{"list":"other","total":58,"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":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"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":"2307.15043","title":"Universal and Transferable Adversarial Attacks on Aligned Language Models","created":"2023-07-27","cited_by_count":3104},{"id":"1508.07909","title":"Neural Machine Translation of Rare Words with Subword Units","created":"2015-08-31","cited_by_count":2918},{"id":"2004.11362","title":"Supervised Contrastive Learning","created":"2020-04-23","cited_by_count":2829},{"id":"1610.02136","title":"A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks","created":"2016-10-07","cited_by_count":2385},{"id":"2310.08419","title":"Jailbreaking Black Box Large Language Models in Twenty Queries","created":"2023-10-12","cited_by_count":1420},{"id":"2010.03759","title":"Energy-based Out-of-distribution Detection","created":"2020-10-08","cited_by_count":1299},{"id":"1909.06146","title":"PubMedQA: A Dataset for Biomedical Research Question Answering","created":"2019-09-13","cited_by_count":1288},{"id":"2012.15723","title":"Making Pre-trained Language Models Better Few-shot Learners","created":"2020-12-31","cited_by_count":1256},{"id":"2312.06674","title":"Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations","created":"2023-12-07","cited_by_count":1207},{"id":"2310.03693","title":"Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!","created":"2023-10-05","cited_by_count":1154},{"id":"2112.00861","title":"A General Language Assistant as a Laboratory for Alignment","created":"2021-12-01","cited_by_count":1055},{"id":"2202.03286","title":"Red Teaming Language Models with Language Models","created":"2022-02-07","cited_by_count":1026},{"id":"2211.09527","title":"Ignore Previous Prompt: Attack Techniques For Language Models","created":"2022-11-17","cited_by_count":832},{"id":"2310.04451","title":"AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models","created":"2023-10-03","cited_by_count":785},{"id":"1908.07125","title":"Universal Adversarial Triggers for Attacking and Analyzing NLP","created":"2019-08-20","cited_by_count":722},{"id":"2312.02119","title":"Tree of Attacks: Jailbreaking Black-Box LLMs Automatically","created":"2023-12-04","cited_by_count":672},{"id":"2310.12773","title":"Safe RLHF: Safe Reinforcement Learning from Human Feedback","created":"2023-10-19","cited_by_count":656},{"id":"2309.00614","title":"Baseline Defenses for Adversarial Attacks Against Aligned Language Models","created":"2023-09-01","cited_by_count":651},{"id":"2210.15097","title":"Contrastive Decoding: Open-ended Text Generation as Optimization","created":"2022-10-27","cited_by_count":609},{"id":"1707.07328","title":"Adversarial Examples for Evaluating Reading Comprehension Systems","created":"2017-07-23","cited_by_count":571},{"id":"2010.14701","title":"Scaling Laws for Autoregressive Generative Modeling","created":"2020-10-28","cited_by_count":522},{"id":"1906.02845","title":"Likelihood Ratios for Out-of-Distribution Detection","created":"2019-06-07","cited_by_count":453},{"id":"2306.15447","title":"Are aligned neural networks adversarially aligned?","created":"2023-06-26","cited_by_count":315},{"id":"2309.02705","title":"Certifying LLM Safety against Adversarial Prompting","created":"2023-09-06","cited_by_count":266},{"id":"2312.14925","title":"A Survey of Reinforcement Learning from Human Feedback","created":"2023-12-22","cited_by_count":264},{"id":"2402.16822","title":"Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts","created":"2024-02-26","cited_by_count":205},{"id":"2305.13971","title":"Grammar-Constrained Decoding for Structured NLP Tasks without Finetuning","created":"2023-05-23","cited_by_count":197},{"id":"2303.04381","title":"Automatically Auditing Large Language Models via Discrete Optimization","created":"2023-03-08","cited_by_count":191},{"id":"2402.05749","title":"Generalized Preference Optimization: A Unified Approach to Offline Alignment","created":"2024-02-08","cited_by_count":157},{"id":"2305.16938","title":"Few-shot Fine-tuning vs. In-context Learning: A Fair Comparison and Evaluation","created":"2023-05-26","cited_by_count":136},{"id":"2209.06640","title":"Revisiting Neural Scaling Laws in Language and Vision","created":"2022-09-13","cited_by_count":132},{"id":"2108.00401","title":"Advances in adversarial attacks and defenses in computer vision: A survey","created":"2021-08-01","cited_by_count":127},{"id":"2405.21018","title":"Improved Techniques for Optimization-Based Jailbreaking on Large Language Models","created":"2024-05-31","cited_by_count":110},{"id":"2406.02622","title":"Safeguarding Large Language Models: A Survey","created":"2024-06-03","cited_by_count":78},{"id":"2104.08812","title":"Contrastive Out-of-Distribution Detection for Pretrained Transformers","created":"2021-04-18","cited_by_count":71},{"id":"2101.03778","title":"Revisiting Mahalanobis Distance for Transformer-Based Out-of-Domain Detection","created":"2021-01-11","cited_by_count":70},{"id":"2112.11668","title":"How Should Pre-Trained Language Models Be Fine-Tuned Towards Adversarial Robustness?","created":"2021-12-22","cited_by_count":49},{"id":"2310.10077","title":"Prompt Packer: Deceiving LLMs through Compositional Instruction with Hidden Attacks","created":"2023-10-16","cited_by_count":35},{"id":"1912.12800","title":"Likelihood Ratios and Generative Classifiers for Unsupervised Out-of-Domain Detection In Task Oriented Dialog","created":"2019-12-30","cited_by_count":33},{"id":"2305.13282","title":"Is Fine-tuning Needed? Pre-trained Language Models Are Near Perfect for Out-of-Domain Detection","created":"2023-05-22","cited_by_count":29},{"id":"2403.10144","title":"NLP Verification: Towards a General Methodology for Certifying Robustness","created":"2024-03-15","cited_by_count":16},{"id":"2408.05284","title":"Can a Bayesian Oracle Prevent Harm from an Agent?","created":"2024-08-09","cited_by_count":13},{"id":"2404.08679","title":"Your Finetuned Large Language Model is Already a Powerful Out-of-distribution Detector","created":"2024-04-07","cited_by_count":11},{"id":"2404.17785","title":"Temporal Scaling Law for Large Language Models","created":"2024-04-27","cited_by_count":11},{"id":"2308.13768","title":"Adversarial Fine-Tuning of Language Models: An Iterative Optimisation Approach for the Generation and Detection of Problematic Content","created":"2023-08-26","cited_by_count":7},{"id":"2310.05083","title":"FLatS: Principled Out-of-Distribution Detection with Feature-Based Likelihood Ratio Score","created":"2023-10-08","cited_by_count":5},{"id":"2411.12946","title":"A Flexible Large Language Models Guardrail Development Methodology Applied to Off-Topic Prompt Detection","created":"2024-11-20","cited_by_count":3},{"id":"2401.01262","title":"Fairness Certification for Natural Language Processing and Large Language Models","created":"2024-01-02","cited_by_count":1}],"next_cursor":null}