{"list":"other","total":69,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1706.06083","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","created":"2017-06-19","cited_by_count":6415},{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"id":"1301.3781","title":"Efficient Estimation of Word Representations in Vector Space","created":"2013-01-16","cited_by_count":4375},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"2307.15043","title":"Universal and Transferable Adversarial Attacks on Aligned Language Models","created":"2023-07-27","cited_by_count":3104},{"id":"2202.05262","title":"Locating and Editing Factual Associations in GPT","created":"2022-02-10","cited_by_count":2691},{"id":"2406.01574","title":"MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark","created":"2024-06-03","cited_by_count":1848},{"id":"2307.02483","title":"Jailbroken: How Does LLM Safety Training Fail?","created":"2023-07-05","cited_by_count":1651},{"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":"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":"1802.00420","title":"Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples","created":"2018-02-01","cited_by_count":1268},{"id":"2308.03688","title":"AgentBench: Evaluating LLMs as Agents","created":"2023-08-07","cited_by_count":1267},{"id":"2212.04089","title":"Editing Models with Task Arithmetic","created":"2022-12-08","cited_by_count":1120},{"id":"2202.03286","title":"Red Teaming Language Models with Language Models","created":"2022-02-07","cited_by_count":1026},{"id":"2210.07229","title":"Mass-Editing Memory in a Transformer","created":"2022-10-13","cited_by_count":1001},{"id":"2305.14233","title":"Enhancing Chat Language Models by Scaling High-quality Instructional Conversations","created":"2023-05-23","cited_by_count":839},{"id":"2312.02119","title":"Tree of Attacks: Jailbreaking Black-Box LLMs Automatically","created":"2023-12-04","cited_by_count":672},{"id":"2110.11309","title":"Fast Model Editing at Scale","created":"2021-10-21","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":"2206.06520","title":"Memory-Based Model Editing at Scale","created":"2022-06-13","cited_by_count":447},{"id":"2308.14132","title":"Detecting Language Model Attacks with Perplexity","created":"2023-08-27","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":"2302.03668","title":"Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery","created":"2023-02-07","cited_by_count":336},{"id":"2306.15447","title":"Are aligned neural networks adversarially aligned?","created":"2023-06-26","cited_by_count":315},{"id":"2401.13601","title":"MM-LLMs: Recent Advances in MultiModal Large Language Models","created":"2024-01-24","cited_by_count":278},{"id":"2404.09932","title":"Foundational Challenges in Assuring Alignment and Safety of Large Language Models","created":"2024-04-15","cited_by_count":199},{"id":"2310.10844","title":"Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attacks","created":"2023-10-16","cited_by_count":194},{"id":"2402.00888","title":"Security and Privacy Challenges of Large Language Models: A Survey","created":"2024-01-30","cited_by_count":186},{"id":"2005.07727","title":"Semantic Photo Manipulation with a Generative Image Prior","created":"2020-05-15","cited_by_count":178},{"id":"2309.00236","title":"Image Hijacks: Adversarial Images can Control Generative Models at Runtime","created":"2023-09-01","cited_by_count":172},{"id":"2202.09061","title":"VLP: A Survey on Vision-Language Pre-training","created":"2022-02-18","cited_by_count":159},{"id":"2111.03186","title":"EditGAN: High-Precision Semantic Image Editing","created":"2021-11-04","cited_by_count":156},{"id":"2401.17263","title":"Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks","created":"2024-01-30","cited_by_count":156},{"id":"2308.10741","title":"On the Adversarial Robustness of Multi-Modal Foundation Models","created":"2023-08-21","cited_by_count":145},{"id":"2401.15897","title":"Red-Teaming for Generative AI: Silver Bullet or Security Theater?","created":"2024-01-29","cited_by_count":83},{"id":"1611.05507","title":"Deep Feature Interpolation for Image Content Changes","created":"2016-11-16","cited_by_count":80},{"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":"2403.07918","title":"On the Societal Impact of Open Foundation Models","created":"2024-02-27","cited_by_count":65},{"id":"2310.02521","title":"Who Audits the Auditors? Recommendations from a field scan of the algorithmic auditing ecosystem","created":"2023-10-04","cited_by_count":52},{"id":"2402.15911","title":"PRP: Propagating Universal Perturbations to Attack Large Language Model Guard-Rails","created":"2024-02-24","cited_by_count":52},{"id":"2404.05880","title":"Eraser: Jailbreaking Defense in Large Language Models via Unlearning Harmful Knowledge","created":"2024-04-08","cited_by_count":51},{"id":"2312.12321","title":"Bypassing the Safety Training of Open-Source LLMs with Priming Attacks","created":"2023-12-19","cited_by_count":50},{"id":"2402.10104","title":"GeoEval: Benchmark for Evaluating LLMs and Multi-Modal Models on Geometry Problem-Solving","created":"2024-02-15","cited_by_count":45},{"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":"2405.11613","title":"Decoding by Contrasting Knowledge: Enhancing LLMs' Confidence on Edited Facts","created":"2024-05-19","cited_by_count":36},{"id":"2305.15065","title":"Inference-Time Policy Adapters (IPA): Tailoring Extreme-Scale LMs without Fine-tuning","created":"2023-05-24","cited_by_count":33},{"id":"2312.14871","title":"BrainVis: Exploring the Bridge between Brain and Visual Signals via Image Reconstruction","created":"2023-12-22","cited_by_count":30},{"id":"2309.05973","title":"Circuit Breaking: Removing Model Behaviors with Targeted Ablation","created":"2023-09-12","cited_by_count":27},{"id":"2406.11668","title":"\"Not Aligned\" is Not \"Malicious\": Being Careful about Hallucinations of Large Language Models' Jailbreak","created":"2024-06-17","cited_by_count":25},{"id":"2007.08128","title":"Detecting Out-of-distribution Samples via Variational Auto-encoder with Reliable Uncertainty Estimation","created":"2020-07-16","cited_by_count":24},{"id":"2311.16476","title":"LANS: A Layout-Aware Neural Solver for Plane Geometry Problem","created":"2023-11-25","cited_by_count":24},{"id":"2401.12585","title":"SLANG: New Concept Comprehension of Large Language Models","created":"2024-01-23","cited_by_count":20},{"id":"2402.07140","title":"Can Graph Descriptive Order Affect Solving Graph Problems with LLMs?","created":"2024-02-11","cited_by_count":16},{"id":"2406.13375","title":"ALiiCE: Evaluating Positional Fine-grained Citation Generation","created":"2024-06-19","cited_by_count":15},{"id":"2407.12023","title":"CMMaTH: A Chinese Multi-modal Math Skill Evaluation Benchmark for Foundation Models","created":"2024-06-28","cited_by_count":15},{"id":"2405.19996","title":"DP-IQA: Utilizing Diffusion Prior for Blind Image Quality Assessment in the Wild","created":"2024-05-30","cited_by_count":14},{"id":"2406.12468","title":"Adaptive Token Biaser: Knowledge Editing via Biasing Key Entities","created":"2024-06-18","cited_by_count":14},{"id":"2407.07327","title":"Fuse, Reason and Verify: Geometry Problem Solving with Parsed Clauses from Diagram","created":"2024-07-10","cited_by_count":13},{"id":"2409.10132","title":"StruEdit: Structured Outputs Enable the Fast and Accurate Knowledge Editing for Large Language Models","created":"2024-09-16","cited_by_count":9},{"id":"2401.13227","title":"LPNL: Scalable Link Prediction with Large Language Models","created":"2024-01-24","cited_by_count":7},{"id":"2306.03538","title":"SDR-GAIN: A High Real-Time Occluded Pedestrian Pose Completion Method for Autonomous Driving","created":"2023-06-06","cited_by_count":1}],"next_cursor":null}