{"list":"other","total":63,"rows":[{"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":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"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":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975},{"id":"2312.10997","title":"Retrieval-Augmented Generation for Large Language Models: A Survey","created":"2023-12-18","cited_by_count":2212},{"id":"2408.00118","title":"Gemma 2: Improving Open Language Models at a Practical Size","created":"2024-07-31","cited_by_count":1998},{"id":"1611.09268","title":"MS MARCO: A Human Generated MAchine Reading COmprehension Dataset","created":"2016-11-28","cited_by_count":1605},{"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":"2112.09118","title":"Unsupervised Dense Information Retrieval with Contrastive Learning","created":"2021-12-16","cited_by_count":1216},{"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":"2210.03350","title":"Measuring and Narrowing the Compositionality Gap in Language Models","created":"2022-10-07","cited_by_count":1075},{"id":"2004.09297","title":"MPNet: Masked and Permuted Pre-training for Language Understanding","created":"2020-04-20","cited_by_count":981},{"id":"2212.09251","title":"Discovering Language Model Behaviors with Model-Written Evaluations","created":"2022-12-19","cited_by_count":836},{"id":"2104.07567","title":"Retrieval Augmentation Reduces Hallucination in Conversation","created":"2021-04-15","cited_by_count":692},{"id":"2406.00515","title":"A Survey on Large Language Models for Code Generation","created":"2024-06-01","cited_by_count":658},{"id":"2009.02252","title":"KILT: a Benchmark for Knowledge Intensive Language Tasks","created":"2020-09-04","cited_by_count":573},{"id":"2210.02406","title":"Decomposed Prompting: A Modular Approach for Solving Complex Tasks","created":"2022-10-05","cited_by_count":558},{"id":"2412.13663","title":"Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference","created":"2024-12-18","cited_by_count":554},{"id":"2212.10496","title":"Precise Zero-Shot Dense Retrieval without Relevance Labels","created":"2022-12-20","cited_by_count":517},{"id":"2301.13848","title":"Benchmarking Large Language Models for News Summarization","created":"2023-01-31","cited_by_count":445},{"id":"2310.01558","title":"Making Retrieval-Augmented Language Models Robust to Irrelevant Context","created":"2023-10-02","cited_by_count":369},{"id":"2305.15294","title":"Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergy","created":"2023-05-24","cited_by_count":346},{"id":"2402.01613","title":"Nomic Embed: Training a Reproducible Long Context Text Embedder","created":"2024-02-02","cited_by_count":265},{"id":"2401.15391","title":"MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries","created":"2024-01-27","cited_by_count":257},{"id":"2405.05904","title":"Does Fine-Tuning LLMs on New Knowledge Encourage Hallucinations?","created":"2024-05-09","cited_by_count":232},{"id":"2308.03958","title":"Simple synthetic data reduces sycophancy in large language models","created":"2023-08-07","cited_by_count":187},{"id":"2204.05149","title":"The Carbon Footprint of Machine Learning Training Will Plateau, Then Shrink","created":"2022-04-11","cited_by_count":184},{"id":"2304.02819","title":"GPT detectors are biased against non-native English writers","created":"2023-04-06","cited_by_count":178},{"id":"2401.06855","title":"Fine-grained Hallucination Detection and Editing for Language Models","created":"2024-01-12","cited_by_count":149},{"id":"2109.08535","title":"Simple Entity-Centric Questions Challenge Dense Retrievers","created":"2021-09-17","cited_by_count":140},{"id":"2306.04136","title":"Knowledge-Augmented Language Model Prompting for Zero-Shot Knowledge Graph Question Answering","created":"2023-06-07","cited_by_count":119},{"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":"2404.08189","title":"Reducing hallucination in structured outputs via Retrieval-Augmented Generation","created":"2024-04-12","cited_by_count":93},{"id":"2108.12237","title":"Evaluating the Robustness of Neural Language Models to Input Perturbations","created":"2021-08-27","cited_by_count":87},{"id":"2308.09729","title":"MindMap: Knowledge Graph Prompting Sparks Graph of Thoughts in Large Language Models","created":"2023-08-17","cited_by_count":73},{"id":"2404.13948","title":"Typos that Broke the RAG's Back: Genetic Attack on RAG Pipeline by Simulating Documents in the Wild via Low-level Perturbations","created":"2024-04-22","cited_by_count":65},{"id":"2205.02832","title":"Entity Cloze By Date: What LMs Know About Unseen Entities","created":"2022-05-05","cited_by_count":55},{"id":"2408.00727","title":"Improving Retrieval-Augmented Generation in Medicine with Iterative Follow-up Questions","created":"2024-08-01","cited_by_count":54},{"id":"1904.05780","title":"Corpora Generation for Grammatical Error Correction","created":"2019-04-10","cited_by_count":53},{"id":"2212.08011","title":"Multi-VALUE: A Framework for Cross-Dialectal English NLP","created":"2022-12-15","cited_by_count":53},{"id":"2310.12418","title":"The Shifted and The Overlooked: A Task-oriented Investigation of User-GPT Interactions","created":"2023-10-19","cited_by_count":45},{"id":"2402.14531","title":"Should We Respect LLMs? A Cross-Lingual Study on the Influence of Prompt Politeness on LLM Performance","created":"2024-02-22","cited_by_count":41},{"id":"2406.10248","title":"On the Worst Prompt Performance of Large Language Models","created":"2024-06-08","cited_by_count":38},{"id":"2111.13057","title":"Evaluating the Robustness of Retrieval Pipelines with Query Variation Generators","created":"2021-11-25","cited_by_count":34},{"id":"2303.03278","title":"Faithfulness-Aware Decoding Strategies for Abstractive Summarization","created":"2023-03-06","cited_by_count":31},{"id":"2308.09055","title":"Don't lose the message while paraphrasing: A study on content preserving style transfer","created":"2023-08-17","cited_by_count":25},{"id":"2108.12139","title":"Dealing with Typos for BERT-based Passage Retrieval and Ranking","created":"2021-08-27","cited_by_count":23},{"id":"2005.05683","title":"On the Robustness of Language Encoders against Grammatical Errors","created":"2020-05-12","cited_by_count":19},{"id":"2408.15533","title":"LRP4RAG: Detecting Hallucinations in Retrieval-Augmented Generation via Layer-wise Relevance Propagation","created":"2024-08-28","cited_by_count":17},{"id":"2309.11064","title":"Exploring the Relationship between LLM Hallucinations and Prompt Linguistic Nuances: Readability, Formality, and Concreteness","created":"2023-09-20","cited_by_count":13},{"id":"2407.02472","title":"ValueScope: Unveiling Implicit Norms and Values via Return Potential Model of Social Interactions","created":"2024-07-02","cited_by_count":12},{"id":"2209.06691","title":"Certified Robustness to Word Substitution Ranking Attack for Neural Ranking Models","created":"2022-09-14","cited_by_count":11},{"id":"2008.02449","title":"Studying Politeness across Cultures Using English Twitter and Mandarin Weibo","created":"2020-08-06","cited_by_count":10},{"id":"2104.07848","title":"Comparison of Grammatical Error Correction Using Back-Translation Models","created":"2021-04-16","cited_by_count":9},{"id":"2410.04784","title":"Formality is Favored: Unraveling the Learning Preferences of Large Language Models on Data with Conflicting Knowledge","created":"2024-10-07","cited_by_count":8},{"id":"2405.02144","title":"MedReadMe: A Systematic Study for Fine-grained Sentence Readability in Medical Domain","created":"2024-05-03","cited_by_count":7},{"id":"2304.03401","title":"Noise-Robust Dense Retrieval via Contrastive Alignment Post Training","created":"2023-04-06","cited_by_count":5},{"id":"2411.09497","title":"The Use of Readability Metrics in Legal Text: A Systematic Literature Review","created":"2024-11-14","cited_by_count":4},{"id":"2307.12520","title":"Lost In Translation: Generating Adversarial Examples Robust to Round-Trip Translation","created":"2023-07-24","cited_by_count":2}],"next_cursor":null}