{"list":"other","total":101,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"id":"2302.04761","title":"Toolformer: Language Models Can Teach Themselves to Use Tools","created":"2023-02-09","cited_by_count":4182},{"id":"2004.04906","title":"Dense Passage Retrieval for Open-Domain Question Answering","created":"2020-04-10","cited_by_count":3824},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"2307.03172","title":"Lost in the Middle: How Language Models Use Long Contexts","created":"2023-07-06","cited_by_count":3455},{"id":"1705.03551","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","created":"2017-05-09","cited_by_count":2955},{"id":"2307.08691","title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning","created":"2023-07-17","cited_by_count":2598},{"id":"2303.12712","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","created":"2023-03-22","cited_by_count":2592},{"id":"2312.10997","title":"Retrieval-Augmented Generation for Large Language Models: A Survey","created":"2023-12-18","cited_by_count":2212},{"id":"2002.08909","title":"REALM: Retrieval-Augmented Language Model Pre-Training","created":"2020-02-10","cited_by_count":2141},{"id":"2202.03629","title":"Survey of Hallucination in Natural Language Generation","created":"2022-02-08","cited_by_count":2075},{"id":"2212.13138","title":"Large Language Models Encode Clinical Knowledge","created":"2022-12-26","cited_by_count":1830},{"id":"2311.05232","title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","created":"2023-11-09","cited_by_count":1601},{"id":"2112.04426","title":"Improving language models by retrieving from trillions of tokens","created":"2021-12-08","cited_by_count":1293},{"id":"2011.01060","title":"Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps","created":"2020-11-02","cited_by_count":1282},{"id":"2112.09118","title":"Unsupervised Dense Information Retrieval with Contrastive Learning","created":"2021-12-16","cited_by_count":1216},{"id":"2007.01282","title":"Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering","created":"2020-07-02","cited_by_count":1210},{"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":"2405.14734","title":"SimPO: Simple Preference Optimization with a Reference-Free Reward","created":"2024-05-23","cited_by_count":963},{"id":"2208.03299","title":"Atlas: Few-shot Learning with Retrieval Augmented Language Models","created":"2022-08-05","cited_by_count":952},{"id":"2310.03714","title":"DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines","created":"2023-10-05","cited_by_count":832},{"id":"1911.00172","title":"Generalization through Memorization: Nearest Neighbor Language Models","created":"2019-11-01","cited_by_count":800},{"id":"2301.12652","title":"REPLUG: Retrieval-Augmented Black-Box Language Models","created":"2023-01-30","cited_by_count":792},{"id":"2302.00083","title":"In-Context Retrieval-Augmented Language Models","created":"2023-01-31","cited_by_count":702},{"id":"2104.07567","title":"Retrieval Augmentation Reduces Hallucination in Conversation","created":"2021-04-15","cited_by_count":692},{"id":"2210.03493","title":"Automatic Chain of Thought Prompting in Large Language Models","created":"2022-10-07","cited_by_count":688},{"id":"2309.00770","title":"Bias and Fairness in Large Language Models: A Survey","created":"2023-09-02","cited_by_count":639},{"id":"2305.14627","title":"Enabling Large Language Models to Generate Text with Citations","created":"2023-05-24","cited_by_count":595},{"id":"2401.18059","title":"RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval","created":"2024-01-31","cited_by_count":532},{"id":"2305.06983","title":"Active Retrieval Augmented Generation","created":"2023-05-11","cited_by_count":516},{"id":"2112.07899","title":"Large Dual Encoders Are Generalizable Retrievers","created":"2021-12-15","cited_by_count":456},{"id":"1811.07871","title":"Scalable agent alignment via reward modeling: a research direction","created":"2018-11-19","cited_by_count":447},{"id":"2310.01558","title":"Making Retrieval-Augmented Language Models Robust to Irrelevant Context","created":"2023-10-02","cited_by_count":369},{"id":"1906.02361","title":"Explain Yourself! Leveraging Language Models for Commonsense Reasoning","created":"2019-06-06","cited_by_count":367},{"id":"2401.11817","title":"Hallucination is Inevitable: An Innate Limitation of Large Language Models","created":"2024-01-22","cited_by_count":332},{"id":"2402.13178","title":"Benchmarking Retrieval-Augmented Generation for Medicine","created":"2024-02-20","cited_by_count":331},{"id":"2309.11495","title":"Chain-of-Verification Reduces Hallucination in Large Language Models","created":"2023-09-20","cited_by_count":324},{"id":"2212.14024","title":"Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLP","created":"2022-12-28","cited_by_count":318},{"id":"2310.03214","title":"FreshLLMs: Refreshing Large Language Models with Search Engine Augmentation","created":"2023-10-05","cited_by_count":318},{"id":"2305.13534","title":"How Language Model Hallucinations Can Snowball","created":"2023-05-22","cited_by_count":311},{"id":"2403.09629","title":"Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking","created":"2024-03-14","cited_by_count":301},{"id":"2310.05736","title":"LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models","created":"2023-10-09","cited_by_count":287},{"id":"2401.14887","title":"The Power of Noise: Redefining Retrieval for RAG Systems","created":"2024-01-26","cited_by_count":281},{"id":"2403.10131","title":"RAFT: Adapting Language Model to Domain Specific RAG","created":"2024-03-15","cited_by_count":262},{"id":"2310.04408","title":"RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentation","created":"2023-10-06","cited_by_count":256},{"id":"2204.02329","title":"Can language models learn from explanations in context?","created":"2022-04-05","cited_by_count":249},{"id":"2207.13332","title":"RealTime QA: What's the Answer Right Now?","created":"2022-07-27","cited_by_count":244},{"id":"2203.08242","title":"Data Contamination: From Memorization to Exploitation","created":"2022-03-15","cited_by_count":236},{"id":"2204.06092","title":"ASQA: Factoid Questions Meet Long-Form Answers","created":"2022-04-12","cited_by_count":234},{"id":"2402.10200","title":"Chain-of-Thought Reasoning Without Prompting","created":"2024-02-15","cited_by_count":210},{"id":"2401.15884","title":"Corrective Retrieval Augmented Generation","created":"2024-01-29","cited_by_count":197},{"id":"2308.08493","title":"Time Travel in LLMs: Tracing Data Contamination in Large Language Models","created":"2023-08-16","cited_by_count":177},{"id":"2405.20362","title":"Hallucination-Free? Assessing the Reliability of Leading AI Legal Research Tools","created":"2024-05-30","cited_by_count":176},{"id":"2211.05110","title":"Large Language Models with Controllable Working Memory","created":"2022-11-09","cited_by_count":169},{"id":"2308.10168","title":"Head-to-Tail: How Knowledgeable are Large Language Models (LLMs)? A.K.A. Will LLMs Replace Knowledge Graphs?","created":"2023-08-20","cited_by_count":168},{"id":"2405.13576","title":"FlashRAG: A Modular Toolkit for Efficient Retrieval-Augmented Generation Research","created":"2024-05-22","cited_by_count":166},{"id":"2010.12762","title":"Measuring Association Between Labels and Free-Text Rationales","created":"2020-10-24","cited_by_count":160},{"id":"2310.06117","title":"Take a Step Back: Evoking Reasoning via Abstraction in Large Language Models","created":"2023-10-09","cited_by_count":159},{"id":"2310.19156","title":"Poisoning Retrieval Corpora by Injecting Adversarial Passages","created":"2023-10-29","cited_by_count":159},{"id":"2402.16893","title":"The Good and The Bad: Exploring Privacy Issues in Retrieval-Augmented Generation (RAG)","created":"2024-02-23","cited_by_count":159},{"id":"2207.05987","title":"DocPrompting: Generating Code by Retrieving the Docs","created":"2022-07-13","cited_by_count":153},{"id":"2405.15556","title":"Certifiably Robust RAG against Retrieval Corruption","created":"2024-05-24","cited_by_count":151},{"id":"2305.10160","title":"Stop Uploading Test Data in Plain Text: Practical Strategies for Mitigating Data Contamination by Evaluation Benchmarks","created":"2023-05-17","cited_by_count":142},{"id":"2305.03268","title":"Verify-and-Edit: A Knowledge-Enhanced Chain-of-Thought Framework","created":"2023-05-05","cited_by_count":139},{"id":"2405.13792","title":"xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Token","created":"2024-05-22","cited_by_count":125},{"id":"2203.07722","title":"ReACC: A Retrieval-Augmented Code Completion Framework","created":"2022-03-15","cited_by_count":119},{"id":"2105.03887","title":"Lawformer: A Pre-trained Language Model for Chinese Legal Long Documents","created":"2021-05-09","cited_by_count":116},{"id":"2310.03025","title":"Retrieval meets Long Context Large Language Models","created":"2023-10-04","cited_by_count":115},{"id":"2404.12457","title":"RAGCache: Efficient Knowledge Caching for Retrieval-Augmented Generation","created":"2024-04-18","cited_by_count":98},{"id":"2406.04744","title":"CRAG -- Comprehensive RAG Benchmark","created":"2024-06-07","cited_by_count":97},{"id":"2305.14002","title":"Improving Language Models via Plug-and-Play Retrieval Feedback","created":"2023-05-23","cited_by_count":87},{"id":"2402.16617","title":"Long-Context Language Modeling with Parallel Context Encoding","created":"2024-02-26","cited_by_count":84},{"id":"2401.08406","title":"RAG vs Fine-tuning: Pipelines, Tradeoffs, and a Case Study on Agriculture","created":"2024-01-16","cited_by_count":81},{"id":"2403.05313","title":"RAT: Retrieval Augmented Thoughts Elicit Context-Aware Reasoning in Long-Horizon Generation","created":"2024-03-08","cited_by_count":75},{"id":"2304.14732","title":"Search-in-the-Chain: Interactively Enhancing Large Language Models with Search for Knowledge-intensive Tasks","created":"2023-04-28","cited_by_count":73},{"id":"2403.03187","title":"Reliable, Adaptable, and Attributable Language Models with Retrieval","created":"2024-03-05","cited_by_count":73},{"id":"2005.00652","title":"An Information Bottleneck Approach for Controlling Conciseness in Rationale Extraction","created":"2020-05-01","cited_by_count":69},{"id":"2102.10073","title":"Pyserini: An Easy-to-Use Python Toolkit to Support Replicable IR Research with Sparse and Dense Representations","created":"2021-02-19","cited_by_count":60},{"id":"2402.12847","title":"Instruction-tuned Language Models are Better Knowledge Learners","created":"2024-02-20","cited_by_count":55},{"id":"2405.14431","title":"RaFe: Ranking Feedback Improves Query Rewriting for RAG","created":"2024-05-23","cited_by_count":49},{"id":"2305.15035","title":"Self-ICL: Zero-Shot In-Context Learning with Self-Generated Demonstrations","created":"2023-05-24","cited_by_count":42},{"id":"2406.02746","title":"RATT: A Thought Structure for Coherent and Correct LLM Reasoning","created":"2024-06-04","cited_by_count":41},{"id":"2204.11790","title":"Can Rationalization Improve Robustness?","created":"2022-04-25","cited_by_count":36},{"id":"2305.14888","title":"Privacy Implications of Retrieval-Based Language Models","created":"2023-05-24","cited_by_count":32},{"id":"2403.05676","title":"PipeRAG: Fast Retrieval-Augmented Generation via Algorithm-System Co-design","created":"2024-03-08","cited_by_count":28},{"id":"2211.05414","title":"ADEPT: A DEbiasing PrompT Framework","created":"2022-11-10","cited_by_count":21},{"id":"2405.07530","title":"Prompt-based Code Completion via Multi-Retrieval Augmented Generation","created":"2024-05-13","cited_by_count":16},{"id":"2404.03414","title":"Can Small Language Models Help Large Language Models Reason Better?: LM-Guided Chain-of-Thought","created":"2024-04-04","cited_by_count":12},{"id":"2305.07355","title":"ZARA: Improving Few-Shot Self-Rationalization for Small Language Models","created":"2023-05-12","cited_by_count":8}],"next_cursor":"100"}