{"list":"other","total":63,"rows":[{"id":"2307.03172","title":"Lost in the Middle: How Language Models Use Long Contexts","created":"2023-07-06","cited_by_count":3455},{"id":"2012.07805","title":"Extracting Training Data from Large Language Models","created":"2020-12-14","cited_by_count":2189},{"id":"2310.11511","title":"Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection","created":"2023-10-17","cited_by_count":1839},{"id":"2112.09332","title":"WebGPT: Browser-assisted question-answering with human feedback","created":"2021-12-17","cited_by_count":1745},{"id":"2212.10511","title":"When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories","created":"2022-12-20","cited_by_count":1128},{"id":"2305.14627","title":"Enabling Large Language Models to Generate Text with Citations","created":"2023-05-24","cited_by_count":595},{"id":"1907.09190","title":"ELI5: Long Form Question Answering","created":"2019-07-22","cited_by_count":575},{"id":"2009.02252","title":"KILT: a Benchmark for Knowledge Intensive Language Tasks","created":"2020-09-04","cited_by_count":573},{"id":"1911.00359","title":"CCNet: Extracting High Quality Monolingual Datasets from Web Crawl Data","created":"2019-11-01","cited_by_count":548},{"id":"2305.16264","title":"Scaling Data-Constrained Language Models","created":"2023-05-25","cited_by_count":403},{"id":"2305.13300","title":"Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflicts","created":"2023-05-22","cited_by_count":341},{"id":"2310.03214","title":"FreshLLMs: Refreshing Large Language Models with Search Engine Augmentation","created":"2023-10-05","cited_by_count":318},{"id":"2304.09848","title":"Evaluating Verifiability in Generative Search Engines","created":"2023-04-19","cited_by_count":303},{"id":"2203.11147","title":"Teaching language models to support answers with verified quotes","created":"2022-03-21","cited_by_count":292},{"id":"2210.08726","title":"RARR: Researching and Revising What Language Models Say, Using Language Models","created":"2022-10-17","cited_by_count":287},{"id":"2303.14186","title":"TRAK: Attributing Model Behavior at Scale","created":"2023-03-24","cited_by_count":283},{"id":"2112.12870","title":"Measuring Attribution in Natural Language Generation Models","created":"2021-12-23","cited_by_count":256},{"id":"2202.06991","title":"Transformer Memory as a Differentiable Search Index","created":"2022-02-14","cited_by_count":247},{"id":"2204.06092","title":"ASQA: Factoid Questions Meet Long-Form Answers","created":"2022-04-12","cited_by_count":234},{"id":"2310.07521","title":"Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificity","created":"2023-10-11","cited_by_count":206},{"id":"2005.04611","title":"How Context Affects Language Models' Factual Predictions","created":"2020-05-10","cited_by_count":181},{"id":"2301.00303","title":"Rethinking with Retrieval: Faithful Large Language Model Inference","created":"2022-12-31","cited_by_count":145},{"id":"2309.14402","title":"Physics of Language Models: Part 3.2, Knowledge Manipulation","created":"2023-09-25","cited_by_count":143},{"id":"2305.18248","title":"Do Language Models Know When They're Hallucinating References?","created":"2023-05-29","cited_by_count":116},{"id":"2206.02743","title":"A Neural Corpus Indexer for Document Retrieval","created":"2022-06-06","cited_by_count":111},{"id":"2309.07852","title":"ExpertQA: Expert-Curated Questions and Attributed Answers","created":"2023-09-14","cited_by_count":97},{"id":"2404.14851","title":"From Matching to Generation: A Survey on Generative Information Retrieval","created":"2024-04-23","cited_by_count":89},{"id":"2407.14985","title":"Generalization v.s. Memorization: Tracing Language Models' Capabilities Back to Pretraining Data","created":"2024-07-20","cited_by_count":85},{"id":"2305.11171","title":"TrueTeacher: Learning Factual Consistency Evaluation with Large Language Models","created":"2023-05-18","cited_by_count":83},{"id":"2409.02897","title":"LongCite: Enabling LLMs to Generate Fine-grained Citations in Long-context QA","created":"2024-09-04","cited_by_count":81},{"id":"2305.06311","title":"Automatic Evaluation of Attribution by Large Language Models","created":"2023-05-10","cited_by_count":72},{"id":"2210.01296","title":"Recitation-Augmented Language Models","created":"2022-10-04","cited_by_count":65},{"id":"2112.09924","title":"The Web Is Your Oyster - Knowledge-Intensive NLP against a Very Large Web Corpus","created":"2021-12-18","cited_by_count":60},{"id":"2409.07431","title":"Synthetic continued pretraining","created":"2024-09-11","cited_by_count":60},{"id":"2410.07176","title":"Astute RAG: Overcoming Imperfect Retrieval Augmentation and Knowledge Conflicts for Large Language Models","created":"2024-10-09","cited_by_count":58},{"id":"2307.16883","title":"HAGRID: A Human-LLM Collaborative Dataset for Generative Information-Seeking with Attribution","created":"2023-07-31","cited_by_count":56},{"id":"2403.17104","title":"Attribute First, then Generate: Locally-attributable Grounded Text Generation","created":"2024-03-25","cited_by_count":54},{"id":"2503.19551","title":"Scaling Laws of Synthetic Data for Language Models","created":"2025-03-25","cited_by_count":46},{"id":"2311.09533","title":"Effective Large Language Model Adaptation for Improved Grounding and Citation Generation","created":"2023-11-16","cited_by_count":45},{"id":"2305.13252","title":"\"According to ...\": Prompting Language Models Improves Quoting from Pre-Training Data","created":"2023-05-22","cited_by_count":42},{"id":"2402.04315","title":"Training Language Models to Generate Text with Citations via Fine-grained Rewards","created":"2024-02-06","cited_by_count":42},{"id":"2410.17413","title":"Scalable Influence and Fact Tracing for Large Language Model Pretraining","created":"2024-10-22","cited_by_count":42},{"id":"2407.07087","title":"CopyBench: Measuring Literal and Non-Literal Reproduction of Copyright-Protected Text in Language Model Generation","created":"2024-07-09","cited_by_count":35},{"id":"2404.01019","title":"Source-Aware Training Enables Knowledge Attribution in Language Models","created":"2024-04-01","cited_by_count":30},{"id":"2504.07096","title":"OLMoTrace: Tracing Language Model Outputs Back to Trillions of Training Tokens","created":"2025-04-09","cited_by_count":27},{"id":"2406.11811","title":"RepLiQA: A Question-Answering Dataset for Benchmarking LLMs on Unseen Reference Content","created":"2024-06-17","cited_by_count":26},{"id":"2410.14675","title":"To Trust or Not to Trust? Enhancing Large Language Models' Situated Faithfulness to External Contexts","created":"2024-10-18","cited_by_count":25},{"id":"2405.09939","title":"SciQAG: A Framework for Auto-Generated Science Question Answering Dataset with Fine-grained Evaluation","created":"2024-05-16","cited_by_count":24},{"id":"2501.01956","title":"Metadata Conditioning Accelerates Language Model Pre-training","created":"2025-01-03","cited_by_count":22},{"id":"2305.11161","title":"TOME: A Two-stage Approach for Model-based Retrieval","created":"2023-05-18","cited_by_count":21},{"id":"2405.11724","title":"Token-wise Influential Training Data Retrieval for Large Language Models","created":"2024-05-20","cited_by_count":20},{"id":"2502.09604","title":"SelfCite: Self-Supervised Alignment for Context Attribution in Large Language Models","created":"2025-02-13","cited_by_count":20},{"id":"2311.04886","title":"SEMQA: Semi-Extractive Multi-Source Question Answering","created":"2023-11-08","cited_by_count":19},{"id":"2402.01176","title":"CorpusLM: Towards a Unified Language Model on Corpus for Knowledge-Intensive Tasks","created":"2024-02-02","cited_by_count":18},{"id":"2507.05261","title":"TokenShapley: Token Level Context Attribution with Shapley Value","created":"2025-06-18","cited_by_count":15},{"id":"2309.09401","title":"ChatGPT Hallucinates when Attributing Answers","created":"2023-09-17","cited_by_count":14},{"id":"2312.11036","title":"UniGen: A Unified Generative Framework for Retrieval and Question Answering with Large Language Models","created":"2023-12-18","cited_by_count":14},{"id":"2404.03862","title":"Verifiable by Design: Aligning Language Models to Quote from Pre-Training Data","created":"2024-04-05","cited_by_count":13},{"id":"2409.17073","title":"Enhancing Post-Hoc Attributions in Long Document Comprehension via Coarse Grained Answer Decomposition","created":"2024-09-25","cited_by_count":12},{"id":"2410.14651","title":"Real-time Factuality Assessment from Adversarial Feedback","created":"2024-10-18","cited_by_count":12},{"id":"2406.06938","title":"Post-Hoc Answer Attribution for Grounded and Trustworthy Long Document Comprehension: Task, Insights, and Challenges","created":"2024-06-11","cited_by_count":5},{"id":"2408.02152","title":"Generative Retrieval with Few-shot Indexing","created":"2024-08-04","cited_by_count":3},{"id":"2412.17558","title":"A Survey of Query Optimization in Large Language Models","created":"2024-12-23","cited_by_count":1}],"next_cursor":null}