{"list":"other","total":54,"rows":[{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"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":"1905.07830","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","created":"2019-05-19","cited_by_count":4100},{"id":"1502.01852","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","created":"2015-02-06","cited_by_count":3611},{"id":"2307.15043","title":"Universal and Transferable Adversarial Attacks on Aligned Language Models","created":"2023-07-27","cited_by_count":3104},{"id":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"2402.04249","title":"HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal","created":"2024-02-06","cited_by_count":1429},{"id":"2009.11462","title":"RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models","created":"2020-09-24","cited_by_count":1255},{"id":"2111.09543","title":"DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing","created":"2021-11-18","cited_by_count":1254},{"id":"2202.03286","title":"Red Teaming Language Models with Language Models","created":"2022-02-07","cited_by_count":1026},{"id":"2102.12452","title":"Probing Classifiers: Promises, Shortcomings, and Advances","created":"2021-02-24","cited_by_count":876},{"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":"1503.02406","title":"Deep Learning and the Information Bottleneck Principle","created":"2015-03-09","cited_by_count":802},{"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":"2008.02275","title":"Aligning AI With Shared Human Values","created":"2020-08-05","cited_by_count":723},{"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":"2309.00614","title":"Baseline Defenses for Adversarial Attacks Against Aligned Language Models","created":"2023-09-01","cited_by_count":651},{"id":"2303.08112","title":"Eliciting Latent Predictions from Transformers with the Tuned Lens","created":"2023-03-14","cited_by_count":623},{"id":"2401.05566","title":"Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training","created":"2024-01-10","cited_by_count":529},{"id":"2306.11698","title":"DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models","created":"2023-06-20","cited_by_count":518},{"id":"2308.01263","title":"XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models","created":"2023-08-02","cited_by_count":505},{"id":"2305.13860","title":"Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study","created":"2023-05-23","cited_by_count":498},{"id":"2310.02949","title":"Shadow Alignment: The Ease of Subverting Safely-Aligned Language Models","created":"2023-10-04","cited_by_count":297},{"id":"2309.15025","title":"Large Language Model Alignment: A Survey","created":"2023-09-26","cited_by_count":243},{"id":"2111.08947","title":"Fast Yet Effective Machine Unlearning","created":"2021-11-17","cited_by_count":217},{"id":"2101.04898","title":"Unlearnable Examples: Making Personal Data Unexploitable","created":"2021-01-13","cited_by_count":193},{"id":"2202.11176","title":"A New Generation of Perspective API: Efficient Multilingual Character-level Transformers","created":"2022-02-22","cited_by_count":185},{"id":"2401.01967","title":"A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity","created":"2024-01-03","cited_by_count":185},{"id":"2311.09096","title":"Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization","created":"2023-11-15","cited_by_count":170},{"id":"2402.02207","title":"Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models","created":"2024-02-03","cited_by_count":167},{"id":"2403.06634","title":"Stealing Part of a Production Language Model","created":"2024-03-11","cited_by_count":159},{"id":"2007.02871","title":"DART: Open-Domain Structured Data Record to Text Generation","created":"2020-07-06","cited_by_count":145},{"id":"1611.01353","title":"Information Dropout: Learning Optimal Representations Through Noisy Computation","created":"2016-11-04","cited_by_count":132},{"id":"2311.12786","title":"Mechanistically analyzing the effects of fine-tuning on procedurally defined tasks","created":"2023-11-21","cited_by_count":115},{"id":"2402.01109","title":"Vaccine: Perturbation-aware Alignment for Large Language Models against Harmful Fine-tuning Attack","created":"2024-02-02","cited_by_count":115},{"id":"2308.13320","title":"Fine-tuning can cripple your foundation model; preserving features may be the solution","created":"2023-08-25","cited_by_count":96},{"id":"2402.18540","title":"Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates","created":"2024-02-28","cited_by_count":96},{"id":"2403.05030","title":"Defending Against Unforeseen Failure Modes with Latent Adversarial Training","created":"2024-03-08","cited_by_count":88},{"id":"1911.03905","title":"Semantic Noise Matters for Neural Natural Language Generation","created":"2019-11-10","cited_by_count":64},{"id":"2211.14946","title":"Self-Destructing Models: Increasing the Costs of Harmful Dual Uses of Foundation Models","created":"2022-11-27","cited_by_count":57},{"id":"2311.18140","title":"ROBBIE: Robust Bias Evaluation of Large Generative Language Models","created":"2023-11-29","cited_by_count":53},{"id":"2106.06916","title":"Non-Transferable Learning: A New Approach for Model Ownership Verification and Applicability Authorization","created":"2021-06-13","cited_by_count":52},{"id":"1906.07220","title":"Constrained Decoding for Neural NLG from Compositional Representations in Task-Oriented Dialogue","created":"2019-06-17","cited_by_count":35},{"id":"2402.16382","title":"Immunization against harmful fine-tuning attacks","created":"2024-02-26","cited_by_count":35},{"id":"1910.12129","title":"ViGGO: A Video Game Corpus for Data-To-Text Generation in Open-Domain Conversation","created":"2019-10-26","cited_by_count":31},{"id":"2312.14302","title":"Exploiting Novel GPT-4 APIs","created":"2023-12-21","cited_by_count":28},{"id":"2310.18233","title":"Will releasing the weights of future large language models grant widespread access to pandemic agents?","created":"2023-10-25","cited_by_count":26},{"id":"1907.07331","title":"Learnability for the Information Bottleneck","created":"2019-07-17","cited_by_count":24},{"id":"2310.14303","title":"Language Model Unalignment: Parametric Red-Teaming to Expose Hidden Harms and Biases","created":"2023-10-22","cited_by_count":24},{"id":"2311.02105","title":"Making Harmful Behaviors Unlearnable for Large Language Models","created":"2023-11-02","cited_by_count":20},{"id":"2404.12699","title":"SOPHON: Non-Fine-Tunable Learning to Restrain Task Transferability For Pre-trained Models","created":"2024-04-19","cited_by_count":17},{"id":"2312.14751","title":"Hazards from Increasingly Accessible Fine-Tuning of Downloadable Foundation Models","created":"2023-12-22","cited_by_count":7}],"next_cursor":null}