{"total":208,"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":"2312.10997","title":"Retrieval-Augmented Generation for Large Language Models: A Survey","created":"2023-12-18","cited_by_count":2212,"area":"lr"},{"id":"2207.05221","title":"Language Models (Mostly) Know What They Know","created":"2022-07-11","cited_by_count":1856,"area":"lr"},{"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":"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":"2406.02818","title":"Chain of Agents: Large Language Models Collaborating on Long-Context Tasks","created":"2024-06-04","cited_by_count":206,"area":"agents"},{"id":"2503.16416","title":"Survey on Evaluation of LLM-based Agents","created":"2025-03-20","cited_by_count":204,"area":"agents"},{"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":"2407.00215","title":"LLM Critics Help Catch LLM Bugs","created":"2024-06-28","cited_by_count":147,"area":"lr"},{"id":"2402.09727","title":"A Human-Inspired Reading Agent with Gist Memory of Very Long Contexts","created":"2024-02-15","cited_by_count":146,"area":"agents"},{"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":"2412.19442","title":"A Survey on Large Language Model Acceleration based on KV Cache Management","created":"2024-12-27","cited_by_count":131,"area":"lr"},{"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":"2409.12822","title":"Language Models Learn to Mislead Humans via RLHF","created":"2024-09-19","cited_by_count":124,"area":"alignment"},{"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":"2504.02259","title":"T*: Re-thinking Temporal Search for Long-Form Video Understanding","created":"2025-04-03","cited_by_count":82,"area":"lr"},{"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":"2409.14924","title":"Retrieval Augmented Generation (RAG) and Beyond: A Comprehensive Survey on How to Make your LLMs use External Data More Wisely","created":"2024-09-23","cited_by_count":66,"area":"rag"},{"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":"2305.14564","title":"PEARL: Prompting Large Language Models to Plan and Execute Actions Over Long Documents","created":"2023-05-23","cited_by_count":61,"area":"lr"},{"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":"2602.22769","title":"AMA-Bench: Evaluating Long-Horizon Memory for Agentic Applications","created":"2026-02-26","cited_by_count":53,"area":"agents"},{"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":"2503.04338","title":"In-depth Analysis of Graph-based RAG in a Unified Framework","created":"2025-03-06","cited_by_count":46,"area":"rag"},{"id":"2203.13240","title":"Token Dropping for Efficient BERT Pretraining","created":"2022-03-24","cited_by_count":42,"area":"inference"},{"id":"2507.09477","title":"Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMs","created":"2025-07-13","cited_by_count":42,"area":"lr"},{"id":"2406.15187","title":"UDA: A Benchmark Suite for Retrieval Augmented Generation in Real-world Document Analysis","created":"2024-06-21","cited_by_count":40,"area":"rag"},{"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":"2412.15266","title":"On the Structural Memory of LLM Agents","created":"2024-12-17","cited_by_count":37,"area":"agents"},{"id":"2408.11865","title":"How Susceptible are LLMs to Influence in Prompts?","created":"2024-08-17","cited_by_count":33,"area":null},{"id":"2410.05004","title":"Fast State Restoration in LLM Serving with HCache","created":"2024-10-07","cited_by_count":33,"area":"rag"},{"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":"2502.09977","title":"LaRA: Benchmarking Retrieval-Augmented Generation and Long-Context LLMs -- No Silver Bullet for LC or RAG Routing","created":"2025-02-14","cited_by_count":29,"area":"rag"},{"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":"2506.02404","title":"GraphRAG-Bench: Challenging Domain-Specific Reasoning for Evaluating Graph Retrieval-Augmented Generation","created":"2025-06-03","cited_by_count":24,"area":"lr"},{"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":"2504.18530","title":"Scaling Laws For Scalable Oversight","created":"2025-04-25","cited_by_count":23,"area":"safety"},{"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":"2409.02465","title":"DetectiveQA: Evaluating Long-Context Reasoning on Detective Novels","created":"2024-09-04","cited_by_count":21,"area":"lr"},{"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":"2404.07979","title":"LLoCO: Learning Long Contexts Offline","created":"2024-04-11","cited_by_count":16,"area":"inference"},{"id":"2409.16636","title":"Training Language Models to Win Debates with Self-Play Improves Judge Accuracy","created":"2024-09-25","cited_by_count":16,"area":"synth"},{"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":"2502.20548","title":"$Q\\sharp$: Provably Optimal Distributional RL for LLM Post-Training","created":"2025-02-27","cited_by_count":15,"area":"lr"},{"id":"2506.20963","title":"EraRAG: Efficient and Incremental Retrieval Augmented Generation for Growing Corpora","created":"2025-06-26","cited_by_count":15,"area":"rag"},{"id":"2409.06679","title":"E2LLM: Encoder Elongated Large Language Models for Long-Context Understanding and Reasoning","created":"2024-09-10","cited_by_count":13,"area":"lr"},{"id":"2412.16468","title":"The Road to Artificial SuperIntelligence: A Comprehensive Survey of Superalignment","created":"2024-12-21","cited_by_count":13,"area":"alignment"},{"id":"2506.11102","title":"Evolutionary Perspectives on the Evaluation of LLM-Based AI Agents: A Comprehensive Survey","created":"2025-06-06","cited_by_count":13,"area":"agents"},{"id":"2406.18312","title":"AI-native Memory: A Pathway from LLMs Towards AGI","created":"2024-06-26","cited_by_count":12,"area":null},{"id":"2509.11552","title":"HiChunk: Evaluating and Enhancing Retrieval-Augmented Generation with Hierarchical Chunking","created":"2025-09-15","cited_by_count":12,"area":"rag"},{"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":"2406.06572","title":"Graph Neural Network Enhanced Retrieval for Question Answering of LLMs","created":"2024-06-03","cited_by_count":10,"area":"rag"},{"id":"2507.05633","title":"SARA: Selective and Adaptive Retrieval-augmented Generation with Context Compression","created":"2025-07-08","cited_by_count":10,"area":"rag"},{"id":"2602.23368","title":"Keyword search is all you need: Achieving RAG-Level Performance without vector databases using agentic tool use","created":"2025-12-19","cited_by_count":10,"area":"rag"},{"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":"2506.03989","title":"Stronger Baselines for Retrieval-Augmented Generation with Long-Context Language Models","created":"2025-06-04","cited_by_count":9,"area":"rag"},{"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":"2503.01713","title":"SAGE: A Framework of Precise Retrieval for RAG","created":"2025-03-03","cited_by_count":8,"area":"rag"},{"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":"2506.02000","title":"NovelHopQA: Diagnosing Multi-Hop Reasoning Failures in Long Narrative Contexts","created":"2025-05-20","cited_by_count":8,"area":"lr"},{"id":"2507.09935","title":"Enhancing Retrieval Augmented Generation with Hierarchical Text Segmentation Chunking","created":"2025-07-14","cited_by_count":8,"area":"rag"}],"next_cursor":"100"}