{"total":47,"rows":[{"id":"2410.14052","title":"From Isolated Conversations to Hierarchical Schemas: Dynamic Tree Memory Representation for LLMs","created":"2024-10-17","cited_by_count":79,"area":null},{"id":"2506.06541","title":"KramaBench: A Benchmark for AI Systems on Data-to-Insight Pipelines over Data Lakes","created":"2025-06-06","cited_by_count":33,"area":null},{"id":"2508.09303","title":"ParallelSearch: Train your LLMs to Decompose Query and Search Sub-queries in Parallel with Reinforcement Learning","created":"2025-08-12","cited_by_count":26,"area":null},{"id":"2506.07671","title":"GaRAGe: A Benchmark with Grounding Annotations for RAG Evaluation","created":"2025-06-09","cited_by_count":18,"area":null},{"id":"2406.06326","title":"Self-Tuning: Instructing LLMs to Effectively Acquire New Knowledge through Self-Teaching","created":"2024-06-10","cited_by_count":17,"area":null},{"id":"2406.14394","title":"SEC-QA: A Systematic Evaluation Corpus for Financial QA","created":"2024-06-20","cited_by_count":17,"area":null},{"id":"2502.01523","title":"CondAmbigQA: A Benchmark and Dataset for Conditional Ambiguous Question Answering","created":"2025-02-03","cited_by_count":15,"area":null},{"id":"2504.05571","title":"Knowledge-Instruct: Effective Continual Pre-training from Limited Data using Instructions","created":"2025-04-08","cited_by_count":12,"area":null},{"id":"2506.08354","title":"Position: Text Embeddings Should Capture Implicit Semantics, Not Just Surface Meaning","created":"2025-06-10","cited_by_count":10,"area":null},{"id":"2506.00264","title":"MultiHoax: A Dataset of Multi-hop False-Premise Questions","created":"2025-05-30","cited_by_count":9,"area":null},{"id":"2509.18868","title":"Memory in Large Language Models: Mechanisms, Evaluation and Evolution","created":"2025-09-23","cited_by_count":8,"area":null},{"id":"2408.14906","title":"Writing in the Margins: Better Inference Pattern for Long Context Retrieval","created":"2024-08-27","cited_by_count":7,"area":null},{"id":"2505.14212","title":"Automatic Dataset Generation for Knowledge Intensive Question Answering Tasks","created":"2025-05-20","cited_by_count":7,"area":null},{"id":"2410.13959","title":"FinQAPT: Empowering Financial Decisions with End-to-End LLM-driven Question Answering Pipeline","created":"2024-10-17","cited_by_count":6,"area":null},{"id":"2604.20572","title":"Ask Only When Needed: Proactive Retrieval from Memory and Skills for Experience-Driven Lifelong Agents","created":"2026-04-22","cited_by_count":4,"area":null},{"id":"2605.15156","title":"MeMo: Memory as a Model","created":"2026-05-14","cited_by_count":4,"area":null},{"id":"2412.12632","title":"What External Knowledge is Preferred by LLMs? Characterizing and Exploring Chain of Evidence in Imperfect Context for Multi-Hop QA","created":"2024-12-17","cited_by_count":3,"area":null},{"id":"2504.08756","title":"MHTS: Multi-Hop Tree Structure Framework for Generating Difficulty-Controllable QA Datasets for RAG Evaluation","created":"2025-03-29","cited_by_count":3,"area":null},{"id":"2505.23765","title":"From Chat Logs to Collective Insights: Aggregative Question Answering","created":"2025-05-29","cited_by_count":3,"area":null},{"id":"2601.08847","title":"Scalable and Reliable Evaluation of AI Knowledge Retrieval Systems: RIKER and the Coherent Simulated Universe","created":"2025-12-22","cited_by_count":3,"area":null},{"id":"2603.00801","title":"The Synthetic Web: Adversarially-Curated Mini-Internets for Diagnosing Epistemic Weaknesses of Language Agents","created":"2026-02-28","cited_by_count":3,"area":null},{"id":"2605.04523","title":"RaguTeam at SemEval-2026 Task 8: Meno and Friends in a Judge-Orchestrated LLM Ensemble for Faithful Multi-Turn Response Generation","created":"2026-05-06","cited_by_count":3,"area":null},{"id":"2503.07519","title":"GRITHopper: Decomposition-Free Multi-Hop Dense Retrieval","created":"2025-03-10","cited_by_count":2,"area":null},{"id":"2505.17156","title":"PersonaBOT: Bringing Customer Personas to Life with LLMs and RAG","created":"2025-05-22","cited_by_count":2,"area":null},{"id":"2509.02097","title":"JudgeAgent: Beyond Static Benchmarks for Knowledge-Driven and Dynamic LLM Evaluation","created":"2025-09-02","cited_by_count":2,"area":null},{"id":"2603.13168","title":"Developing and evaluating a chatbot to support maternal health care","created":"2026-03-13","cited_by_count":2,"area":null},{"id":"2603.17386","title":"PJB: A Reasoning-Aware Benchmark for Person-Job Retrieval","created":"2026-03-18","cited_by_count":2,"area":null},{"id":"2412.15101","title":"Review-Then-Refine: A Dynamic Framework for Multi-Hop Question Answering with Temporal Adaptability","created":"2024-12-19","cited_by_count":1,"area":null},{"id":"2501.06286","title":"Bactrainus: Optimizing Large Language Models for Multi-hop Complex Question Answering Tasks","created":"2025-01-10","cited_by_count":1,"area":null},{"id":"2503.00309","title":"Pseudo-Knowledge Graph: Meta-Path Guided Retrieval and In-Graph Text for RAG-Equipped LLM","created":"2025-03-01","cited_by_count":1,"area":null},{"id":"2505.11557","title":"AC-LoRA: (Almost) Training-Free Access Control-Aware Multi-Modal LLMs","created":"2025-05-15","cited_by_count":1,"area":null},{"id":"2509.07846","title":"Aligning LLMs for the Classroom with Knowledge-Based Retrieval -- A Comparative RAG Study","created":"2025-09-09","cited_by_count":1,"area":null},{"id":"2603.00460","title":"MED-COPILOT: A Medical Assistant Powered by GraphRAG and Similar Patient Case Retrieval","created":"2026-02-28","cited_by_count":1,"area":null},{"id":"2604.17943","title":"A Benchmark Construction and Evaluation Framework for Specialist Domains: Case Study on Defense-related Documents","created":"2026-04-20","cited_by_count":1,"area":null},{"id":"2606.17910","title":"Non-negative Elastic Net Decoding for Information Retrieval","created":"2026-06-16","cited_by_count":1,"area":null},{"id":"2501.00562","title":"An Overview and Discussion on Using Large Language Models for Implementation Generation of Solutions to Open-Ended Problems","created":"2024-12-31","cited_by_count":0,"area":null},{"id":"2504.07738","title":"Automated Construction of a Knowledge Graph of Nuclear Fusion Energy for Effective Elicitation and Retrieval of Information","created":"2025-04-10","cited_by_count":0,"area":null},{"id":"2506.07940","title":"Gradients: When Markets Meet Fine-tuning -- A Distributed Approach to Model Optimisation","created":"2025-06-09","cited_by_count":0,"area":null},{"id":"2603.22213","title":"SPA: A Simple but Tough-to-Beat Baseline for Knowledge Injection","created":"2026-03-23","cited_by_count":0,"area":null},{"id":"2604.03291","title":"RAGnaroX: A Secure, Local-Hosted ChatOps Assistant Using Small Language Models","created":"2026-03-27","cited_by_count":0,"area":null},{"id":"2605.02010","title":"Reliable AI Needs to Externalize Implicit Knowledge: A Human-AI Collaboration Perspective","created":"2026-05-03","cited_by_count":0,"area":null},{"id":"2605.10168","title":"ASTRA-QA: A Benchmark for Abstract Question Answering over Documents","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2607.03929","title":"Probe, Don't Prompt: A Hidden-State Probe for Metadata Filtering in Multi-Meta-RAG","created":"2026-07-04","cited_by_count":0,"area":null},{"id":"2608.05153","title":"Universal Pathologies, Conditional Consequences: A Triple-Robustness Analysis of RAG for Multi-Hop Traceability","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2608.11584","title":"EnterpriseRAG: Benchmarking LLM Instruction Adherence and Robustness under Non-Ideal Enterprise Retrieval","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2610.03063","title":"HARPO: Hallucination-Aware Reinforcement Learning for Faithful and Creative Language Generation","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.18786","title":"Where Do LLM Ensemble Gains Come From? Decomposing Candidate Value, Diversity, and Aggregation","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}