{"total":87,"rows":[{"id":"2505.06120","title":"LLMs Get Lost In Multi-Turn Conversation","created":"2025-05-09","cited_by_count":429,"area":null},{"id":"2412.15204","title":"LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitasks","created":"2024-12-19","cited_by_count":379,"area":"lr"},{"id":"2410.02694","title":"HELMET: How to Evaluate Long-Context Language Models Effectively and Thoroughly","created":"2024-10-03","cited_by_count":125,"area":null},{"id":"2411.02305","title":"CRMArena: Understanding the Capacity of LLM Agents to Perform Professional CRM Tasks in Realistic Environments","created":"2024-11-04","cited_by_count":71,"area":"agents"},{"id":"2408.07702","title":"The Death of Schema Linking? Text-to-SQL in the Age of Well-Reasoned Language Models","created":"2024-08-14","cited_by_count":67,"area":"lr"},{"id":"2510.17800","title":"Glyph: Scaling Context Windows via Visual-Text Compression","created":"2025-10-20","cited_by_count":49,"area":null},{"id":"2501.05414","title":"LongProc: Benchmarking Long-Context Language Models on Long Procedural Generation","created":"2025-01-09","cited_by_count":29,"area":null},{"id":"2504.18838","title":"Toward Generalizable Evaluation in the LLM Era: A Survey Beyond Benchmarks","created":"2025-04-26","cited_by_count":28,"area":null},{"id":"2503.15620","title":"Does Context Matter? ContextualJudgeBench for Evaluating LLM-based Judges in Contextual Settings","created":"2025-03-19","cited_by_count":24,"area":null},{"id":"2411.03538","title":"Long Context RAG Performance of Large Language Models","created":"2024-11-05","cited_by_count":23,"area":null},{"id":"2412.06206","title":"SiReRAG: Indexing Similar and Related Information for Multihop Reasoning","created":"2024-12-09","cited_by_count":23,"area":"lr"},{"id":"2506.23139","title":"Benchmarking Deep Search over Heterogeneous Enterprise Data","created":"2025-06-29","cited_by_count":23,"area":"lr"},{"id":"2410.23609","title":"On Positional Bias of Faithfulness for Long-form Summarization","created":"2024-10-31","cited_by_count":22,"area":null},{"id":"2503.00353","title":"U-NIAH: Unified RAG and LLM Evaluation for Long Context Needle-In-A-Haystack","created":"2025-03-01","cited_by_count":20,"area":"rag"},{"id":"2503.01996","title":"One ruler to measure them all: Benchmarking multilingual long-context language models","created":"2025-03-03","cited_by_count":19,"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":"2410.13961","title":"From Single to Multi: How LLMs Hallucinate in Multi-Document Summarization","created":"2024-10-17","cited_by_count":17,"area":null},{"id":"2503.22732","title":"Reasoning Beyond Limits: Advances and Open Problems for LLMs","created":"2025-03-26","cited_by_count":16,"area":"lr"},{"id":"2407.15814","title":"Perceptions of Linguistic Uncertainty by Language Models and Humans","created":"2024-07-22","cited_by_count":15,"area":null},{"id":"2410.22349","title":"Search Engines in an AI Era: The False Promise of Factual and Verifiable Source-Cited Responses","created":"2024-10-15","cited_by_count":15,"area":null},{"id":"2410.04698","title":"MathHay: An Automated Benchmark for Long-Context Mathematical Reasoning in LLMs","created":"2024-10-07","cited_by_count":13,"area":"lr"},{"id":"2506.04156","title":"A Dataset for Addressing Patient's Information Needs related to Clinical Course of Hospitalization","created":"2025-06-04","cited_by_count":13,"area":null},{"id":"2411.05000","title":"Needle Threading: Can LLMs Follow Threads through Near-Million-Scale Haystacks?","created":"2024-11-07","cited_by_count":12,"area":null},{"id":"2502.14613","title":"Behavioral Analysis of Information Salience in Large Language Models","created":"2025-02-20","cited_by_count":12,"area":null},{"id":"2410.11996","title":"Holistic Reasoning with Long-Context LMs: A Benchmark for Database Operations on Massive Textual Data","created":"2024-10-15","cited_by_count":11,"area":"lr"},{"id":"2410.22316","title":"Understanding Synthetic Context Extension via Retrieval Heads","created":"2024-10-29","cited_by_count":10,"area":"rag"},{"id":"2503.13514","title":"RAG-KG-IL: A Multi-Agent Hybrid Framework for Reducing Hallucinations and Enhancing LLM Reasoning through RAG and Incremental Knowledge Graph Learning Integration","created":"2025-03-14","cited_by_count":9,"area":"lr"},{"id":"2603.04783","title":"Breaking Contextual Inertia: Reinforcement Learning with Single-Turn Anchors for Stable Multi-Turn Interaction","created":"2026-03-05","cited_by_count":9,"area":"lr"},{"id":"2604.15597","title":"LLMs Corrupt Your Documents When You Delegate","created":"2026-04-17","cited_by_count":9,"area":null},{"id":"2407.19794","title":"Introducing a new hyper-parameter for RAG: Context Window Utilization","created":"2024-07-29","cited_by_count":8,"area":"rag"},{"id":"2410.15531","title":"Do RAG Systems Cover What Matters? Evaluating and Optimizing Responses with Sub-Question Coverage","created":"2024-10-20","cited_by_count":8,"area":"rag"},{"id":"2411.19655","title":"Truth or Mirage? Towards End-to-End Factuality Evaluation with LLM-Oasis","created":"2024-11-29","cited_by_count":8,"area":null},{"id":"2505.19959","title":"MiniLongBench: The Low-cost Long Context Understanding Benchmark for Large Language Models","created":"2025-05-26","cited_by_count":8,"area":null},{"id":"2509.00877","title":"EviNote-RAG: Enhancing RAG Models via Answer-Supportive Evidence Notes","created":"2025-08-31","cited_by_count":8,"area":"rag"},{"id":"2510.14278","title":"PRISM: Agentic Retrieval with LLMs for Multi-Hop Question Answering","created":"2025-10-16","cited_by_count":8,"area":"agents"},{"id":"2511.03475","title":"ContextPilot: Fast Long-Context Inference via Context Reuse","created":"2025-11-05","cited_by_count":8,"area":"inference"},{"id":"2502.17611","title":"Evaluating the Effect of Retrieval Augmentation on Social Biases","created":"2025-02-24","cited_by_count":7,"area":"rag"},{"id":"2508.15396","title":"Attribution, Citation, and Quotation: A Survey of Evidence-based Text Generation with Large Language Models","created":"2025-08-21","cited_by_count":7,"area":null},{"id":"2502.14409","title":"Unstructured Evidence Attribution for Long Context Query Focused Summarization","created":"2025-02-20","cited_by_count":5,"area":null},{"id":"2510.13366","title":"Document Intelligence in the Era of Large Language Models: A Survey","created":"2025-10-15","cited_by_count":5,"area":null},{"id":"2410.01772","title":"DeFine: Decision-Making with Analogical Reasoning over Factor Profiles","created":"2024-10-02","cited_by_count":4,"area":"lr"},{"id":"2506.14580","title":"GenerationPrograms: Fine-grained Attribution with Executable Programs","created":"2025-06-17","cited_by_count":4,"area":null},{"id":"2509.00285","title":"OpinioRAG: Towards Generating User-Centric Opinion Highlights from Large-scale Online Reviews","created":"2025-08-30","cited_by_count":4,"area":null},{"id":"2509.00421","title":"Memory Limitations of Prompt Tuning in Transformers","created":"2025-08-30","cited_by_count":4,"area":null},{"id":"2510.14296","title":"Rethinking Schema Linking: A Context-Aware Bidirectional Retrieval Approach for Text-to-SQL","created":"2025-10-16","cited_by_count":4,"area":null},{"id":"2409.06338","title":"Retrieval Or Holistic Understanding? Dolce: Differentiate Our Long Context Evaluation Tasks","created":"2024-09-10","cited_by_count":3,"area":null},{"id":"2502.06617","title":"Scaling Multi-Document Event Summarization: Evaluating Compression vs. Full-Text Approaches","created":"2025-02-10","cited_by_count":3,"area":null},{"id":"2503.06868","title":"Lost-in-the-Middle in Long-Text Generation: Synthetic Dataset, Evaluation Framework, and Mitigation","created":"2025-03-10","cited_by_count":3,"area":"synth"},{"id":"2503.16575","title":"Extract, Match, and Score: An Evaluation Paradigm for Long Question-context-answer Triplets in Financial Analysis","created":"2025-03-20","cited_by_count":3,"area":null},{"id":"2508.05100","title":"BEE-RAG: Balanced Entropy Engineering for Retrieval-Augmented Generation","created":"2025-08-07","cited_by_count":3,"area":"rag"},{"id":"2510.00361","title":"Attribution Gradients: Incrementally Unfolding Citations for Critical Examination of Attributed AI Answers","created":"2025-10-01","cited_by_count":3,"area":null},{"id":"2605.25354","title":"Context-CoT: Enhancing Context Learning via High-Quality Reasoning Synthesis","created":"2026-05-25","cited_by_count":3,"area":"lr"},{"id":"2605.30251","title":"Same Evidence, Different Answers: Canonical-Context On-Policy Distillation for Multi-Turn Language Models","created":"2026-05-28","cited_by_count":3,"area":"distill"},{"id":"2410.20791","title":"From Cool Demos to Production-Ready FMware: Core Challenges and a Technology Roadmap","created":"2024-10-28","cited_by_count":2,"area":null},{"id":"2502.19779","title":"Do Retrieval-Augmented Language Models Adapt to Varying User Needs?","created":"2025-02-27","cited_by_count":2,"area":"rag"},{"id":"2503.04789","title":"Aligning Extraction and Generation for Robust Retrieval-Augmented Generation","created":"2025-02-28","cited_by_count":2,"area":"rag"},{"id":"2506.19897","title":"Can LLMs Replace Humans During Code Chunking?","created":"2025-06-24","cited_by_count":2,"area":null},{"id":"2507.09506","title":"Ref-Long: Benchmarking the Long-context Referencing Capability of Long-context Language Models","created":"2025-07-13","cited_by_count":2,"area":null},{"id":"2508.19578","title":"Towards a Holistic and Automated Evaluation Framework for Multi-Level Comprehension of LLMs in Book-Length Contexts","created":"2025-08-27","cited_by_count":2,"area":null},{"id":"2509.11492","title":"ClaimIQ at CheckThat! 2025: Comparing Prompted and Fine-Tuned Language Models for Verifying Numerical Claims","created":"2025-09-15","cited_by_count":2,"area":null},{"id":"2511.07689","title":"Stress Testing Factual Consistency Metrics for Long-Document Summarization","created":"2025-11-10","cited_by_count":2,"area":null},{"id":"2604.08782","title":"MT-OSC: Path for LLMs that Get Lost in Multi-Turn Conversation","created":"2026-04-09","cited_by_count":2,"area":null},{"id":"2410.13037","title":"LFOSum: Summarizing Long-form Opinions with Large Language Models","created":"2024-10-16","cited_by_count":1,"area":null},{"id":"2502.13753","title":"SCALAR: Scientific Citation-based Live Assessment of Long-context Academic Reasoning","created":"2025-02-19","cited_by_count":1,"area":"lr"},{"id":"2504.12972","title":"Estimating Optimal Context Length for Hybrid Retrieval-augmented Multi-document Summarization","created":"2025-04-17","cited_by_count":1,"area":"lr"},{"id":"2505.21419","title":"Diagnosing and Resolving Cloud Platform Instability with Multi-modal RAG LLMs","created":"2025-05-27","cited_by_count":1,"area":null},{"id":"2506.09657","title":"Team Anotheroption at SemEval-2025 Task 8: Bridging the Gap Between Open-Source and Proprietary LLMs in Table QA","created":"2025-06-11","cited_by_count":1,"area":null},{"id":"2512.13374","title":"Behavior and Representation in Open-Weight Large Language Models for Combinatorial Optimization: From Feature Extraction to Algorithm Selection","created":"2025-12-15","cited_by_count":1,"area":null},{"id":"2604.22335","title":"Context-Fidelity Boosting: Enhancing Faithful Generation through Watermark-Inspired Decoding","created":"2026-04-24","cited_by_count":1,"area":"safety"},{"id":"2605.25652","title":"A Two-Phase Stability Study of LLM Judges and Bar Council Examiners on Thai Bar-Exam Free-Form Essays","created":"2026-05-25","cited_by_count":1,"area":null},{"id":"2606.28379","title":"LEDGER: Scaling Agentic Document Editing with Dependency-aware Graph Retrieval","created":"2026-06-19","cited_by_count":1,"area":"agents"},{"id":"2609.03874","title":"STAIR (STructure Aware Information Retriever): A novel dataset and LLM based retriever for document structure augmentation","created":"2026-09-03","cited_by_count":1,"area":"rag"},{"id":"2609.05882","title":"What if LLMs Ate Their Words: Causal History Effects in Multi-Turn Interaction","created":"2026-09-05","cited_by_count":1,"area":null},{"id":"2504.08852","title":"ML For Hardware Design Interpretability: Challenges and Opportunities","created":"2025-04-11","cited_by_count":0,"area":null},{"id":"2507.07695","title":"KeyKnowledgeRAG (K^2RAG): An Enhanced RAG method for improved LLM question-answering capabilities","created":"2025-07-10","cited_by_count":0,"area":"rag"},{"id":"2509.09852","title":"Topic-Guided Reinforcement Learning with LLMs for Enhancing Multi-Document Summarization","created":"2025-09-11","cited_by_count":0,"area":null},{"id":"2509.13326","title":"LLM Chatbot-Creation Approaches","created":"2025-08-28","cited_by_count":0,"area":null},{"id":"2510.18297","title":"From Retrieval to Generation: Unifying External and Parametric Knowledge for Medical Question Answering","created":"2025-10-21","cited_by_count":0,"area":null},{"id":"2602.02539","title":"How Much Information Can a Vision Token Hold? A Scaling Law for Recognition Limits in VLMs","created":"2026-01-28","cited_by_count":0,"area":null},{"id":"2605.24366","title":"Structure-Aware RAG: Structured Retrieval Augmented Generation from Noisy Data for Conversational Agents","created":"2026-05-23","cited_by_count":0,"area":"rag"},{"id":"2606.07753","title":"ReadingMachine: A Computational Methodology for Structured Corpus Reading and Large-Scale Synthesis","created":"2026-06-05","cited_by_count":0,"area":null},{"id":"2606.25533","title":"Security and Privacy in Retrieval-Augmented Generation: Architectures, Threats, Defenses, and Future Directions for Building Trustworthy Systems","created":"2026-06-24","cited_by_count":0,"area":"rag"},{"id":"2607.22610","title":"Tokengeist: Multi-Turn Attribution Tracing in Agentic Conversations","created":"2026-06-14","cited_by_count":0,"area":"agents"},{"id":"2608.04286","title":"Eliciting Intrinsic Hallucinations in LLMs via Semantically Equivalent Adversarial Attacks","created":"2026-08-04","cited_by_count":0,"area":"rag"},{"id":"2608.28766","title":"Beyond Vector Search: Comparing Classical RAG with Hybrid GraphRAG for Climate Science Q\\&A","created":"2026-08-28","cited_by_count":0,"area":"rag"},{"id":"2609.19113","title":"Playing log(N)-Questions over Wikipedia Abstracts: How Per-Round Errors Compound Under Information Asymmetry","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.32520","title":"When Users Change Their Minds: Measuring and Repairing Intent Drift in LLM Agents","created":"2026-09-26","cited_by_count":0,"area":"agents"}],"next_cursor":null}