{"list":"other","total":64,"rows":[{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"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":"1705.03551","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","created":"2017-05-09","cited_by_count":2955},{"id":"2202.05262","title":"Locating and Editing Factual Associations in GPT","created":"2022-02-10","cited_by_count":2691},{"id":"2307.02483","title":"Jailbroken: How Does LLM Safety Training Fail?","created":"2023-07-05","cited_by_count":1651},{"id":"2310.01405","title":"Representation Engineering: A Top-Down Approach to AI Transparency","created":"2023-10-02","cited_by_count":1336},{"id":"1808.08745","title":"Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization","created":"2018-08-27","cited_by_count":1317},{"id":"2210.07229","title":"Mass-Editing Memory in a Transformer","created":"2022-10-13","cited_by_count":1001},{"id":"2309.10253","title":"GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts","created":"2023-09-19","cited_by_count":560},{"id":"2203.14680","title":"Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space","created":"2022-03-28","cited_by_count":532},{"id":"2306.11698","title":"DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models","created":"2023-06-20","cited_by_count":518},{"id":"2305.13860","title":"Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study","created":"2023-05-23","cited_by_count":498},{"id":"2310.03684","title":"SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks","created":"2023-10-05","cited_by_count":469},{"id":"2310.06987","title":"Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation","created":"2023-10-10","cited_by_count":451},{"id":"2206.06520","title":"Memory-Based Model Editing at Scale","created":"2022-06-13","cited_by_count":447},{"id":"2310.06387","title":"Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations","created":"2023-10-10","cited_by_count":431},{"id":"2305.13172","title":"Editing Large Language Models: Problems, Methods, and Opportunities","created":"2023-05-22","cited_by_count":372},{"id":"2304.05335","title":"Toxicity in ChatGPT: Analyzing Persona-assigned Language Models","created":"2023-04-11","cited_by_count":360},{"id":"2305.14795","title":"MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questions","created":"2023-05-24","cited_by_count":300},{"id":"2305.12740","title":"Can We Edit Factual Knowledge by In-Context Learning?","created":"2023-05-22","cited_by_count":285},{"id":"2211.11031","title":"Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors","created":"2022-11-20","cited_by_count":271},{"id":"2306.03819","title":"LEACE: Perfect linear concept erasure in closed form","created":"2023-06-06","cited_by_count":267},{"id":"2311.08268","title":"A Wolf in Sheep's Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily","created":"2023-11-14","cited_by_count":259},{"id":"2301.04213","title":"Does Localization Inform Editing? Surprising Differences in Causality-Based Localization vs. Knowledge Editing in Language Models","created":"2023-01-10","cited_by_count":243},{"id":"2307.12976","title":"Evaluating the Ripple Effects of Knowledge Editing in Language Models","created":"2023-07-24","cited_by_count":242},{"id":"2301.09785","title":"Transformer-Patcher: One Mistake worth One Neuron","created":"2023-01-24","cited_by_count":197},{"id":"2310.16218","title":"Knowledge Editing for Large Language Models: A Survey","created":"2023-10-24","cited_by_count":194},{"id":"2309.14348","title":"Defending Against Alignment-Breaking Attacks via Robustly Aligned LLM","created":"2023-09-18","cited_by_count":192},{"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":"2308.08742","title":"PMET: Precise Model Editing in a Transformer","created":"2023-08-17","cited_by_count":173},{"id":"2401.06080","title":"Secrets of RLHF in Large Language Models Part II: Reward Modeling","created":"2024-01-11","cited_by_count":171},{"id":"2311.09096","title":"Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization","created":"2023-11-15","cited_by_count":170},{"id":"2401.07453","title":"Model Editing at Scale leads to Gradual and Catastrophic Forgetting","created":"2024-01-15","cited_by_count":93},{"id":"2312.11795","title":"MELO: Enhancing Model Editing with Neuron-Indexed Dynamic LoRA","created":"2023-12-19","cited_by_count":80},{"id":"2010.05906","title":"Back to the Future: Unsupervised Backprop-based Decoding for Counterfactual and Abductive Commonsense Reasoning","created":"2020-10-12","cited_by_count":65},{"id":"2308.13198","title":"Journey to the Center of the Knowledge Neurons: Discoveries of Language-Independent Knowledge Neurons and Degenerate Knowledge Neurons","created":"2023-08-25","cited_by_count":56},{"id":"2310.09573","title":"Self-Detoxifying Language Models via Toxification Reversal","created":"2023-10-14","cited_by_count":46},{"id":"2311.10538","title":"Testing Language Model Agents Safely in the Wild","created":"2023-11-17","cited_by_count":46},{"id":"2308.12014","title":"From Instructions to Intrinsic Human Values -- A Survey of Alignment Goals for Big Models","created":"2023-08-23","cited_by_count":45},{"id":"2302.00871","title":"Using In-Context Learning to Improve Dialogue Safety","created":"2023-02-02","cited_by_count":42},{"id":"2207.04153","title":"Probing Classifiers are Unreliable for Concept Removal and Detection","created":"2022-07-08","cited_by_count":41},{"id":"2212.10543","title":"Detoxifying Text with MaRCo: Controllable Revision with Experts and Anti-Experts","created":"2022-12-20","cited_by_count":36},{"id":"2311.07470","title":"Finding and Editing Multi-Modal Neurons in Pre-Trained Transformers","created":"2023-11-13","cited_by_count":36},{"id":"2310.19704","title":"A Survey on Knowledge Editing of Neural Networks","created":"2023-10-30","cited_by_count":34},{"id":"2308.08090","title":"Separate the Wheat from the Chaff: Model Deficiency Unlearning via Parameter-Efficient Module Operation","created":"2023-08-16","cited_by_count":33},{"id":"2401.10471","title":"DeepEdit: Knowledge Editing as Decoding with Constraints","created":"2024-01-19","cited_by_count":33},{"id":"2311.05876","title":"Trends in Integration of Knowledge and Large Language Models: A Survey and Taxonomy of Methods, Benchmarks, and Applications","created":"2023-11-10","cited_by_count":28},{"id":"2310.11958","title":"Emptying the Ocean with a Spoon: Should We Edit Models?","created":"2023-10-18","cited_by_count":27},{"id":"2401.01814","title":"Large Language Models Relearn Removed Concepts","created":"2024-01-03","cited_by_count":27},{"id":"2401.17268","title":"Weaver: Foundation Models for Creative Writing","created":"2024-01-30","cited_by_count":27},{"id":"2205.12677","title":"Language Anisotropic Cross-Lingual Model Editing","created":"2022-05-25","cited_by_count":26},{"id":"2308.09954","title":"DocTER: Evaluating Document-based Knowledge Editing","created":"2023-08-19","cited_by_count":26},{"id":"2401.17585","title":"Propagation and Pitfalls: Reasoning-based Assessment of Knowledge Editing through Counterfactual Tasks","created":"2024-01-31","cited_by_count":24},{"id":"2401.10647","title":"Sowing the Wind, Reaping the Whirlwind: The Impact of Editing Language Models","created":"2024-01-19","cited_by_count":20},{"id":"2311.16087","title":"DUnE: Dataset for Unified Editing","created":"2023-11-27","cited_by_count":19},{"id":"2302.07388","title":"Adding Instructions during Pretraining: Effective Way of Controlling Toxicity in Language Models","created":"2023-02-14","cited_by_count":16},{"id":"2312.01858","title":"Evaluating Dependencies in Fact Editing for Language Models: Specificity and Implication Awareness","created":"2023-12-04","cited_by_count":14},{"id":"2312.13040","title":"Retrieval-augmented Multilingual Knowledge Editing","created":"2023-12-20","cited_by_count":13},{"id":"2402.13462","title":"Potential and Challenges of Model Editing for Social Debiasing","created":"2024-02-21","cited_by_count":10},{"id":"2310.17551","title":"Unpacking the Ethical Value Alignment in Big Models","created":"2023-10-26","cited_by_count":9},{"id":"2401.03190","title":"MPN: Leveraging Multilingual Patch Neuron for Cross-lingual Model Editing","created":"2024-01-06","cited_by_count":9},{"id":"2402.05827","title":"On the Robustness of Editing Large Language Models","created":"2024-02-08","cited_by_count":9},{"id":"2401.07544","title":"See the Unseen: Better Context-Consistent Knowledge-Editing by Noises","created":"2024-01-15","cited_by_count":5}],"next_cursor":null}