{"total":44,"rows":[{"id":"2506.05334","title":"Search Arena: Analyzing Search-Augmented LLMs","created":"2025-06-05","cited_by_count":34,"area":null},{"id":"2508.20033","title":"DeepScholar-Bench: A Live Benchmark and Automated Evaluation for Generative Research Synthesis","created":"2025-08-27","cited_by_count":34,"area":null},{"id":"2505.03739","title":"VITA-Audio: Fast Interleaved Cross-Modal Token Generation for Efficient Large Speech-Language Model","created":"2025-05-06","cited_by_count":31,"area":null},{"id":"2506.01829","title":"CiteEval: Principle-Driven Citation Evaluation for Source Attribution","created":"2025-06-02","cited_by_count":19,"area":null},{"id":"2411.13476","title":"When Precision Meets Position: BFloat16 Breaks Down RoPE in Long-Context Training","created":"2024-11-20","cited_by_count":15,"area":null},{"id":"2502.19103","title":"LongEval: A Comprehensive Analysis of Long-Text Generation Through a Plan-based Paradigm","created":"2025-02-26","cited_by_count":14,"area":null},{"id":"2604.27043","title":"CL-bench Life: Can Language Models Learn from Real-Life Context?","created":"2026-04-29","cited_by_count":9,"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":"2510.22548","title":"LooGLE v2: Are LLMs Ready for Real World Long Dependency Challenges?","created":"2025-10-26","cited_by_count":8,"area":null},{"id":"2502.06329","title":"Expect the Unexpected: FailSafe Long Context QA for Finance","created":"2025-02-10","cited_by_count":7,"area":null},{"id":"2505.18148","title":"Hidden in the Haystack: Smaller Needles are More Difficult for LLMs to Find","created":"2025-05-23","cited_by_count":7,"area":null},{"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":"2509.21557","title":"Generation-Time vs. Post-hoc Citation: A Holistic Evaluation of LLM Attribution","created":"2025-09-25","cited_by_count":6,"area":null},{"id":"2410.02115","title":"L-CiteEval: Do Long-Context Models Truly Leverage Context for Responding?","created":"2024-10-03","cited_by_count":5,"area":null},{"id":"2510.05862","title":"Revisiting Long-context Modeling from Context Denoising Perspective","created":"2025-10-07","cited_by_count":5,"area":null},{"id":"2510.10161","title":"Large Language Model Sourcing: A Survey","created":"2025-10-11","cited_by_count":5,"area":null},{"id":"2602.01766","title":"CoMeT: Collaborative Memory Transformer for Efficient Long Context Modeling","created":"2026-02-02","cited_by_count":5,"area":null},{"id":"2506.14580","title":"GenerationPrograms: Fine-grained Attribution with Executable Programs","created":"2025-06-17","cited_by_count":4,"area":null},{"id":"2503.07680","title":"Hierarchical Balance Packing: Towards Efficient Supervised Fine-tuning for Long-Context LLM","created":"2025-03-10","cited_by_count":2,"area":null},{"id":"2506.17585","title":"Cite Pretrain: Retrieval-Free Knowledge Attribution for Large Language Models","created":"2025-06-21","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":"2604.01432","title":"Are Finer Citations Always Better? Rethinking Granularity for Attributed Generation","created":"2026-04-01","cited_by_count":2,"area":null},{"id":"2503.02589","title":"MCiteBench: A Multimodal Benchmark for Generating Text with Citations","created":"2025-03-04","cited_by_count":1,"area":null},{"id":"2503.07170","title":"DeFine: A Decomposed and Fine-Grained Annotated Dataset for Long-form Article Generation","created":"2025-03-10","cited_by_count":1,"area":null},{"id":"2510.25766","title":"Decomposition-Enhanced Training for Post-Hoc Attributions In Language Models","created":"2025-10-29","cited_by_count":1,"area":null},{"id":"2607.00738","title":"Phantom References: Hallucinated Citations That Survive Peer Review at Top-Tier Conferences","created":"2026-07-01","cited_by_count":1,"area":null},{"id":"2607.24236","title":"CAGE: Cognitive Attribution Graphs for Faithful Inline Citation Generation in Long-Form Question Answering","created":"2026-07-27","cited_by_count":1,"area":null},{"id":"2501.02772","title":"GeAR: Generation Augmented Retrieval","created":"2025-01-06","cited_by_count":0,"area":null},{"id":"2506.23393","title":"Hierarchical Memory Organization for Wikipedia Generation","created":"2025-06-29","cited_by_count":0,"area":null},{"id":"2509.05331","title":"ForensicsData: A Digital Forensics Dataset for Large Language Models","created":"2025-08-31","cited_by_count":0,"area":null},{"id":"2509.06902","title":"Proof-Carrying Numbers (PCN): A Protocol for Trustworthy Numeric Answers from LLMs via Claim Verification","created":"2025-09-08","cited_by_count":0,"area":null},{"id":"2511.11597","title":"CLINB: A Climate Intelligence Benchmark for Foundational Models","created":"2025-10-29","cited_by_count":0,"area":null},{"id":"2601.03669","title":"eTracer: Polarity-Aware Evidence Grounding","created":"2026-01-07","cited_by_count":0,"area":null},{"id":"2601.08472","title":"sui-1: Grounded and Verifiable Long-Form Summarization","created":"2026-01-13","cited_by_count":0,"area":null},{"id":"2602.00004","title":"C$^2$-Cite: Contextual-Aware Citation Generation for Attributed Large Language Models","created":"2025-11-19","cited_by_count":0,"area":null},{"id":"2603.29353","title":"Nomad: Autonomous Exploration and Discovery","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2607.12257","title":"On-Device Deep Research at 4B: Exposure Bounds Faithfulness, Retrieval Bounds Coverage","created":"2026-07-14","cited_by_count":0,"area":null},{"id":"2608.03675","title":"VetScore: Risk-Weighted Fact Verification for Veterinary Long-Form QA with Citations","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2609.15964","title":"Verifiable by Construction: Claim-Level Evaluation of Verbatim Citation in Clinical Question Answering","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2609.27925","title":"Learning When Not to Listen: Selective Anti-Interference Pretraining for Language Models","created":"2026-08-22","cited_by_count":0,"area":null},{"id":"2609.31382","title":"Highlight-Then-Summarize: Learning to Compress Evidence for Long-Context Understanding","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.33642","title":"Learning to Learn from Context: Synthetic Training from Perturbed Public Documents","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.38766","title":"PathAnchor: Path-Structured Evidence for Scientific Agents","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.00606","title":"Where's Waldo? Query-language Preference under Cross-lingual Knowledge Disparities","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}