{"total":90,"rows":[{"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":"2407.02485","title":"RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMs","created":"2024-07-02","cited_by_count":202,"area":"rag"},{"id":"2501.01957","title":"VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction","created":"2025-01-03","cited_by_count":197,"area":"mllm"},{"id":"2407.14679","title":"Compact Language Models via Pruning and Knowledge Distillation","created":"2024-07-19","cited_by_count":148,"area":"distill"},{"id":"2406.11704","title":"Nemotron-4 340B Technical Report","created":"2024-06-17","cited_by_count":144,"area":null},{"id":"2406.07933","title":"Large Language Model Unlearning via Embedding-Corrupted Prompts","created":"2024-06-12","cited_by_count":116,"area":"safety"},{"id":"2407.01219","title":"Searching for Best Practices in Retrieval-Augmented Generation","created":"2024-07-01","cited_by_count":83,"area":"rag"},{"id":"2408.11796","title":"LLM Pruning and Distillation in Practice: The Minitron Approach","created":"2024-08-21","cited_by_count":82,"area":null},{"id":"2506.09033","title":"Router-R1: Teaching LLMs Multi-Round Routing and Aggregation via Reinforcement Learning","created":"2025-06-10","cited_by_count":72,"area":null},{"id":"2410.04343","title":"Inference Scaling for Long-Context Retrieval Augmented Generation","created":"2024-10-06","cited_by_count":65,"area":"rag"},{"id":"2407.14482","title":"ChatQA 2: Bridging the Gap to Proprietary LLMs in Long Context and RAG Capabilities","created":"2024-07-19","cited_by_count":53,"area":"rag"},{"id":"2503.05142","title":"RocketEval: Efficient Automated LLM Evaluation via Grading Checklist","created":"2025-03-07","cited_by_count":39,"area":null},{"id":"2402.11161","title":"PEDANTS: Cheap but Effective and Interpretable Answer Equivalence","created":"2024-02-17","cited_by_count":31,"area":null},{"id":"2410.17952","title":"SimRAG: Self-Improving Retrieval-Augmented Generation for Adapting Large Language Models to Specialized Domains","created":"2024-10-23","cited_by_count":28,"area":"rag"},{"id":"2506.08938","title":"FaithfulRAG: Fact-Level Conflict Modeling for Context-Faithful Retrieval-Augmented Generation","created":"2025-06-10","cited_by_count":28,"area":"rag"},{"id":"2505.20096","title":"MA-RAG: Multi-Agent Retrieval-Augmented Generation via Collaborative Chain-of-Thought Reasoning","created":"2025-05-26","cited_by_count":26,"area":"lr"},{"id":"2501.00353","title":"RAG-Instruct: Boosting LLMs with Diverse Retrieval-Augmented Instructions","created":"2024-12-31","cited_by_count":25,"area":"rag"},{"id":"2412.14964","title":"Efficient Knowledge Injection in LLMs via Self-Distillation","created":"2024-12-19","cited_by_count":24,"area":"distill"},{"id":"2412.13746","title":"RAG-RewardBench: Benchmarking Reward Models in Retrieval Augmented Generation for Preference Alignment","created":"2024-12-18","cited_by_count":23,"area":"rag"},{"id":"2502.18934","title":"Kanana: Compute-efficient Bilingual Language Models","created":"2025-02-26","cited_by_count":20,"area":null},{"id":"2504.04915","title":"Collab-RAG: Boosting Retrieval-Augmented Generation for Complex Question Answering via White-Box and Black-Box LLM Collaboration","created":"2025-04-07","cited_by_count":20,"area":"lr"},{"id":"2406.10991","title":"Adaptive Query Rewriting: Aligning Rewriters through Marginal Probability of Conversational Answers","created":"2024-06-16","cited_by_count":15,"area":"alignment"},{"id":"2505.07233","title":"DynamicRAG: Leveraging Outputs of Large Language Model as Feedback for Dynamic Reranking in Retrieval-Augmented Generation","created":"2025-05-12","cited_by_count":15,"area":"rag"},{"id":"2406.07348","title":"DR-RAG: Applying Dynamic Document Relevance to Retrieval-Augmented Generation for Question-Answering","created":"2024-06-11","cited_by_count":14,"area":"rag"},{"id":"2409.05152","title":"OneGen: Efficient One-Pass Unified Generation and Retrieval for LLMs","created":"2024-09-08","cited_by_count":14,"area":null},{"id":"2410.13716","title":"MIRAGE-Bench: Automatic Multilingual Benchmark Arena for Retrieval-Augmented Generation Systems","created":"2024-10-17","cited_by_count":14,"area":"rag"},{"id":"2505.20871","title":"Divide-Then-Align: Honest Alignment based on the Knowledge Boundary of RAG","created":"2025-05-27","cited_by_count":14,"area":"rag"},{"id":"2603.20432","title":"Coding Agents are Effective Long-Context Processors","created":"2026-03-20","cited_by_count":12,"area":"agents"},{"id":"2604.23626","title":"GraphPlanner: Graph Memory-Augmented Agentic Routing for Multi-Agent LLMs","created":"2026-04-26","cited_by_count":12,"area":"agents"},{"id":"2502.18139","title":"LevelRAG: Enhancing Retrieval-Augmented Generation with Multi-hop Logic Planning over Rewriting Augmented Searchers","created":"2025-02-25","cited_by_count":11,"area":"rag"},{"id":"2505.20128","title":"Iterative Self-Incentivization Empowers Large Language Models as Agentic Searchers","created":"2025-05-26","cited_by_count":11,"area":"agents"},{"id":"2511.18659","title":"CLaRa: Bridging Retrieval and Generation with Continuous Latent Reasoning","created":"2025-11-24","cited_by_count":11,"area":"lr"},{"id":"2507.10540","title":"FusionFactory: Fusing LLM Capabilities with Multi-LLM Log Data","created":"2025-07-14","cited_by_count":10,"area":null},{"id":"2604.09557","title":"SPEED-Bench: A Unified and Diverse Benchmark for Speculative Decoding","created":"2026-02-10","cited_by_count":10,"area":"inference"},{"id":"2502.13233","title":"SearchRAG: Can Search Engines Be Helpful for LLM-based Medical Question Answering?","created":"2025-02-18","cited_by_count":9,"area":null},{"id":"2505.03075","title":"Direct Retrieval-augmented Optimization: Synergizing Knowledge Selection and Language Models","created":"2025-05-05","cited_by_count":9,"area":"rag"},{"id":"2509.03934","title":"SelfAug: Mitigating Catastrophic Forgetting in Retrieval-Augmented Generation via Distribution Self-Alignment","created":"2025-09-04","cited_by_count":9,"area":"rag"},{"id":"2405.17088","title":"Phase Transitions in the Output Distribution of Large Language Models","created":"2024-05-27","cited_by_count":7,"area":null},{"id":"2410.03780","title":"Reward-RAG: Enhancing RAG with Reward Driven Supervision","created":"2024-10-03","cited_by_count":7,"area":"rag"},{"id":"2501.17132","title":"ASTRAL: Automated Safety Testing of Large Language Models","created":"2025-01-28","cited_by_count":7,"area":null},{"id":"2504.03101","title":"Single-Pass Document Scanning for Question Answering","created":"2025-04-04","cited_by_count":6,"area":null},{"id":"2507.05714","title":"HIRAG: Hierarchical-Thought Instruction-Tuning Retrieval-Augmented Generation","created":"2025-07-08","cited_by_count":6,"area":"lr"},{"id":"2408.02545","title":"RAG Foundry: A Framework for Enhancing LLMs for Retrieval Augmented Generation","created":"2024-08-05","cited_by_count":5,"area":"rag"},{"id":"2509.06274","title":"IPR: Intelligent Prompt Routing with User-Controlled Quality-Cost Trade-offs","created":"2025-09-08","cited_by_count":5,"area":null},{"id":"2406.17305","title":"Retrieval Augmented Instruction Tuning for Open NER with Large Language Models","created":"2024-06-25","cited_by_count":4,"area":"rag"},{"id":"2409.04181","title":"Combining LLMs and Knowledge Graphs to Reduce Hallucinations in Question Answering","created":"2024-09-06","cited_by_count":4,"area":null},{"id":"2503.08398","title":"OpenRAG: Optimizing RAG End-to-End via In-Context Retrieval Learning","created":"2025-03-11","cited_by_count":4,"area":"rag"},{"id":"2506.05766","title":"BioMol-MQA: A Multi-Modal Question Answering Dataset For LLM Reasoning Over Bio-Molecular Interactions","created":"2025-06-06","cited_by_count":4,"area":"lr"},{"id":"2510.11496","title":"AndesVL Technical Report: An Efficient Mobile-side Multimodal Large Language Model","created":"2025-10-13","cited_by_count":4,"area":"mllm"},{"id":"2505.04680","title":"Retrieval Augmented Generation Evaluation for Health Documents","created":"2025-05-07","cited_by_count":3,"area":"rag"},{"id":"2604.00901","title":"Experience as a Compass: Multi-agent RAG with Evolving Orchestration and Agent Prompts","created":"2026-04-01","cited_by_count":3,"area":"rag"},{"id":"2502.05497","title":"DeepThink: Aligning Language Models with Domain-Specific User Intents","created":"2025-02-08","cited_by_count":2,"area":"lr"},{"id":"2505.01307","title":"Document Retrieval Augmented Fine-Tuning (DRAFT) for safety-critical software assessments","created":"2025-05-02","cited_by_count":2,"area":"rag"},{"id":"2505.14978","title":"JARVIS: A Multi-Agent Code Assistant for High-Quality EDA Script Generation","created":"2025-05-20","cited_by_count":2,"area":"agents"},{"id":"2507.13625","title":"Bridging Dual Knowledge Graphs for Multi-Hop Question Answering in Construction Safety","created":"2025-07-18","cited_by_count":2,"area":null},{"id":"2512.06255","title":"Language-driven Fine-grained Retrieval","created":"2025-12-06","cited_by_count":2,"area":null},{"id":"2601.01718","title":"Yuan3.0 Flash: An Open Multimodal Large Language Model for Enterprise Applications","created":"2026-01-05","cited_by_count":2,"area":"lr"},{"id":"2601.11443","title":"Predict the Retrieval! Test time adaptation for Retrieval Augmented Generation","created":"2026-01-16","cited_by_count":2,"area":"rag"},{"id":"2410.15005","title":"CAP: Data Contamination Detection via Consistency Amplification","created":"2024-10-19","cited_by_count":1,"area":null},{"id":"2501.00874","title":"LUSIFER: Language Universal Space Integration for Enhanced Multilingual Embeddings with Large Language Models","created":"2025-01-01","cited_by_count":1,"area":null},{"id":"2502.03618","title":"The Logical Implication Steering Method for Conditional Interventions on Transformer Generation","created":"2025-02-05","cited_by_count":1,"area":"mechinterp"},{"id":"2502.12502","title":"Efficient OpAmp Adaptation for Zoom Attention to Golden Contexts","created":"2025-02-18","cited_by_count":1,"area":"rag"},{"id":"2505.10493","title":"DACL-RAG: Data Augmentation Strategy with Curriculum Learning for Retrieval-Augmented Generation","created":"2025-05-15","cited_by_count":1,"area":"rag"},{"id":"2506.19385","title":"CID-GraphRAG: Enhancing Multi-Turn Dialogue Systems through Dual-Pathway Retrieval of Conversation Flow and Context Semantics","created":"2025-06-24","cited_by_count":1,"area":"rag"},{"id":"2509.05716","title":"A Survey of the State-of-the-Art in Conversational Question Answering Systems","created":"2025-09-06","cited_by_count":1,"area":null},{"id":"2509.17788","title":"One Agent to Serve All: a Lite-Adaptive Stylized AI Assistant for Millions of Multi-Style Official Accounts","created":"2025-09-22","cited_by_count":1,"area":null},{"id":"2510.24652","title":"Optimizing Retrieval for RAG via Reinforcement Learning","created":"2025-10-28","cited_by_count":1,"area":"lr"},{"id":"2602.09843","title":"Kelix Technical Report","created":"2026-02-10","cited_by_count":1,"area":null},{"id":"2604.02091","title":"Optimizing RAG Rerankers with LLM Feedback via Reinforcement Learning","created":"2026-04-02","cited_by_count":1,"area":"rag"},{"id":"2604.06831","title":"Towards Privacy-Preserving Large Language Model: Text-free Inference Through Alignment and Adaptation","created":"2026-04-08","cited_by_count":1,"area":null},{"id":"2608.17605","title":"Multi-turn Conversational AI from Text to Multimodal Interaction: Data, Models, Evaluation, and Open Challenges","created":"2026-08-18","cited_by_count":1,"area":null},{"id":"2608.28978","title":"Selective Forgetting: A Graph-Based Memory Framework for Long-Term LLM Agents","created":"2026-08-29","cited_by_count":1,"area":"rag"},{"id":"2405.01924","title":"Semi-Parametric Retrieval via Binary Bag-of-Tokens Index","created":"2024-05-03","cited_by_count":0,"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":"2508.17225","title":"SSFO: Self-Supervised Faithfulness Optimization for Retrieval-Augmented Generation","created":"2025-08-24","cited_by_count":0,"area":"rag"},{"id":"2511.04880","title":"DMA: Online RAG Alignment with Human Feedback","created":"2025-11-06","cited_by_count":0,"area":"rag"},{"id":"2511.15719","title":"Chain of Summaries: Summarization Through Iterative Questioning","created":"2025-11-12","cited_by_count":0,"area":null},{"id":"2601.14327","title":"Yuan3.0 Ultra: A Trillion-Parameter Enterprise-Oriented MoE LLM","created":"2026-01-20","cited_by_count":0,"area":"moe"},{"id":"2602.05152","title":"RAG without Forgetting: Continual Query-Infused Key Memory","created":"2026-02-05","cited_by_count":0,"area":"rag"},{"id":"2602.09552","title":"Comprehensive Comparison of RAG Methods Across Multi-Domain Conversational QA","created":"2026-02-10","cited_by_count":0,"area":"rag"},{"id":"2603.23047","title":"Parametric Knowledge in RAG-SFT for Domain-Specific Document Generation","created":"2026-03-24","cited_by_count":0,"area":"rag"},{"id":"2604.03924","title":"Uncertainty as a Planning Signal: Multi-Turn Decision Making for Goal-Oriented Conversation","created":"2026-04-05","cited_by_count":0,"area":null},{"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":"2605.20729","title":"MTR-Suite: A Framework for Evaluating and Synthesizing Conversational Retrieval Benchmarks","created":"2026-05-20","cited_by_count":0,"area":"rag"},{"id":"2606.28737","title":"5ting at SemEval-2026 Task 8: Strong End-to-End Multi-Turn RAG via LLM-Based Reranking and Faithfulness Control","created":"2026-06-27","cited_by_count":0,"area":"rag"},{"id":"2607.22621","title":"Opti-Q: A Constraint-Based Optimization Framework for Multi-LLM Question Planning","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2607.26470","title":"CMT-RAG: Complementary Memory Traces for Multi-turn Multi-hop RAG","created":"2026-07-29","cited_by_count":0,"area":"lr"},{"id":"2608.27661","title":"Knowing Before Answering: Decoding Language Models for Reliable RAG","created":"2026-08-27","cited_by_count":0,"area":"rag"},{"id":"2609.31130","title":"Do we need to answer that question? Salience and Answerability of Potential Questions in Naturalistic Dialogue","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.36651","title":"FocusVTC: Efficient and High-Performance Visual Text Compression with Adaptive Resolution","created":"2026-09-29","cited_by_count":0,"area":"lr"}],"next_cursor":null}