{"list":"other","total":71,"rows":[{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"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":"2307.15043","title":"Universal and Transferable Adversarial Attacks on Aligned Language Models","created":"2023-07-27","cited_by_count":3104},{"id":"1609.07843","title":"Pointer Sentinel Mixture Models","created":"2016-09-26","cited_by_count":3096},{"id":"2310.08419","title":"Jailbreaking Black Box Large Language Models in Twenty Queries","created":"2023-10-12","cited_by_count":1420},{"id":"2310.01405","title":"Representation Engineering: A Top-Down Approach to AI Transparency","created":"2023-10-02","cited_by_count":1336},{"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":"2406.11717","title":"Refusal in Language Models Is Mediated by a Single Direction","created":"2024-06-17","cited_by_count":1032},{"id":"2306.11695","title":"A Simple and Effective Pruning Approach for Large Language Models","created":"2023-06-20","cited_by_count":800},{"id":"2307.15217","title":"Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback","created":"2023-07-27","cited_by_count":759},{"id":"2304.06364","title":"AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models","created":"2023-04-13","cited_by_count":716},{"id":"2403.03218","title":"The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning","created":"2024-03-05","cited_by_count":509},{"id":"2404.02151","title":"Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks","created":"2024-04-02","cited_by_count":486},{"id":"2406.05946","title":"Safety Alignment Should Be Made More Than Just a Few Tokens Deep","created":"2024-06-10","cited_by_count":472},{"id":"2402.10260","title":"A StrongREJECT for Empty Jailbreaks","created":"2024-02-15","cited_by_count":385},{"id":"2406.04313","title":"Improving Alignment and Robustness with Circuit Breakers","created":"2024-06-06","cited_by_count":322},{"id":"2306.15447","title":"Are aligned neural networks adversarially aligned?","created":"2023-06-26","cited_by_count":315},{"id":"2310.02446","title":"Low-Resource Languages Jailbreak GPT-4","created":"2023-10-03","cited_by_count":309},{"id":"2310.02949","title":"Shadow Alignment: The Ease of Subverting Safely-Aligned Language Models","created":"2023-10-04","cited_by_count":297},{"id":"2402.08787","title":"Rethinking Machine Unlearning for Large Language Models","created":"2024-02-13","cited_by_count":257},{"id":"2402.14762","title":"MT-Bench-101: A Fine-Grained Benchmark for Evaluating Large Language Models in Multi-Turn Dialogues","created":"2024-02-22","cited_by_count":250},{"id":"2402.05162","title":"Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications","created":"2024-02-07","cited_by_count":231},{"id":"2407.04295","title":"Jailbreak Attacks and Defenses Against Large Language Models: A Survey","created":"2024-07-05","cited_by_count":230},{"id":"2310.20624","title":"LoRA Fine-tuning Efficiently Undoes Safety Training in Llama 2-Chat 70B","created":"2023-10-31","cited_by_count":195},{"id":"2310.10844","title":"Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attacks","created":"2023-10-16","cited_by_count":194},{"id":"2305.15324","title":"Model evaluation for extreme risks","created":"2023-05-24","cited_by_count":177},{"id":"2407.15549","title":"Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs","created":"2024-07-22","cited_by_count":173},{"id":"2311.05553","title":"Removing RLHF Protections in GPT-4 via Fine-Tuning","created":"2023-11-09","cited_by_count":171},{"id":"2402.16835","title":"Eight Methods to Evaluate Robust Unlearning in LLMs","created":"2024-02-26","cited_by_count":163},{"id":"2309.17410","title":"Can Sensitive Information Be Deleted From LLMs? Objectives for Defending Against Extraction Attacks","created":"2023-09-29","cited_by_count":158},{"id":"2408.15221","title":"LLM Defenses Are Not Robust to Multi-Turn Human Jailbreaks Yet","created":"2024-08-27","cited_by_count":151},{"id":"2406.07358","title":"AI Sandbagging: Language Models can Strategically Underperform on Evaluations","created":"2024-06-11","cited_by_count":145},{"id":"2408.00761","title":"Tamper-Resistant Safeguards for Open-Weight LLMs","created":"2024-08-01","cited_by_count":138},{"id":"2203.12817","title":"Continual Learning and Private Unlearning","created":"2022-03-24","cited_by_count":130},{"id":"2409.18025","title":"An Adversarial Perspective on Machine Unlearning for AI Safety","created":"2024-09-26","cited_by_count":123},{"id":"2311.12786","title":"Mechanistically analyzing the effects of fine-tuning on procedurally defined tasks","created":"2023-11-21","cited_by_count":115},{"id":"2405.15589","title":"Efficient Adversarial Training in LLMs with Continuous Attacks","created":"2024-05-24","cited_by_count":113},{"id":"2402.09063","title":"Soft Prompt Threats: Attacking Safety Alignment and Unlearning in Open-Source LLMs through the Embedding Space","created":"2024-02-14","cited_by_count":91},{"id":"2409.18169","title":"Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey","created":"2024-09-26","cited_by_count":90},{"id":"2402.15570","title":"Fast Adversarial Attacks on Language Models In One GPU Minute","created":"2024-02-23","cited_by_count":88},{"id":"2403.05030","title":"Defending Against Unforeseen Failure Modes with Latent Adversarial Training","created":"2024-03-08","cited_by_count":88},{"id":"2410.16454","title":"Catastrophic Failure of LLM Unlearning via Quantization","created":"2024-10-21","cited_by_count":81},{"id":"2406.20053","title":"Covert Malicious Finetuning: Challenges in Safeguarding LLM Adaptation","created":"2024-06-28","cited_by_count":80},{"id":"2410.08827","title":"Do Unlearning Methods Remove Information from Language Model Weights?","created":"2024-10-11","cited_by_count":73},{"id":"2407.01599","title":"JailbreakZoo: Survey, Landscapes, and Horizons in Jailbreaking Large Language and Vision-Language Models","created":"2024-06-26","cited_by_count":70},{"id":"2407.09121","title":"Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training","created":"2024-07-12","cited_by_count":69},{"id":"2206.04737","title":"Outsider Oversight: Designing a Third Party Audit Ecosystem for AI Governance","created":"2022-06-09","cited_by_count":67},{"id":"2404.00629","title":"Against The Achilles' Heel: A Survey on Red Teaming for Generative Models","created":"2024-03-31","cited_by_count":59},{"id":"2406.17092","title":"BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Language Models","created":"2024-06-24","cited_by_count":58},{"id":"2412.07097","title":"On Evaluating the Durability of Safeguards for Open-Weight LLMs","created":"2024-12-10","cited_by_count":52},{"id":"2407.00106","title":"UnUnlearning: Unlearning is not sufficient for content regulation in advanced generative AI","created":"2024-06-27","cited_by_count":51},{"id":"2501.04952","title":"Open Problems in Machine Unlearning for AI Safety","created":"2025-01-09","cited_by_count":51},{"id":"2310.19737","title":"Adversarial Attacks and Defenses in Large Language Models: Old and New Threats","created":"2023-10-30","cited_by_count":49},{"id":"2407.14981","title":"Open Problems in Technical AI Governance","created":"2024-07-20","cited_by_count":49},{"id":"2403.10462","title":"Safety Cases: How to Justify the Safety of Advanced AI Systems","created":"2024-03-15","cited_by_count":48},{"id":"2405.17374","title":"Navigating the Safety Landscape: Measuring Risks in Finetuning Large Language Models","created":"2024-05-27","cited_by_count":46},{"id":"2405.19550","title":"Stress-Testing Capability Elicitation With Password-Locked Models","created":"2024-05-29","cited_by_count":46},{"id":"2403.04786","title":"Breaking Down the Defenses: A Comparative Survey of Attacks on Large Language Models","created":"2024-03-03","cited_by_count":44},{"id":"2403.13682","title":"Threats, Attacks, and Defenses in Machine Unlearning: A Survey","created":"2024-03-20","cited_by_count":39},{"id":"2410.02760","title":"Erasing Conceptual Knowledge from Language Models","created":"2024-10-03","cited_by_count":34},{"id":"2405.16229","title":"No Two Devils Alike: Unveiling Distinct Mechanisms of Fine-tuning Attacks","created":"2024-05-25","cited_by_count":29},{"id":"2305.07153","title":"Towards best practices in AGI safety and governance: A survey of expert opinion","created":"2023-05-11","cited_by_count":27},{"id":"2401.01814","title":"Large Language Models Relearn Removed Concepts","created":"2024-01-03","cited_by_count":27},{"id":"1905.05186","title":"Harnessing the Vulnerability of Latent Layers in Adversarially Trained Models","created":"2019-05-13","cited_by_count":26},{"id":"1705.07819","title":"Regularizing deep networks using efficient layerwise adversarial training","created":"2017-05-22","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":"2312.02780","title":"Scaling Laws for Adversarial Attacks on Language Model Activations","created":"2023-12-05","cited_by_count":19},{"id":"2402.00402","title":"Investigating Bias Representations in Llama 2 Chat via Activation Steering","created":"2024-02-01","cited_by_count":14},{"id":"2311.14711","title":"Towards Publicly Accountable Frontier LLMs: Building an External Scrutiny Ecosystem under the ASPIRE Framework","created":"2023-11-15","cited_by_count":11}],"next_cursor":null}