{"list":"other","total":51,"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":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"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":"2305.10601","title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","created":"2023-05-17","cited_by_count":3211},{"id":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"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":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984},{"id":"1508.05326","title":"A large annotated corpus for learning natural language inference","created":"2015-08-21","cited_by_count":1847},{"id":"2004.09456","title":"StereoSet: Measuring stereotypical bias in pretrained language models","created":"2020-04-20","cited_by_count":924},{"id":"1910.14599","title":"Adversarial NLI: A New Benchmark for Natural Language Understanding","created":"2019-10-31","cited_by_count":807},{"id":"1404.7828","title":"Deep Learning in Neural Networks: An Overview","created":"2014-04-30","cited_by_count":770},{"id":"2306.01116","title":"The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Only","created":"2023-06-01","cited_by_count":763},{"id":"2305.04091","title":"Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models","created":"2023-05-06","cited_by_count":560},{"id":"2311.16867","title":"The Falcon Series of Open Language Models","created":"2023-11-28","cited_by_count":535},{"id":"2402.07927","title":"A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications","created":"2024-02-05","cited_by_count":431},{"id":"2403.19887","title":"Jamba: A Hybrid Transformer-Mamba Language Model","created":"2024-03-28","cited_by_count":401},{"id":"2310.18018","title":"NLP Evaluation in trouble: On the Need to Measure LLM Data Contamination for each Benchmark","created":"2023-10-27","cited_by_count":348},{"id":"2111.07997","title":"Annotators with Attitudes: How Annotator Beliefs And Identities Bias Toxic Language Detection","created":"2021-11-15","cited_by_count":264},{"id":"2402.03927","title":"Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs","created":"2024-02-06","cited_by_count":229},{"id":"2411.12372","title":"RedPajama: an Open Dataset for Training Large Language Models","created":"2024-11-19","cited_by_count":182},{"id":"2407.06023","title":"Distilling System 2 into System 1","created":"2024-07-08","cited_by_count":159},{"id":"2010.03532","title":"What Can We Learn from Collective Human Opinions on Natural Language Inference Data?","created":"2020-10-07","cited_by_count":153},{"id":"1906.06668","title":"Principles alone cannot guarantee ethical AI","created":"2019-06-16","cited_by_count":135},{"id":"2311.11829","title":"System 2 Attention (is something you might need too)","created":"2023-11-20","cited_by_count":89},{"id":"2107.02794","title":"Improving Coherence and Consistency in Neural Sequence Models with Dual-System, Neuro-Symbolic Reasoning","created":"2021-07-06","cited_by_count":85},{"id":"2303.13217","title":"Fairness-guided Few-shot Prompting for Large Language Models","created":"2023-03-23","cited_by_count":53},{"id":"2407.12994","title":"A Survey of Prompt Engineering Methods in Large Language Models for Different NLP Tasks","created":"2024-07-17","cited_by_count":47},{"id":"2404.17218","title":"Prompting Techniques for Reducing Social Bias in LLMs through System 1 and System 2 Cognitive Processes","created":"2024-04-26","cited_by_count":39},{"id":"2010.12729","title":"ANLIzing the Adversarial Natural Language Inference Dataset","created":"2020-10-24","cited_by_count":36},{"id":"1611.00601","title":"Ordinal Common-sense Inference","created":"2016-11-02","cited_by_count":35},{"id":"2407.14414","title":"System-1.x: Learning to Balance Fast and Slow Planning with Language Models","created":"2024-07-19","cited_by_count":35},{"id":"2104.08676","title":"Distributed NLI: Learning to Predict Human Opinion Distributions for Language Reasoning","created":"2021-04-18","cited_by_count":31},{"id":"1802.08535","title":"Can Neural Networks Understand Logical Entailment?","created":"2018-02-23","cited_by_count":24},{"id":"2106.03020","title":"Embracing Ambiguity: Shifting the Training Target of NLI Models","created":"2021-06-06","cited_by_count":23},{"id":"2106.07691","title":"Improving Paraphrase Detection with the Adversarial Paraphrasing Task","created":"2021-06-14","cited_by_count":19},{"id":"2402.15100","title":"Studying LLM Performance on Closed- and Open-source Data","created":"2024-02-23","cited_by_count":11},{"id":"2310.11182","title":"On the Effectiveness of Creating Conversational Agent Personalities Through Prompting","created":"2023-10-17","cited_by_count":10},{"id":"2405.05066","title":"Designing Skill-Compatible AI: Methodologies and Frameworks in Chess","created":"2024-05-08","cited_by_count":10},{"id":"2310.06391","title":"Improved prompting and process for writing user personas with LLMs, using qualitative interviews: Capturing behaviour and personality traits of users","created":"2023-10-10","cited_by_count":9},{"id":"2106.06849","title":"Can Transformer Language Models Predict Psychometric Properties?","created":"2021-06-12","cited_by_count":8},{"id":"2404.02589","title":"Affective-NLI: Towards Accurate and Interpretable Personality Recognition in Conversation","created":"2024-04-03","cited_by_count":7},{"id":"2102.06859","title":"Capturing Label Distribution: A Case Study in NLI","created":"2021-02-13","cited_by_count":6},{"id":"2205.06203","title":"Predicting Human Psychometric Properties Using Computational Language Models","created":"2022-05-12","cited_by_count":5},{"id":"2204.14114","title":"Developmental Negation Processing in Transformer Language Models","created":"2022-04-29","cited_by_count":3},{"id":"2208.09719","title":"Cognitive Modeling of Semantic Fluency Using Transformers","created":"2022-08-20","cited_by_count":2}],"next_cursor":null}