{"list":"other","total":71,"rows":[{"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":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"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":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"2212.10560","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","created":"2022-12-20","cited_by_count":2724},{"id":"2303.12712","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","created":"2023-03-22","cited_by_count":2592},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"2009.11462","title":"RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models","created":"2020-09-24","cited_by_count":1255},{"id":"2305.04388","title":"Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting","created":"2023-05-07","cited_by_count":1122},{"id":"1510.03055","title":"A Diversity-Promoting Objective Function for Neural Conversation Models","created":"2015-10-11","cited_by_count":1077},{"id":"2211.01910","title":"Large Language Models Are Human-Level Prompt Engineers","created":"2022-11-03","cited_by_count":1045},{"id":"2103.10360","title":"GLM: General Language Model Pretraining with Autoregressive Blank Infilling","created":"2021-03-18","cited_by_count":1031},{"id":"2112.04359","title":"Ethical and social risks of harm from Language Models","created":"2021-12-08","cited_by_count":966},{"id":"2004.09456","title":"StereoSet: Measuring stereotypical bias in pretrained language models","created":"2020-04-20","cited_by_count":924},{"id":"2307.04657","title":"BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset","created":"2023-07-10","cited_by_count":860},{"id":"2212.09251","title":"Discovering Language Model Behaviors with Model-Written Evaluations","created":"2022-12-19","cited_by_count":836},{"id":"2305.11738","title":"CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing","created":"2023-05-19","cited_by_count":783},{"id":"1807.02811","title":"A Tutorial on Bayesian Optimization","created":"2018-07-08","cited_by_count":744},{"id":"2008.02275","title":"Aligning AI With Shared Human Values","created":"2020-08-05","cited_by_count":723},{"id":"1802.01886","title":"Texygen: A Benchmarking Platform for Text Generation Models","created":"2018-02-06","cited_by_count":491},{"id":"2304.05302","title":"RRHF: Rank Responses to Align Language Models with Human Feedback without tears","created":"2023-04-11","cited_by_count":463},{"id":"2001.09768","title":"Artificial Intelligence, Values and Alignment","created":"2020-01-13","cited_by_count":448},{"id":"1905.07088","title":"Sliced Score Matching: A Scalable Approach to Density and Score Estimation","created":"2019-05-17","cited_by_count":384},{"id":"2206.05802","title":"Self-critiquing models for assisting human evaluators","created":"2022-06-12","cited_by_count":380},{"id":"2009.06367","title":"GeDi: Generative Discriminator Guided Sequence Generation","created":"2020-09-14","cited_by_count":378},{"id":"2104.05218","title":"FUDGE: Controlled Text Generation With Future Discriminators","created":"2021-04-12","cited_by_count":376},{"id":"2205.12548","title":"RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning","created":"2022-05-25","cited_by_count":366},{"id":"2304.05335","title":"Toxicity in ChatGPT: Analyzing Persona-assigned Language Models","created":"2023-04-11","cited_by_count":360},{"id":"2304.05197","title":"Multi-step Jailbreaking Privacy Attacks on ChatGPT","created":"2023-04-11","cited_by_count":333},{"id":"2106.13219","title":"Towards Understanding and Mitigating Social Biases in Language Models","created":"2021-06-24","cited_by_count":296},{"id":"1502.05700","title":"Scalable Bayesian Optimization Using Deep Neural Networks","created":"2015-02-19","cited_by_count":284},{"id":"2209.00626","title":"The Alignment Problem from a Deep Learning Perspective","created":"2022-08-30","cited_by_count":258},{"id":"2011.00620","title":"Social Chemistry 101: Learning to Reason about Social and Moral Norms","created":"2020-11-01","cited_by_count":255},{"id":"2307.10169","title":"Challenges and Applications of Large Language Models","created":"2023-07-19","cited_by_count":254},{"id":"2203.08242","title":"Data Contamination: From Memorization to Exploitation","created":"2022-03-15","cited_by_count":236},{"id":"2303.04226","title":"A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPT","created":"2023-03-07","cited_by_count":224},{"id":"2307.14324","title":"Evaluating the Moral Beliefs Encoded in LLMs","created":"2023-07-26","cited_by_count":215},{"id":"2306.09479","title":"Inverse Scaling: When Bigger Isn't Better","created":"2023-06-15","cited_by_count":207},{"id":"2303.17466","title":"Assessing Cross-Cultural Alignment between ChatGPT and Human Societies: An Empirical Study","created":"2023-03-30","cited_by_count":206},{"id":"2302.10724","title":"ChatGPT: Jack of all trades, master of none","created":"2023-02-21","cited_by_count":204},{"id":"2105.04054","title":"Societal Biases in Language Generation: Progress and Challenges","created":"2021-05-10","cited_by_count":202},{"id":"2308.03958","title":"Simple synthetic data reduces sycophancy in large language models","created":"2023-08-07","cited_by_count":187},{"id":"1804.06609","title":"Fast Lexically Constrained Decoding with Dynamic Beam Allocation for Neural Machine Translation","created":"2018-04-18","cited_by_count":182},{"id":"2308.08493","title":"Time Travel in LLMs: Tracing Data Contamination in Large Language Models","created":"2023-08-16","cited_by_count":177},{"id":"2302.07459","title":"The Capacity for Moral Self-Correction in Large Language Models","created":"2023-02-15","cited_by_count":173},{"id":"2109.07445","title":"Challenges in Detoxifying Language Models","created":"2021-09-15","cited_by_count":169},{"id":"2202.11705","title":"COLD Decoding: Energy-based Constrained Text Generation with Langevin Dynamics","created":"2022-02-23","cited_by_count":161},{"id":"2112.08726","title":"NeuroLogic A*esque Decoding: Constrained Text Generation with Lookahead Heuristics","created":"2021-12-16","cited_by_count":154},{"id":"2203.13722","title":"Probing Pre-Trained Language Models for Cross-Cultural Differences in Values","created":"2022-03-25","cited_by_count":149},{"id":"2110.07574","title":"Can Machines Learn Morality? The Delphi Experiment","created":"2021-10-14","cited_by_count":141},{"id":"2012.15738","title":"Moral Stories: Situated Reasoning about Norms, Intents, Actions, and their Consequences","created":"2020-12-31","cited_by_count":135},{"id":"2305.18486","title":"A Systematic Study and Comprehensive Evaluation of ChatGPT on Benchmark Datasets","created":"2023-05-29","cited_by_count":123},{"id":"2005.00268","title":"Towards Controllable Biases in Language Generation","created":"2020-05-01","cited_by_count":112},{"id":"1612.00576","title":"Guided Open Vocabulary Image Captioning with Constrained Beam Search","created":"2016-12-02","cited_by_count":105},{"id":"2010.02194","title":"Self-training Improves Pre-training for Natural Language Understanding","created":"2020-10-05","cited_by_count":96},{"id":"2204.03021","title":"The Moral Integrity Corpus: A Benchmark for Ethical Dialogue Systems","created":"2022-04-06","cited_by_count":93},{"id":"2210.01478","title":"When to Make Exceptions: Exploring Language Models as Accounts of Human Moral Judgment","created":"2022-10-04","cited_by_count":93},{"id":"2303.05453","title":"Personalisation within bounds: A risk taxonomy and policy framework for the alignment of large language models with personalised feedback","created":"2023-03-09","cited_by_count":87},{"id":"1912.13464","title":"Model Inversion Networks for Model-Based Optimization","created":"2019-12-31","cited_by_count":83},{"id":"2209.12106","title":"Moral Mimicry: Large Language Models Produce Moral Rationalizations Tailored to Political Identity","created":"2022-09-24","cited_by_count":74},{"id":"1803.05928","title":"RankME: Reliable Human Ratings for Natural Language Generation","created":"2018-03-15","cited_by_count":69},{"id":"2306.03082","title":"InstructZero: Efficient Instruction Optimization for Black-Box Large Language Models","created":"2023-06-05","cited_by_count":68},{"id":"2110.10873","title":"Controllable and Compositional Generation with Latent-Space Energy-Based Models","created":"2021-10-21","cited_by_count":64},{"id":"2205.12771","title":"Does Moral Code Have a Moral Code? Probing Delphi's Moral Philosophy","created":"2022-05-25","cited_by_count":31},{"id":"2302.05619","title":"Evaluating the Robustness of Discrete Prompts","created":"2023-02-11","cited_by_count":18},{"id":"2210.07652","title":"Enabling Classifiers to Make Judgements Explicitly Aligned with Human Values","created":"2022-10-14","cited_by_count":13},{"id":"2302.07371","title":"BiasTestGPT: Using ChatGPT for Social Bias Testing of Language Models","created":"2023-02-14","cited_by_count":8}],"next_cursor":null}