,"area":null},{"id":"2402.15449","title":"Repetition Improves Language Model Embeddings","created":"2024-02-23","cited_by_count":72,"area":null},{"id":"2403.15246","title":"FollowIR: Evaluating and Teaching Information Retrieval Models to Follow Instructions","created":"2024-03-22","cited_by_count":69,"area":null},{"id":"2405.13401","title":"TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Models","created":"2024-05-22","cited_by_count":67,"area":"rag"},{"id":"2409.13731","title":"KAG: Boosting LLMs in Professional Domains via Knowledge Augmented Generation","created":"2024-09-10","cited_by_count":67,"area":"rag"},{"id":"2410.20964","title":"DeTeCtive: Detecting AI-generated Text via Multi-Level Contrastive Learning","created":"2024-10-28","cited_by_count":53,"area":null},{"id":"2404.04689","title":"Multicalibration for Confidence Scoring in LLMs","created":"2024-04-06","cited_by_count":46,"area":null},{"id":"2406.11171","title":"SUGARCREPE++ Dataset: Vision-Language Model Sensitivity to Semantic and Lexical Alterations","created":"2024-06-17","cited_by_count":42,"area":"mllm"},{"id":"2409.02038","title":"BEAVER: An Enterprise Benchmark for Text-to-SQL","created":"2024-09-03","cited_by_count":42,"area":null},{"id":"2402.16829","title":"GISTEmbed: Guided In-sample Selection of Training Negatives for Text Embedding Fine-tuning","created":"2024-02-26","cited_by_count":40,"area":"rag"},{"id":"2502.18943","title":"Towards Label-Only Membership Inference Attack against Pre-trained Large Language Models","created":"2025-02-26","cited_by_count":37,"area":"safety"},{"id":"2403.13310","title":"A Semantic Search Engine for Mathlib4","created":"2024-03-20","cited_by_count":31,"area":null},{"id":"2407.01102","title":"BERGEN: A Benchmarking Library for Retrieval-Augmented Generation","created":"2024-07-01","cited_by_count":31,"area":"rag"},{"id":"2404.03921","title":"Simple Techniques for Enhancing Sentence Embeddings in Generative Language Models","created":"2024-04-05","cited_by_count":26,"area":null},{"id":"2310.01208","title":"Label Supervised LLaMA Finetuning","created":"2023-10-02","cited_by_count":20,"area":null},{"id":"2405.01886","title":"Aloe: A Family of Fine-tuned Open Healthcare LLMs","created":"2024-05-03","cited_by_count":20,"area":"safety"},{"id":"2402.11891","title":"FeB4RAG: Evaluating Federated Search in the Context of Retrieval Augmented Generation","created":"2024-02-19","cited_by_count":19,"area":"rag"},{"id":"2406.01607","title":"Recent advances in text embedding: A Comprehensive Review of Top-Performing Methods on the MTEB Benchmark","created":"2024-05-27","cited_by_count":19,"area":null},{"id":"2407.21424","title":"Cost-Effective Hallucination Detection for LLMs","created":"2024-07-31","cited_by_count":18,"area":null},{"id":"2412.09754","title":"ViCaS: A Dataset for Combining Holistic and Pixel-level Video Understanding using Captions with Grounded Segmentation","created":"2024-12-12","cited_by_count":17,"area":"mllm"},{"id":"2502.19587","title":"NeoBERT: A Next-Generation BERT","created":"2025-02-26","cited_by_count":16,"area":"lr"},{"id":"2504.03598","title":"EnrichIndex: Using LLMs to Enrich Retrieval Indices Offline","created":"2025-04-04","cited_by_count":15,"area":null},{"id":"2407.04681","title":"Rethinking Visual Prompting for Multimodal Large Language Models with External Knowledge","created":"2024-07-05","cited_by_count":13,"area":"lr"},{"id":"2504.06265","title":"Large language models as uncertainty-calibrated optimizers for experimental discovery","created":"2025-04-08","cited_by_count":13,"area":null},{"id":"2412.10415","title":"Generative Adversarial Reviews: When LLMs Become the Critic","created":"2024-12-09","cited_by_count":12,"area":null},{"id":"2502.05878","title":"Retrieval-augmented Large Language Models for Financial Time Series Forecasting","created":"2025-02-09","cited_by_count":12,"area":"rag"},{"id":"2509.13772","title":"Who Taught the Lie? Responsibility Attribution for Poisoned Knowledge in Retrieval-Augmented Generation","created":"2025-09-17","cited_by_count":12,"area":"rag"},{"id":"2407.12068","title":"Learning on Graphs with Large Language Models(LLMs): A Deep Dive into Model Robustness","created":"2024-07-16","cited_by_count":11,"area":null},{"id":"2410.01727","title":"Automated Knowledge Concept Annotation and Question Representation Learning for Knowledge Tracing","created":"2024-10-02","cited_by_count":11,"area":null},{"id":"2508.02835","title":"Defending Against Knowledge Poisoning Attacks During Retrieval-Augmented Generation","created":"2025-08-04","cited_by_count":11,"area":"rag"},{"id":"2407.20164","title":"Language-Conditioned Offline RL for Multi-Robot Navigation","created":"2024-07-29","cited_by_count":9,"area":"offlinerl"},{"id":"2409.06328","title":"Extracting Paragraphs from LLM Token Activations","created":"2024-09-10","cited_by_count":9,"area":null},{"id":"2503.01713","title":"SAGE: A Framework of Precise Retrieval for RAG","created":"2025-03-03","cited_by_count":8,"area":"rag"},{"id":"2509.10697","title":"A Survey on Retrieval And Structuring Augmented Generation with Large Language Models","created":"2025-09-12","cited_by_count":8,"area":null},{"id":"2401.06466","title":"PersianMind: A Cross-Lingual Persian-English Large Language Model","created":"2024-01-12","cited_by_count":7,"area":null},{"id":"2510.10062","title":"HUME: Measuring the Human-Model Performance Gap in Text Embedding Tasks","created":"2025-10-11","cited_by_count":7,"area":null},{"id":"2408.11490","title":"DocTabQA: Answering Questions from Long Documents Using Tables","created":"2024-08-21","cited_by_count":6,"area":null},{"id":"2408.11650","title":"CIPHER: Cybersecurity Intelligent Penetration-testing Helper for Ethical Researcher","created":"2024-08-21","cited_by_count":6,"area":null},{"id":"2410.03721","title":"Thematic Analysis with Open-Source Generative AI and Machine Learning: A New Method for Inductive Qualitative Codebook Development","created":"2024-09-28","cited_by_count":6,"area":null},{"id":"2412.06182","title":"Towards Long Video Understanding via Fine-detailed Video Story Generation","created":"2024-12-09","cited_by_count":6,"area":null},{"id":"2505.17810","title":"VIBE: Vector Index Benchmark for Embeddings","created":"2025-05-23","cited_by_count":6,"area":null},{"id":"2405.16800","title":"TAGA: Text-Attributed Graph Self-Supervised Learning by Synergizing Graph and Text Mutual Transformations","created":"2024-05-27","cited_by_count":5,"area":null},{"id":"2406.12881","title":"Towards Unlocking Insights from Logbooks Using AI","created":"2024-05-25","cited_by_count":5,"area":"rag"},{"id":"2508.17858","title":"LexSemBridge: Fine-Grained Dense Representation Enhancement through Token-Aware Embedding Augmentation","created":"2025-08-25","cited_by_count":5,"area":"rag"},{"id":"2403.11984","title":"Using Generative Text Models to Create Qualitative Codebooks for Student Evaluations of Teaching","created":"2024-03-18","cited_by_count":4,"area":null},{"id":"2404.00604","title":"Extensive Self-Contrast Enables Feedback-Free Language Model Alignment","created":"2024-03-31","cited_by_count":4,"area":"alignment"},{"id":"2407.19527","title":"Open Sentence Embeddings for Portuguese with the Serafim PT* encoders family","created":"2024-07-28","cited_by_count":4,"area":null},{"id":"2312.16144","title":"Towards Better Monolingual Japanese Retrievers with Multi-Vector Models","created":"2023-12-26","cited_by_count":3,"area":null},{"id":"2404.12192","title":"Aligning Actions and Walking to LLM-Generated Textual Descriptions","created":"2024-04-18","cited_by_count":3,"area":null},{"id":"2408.09794","title":"AutoML-guided Fusion of Entity and LLM-based Representations for Document Classification","created":"2024-08-19","cited_by_count":3,"area":null},{"id":"2408.13366","title":"CodeRefine: A Pipeline for Enhancing LLM-Generated Code Implementations of Research Papers","created":"2024-08-23","cited_by_count":3,"area":null},{"id":"2408.14830","title":"PolicyLR: A Logic Representation For Privacy Policies","created":"2024-08-27","cited_by_count":3,"area":null},{"id":"2502.09532","title":"Mind the Gap! Choice Independence in Using Multilingual LLMs for Persuasive Co-Writing Tasks in Different Languages","created":"2025-02-13","cited_by_count":3,"area":null},{"id":"2504.11889","title":"Rethinking LLM-Based Recommendations: A Personalized Query-Driven Parallel Integration","created":"2025-04-16","cited_by_count":3,"area":"lr"},{"id":"2508.06030","title":"Efficient Knowledge Probing of Large Language Models by Adapting Pre-trained Embeddings","created":"2025-08-08","cited_by_count":3,"area":null},{"id":"2605.11325","title":"Structured Belief State and the First Precision-Aware Benchmark for LLM Memory Retrieval","created":"2026-05-11","cited_by_count":3,"area":null},{"id":"2406.06279","title":"Multi-Prompting Decoder Helps Better Language Understanding","created":"2024-06-10","cited_by_count":2,"area":null},{"id":"2406.10746","title":"SparseCL: Sparse Contrastive Learning for Contradiction Retrieval","created":"2024-06-15","cited_by_count":2,"area":null},{"id":"2408.00300","title":"Towards Flexible Evaluation for Generative Visual Question Answering","created":"2024-08-01","cited_by_count":2,"area":"mllm"},{"id":"2408.11609","title":"Xinyu: An Efficient LLM-based System for Commentary Generation","created":"2024-08-21","cited_by_count":2,"area":null},{"id":"2409.15127","title":"Pareto-Optimized Open-Source LLMs for Healthcare via Context Retrieval","created":"2024-09-23","cited_by_count":2,"area":null},{"id":"2508.11442","title":"CoDiEmb: A Collaborative yet Distinct Framework for Unified Representation Learning in Information Retrieval and Semantic Textual Similarity","created":"2025-08-15","cited_by_count":2,"area":null},{"id":"2510.02964","title":"External Data Extraction Attacks against Retrieval-Augmented Large Language Models","created":"2025-10-03","cited_by_count":2,"area":"rag"},{"id":"2603.13647","title":"PLUME: Building a Network-Native Foundation Model for Wireless Traces via Protocol-Aware Tokenization","created":"2026-03-13","cited_by_count":2,"area":null},{"id":"2605.31142","title":"On the Robustness of Multilingual Text Embedding Rankings Across Learning Tasks, Languages, and Benchmark Datasets","created":"2026-05-29","cited_by_count":2,"area":null},{"id":"2404.16365","title":"VISLA Benchmark: Evaluating Embedding Sensitivity to Semantic and Lexical Alterations","created":"2024-04-25","cited_by_count":1,"area":null},{"id":"2410.23578","title":"Automating Quantum Software Maintenance: Flakiness Detection and Root Cause Analysis","created":"2024-10-31","cited_by_count":1,"area":null},{"id":"2411.12056","title":"Benchmarking pre-trained text embedding models in aligning built asset information","created":"2024-11-18","cited_by_count":1,"area":null},{"id":"2411.12156","title":"HNCSE: Advancing Sentence Embeddings via Hybrid Contrastive Learning with Hard Negatives","created":"2024-11-19","cited_by_count":1,"area":null},{"id":"2411.18472","title":"Isolating authorship from content with semantic embeddings and contrastive learning","created":"2024-11-27","cited_by_count":1,"area":null},{"id":"2411.18947","title":"ICLERB: In-Context Learning Embedding and Reranker Benchmark","created":"2024-11-28","cited_by_count":1,"area":null},{"id":"2504.00584","title":"Semantic Adapter for Universal Text Embeddings: Diagnosing and Mitigating Negation Blindness to Enhance Universality","created":"2025-04-01","cited_by_count":1,"area":null},{"id":"2507.10039","title":"Towards Applying Large Language Models to Complement Single-Cell Foundation Models","created":"2025-07-14","cited_by_count":1,"area":null},{"id":"2509.18690","title":"Advances in Large Language Models for Medicine","created":"2025-09-23","cited_by_count":1,"area":null},{"id":"2511.04956","title":"ORCHID: Orchestrated Retrieval-Augmented Classification with Human-in-the-Loop Intelligent Decision-Making for High-Risk Property","created":"2025-11-07","cited_by_count":1,"area":"rag"},{"id":"2601.03270","title":"Advances and Challenges in Semantic Textual Similarity: A Comprehensive Survey","created":"2025-12-19","cited_by_count":1,"area":null},{"id":"2605.02950","title":"Kernel Affine Hull Machines as Compute-Efficient Encoders for Frozen Semantic Spaces","created":"2026-05-01","cited_by_count":1,"area":null},{"id":"2405.14862","title":"Bitune: Leveraging Bidirectional Attention to Improve Decoder-Only LLMs","created":"2024-05-23","cited_by_count":0,"area":null},{"id":"2406.18133","title":"ConvoCache: Smart Re-Use of Chatbot Responses","created":"2024-06-26","cited_by_count":0,"area":null},{"id":"2409.02711","title":"Creating a Gen-AI based Track and Trace Assistant MVP (SuperTracy) for PostNL","created":"2024-09-04","cited_by_count":0,"area":null},{"id":"2410.12874","title":"On Debiasing Text Embeddings Through Context Injection","created":"2024-10-14","cited_by_count":0,"area":null},{"id":"2410.17112","title":"Enhancing Answer Attribution for Faithful Text Generation with Large Language Models","created":"2024-10-22","cited_by_count":0,"area":null},{"id":"2501.12896","title":"Irrational Complex Rotations Empower Low-bit Optimizers","created":"2025-01-22","cited_by_count":0,"area":null},{"id":"2502.10250","title":"VisCon-100K: Leveraging Contextual Web Data for Fine-tuning Vision Language Models","created":"2025-02-14","cited_by_count":0,"area":"mllm"},{"id":"2506.00242","title":"Whispers of Many Shores: Cultural Alignment through Collaborative Cultural Expertise","created":"2025-05-30","cited_by_count":0,"area":null},{"id":"2508.20587","title":"SemSR: Semantics aware robust Session-based Recommendations","created":"2025-08-28","cited_by_count":0,"area":null},{"id":"2603.04885","title":"Proactive Memory for Ad-Hoc Recall over Streaming Dialogues","created":"2026-03-05","cited_by_count":0,"area":null},{"id":"2603.09029","title":"Automating Detection and Root-Cause Analysis of Flaky Tests in Quantum Software","created":"2026-03-09","cited_by_count":0,"area":null},{"id":"2603.27264","title":"TrendGen: An Outfit Recommendation and Display System","created":"2026-03-28","cited_by_count":0,"area":null},{"id":"2603.28205","title":"Beyond Cosine Similarity: Zero-Initialized Residual Complex Projection for Aspect-Based Sentiment Analysis","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2609.08887","title":"Q2D-Web: A Large-Scale Benchmark for Retrieval in Agentic RAG Systems","created":"2026-09-08","cited_by_count":0,"area":"rag"},{"id":"2609.23307","title":"Semantic Candidate-Job Matching: A Comparative Evaluation of Dense Embedding Models in Hybrid Retrieval","created":"2026-09-20","cited_by_count":0,"area":null},{"id":"2609.33075","title":"QureRadEmbed: Structuring Radiological Similarity through Attribute and Reasoning Supervision","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.36376","title":"Quantization Enables Private Dense Retrieval against Malicious Service Providers","created":"2026-09-28","cited_by_count":0,"area":"rag"}],"next_cursor":null}