{"list":"other","total":75,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"2004.04906","title":"Dense Passage Retrieval for Open-Domain Question Answering","created":"2020-04-10","cited_by_count":3824},{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576},{"id":"2310.11511","title":"Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection","created":"2023-10-17","cited_by_count":1839},{"id":"1803.05355","title":"FEVER: a large-scale dataset for Fact Extraction and VERification","created":"2018-03-14","cited_by_count":1375},{"id":"2305.15334","title":"Gorilla: Large Language Model Connected with Massive APIs","created":"2023-05-24","cited_by_count":1332},{"id":"2305.14251","title":"FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation","created":"2023-05-23","cited_by_count":1282},{"id":"2212.03533","title":"Text Embeddings by Weakly-Supervised Contrastive Pre-training","created":"2022-12-07","cited_by_count":1253},{"id":"2212.10509","title":"Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions","created":"2022-12-20","cited_by_count":923},{"id":"2308.09687","title":"Graph of Thoughts: Solving Elaborate Problems with Large Language Models","created":"2023-08-18","cited_by_count":886},{"id":"2210.07316","title":"MTEB: Massive Text Embedding Benchmark","created":"2022-10-13","cited_by_count":640},{"id":"2308.10792","title":"Instruction Tuning for Large Language Models: A Survey","created":"2023-08-21","cited_by_count":623},{"id":"2102.07350","title":"Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigm","created":"2021-02-15","cited_by_count":606},{"id":"1811.01241","title":"Wizard of Wikipedia: Knowledge-Powered Conversational agents","created":"2018-11-03","cited_by_count":530},{"id":"1911.03429","title":"ERASER: A Benchmark to Evaluate Rationalized NLP Models","created":"2019-11-08","cited_by_count":530},{"id":"2401.08281","title":"The Faiss library","created":"2024-01-16","cited_by_count":376},{"id":"2302.04166","title":"GPTScore: Evaluate as You Desire","created":"2023-02-08","cited_by_count":361},{"id":"2402.13178","title":"Benchmarking Retrieval-Augmented Generation for Medicine","created":"2024-02-20","cited_by_count":331},{"id":"2310.03214","title":"FreshLLMs: Refreshing Large Language Models with Search Engine Augmentation","created":"2023-10-05","cited_by_count":318},{"id":"2309.01431","title":"Benchmarking Large Language Models in Retrieval-Augmented Generation","created":"2023-09-04","cited_by_count":312},{"id":"2402.07867","title":"PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models","created":"2024-02-12","cited_by_count":267},{"id":"2207.13332","title":"RealTime QA: What's the Answer Right Now?","created":"2022-07-27","cited_by_count":244},{"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":"2402.17193","title":"When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method","created":"2024-02-27","cited_by_count":204},{"id":"1810.12885","title":"ReCoRD: Bridging the Gap between Human and Machine Commonsense Reading Comprehension","created":"2018-10-30","cited_by_count":200},{"id":"2009.08553","title":"Generation-Augmented Retrieval for Open-domain Question Answering","created":"2020-09-17","cited_by_count":186},{"id":"2310.01469","title":"LLM Lies: Hallucinations are not Bugs, but Features as Adversarial Examples","created":"2023-10-02","cited_by_count":177},{"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":"2405.13792","title":"xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Token","created":"2024-05-22","cited_by_count":125},{"id":"2502.13595","title":"MMTEB: Massive Multilingual Text Embedding Benchmark","created":"2025-02-19","cited_by_count":125},{"id":"2311.04205","title":"Rephrase and Respond: Let Large Language Models Ask Better Questions for Themselves","created":"2023-11-07","cited_by_count":123},{"id":"2408.10343","title":"LegalBench-RAG: A Benchmark for Retrieval-Augmented Generation in the Legal Domain","created":"2024-08-19","cited_by_count":118},{"id":"2406.19276","title":"VERISCORE: Evaluating the factuality of verifiable claims in long-form text generation","created":"2024-06-27","cited_by_count":117},{"id":"2406.05870","title":"Machine Against the RAG: Jamming Retrieval-Augmented Generation with Blocker Documents","created":"2024-06-09","cited_by_count":102},{"id":"2410.11414","title":"ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic Interpretability","created":"2024-10-15","cited_by_count":101},{"id":"2409.10102","title":"Trustworthiness in Retrieval-Augmented Generation Systems: A Survey","created":"2024-09-16","cited_by_count":83},{"id":"2307.15780","title":"LLM-Rec: Personalized Recommendation via Prompting Large Language Models","created":"2023-07-24","cited_by_count":77},{"id":"2304.03516","title":"Generative Recommendation: Towards Next-generation Recommender Paradigm","created":"2023-04-07","cited_by_count":70},{"id":"2311.08147","title":"RECALL: A Benchmark for LLMs Robustness against External Counterfactual Knowledge","created":"2023-11-14","cited_by_count":51},{"id":"2501.03468","title":"MTRAG: A Multi-Turn Conversational Benchmark for Evaluating Retrieval-Augmented Generation Systems","created":"2025-01-07","cited_by_count":51},{"id":"2405.20485","title":"Phantom: General Backdoor Attacks on Retrieval Augmented Language Generation","created":"2024-05-30","cited_by_count":49},{"id":"2310.04276","title":"From task structures to world models: What do LLMs know?","created":"2023-10-06","cited_by_count":46},{"id":"2402.05131","title":"Financial Report Chunking for Effective Retrieval Augmented Generation","created":"2024-02-05","cited_by_count":46},{"id":"2404.03302","title":"How Easily do Irrelevant Inputs Skew the Responses of Large Language Models?","created":"2024-04-04","cited_by_count":44},{"id":"2403.19964","title":"FairRAG: Fair Human Generation via Fair Retrieval Augmentation","created":"2024-03-29","cited_by_count":34},{"id":"1906.02738","title":"Conversing by Reading: Contentful Neural Conversation with On-demand Machine Reading","created":"2019-06-06","cited_by_count":32},{"id":"2501.18636","title":"SafeRAG: Benchmarking Security in Retrieval-Augmented Generation of Large Language Model","created":"2025-01-28","cited_by_count":32},{"id":"2305.00833","title":"Learning to Reason and Memorize with Self-Notes","created":"2023-05-01","cited_by_count":30},{"id":"2412.13018","title":"OmniEval: An Omnidirectional and Automatic RAG Evaluation Benchmark in Financial Domain","created":"2024-12-17","cited_by_count":29},{"id":"2310.12516","title":"ReEval: Automatic Hallucination Evaluation for Retrieval-Augmented Large Language Models via Transferable Adversarial Attacks","created":"2023-10-19","cited_by_count":28},{"id":"2402.03181","title":"C-RAG: Certified Generation Risks for Retrieval-Augmented Language Models","created":"2024-02-05","cited_by_count":27},{"id":"2410.22832","title":"HijackRAG: Hijacking Attacks against Retrieval-Augmented Large Language Models","created":"2024-10-30","cited_by_count":27},{"id":"2402.11626","title":"Metacognitive Retrieval-Augmented Large Language Models","created":"2024-02-18","cited_by_count":26},{"id":"2409.19804","title":"Does RAG Introduce Unfairness in LLMs? Evaluating Fairness in Retrieval-Augmented Generation Systems","created":"2024-09-29","cited_by_count":26},{"id":"2412.02592","title":"OCR Hinders RAG: Evaluating the Cascading Impact of OCR on Retrieval-Augmented Generation","created":"2024-12-03","cited_by_count":26},{"id":"2503.01478","title":"SePer: Measure Retrieval Utility Through The Lens Of Semantic Perplexity Reduction","created":"2025-03-03","cited_by_count":24},{"id":"2410.19572","title":"ChunkRAG: Novel LLM-Chunk Filtering Method for RAG Systems","created":"2024-10-25","cited_by_count":23},{"id":"2402.19248","title":"Let LLMs Take on the Latest Challenges! A Chinese Dynamic Question Answering Benchmark","created":"2024-02-29","cited_by_count":22},{"id":"2407.12873","title":"Evaluation of RAG Metrics for Question Answering in the Telecom Domain","created":"2024-07-15","cited_by_count":20},{"id":"2406.01549","title":"An Information Bottleneck Perspective for Effective Noise Filtering on Retrieval-Augmented Generation","created":"2024-06-03","cited_by_count":16},{"id":"2306.07471","title":"Resources for Brewing BEIR: Reproducible Reference Models and an Official Leaderboard","created":"2023-06-13","cited_by_count":15},{"id":"2205.12604","title":"Leveraging QA Datasets to Improve Generative Data Augmentation","created":"2022-05-25","cited_by_count":12},{"id":"2409.16146","title":"Controlling Risk of Retrieval-augmented Generation: A Counterfactual Prompting Framework","created":"2024-09-24","cited_by_count":12},{"id":"2406.00562","title":"SPAGHETTI: Open-Domain Question Answering from Heterogeneous Data Sources with Retrieval and Semantic Parsing","created":"2024-06-01","cited_by_count":11},{"id":"2204.13596","title":"Generative Multi-hop Retrieval","created":"2022-04-27","cited_by_count":10},{"id":"2503.01713","title":"SAGE: A Framework of Precise Retrieval for RAG","created":"2025-03-03","cited_by_count":8},{"id":"2406.10254","title":"Towards Signal Processing In Large Language Models","created":"2024-06-10","cited_by_count":7},{"id":"2403.18350","title":"Evaluation of Semantic Search and its Role in Retrieved-Augmented-Generation (RAG) for Arabic Language","created":"2024-03-27","cited_by_count":4},{"id":"2412.12322","title":"RAG Playground: A Framework for Systematic Evaluation of Retrieval Strategies and Prompt Engineering in RAG Systems","created":"2024-12-16","cited_by_count":4},{"id":"2307.10442","title":"Thrust: Adaptively Propels Large Language Models with External Knowledge","created":"2023-07-19","cited_by_count":3},{"id":"2405.20680","title":"Unraveling and Mitigating Retriever Inconsistencies in Retrieval-Augmented Large Language Models","created":"2024-05-31","cited_by_count":2}],"next_cursor":null}