{"list":"other","total":65,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"1803.05457","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","created":"2018-03-14","cited_by_count":4886},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"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":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"2107.13586","title":"Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing","created":"2021-07-28","cited_by_count":2234},{"id":"2104.08821","title":"SimCSE: Simple Contrastive Learning of Sentence Embeddings","created":"2021-04-18","cited_by_count":2173},{"id":"1508.05326","title":"A large annotated corpus for learning natural language inference","created":"2015-08-21","cited_by_count":1847},{"id":"1611.09268","title":"MS MARCO: A Human Generated MAchine Reading COmprehension Dataset","created":"2016-11-28","cited_by_count":1605},{"id":"2110.08207","title":"Multitask Prompted Training Enables Zero-Shot Task Generalization","created":"2021-10-15","cited_by_count":1470},{"id":"2202.12837","title":"Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?","created":"2022-02-25","cited_by_count":1434},{"id":"1903.10676","title":"SciBERT: A Pretrained Language Model for Scientific Text","created":"2019-03-26","cited_by_count":1414},{"id":"2102.09690","title":"Calibrate Before Use: Improving Few-Shot Performance of Language Models","created":"2021-02-19","cited_by_count":1392},{"id":"1803.09010","title":"Datasheets for Datasets","created":"2018-03-23","cited_by_count":1386},{"id":"2012.15723","title":"Making Pre-trained Language Models Better Few-shot Learners","created":"2020-12-31","cited_by_count":1256},{"id":"2212.03533","title":"Text Embeddings by Weakly-Supervised Contrastive Pre-training","created":"2022-12-07","cited_by_count":1253},{"id":"2104.08663","title":"BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models","created":"2021-04-17","cited_by_count":1252},{"id":"2004.12832","title":"ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT","created":"2020-04-27","cited_by_count":1178},{"id":"2201.07207","title":"Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents","created":"2022-01-18","cited_by_count":1035},{"id":"2302.04023","title":"A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity","created":"2023-02-08","cited_by_count":894},{"id":"2303.15056","title":"ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks","created":"2023-03-27","cited_by_count":870},{"id":"2007.00808","title":"Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval","created":"2020-07-01","cited_by_count":849},{"id":"2302.09664","title":"Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation","created":"2023-02-19","cited_by_count":819},{"id":"2303.08896","title":"SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models","created":"2023-03-15","cited_by_count":810},{"id":"1808.07042","title":"CoQA: A Conversational Question Answering Challenge","created":"2018-08-21","cited_by_count":683},{"id":"2302.06476","title":"Is ChatGPT a General-Purpose Natural Language Processing Task Solver?","created":"2023-02-08","cited_by_count":488},{"id":"2112.01488","title":"ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction","created":"2021-12-02","cited_by_count":476},{"id":"2004.07180","title":"SPECTER: Document-level Representation Learning using Citation-informed Transformers","created":"2020-04-15","cited_by_count":430},{"id":"2305.13534","title":"How Language Model Hallucinations Can Snowball","created":"2023-05-22","cited_by_count":311},{"id":"2212.10450","title":"Is GPT-3 a Good Data Annotator?","created":"2022-12-20","cited_by_count":208},{"id":"2102.07662","title":"Overview of the TREC 2020 deep learning track","created":"2021-02-15","cited_by_count":196},{"id":"2110.07367","title":"RocketQAv2: A Joint Training Method for Dense Passage Retrieval and Passage Re-ranking","created":"2021-10-14","cited_by_count":176},{"id":"2104.08704","title":"A Token-level Reference-free Hallucination Detection Benchmark for Free-form Text Generation","created":"2021-04-18","cited_by_count":138},{"id":"2109.10086","title":"SPLADE v2: Sparse Lexical and Expansion Model for Information Retrieval","created":"2021-09-21","cited_by_count":127},{"id":"2301.10140","title":"The Semantic Scholar Open Data Platform","created":"2023-01-24","cited_by_count":118},{"id":"2206.02743","title":"A Neural Corpus Indexer for Document Retrieval","created":"2022-06-06","cited_by_count":111},{"id":"2304.06588","title":"ChatGPT-4 Outperforms Experts and Crowd Workers in Annotating Political Twitter Messages with Zero-Shot Learning","created":"2023-04-13","cited_by_count":100},{"id":"2207.02578","title":"SimLM: Pre-training with Representation Bottleneck for Dense Passage Retrieval","created":"2022-07-06","cited_by_count":90},{"id":"1809.01494","title":"Interpretation of Natural Language Rules in Conversational Machine Reading","created":"2018-08-28","cited_by_count":75},{"id":"2305.14871","title":"ClusterLLM: Large Language Models as a Guide for Text Clustering","created":"2023-05-24","cited_by_count":70},{"id":"2009.00751","title":"Text Modular Networks: Learning to Decompose Tasks in the Language of Existing Models","created":"2020-09-01","cited_by_count":65},{"id":"2003.13956","title":"SPARQA: Skeleton-based Semantic Parsing for Complex Questions over Knowledge Bases","created":"2020-03-31","cited_by_count":47},{"id":"2102.05281","title":"Biomedical Question Answering: A Survey of Approaches and Challenges","created":"2021-02-10","cited_by_count":46},{"id":"2205.09153","title":"ERNIE-Search: Bridging Cross-Encoder with Dual-Encoder via Self On-the-fly Distillation for Dense Passage Retrieval","created":"2022-05-18","cited_by_count":41},{"id":"2111.08366","title":"Multi-Vector Models with Textual Guidance for Fine-Grained Scientific Document Similarity","created":"2021-11-16","cited_by_count":35},{"id":"1703.04816","title":"Making Neural QA as Simple as Possible but not Simpler","created":"2017-03-14","cited_by_count":33},{"id":"2302.11266","title":"One-Shot Labeling for Automatic Relevance Estimation","created":"2023-02-22","cited_by_count":31},{"id":"2306.02250","title":"Large Language Model Augmented Narrative Driven Recommendations","created":"2023-06-04","cited_by_count":31},{"id":"2011.00696","title":"ABNIRML: Analyzing the Behavior of Neural IR Models","created":"2020-11-02","cited_by_count":23},{"id":"2103.12906","title":"CSFCube -- A Test Collection of Computer Science Research Articles for Faceted Query by Example","created":"2021-03-24","cited_by_count":20},{"id":"2210.16865","title":"Learning to Decompose: Hypothetical Question Decomposition Based on Comparable Texts","created":"2022-10-30","cited_by_count":18},{"id":"2001.11396","title":"Non-Determinism in TensorFlow ResNets","created":"2020-01-30","cited_by_count":11},{"id":"2008.00202","title":"Contextual Document Similarity for Content-based Literature Recommender Systems","created":"2020-08-01","cited_by_count":5},{"id":"2105.09204","title":"POINTREC: A Test Collection for Narrative-driven Point of Interest Recommendation","created":"2021-05-19","cited_by_count":4},{"id":"1304.5457","title":"Personalized Academic Research Paper Recommendation System","created":"2013-04-19","cited_by_count":2},{"id":"2303.17161","title":"TreePiece: Faster Semantic Parsing via Tree Tokenization","created":"2023-03-30","cited_by_count":2}],"next_cursor":null}