{"total":78,"rows":[{"id":"2410.05983","title":"Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAG","created":"2024-10-08","cited_by_count":123,"area":"rag"},{"id":"2410.03727","title":"FaithEval: Can Your Language Model Stay Faithful to Context, Even If \"The Moon is Made of Marshmallows\"","created":"2024-09-30","cited_by_count":86,"area":"rag"},{"id":"2409.15700","title":"Making Text Embedders Few-Shot Learners","created":"2024-09-24","cited_by_count":79,"area":null},{"id":"2410.12837","title":"A Comprehensive Survey of Retrieval-Augmented Generation (RAG): Evolution, Current Landscape and Future Directions","created":"2024-10-03","cited_by_count":70,"area":"rag"},{"id":"2409.14924","title":"Retrieval Augmented Generation (RAG) and Beyond: A Comprehensive Survey on How to Make your LLMs use External Data More Wisely","created":"2024-09-23","cited_by_count":66,"area":"rag"},{"id":"2502.14902","title":"PathRAG: Pruning Graph-based Retrieval Augmented Generation with Relational Paths","created":"2025-02-18","cited_by_count":61,"area":"rag"},{"id":"2502.08468","title":"mmE5: Improving Multimodal Multilingual Embeddings via High-quality Synthetic Data","created":"2025-02-12","cited_by_count":49,"area":"synth"},{"id":"2503.01763","title":"Retrieval Models Aren't Tool-Savvy: Benchmarking Tool Retrieval for Large Language Models","created":"2025-03-03","cited_by_count":47,"area":"agents"},{"id":"2404.18443","title":"BMRetriever: Tuning Large Language Models as Better Biomedical Text Retrievers","created":"2024-04-29","cited_by_count":38,"area":null},{"id":"2503.10677","title":"A Survey on Knowledge-Oriented Retrieval-Augmented Generation","created":"2025-03-11","cited_by_count":36,"area":"rag"},{"id":"2412.12591","title":"LLMs are Also Effective Embedding Models: An In-depth Overview","created":"2024-12-17","cited_by_count":32,"area":null},{"id":"2405.13179","title":"RAG-RLRC-LaySum at BioLaySumm: Integrating Retrieval-Augmented Generation and Readability Control for Layman Summarization of Biomedical Texts","created":"2024-05-21","cited_by_count":23,"area":"rag"},{"id":"2407.01796","title":"Ground Every Sentence: Improving Retrieval-Augmented LLMs with Interleaved Reference-Claim Generation","created":"2024-07-01","cited_by_count":21,"area":"rag"},{"id":"2502.00409","title":"Doing More with Less: A Survey on Routing Strategies for Resource Optimisation in Large Language Model-Based Systems","created":"2025-02-01","cited_by_count":20,"area":null},{"id":"2404.13556","title":"ChatRetriever: Adapting Large Language Models for Generalized and Robust Conversational Dense Retrieval","created":"2024-04-21","cited_by_count":19,"area":null},{"id":"2408.12194","title":"Large Language Models as Foundations for Next-Gen Dense Retrieval: A Comprehensive Empirical Assessment","created":"2024-08-22","cited_by_count":19,"area":null},{"id":"2412.12559","title":"EXIT: Context-Aware Extractive Compression for Enhancing Retrieval-Augmented Generation","created":"2024-12-17","cited_by_count":17,"area":"rag"},{"id":"2410.02719","title":"UncertaintyRAG: Span-Level Uncertainty Enhanced Long-Context Modeling for Retrieval-Augmented Generation","created":"2024-10-03","cited_by_count":16,"area":"rag"},{"id":"2402.11573","title":"BGE Landmark Embedding: A Chunking-Free Embedding Method For Retrieval Augmented Long-Context Large Language Models","created":"2024-02-18","cited_by_count":15,"area":"rag"},{"id":"2411.00304","title":"Unified Generative and Discriminative Training for Multi-modal Large Language Models","created":"2024-11-01","cited_by_count":15,"area":"mllm"},{"id":"2502.11401","title":"Following the Autoregressive Nature of LLM Embeddings via Compression and Alignment","created":"2025-02-17","cited_by_count":14,"area":null},{"id":"2510.14337","title":"Stop-RAG: Value-Based Retrieval Control for Iterative RAG","created":"2025-10-16","cited_by_count":14,"area":"rag"},{"id":"2404.04163","title":"Dwell in the Beginning: How Language Models Embed Long Documents for Dense Retrieval","created":"2024-04-05","cited_by_count":13,"area":null},{"id":"2501.18539","title":"Can we Retrieve Everything All at Once? ARM: An Alignment-Oriented LLM-based Retrieval Method","created":"2025-01-30","cited_by_count":10,"area":"agents"},{"id":"2602.21202","title":"Multi-Vector Index Compression in Any Modality","created":"2026-02-24","cited_by_count":10,"area":null},{"id":"2406.17262","title":"D2LLM: Decomposed and Distilled Large Language Models for Semantic Search","created":"2024-06-25","cited_by_count":9,"area":"distill"},{"id":"2407.15748","title":"MoRSE: Bridging the Gap in Cybersecurity Expertise with Retrieval Augmented Generation","created":"2024-07-22","cited_by_count":8,"area":"rag"},{"id":"2408.17344","title":"rerankers: A Lightweight Python Library to Unify Ranking Methods","created":"2024-08-30","cited_by_count":8,"area":null},{"id":"2502.11431","title":"Any Information Is Just Worth One Single Screenshot: Unifying Search With Visualized Information Retrieval","created":"2025-02-17","cited_by_count":8,"area":null},{"id":"2506.08074","title":"Hierarchical Lexical Graph for Enhanced Multi-Hop Retrieval","created":"2025-06-09","cited_by_count":7,"area":"rag"},{"id":"2605.18775","title":"Query-Aware Flow Diffusion for Graph-Based RAG with Retrieval Guarantees","created":"2026-04-21","cited_by_count":7,"area":"lr"},{"id":"2409.15699","title":"Lighter And Better: Towards Flexible Context Adaptation For Retrieval Augmented Generation","created":"2024-09-24","cited_by_count":6,"area":"rag"},{"id":"2501.09749","title":"Enhancing Lexicon-Based Text Embeddings with Large Language Models","created":"2025-01-16","cited_by_count":6,"area":null},{"id":"2509.03020","title":"Training LLMs to be Better Text Embedders through Bidirectional Reconstruction","created":"2025-09-03","cited_by_count":6,"area":null},{"id":"2410.20163","title":"UniHGKR: Unified Instruction-aware Heterogeneous Knowledge Retrievers","created":"2024-10-26","cited_by_count":5,"area":null},{"id":"2504.05220","title":"Utility-Focused LLM Annotation for Retrieval and Retrieval-Augmented Generation","created":"2025-04-07","cited_by_count":5,"area":"rag"},{"id":"2506.22900","title":"MOTOR: Multimodal Optimal Transport via Grounded Retrieval in Medical Visual Question Answering","created":"2025-06-28","cited_by_count":5,"area":null},{"id":"2507.07543","title":"The Cross-Lingual Cost: Retrieval Biases in RAG over Arabic-English Corpora","created":"2025-07-10","cited_by_count":5,"area":"rag"},{"id":"2508.00955","title":"From Generator to Embedder: Harnessing Innate Abilities of Multimodal LLMs via Building Zero-Shot Discriminative Embedding Model","created":"2025-08-01","cited_by_count":5,"area":"mllm"},{"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":"2501.13959","title":"Learning an Effective Premise Retrieval Model for Efficient Mathematical Formalization","created":"2025-01-21","cited_by_count":4,"area":null},{"id":"2503.14887","title":"Pseudo Relevance Feedback is Enough to Close the Gap Between Small and Large Dense Retrieval Models","created":"2025-03-19","cited_by_count":4,"area":null},{"id":"2506.03100","title":"Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds","created":"2025-06-03","cited_by_count":4,"area":"rag"},{"id":"2509.06444","title":"HyFedRAG: A Federated Retrieval-Augmented Generation Framework for Heterogeneous and Privacy-Sensitive Data","created":"2025-09-08","cited_by_count":4,"area":"rag"},{"id":"2511.15163","title":"Teaching According to Students' Aptitude: Personalized Mathematics Tutoring via Persona-, Memory-, and Forgetting-Aware LLMs","created":"2025-11-19","cited_by_count":3,"area":null},{"id":"2511.17129","title":"Learning to Compress: Unlocking the Potential of Large Language Models for Text Representation","created":"2025-11-21","cited_by_count":3,"area":null},{"id":"2512.03514","title":"M3DR: Towards Universal Multilingual Multimodal Document Retrieval","created":"2025-12-03","cited_by_count":3,"area":null},{"id":"2502.17036","title":"Language Model Re-rankers are Fooled by Lexical Similarities","created":"2025-02-24","cited_by_count":2,"area":"rag"},{"id":"2505.07166","title":"Pre-training vs. Fine-tuning: A Reproducibility Study on Dense Retrieval Knowledge Acquisition","created":"2025-05-12","cited_by_count":2,"area":null},{"id":"2508.18984","title":"Enhancing Document VQA Models via Retrieval-Augmented Generation","created":"2025-08-26","cited_by_count":2,"area":"mllm"},{"id":"2404.16248","title":"URL: Universal Referential Knowledge Linking via Task-instructed Representation Compression","created":"2024-04-24","cited_by_count":1,"area":null},{"id":"2409.06568","title":"Think-on-Process: Dynamic Process Generation for Collaborative Development of Multi-Agent System","created":"2024-09-10","cited_by_count":1,"area":"agents"},{"id":"2412.13205","title":"Adaptive Two-Phase Finetuning LLMs for Japanese Legal Text Retrieval","created":"2024-12-03","cited_by_count":1,"area":null},{"id":"2412.16615","title":"Large Language Model Can Be a Foundation for Hidden Rationale-Based Retrieval","created":"2024-12-21","cited_by_count":1,"area":"rag"},{"id":"2502.11770","title":"Cognitive-Aligned Document Selection for Retrieval-augmented Generation","created":"2025-02-17","cited_by_count":1,"area":"rag"},{"id":"2505.07345","title":"QUPID: Quantified Understanding for Enhanced Performance, Insights, and Decisions in Korean Search Engines","created":"2025-05-12","cited_by_count":1,"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":"2505.23250","title":"Deep Retrieval at CheckThat! 2025: Identifying Scientific Papers from Implicit Social Media Mentions via Hybrid Retrieval and Re-Ranking","created":"2025-05-29","cited_by_count":1,"area":null},{"id":"2507.02949","title":"RADIANT: Retrieval AugmenteD entIty-context AligNmenT -- Introducing RAG-ability and Entity-Context Divergence","created":"2025-06-28","cited_by_count":1,"area":"rag"},{"id":"2507.03958","title":"A Comparative Study of Specialized LLMs as Dense Retrievers","created":"2025-07-05","cited_by_count":1,"area":"mllm"},{"id":"2607.02387","title":"Bringing Agentic Search to Earth Observation Data Discovery","created":"2026-07-02","cited_by_count":1,"area":"agents"},{"id":"2609.18262","title":"REPAIR: Resolving Long-Tail Confusion in Scientific Retrievers via Fact-Verified Iterative Refinement","created":"2026-09-16","cited_by_count":1,"area":null},{"id":"2410.08352","title":"Revealing COVID-19's Social Dynamics: Diachronic Semantic Analysis of Vaccine and Symptom Discourse on Twitter","created":"2024-10-10","cited_by_count":0,"area":null},{"id":"2504.01309","title":"Biomedical Question Answering via Multi-Level Summarization on a Local Knowledge Graph","created":"2025-04-02","cited_by_count":0,"area":"rag"},{"id":"2504.20679","title":"Are Information Retrieval Approaches Good at Harmonising Longitudinal Survey Questions in Social Science?","created":"2025-04-29","cited_by_count":0,"area":null},{"id":"2505.21849","title":"Xinyu AI Search: Enhanced Relevance and Comprehensive Results with Rich Answer Presentations","created":"2025-05-28","cited_by_count":0,"area":null},{"id":"2506.12886","title":"ArgHiTZ at ArchEHR-QA 2025: A Two-Step Divide and Conquer Approach to Patient Question Answering for Top Factuality","created":"2025-06-15","cited_by_count":0,"area":null},{"id":"2510.10224","title":"Text2Token: Unsupervised Text Representation Learning with Token Target Prediction","created":"2025-10-11","cited_by_count":0,"area":null},{"id":"2511.04643","title":"When retrieval outperforms generation: Dense evidence retrieval for scalable fake news detection","created":"2025-11-06","cited_by_count":0,"area":null},{"id":"2604.03127","title":"Domain-Adapted Retrieval for In-Context Annotation of Pedagogical Dialogue Acts","created":"2026-04-03","cited_by_count":0,"area":null},{"id":"2604.16576","title":"On the Robustness of LLM-Based Dense Retrievers: A Systematic Analysis of Generalizability and Stability","created":"2026-04-17","cited_by_count":0,"area":null},{"id":"2604.23336","title":"Efficient Rationale-based Retrieval: On-policy Distillation from Generative Rerankers based on JEPA","created":"2026-04-25","cited_by_count":0,"area":"distill"},{"id":"2605.01372","title":"Embedding-based In-Context Prompt Training for Enhancing LLMs as Text Encoders","created":"2026-05-02","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":"2606.25674","title":"BitNet Text Embeddings","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2608.18988","title":"DeepWeaver: Bridging the Evidence Synthesis Gap in Open-Ended Question Answering","created":"2026-08-19","cited_by_count":0,"area":null},{"id":"2609.20563","title":"Reasoning Quality Matters: Combating Reasoning Collapse in LLM-based Embedding Learning","created":"2026-09-17","cited_by_count":0,"area":"lr"},{"id":"2610.05717","title":"Retrieval-Based In-Context Learning: A Domain Adaptation Framework","created":"2026-10-05","cited_by_count":0,"area":null}],"next_cursor":null}