{"list":"other","total":130,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"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":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"1705.07874","title":"A Unified Approach to Interpreting Model Predictions","created":"2017-05-22","cited_by_count":6555},{"id":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"id":"1602.04938","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","created":"2016-02-16","cited_by_count":5070},{"id":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"id":"1301.3781","title":"Efficient Estimation of Word Representations in Vector Space","created":"2013-01-16","cited_by_count":4375},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720},{"id":"2212.08073","title":"Constitutional AI: Harmlessness from AI Feedback","created":"2022-12-15","cited_by_count":3050},{"id":"2303.12712","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","created":"2023-03-22","cited_by_count":2592},{"id":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588},{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576},{"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":"1909.08593","title":"Fine-Tuning Language Models from Human Preferences","created":"2019-09-18","cited_by_count":2150},{"id":"1610.02413","title":"Equality of Opportunity in Supervised Learning","created":"2016-10-07","cited_by_count":2007},{"id":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984},{"id":"1908.09635","title":"A Survey on Bias and Fairness in Machine Learning","created":"2019-08-23","cited_by_count":1917},{"id":"2102.09690","title":"Calibrate Before Use: Improving Few-Shot Performance of Language Models","created":"2021-02-19","cited_by_count":1392},{"id":"1607.06520","title":"Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings","created":"2016-07-21","cited_by_count":1312},{"id":"2312.06674","title":"Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations","created":"2023-12-07","cited_by_count":1207},{"id":"2112.04359","title":"Ethical and social risks of harm from Language Models","created":"2021-12-08","cited_by_count":966},{"id":"2005.14050","title":"Language (Technology) is Power: A Critical Survey of \"Bias\" in NLP","created":"2020-05-28","cited_by_count":956},{"id":"1608.07187","title":"Semantics derived automatically from language corpora contain human-like biases","created":"2016-08-25","cited_by_count":901},{"id":"2307.15217","title":"Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback","created":"2023-07-27","cited_by_count":759},{"id":"2209.07858","title":"Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned","created":"2022-08-23","cited_by_count":729},{"id":"2103.10385","title":"GPT Understands, Too","created":"2021-03-18","cited_by_count":716},{"id":"1412.3756","title":"Certifying and removing disparate impact","created":"2014-12-11","cited_by_count":715},{"id":"2010.00133","title":"CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models","created":"2020-09-30","cited_by_count":710},{"id":"2110.08193","title":"BBQ: A Hand-Built Bias Benchmark for Question Answering","created":"2021-10-15","cited_by_count":701},{"id":"2110.07602","title":"P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks","created":"2021-10-14","cited_by_count":689},{"id":"1801.07593","title":"Mitigating Unwanted Biases with Adversarial Learning","created":"2018-01-22","cited_by_count":663},{"id":"2308.08747","title":"An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning","created":"2023-08-17","cited_by_count":639},{"id":"2309.00770","title":"Bias and Fairness in Large Language Models: A Survey","created":"2023-09-02","cited_by_count":639},{"id":"2007.01852","title":"Language-agnostic BERT Sentence Embedding","created":"2020-07-03","cited_by_count":627},{"id":"2309.05463","title":"Textbooks Are All You Need II: phi-1.5 technical report","created":"2023-09-11","cited_by_count":565},{"id":"2402.06196","title":"Large Language Models: A Survey","created":"2024-02-09","cited_by_count":525},{"id":"2004.07667","title":"Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection","created":"2020-04-16","cited_by_count":455},{"id":"2101.11718","title":"BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generation","created":"2021-01-27","cited_by_count":412},{"id":"1709.02012","title":"On Fairness and Calibration","created":"2017-09-06","cited_by_count":406},{"id":"1903.10561","title":"On Measuring Social Biases in Sentence Encoders","created":"2019-03-25","cited_by_count":398},{"id":"2110.01963","title":"Multimodal datasets: misogyny, pornography, and malignant stereotypes","created":"2021-10-05","cited_by_count":327},{"id":"1810.01943","title":"AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias","created":"2018-10-03","cited_by_count":319},{"id":"1912.05511","title":"Measurement and Fairness","created":"2019-12-11","cited_by_count":308},{"id":"1906.07337","title":"Measuring Bias in Contextualized Word Representations","created":"2019-06-18","cited_by_count":276},{"id":"1903.03862","title":"Lipstick on a Pig: Debiasing Methods Cover up Systematic Gender Biases in Word Embeddings But do not Remove Them","created":"2019-03-09","cited_by_count":268},{"id":"1711.08412","title":"Word Embeddings Quantify 100 Years of Gender and Ethnic Stereotypes","created":"2017-11-22","cited_by_count":253},{"id":"2402.19446","title":"ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL","created":"2024-02-29","cited_by_count":228},{"id":"2010.06032","title":"Measuring and Reducing Gendered Correlations in Pre-trained Models","created":"2020-10-12","cited_by_count":224},{"id":"1904.03035","title":"Identifying and Reducing Gender Bias in Word-Level Language Models","created":"2019-04-05","cited_by_count":214},{"id":"1807.11714","title":"Gender Bias in Neural Natural Language Processing","created":"2018-07-31","cited_by_count":211},{"id":"1904.03310","title":"Gender Bias in Contextualized Word Embeddings","created":"2019-04-05","cited_by_count":203},{"id":"2012.15816","title":"Fairness in Machine Learning","created":"2020-12-31","cited_by_count":194},{"id":"1901.10002","title":"A Framework for Understanding Sources of Harm throughout the Machine Learning Life Cycle","created":"2019-01-28","cited_by_count":193},{"id":"2308.14921","title":"Gender bias and stereotypes in Large Language Models","created":"2023-08-28","cited_by_count":187},{"id":"2202.11176","title":"A New Generation of Perspective API: Efficient Multilingual Character-level Transformers","created":"2022-02-22","cited_by_count":185},{"id":"2308.13387","title":"Do-Not-Answer: A Dataset for Evaluating Safeguards in LLMs","created":"2023-08-25","cited_by_count":184},{"id":"2106.10328","title":"Process for Adapting Language Models to Society (PALMS) with Values-Targeted Datasets","created":"2021-06-18","cited_by_count":181},{"id":"1905.12843","title":"Fair Regression: Quantitative Definitions and Reduction-based Algorithms","created":"2019-05-30","cited_by_count":168},{"id":"2006.03955","title":"Detecting Emergent Intersectional Biases: Contextualized Word Embeddings Contain a Distribution of Human-like Biases","created":"2020-06-06","cited_by_count":167},{"id":"1911.03842","title":"Queens are Powerful too: Mitigating Gender Bias in Dialogue Generation","created":"2019-11-10","cited_by_count":152},{"id":"1809.10610","title":"Counterfactual Fairness in Text Classification through Robustness","created":"2018-09-27","cited_by_count":151},{"id":"2012.15859","title":"Intrinsic Bias Metrics Do Not Correlate with Application Bias","created":"2020-12-31","cited_by_count":148},{"id":"2304.03738","title":"Should ChatGPT be Biased? Challenges and Risks of Bias in Large Language Models","created":"2023-04-07","cited_by_count":148},{"id":"2402.01908","title":"Large language models that replace human participants can harmfully misportray and flatten identity groups","created":"2024-02-02","cited_by_count":144},{"id":"1912.03593","title":"Towards a Critical Race Methodology in Algorithmic Fairness","created":"2019-12-08","cited_by_count":125},{"id":"2309.10313","title":"Investigating the Catastrophic Forgetting in Multimodal Large Language Models","created":"2023-09-19","cited_by_count":119},{"id":"1705.09899","title":"Understanding Abuse: A Typology of Abusive Language Detection Subtasks","created":"2017-05-28","cited_by_count":116},{"id":"2205.12688","title":"ProsocialDialog: A Prosocial Backbone for Conversational Agents","created":"2022-05-25","cited_by_count":109},{"id":"2101.09523","title":"Debiasing Pre-trained Contextualised Embeddings","created":"2021-01-23","cited_by_count":107},{"id":"2109.03646","title":"Sustainable Modular Debiasing of Language Models","created":"2021-09-08","cited_by_count":100},{"id":"1810.03611","title":"Understanding the Origins of Bias in Word Embeddings","created":"2018-10-08","cited_by_count":91},{"id":"1910.10486","title":"Does Gender Matter? Towards Fairness in Dialogue Systems","created":"2019-10-16","cited_by_count":89},{"id":"2109.05704","title":"Mitigating Language-Dependent Ethnic Bias in BERT","created":"2021-09-13","cited_by_count":87},{"id":"2303.13379","title":"Practical and Ethical Challenges of Large Language Models in Education: A Systematic Scoping Review","created":"2023-03-17","cited_by_count":83},{"id":"2010.14534","title":"Unmasking Contextual Stereotypes: Measuring and Mitigating BERT's Gender Bias","created":"2020-10-27","cited_by_count":82},{"id":"2303.16626","title":"Fairlearn: Assessing and Improving Fairness of AI Systems","created":"2023-03-29","cited_by_count":74},{"id":"1906.00742","title":"Gender-preserving Debiasing for Pre-trained Word Embeddings","created":"2019-06-03","cited_by_count":61},{"id":"1805.10627","title":"Reliability and Learnability of Human Bandit Feedback for Sequence-to-Sequence Reinforcement Learning","created":"2018-05-27","cited_by_count":57},{"id":"1905.12801","title":"Reducing Gender Bias in Word-Level Language Models with a Gender-Equalizing Loss Function","created":"2019-05-30","cited_by_count":57},{"id":"2203.09192","title":"Entropy-based Attention Regularization Frees Unintended Bias Mitigation from Lists","created":"2022-03-17","cited_by_count":55},{"id":"2311.03449","title":"Into the LAIONs Den: Investigating Hate in Multimodal Datasets","created":"2023-11-06","cited_by_count":54},{"id":"2407.12687","title":"Towards Responsible Development of Generative AI for Education: An Evaluation-Driven Approach","created":"2024-05-21","cited_by_count":54},{"id":"2205.12586","title":"Perturbation Augmentation for Fairer NLP","created":"2022-05-25","cited_by_count":52},{"id":"2310.10072","title":"Fine-tuning ChatGPT for Automatic Scoring","created":"2023-10-16","cited_by_count":51},{"id":"2302.02463","title":"Nationality Bias in Text Generation","created":"2023-02-05","cited_by_count":50},{"id":"2310.08184","title":"Learning from models beyond fine-tuning","created":"2023-10-12","cited_by_count":48},{"id":"2202.11923","title":"Welcome to the Modern World of Pronouns: Identity-Inclusive Natural Language Processing beyond Gender","created":"2022-02-24","cited_by_count":47},{"id":"2204.03031","title":"VALUE: Understanding Dialect Disparity in NLU","created":"2022-04-06","cited_by_count":47}],"next_cursor":"100"}