{"total":119,"rows":[{"id":"2311.12022","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","created":"2023-11-20","cited_by_count":2879,"area":null},{"id":"2309.16039","title":"Effective Long-Context Scaling of Foundation Models","created":"2023-09-27","cited_by_count":303,"area":null},{"id":"2205.05131","title":"UL2: Unifying Language Learning Paradigms","created":"2022-05-10","cited_by_count":295,"area":null},{"id":"2203.11147","title":"Teaching language models to support answers with verified quotes","created":"2022-03-21","cited_by_count":292,"area":null},{"id":"2307.11088","title":"L-Eval: Instituting Standardized Evaluation for Long Context Language Models","created":"2023-07-20","cited_by_count":233,"area":null},{"id":"2211.03540","title":"Measuring Progress on Scalable Oversight for Large Language Models","created":"2022-11-04","cited_by_count":225,"area":null},{"id":"2305.14196","title":"ZeroSCROLLS: A Zero-Shot Benchmark for Long Text Understanding","created":"2023-05-23","cited_by_count":176,"area":null},{"id":"2201.03533","title":"SCROLLS: Standardized CompaRison Over Long Language Sequences","created":"2022-01-10","cited_by_count":170,"area":null},{"id":"2310.05029","title":"Walking Down the Memory Maze: Beyond Context Limit through Interactive Reading","created":"2023-10-08","cited_by_count":133,"area":null},{"id":"2310.05209","title":"Scaling Laws of RoPE-based Extrapolation","created":"2023-10-08","cited_by_count":125,"area":null},{"id":"2310.12963","title":"AutoMix: Automatically Mixing Language Models","created":"2023-10-19","cited_by_count":125,"area":null},{"id":"2310.03025","title":"Retrieval meets Long Context Large Language Models","created":"2023-10-04","cited_by_count":115,"area":null},{"id":"2407.04622","title":"On scalable oversight with weak LLMs judging strong LLMs","created":"2024-07-05","cited_by_count":99,"area":null},{"id":"2304.11062","title":"Scaling Transformer to 1M tokens and beyond with RMT","created":"2023-04-19","cited_by_count":98,"area":null},{"id":"2407.13692","title":"Prover-Verifier Games improve legibility of LLM outputs","created":"2024-07-18","cited_by_count":85,"area":null},{"id":"2303.09752","title":"CoLT5: Faster Long-Range Transformers with Conditional Computation","created":"2023-03-17","cited_by_count":84,"area":null},{"id":"2402.16617","title":"Long-Context Language Modeling with Parallel Context Encoding","created":"2024-02-26","cited_by_count":84,"area":null},{"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":"2409.07146","title":"Gated Slot Attention for Efficient Linear-Time Sequence Modeling","created":"2024-09-11","cited_by_count":76,"area":null},{"id":"2310.14735","title":"Unleashing the potential of prompt engineering for large language models","created":"2023-10-23","cited_by_count":72,"area":null},{"id":"2208.00748","title":"Efficient Long-Text Understanding with Short-Text Models","created":"2022-08-01","cited_by_count":71,"area":null},{"id":"2410.18745","title":"Why Does the Effective Context Length of LLMs Fall Short?","created":"2024-10-24","cited_by_count":63,"area":null},{"id":"2402.17463","title":"Training-Free Long-Context Scaling of Large Language Models","created":"2024-02-27","cited_by_count":62,"area":null},{"id":"2407.21792","title":"Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress?","created":"2024-07-31","cited_by_count":61,"area":null},{"id":"2409.07431","title":"Synthetic continued pretraining","created":"2024-09-11","cited_by_count":60,"area":null},{"id":"2309.13345","title":"BAMBOO: A Comprehensive Benchmark for Evaluating Long Text Modeling Capacities of Large Language Models","created":"2023-09-23","cited_by_count":53,"area":null},{"id":"2502.14127","title":"Which of These Best Describes Multiple Choice Evaluation with LLMs? A) Forced B) Flawed C) Fixable D) All of the Above","created":"2025-02-19","cited_by_count":52,"area":null},{"id":"2205.11465","title":"SQuALITY: Building a Long-Document Summarization Dataset the Hard Way","created":"2022-05-23","cited_by_count":50,"area":null},{"id":"2404.03602","title":"Evaluating LLMs at Detecting Errors in LLM Responses","created":"2024-04-04","cited_by_count":50,"area":null},{"id":"2210.05529","title":"An Exploration of Hierarchical Attention Transformers for Efficient Long Document Classification","created":"2022-10-11","cited_by_count":38,"area":null},{"id":"2407.10701","title":"DOCBENCH: A Benchmark for Evaluating LLM-based Document Reading Systems","created":"2024-07-15","cited_by_count":37,"area":null},{"id":"2408.11865","title":"How Susceptible are LLMs to Influence in Prompts?","created":"2024-08-17","cited_by_count":33,"area":null},{"id":"2602.16763","title":"When AI Benchmarks Plateau: A Systematic Study of Benchmark Saturation","created":"2026-02-18","cited_by_count":33,"area":null},{"id":"2403.12766","title":"NovelQA: Benchmarking Question Answering on Documents Exceeding 200K Tokens","created":"2024-03-18","cited_by_count":32,"area":null},{"id":"2301.12307","title":"MQAG: Multiple-choice Question Answering and Generation for Assessing Information Consistency in Summarization","created":"2023-01-28","cited_by_count":30,"area":null},{"id":"2404.10308","title":"Hierarchical Context Merging: Better Long Context Understanding for Pre-trained LLMs","created":"2024-04-16","cited_by_count":30,"area":null},{"id":"2504.17768","title":"The Sparse Frontier: Sparse Attention Trade-offs in Transformer LLMs","created":"2025-04-24","cited_by_count":29,"area":null},{"id":"2406.11852","title":"Risks from Language Models for Automated Mental Healthcare: Ethics and Structure for Implementation","created":"2024-04-02","cited_by_count":27,"area":null},{"id":"2401.16421","title":"Two Stones Hit One Bird: Bilevel Positional Encoding for Better Length Extrapolation","created":"2024-01-29","cited_by_count":24,"area":null},{"id":"2503.08727","title":"Training Plug-n-Play Knowledge Modules with Deep Context Distillation","created":"2025-03-11","cited_by_count":24,"area":null},{"id":"2204.05212","title":"Single-Turn Debate Does Not Help Humans Answer Hard Reading-Comprehension Questions","created":"2022-04-11","cited_by_count":23,"area":null},{"id":"2405.00982","title":"On the Evaluation of Machine-Generated Reports","created":"2024-05-02","cited_by_count":23,"area":null},{"id":"2202.07856","title":"The NLP Task Effectiveness of Long-Range Transformers","created":"2022-02-16","cited_by_count":22,"area":null},{"id":"2209.10052","title":"Adapting Pretrained Text-to-Text Models for Long Text Sequences","created":"2022-09-21","cited_by_count":21,"area":null},{"id":"2204.10878","title":"ChapterBreak: A Challenge Dataset for Long-Range Language Models","created":"2022-04-22","cited_by_count":18,"area":null},{"id":"2210.10860","title":"Two-Turn Debate Doesn't Help Humans Answer Hard Reading Comprehension Questions","created":"2022-10-19","cited_by_count":17,"area":null},{"id":"2406.19598","title":"Mixture of In-Context Experts Enhance LLMs' Long Context Awareness","created":"2024-06-28","cited_by_count":17,"area":null},{"id":"2502.00919","title":"Attention Sinks: A 'Catch, Tag, Release' Mechanism for Embeddings","created":"2025-02-02","cited_by_count":16,"area":null},{"id":"2505.03989","title":"An alignment safety case sketch based on debate","created":"2025-05-06","cited_by_count":16,"area":null},{"id":"2311.16989","title":"ChatGPT's One-year Anniversary: Are Open-Source Large Language Models Catching up?","created":"2023-11-28","cited_by_count":15,"area":null},{"id":"2406.18312","title":"AI-native Memory: A Pathway from LLMs Towards AGI","created":"2024-06-26","cited_by_count":12,"area":null},{"id":"2603.01097","title":"Understanding LoRA as Knowledge Memory: An Empirical Analysis","created":"2026-03-01","cited_by_count":12,"area":null},{"id":"2402.00857","title":"Early Time Classification with Accumulated Accuracy Gap Control","created":"2024-02-01","cited_by_count":11,"area":null},{"id":"2202.07362","title":"MuLD: The Multitask Long Document Benchmark","created":"2022-02-15","cited_by_count":9,"area":null},{"id":"2308.13191","title":"Chunk, Align, Select: A Simple Long-sequence Processing Method for Transformers","created":"2023-08-25","cited_by_count":9,"area":null},{"id":"2309.08210","title":"Investigating Answerability of LLMs for Long-Form Question Answering","created":"2023-09-15","cited_by_count":9,"area":null},{"id":"2411.05928","title":"Reducing Distraction in Long-Context Language Models by Focused Learning","created":"2024-11-08","cited_by_count":9,"area":null},{"id":"2504.16795","title":"Hardware-aligned Hierarchical Sparse Attention for Efficient Long-term Memory Access","created":"2025-04-23","cited_by_count":9,"area":null},{"id":"2204.04991","title":"TRUE: Re-evaluating Factual Consistency Evaluation","created":"2022-04-11","cited_by_count":8,"area":null},{"id":"2406.13161","title":"APPL: A Prompt Programming Language for Harmonious Integration of Programs and Large Language Model Prompts","created":"2024-06-19","cited_by_count":8,"area":null},{"id":"2501.01705","title":"The Essence of Contextual Understanding in Theory of Mind: A Study on Question Answering with Story Characters","created":"2025-01-03","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":"2510.23948","title":"ChessQA: Evaluating Large Language Models for Chess Understanding","created":"2025-10-28","cited_by_count":8,"area":null},{"id":"2407.11789","title":"Large Language Models as Misleading Assistants in Conversation","created":"2024-07-16","cited_by_count":7,"area":null},{"id":"2410.12049","title":"Sabi\\'a-3 Technical Report","created":"2024-10-15","cited_by_count":7,"area":null},{"id":"2506.06313","title":"Beyond Chunking: Discourse-Aware Hierarchical Retrieval for Long Document Question Answering","created":"2025-05-26","cited_by_count":7,"area":null},{"id":"2603.18534","title":"Data-efficient pre-training by scaling synthetic megadocs","created":"2026-03-19","cited_by_count":7,"area":null},{"id":"2211.07040","title":"World Knowledge in Multiple Choice Reading Comprehension","created":"2022-11-13","cited_by_count":6,"area":null},{"id":"2305.04241","title":"Vcc: Scaling Transformers to 128K Tokens or More by Prioritizing Important Tokens","created":"2023-05-07","cited_by_count":6,"area":null},{"id":"2312.04792","title":"Playing Large Games with Oracles and AI Debate","created":"2023-12-08","cited_by_count":6,"area":null},{"id":"2406.13167","title":"QRMeM: Unleash the Length Limitation through Question then Reflection Memory Mechanism","created":"2024-06-19","cited_by_count":6,"area":null},{"id":"2407.08330","title":"HDT: Hierarchical Document Transformer","created":"2024-07-11","cited_by_count":6,"area":null},{"id":"2502.14644","title":"LIFT: A Novel Framework for Enhancing Long-Context Understanding of LLMs via Long Input Fine-Tuning","created":"2025-02-20","cited_by_count":6,"area":null},{"id":"2503.15450","title":"SkyLadder: Better and Faster Pretraining via Context Window Scheduling","created":"2025-03-19","cited_by_count":6,"area":null},{"id":"2512.05379","title":"Mitigating Self-Preference by Authorship Obfuscation","created":"2025-12-05","cited_by_count":6,"area":null},{"id":"2509.05276","title":"SpikingBrain: Spiking Brain-inspired Large Models","created":"2025-09-05","cited_by_count":5,"area":null},{"id":"2601.22548","title":"Are LLM Evaluators Really Narcissists? Sanity Checking Self-Preference Evaluations","created":"2026-01-30","cited_by_count":5,"area":null},{"id":"2210.11870","title":"LittleBird: Efficient Faster & Longer Transformer for Question Answering","created":"2022-10-21","cited_by_count":4,"area":null},{"id":"2211.05044","title":"What is Wrong with Language Models that Can Not Tell a Story?","created":"2022-11-09","cited_by_count":4,"area":null},{"id":"2503.05856","title":"This Is Your Doge, If It Please You: Exploring Deception and Robustness in Mixture of LLMs","created":"2025-03-07","cited_by_count":4,"area":null},{"id":"2601.20131","title":"Taxonomy of the Retrieval System Framework: Pitfalls and Paradigms","created":"2026-01-27","cited_by_count":4,"area":null},{"id":"2603.25340","title":"Large Language Model as Token Compressor and Decompressor","created":"2026-03-26","cited_by_count":4,"area":null},{"id":"2610.02076","title":"LLM-as-Jev: LLMs Are Already Jev-Style Decision Models -- When and How to Fine-Tune Them","created":"2026-10-01","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":"2503.01820","title":"RSQ: Learning from Important Tokens Leads to Better Quantized LLMs","created":"2025-03-03","cited_by_count":3,"area":null},{"id":"2503.22989","title":"FindTheFlaws: Annotated Errors for Detecting Flawed Reasoning and Scalable Oversight Research","created":"2025-03-29","cited_by_count":3,"area":null},{"id":"2505.24179","title":"SALE : Low-bit Estimation for Efficient Sparse Attention in Long-context LLM Prefilling","created":"2025-05-30","cited_by_count":3,"area":null},{"id":"2305.07565","title":"A Memory Model for Question Answering from Streaming Data Supported by Rehearsal and Anticipation of Coreference Information","created":"2023-05-12","cited_by_count":2,"area":null},{"id":"2305.13877","title":"NarrativeXL: A Large-scale Dataset For Long-Term Memory Models","created":"2023-05-23","cited_by_count":2,"area":null},{"id":"2402.16986","title":"Long Dialog Summarization: An Analysis","created":"2024-02-26","cited_by_count":2,"area":null},{"id":"2603.12249","title":"SciMDR: Advancing Scientific Multimodal Document Reasoning","created":"2026-03-12","cited_by_count":2,"area":null},{"id":"2310.08072","title":"Training Generative Question-Answering on Synthetic Data Obtained from an Instruct-tuned Model","created":"2023-10-12","cited_by_count":1,"area":null},{"id":"2408.02439","title":"Long Input Benchmark for Russian Analysis","created":"2024-08-05","cited_by_count":1,"area":null},{"id":"2505.21859","title":"Principled Content Selection to Generate Diverse and Personalized Multi-Document Summaries","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2505.24033","title":"Studying the Soupability of Documents in State Space Models","created":"2025-05-29","cited_by_count":1,"area":null},{"id":"2512.08082","title":"Short-Context Dominance: How Much Local Context Natural Language Actually Needs?","created":"2025-12-08","cited_by_count":1,"area":null},{"id":"2605.27483","title":"Debate Helps Weak Judges Reward Stronger Models","created":"2026-05-26","cited_by_count":1,"area":null},{"id":"2606.19857","title":"Large Language Models Do Not Always Need Readable Language","created":"2026-06-18","cited_by_count":1,"area":null},{"id":"2306.02334","title":"Long Text Generation Challenge","created":"2023-06-04","cited_by_count":0,"area":null},{"id":"2306.08667","title":"When to Use Efficient Self Attention? Profiling Text, Speech and Image Transformer Variants","created":"2023-06-14","cited_by_count":0,"area":null}],"next_cursor":"100"}