{"list":"other","total":60,"rows":[{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"2307.15043","title":"Universal and Transferable Adversarial Attacks on Aligned Language Models","created":"2023-07-27","cited_by_count":3104},{"id":"2404.14219","title":"Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone","created":"2024-04-22","cited_by_count":1917},{"id":"1611.09268","title":"MS MARCO: A Human Generated MAchine Reading COmprehension Dataset","created":"2016-11-28","cited_by_count":1605},{"id":"2112.09118","title":"Unsupervised Dense Information Retrieval with Contrastive Learning","created":"2021-12-16","cited_by_count":1216},{"id":"2211.09527","title":"Ignore Previous Prompt: Attack Techniques For Language Models","created":"2022-11-17","cited_by_count":832},{"id":"1806.04910","title":"Bilevel Programming for Hyperparameter Optimization and Meta-Learning","created":"2018-06-13","cited_by_count":405},{"id":"2004.06660","title":"Weight Poisoning Attacks on Pre-trained Models","created":"2020-04-14","cited_by_count":341},{"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":"2306.13213","title":"Visual Adversarial Examples Jailbreak Aligned Large Language Models","created":"2023-06-22","cited_by_count":328},{"id":"2309.01431","title":"Benchmarking Large Language Models in Retrieval-Augmented Generation","created":"2023-09-04","cited_by_count":312},{"id":"2302.10149","title":"Poisoning Web-Scale Training Datasets is Practical","created":"2023-02-20","cited_by_count":290},{"id":"2305.00944","title":"Poisoning Language Models During Instruction Tuning","created":"2023-05-01","cited_by_count":269},{"id":"2010.07962","title":"Bilevel Optimization: Convergence Analysis and Enhanced Design","created":"2020-10-15","cited_by_count":222},{"id":"2402.00888","title":"Security and Privacy Challenges of Large Language Models: A Survey","created":"2024-01-30","cited_by_count":186},{"id":"2310.19156","title":"Poisoning Retrieval Corpora by Injecting Adversarial Passages","created":"2023-10-29","cited_by_count":159},{"id":"2305.13661","title":"On the Risk of Misinformation Pollution with Large Language Models","created":"2023-05-23","cited_by_count":128},{"id":"2402.11592","title":"Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark","created":"2024-02-18","cited_by_count":114},{"id":"2106.04692","title":"Provably Faster Algorithms for Bilevel Optimization","created":"2021-06-08","cited_by_count":106},{"id":"2402.13457","title":"A Comprehensive Study of Jailbreak Attack versus Defense for Large Language Models","created":"2024-02-21","cited_by_count":106},{"id":"2209.08709","title":"BOME! Bilevel Optimization Made Easy: A Simple First-Order Approach","created":"2022-09-19","cited_by_count":105},{"id":"2404.05970","title":"Optimization Methods for Personalizing Large Language Models through Retrieval Augmentation","created":"2024-04-09","cited_by_count":99},{"id":"2110.00455","title":"Towards Gradient-based Bilevel Optimization with Non-convex Followers and Beyond","created":"2021-10-01","cited_by_count":63},{"id":"2211.14719","title":"BadPrompt: Backdoor Attacks on Continuous Prompts","created":"2022-11-27","cited_by_count":63},{"id":"2402.09179","title":"Instruction Backdoor Attacks Against Customized LLMs","created":"2024-02-14","cited_by_count":62},{"id":"2106.07991","title":"A Value-Function-based Interior-point Method for Non-convex Bi-level Optimization","created":"2021-06-15","cited_by_count":60},{"id":"2308.10819","title":"Evaluating the Instruction-Following Robustness of Large Language Models to Prompt Injection","created":"2023-08-17","cited_by_count":59},{"id":"2403.01432","title":"Fine Tuning vs. Retrieval Augmented Generation for Less Popular Knowledge","created":"2024-03-03","cited_by_count":50},{"id":"2212.10539","title":"Toward Human Readable Prompt Tuning: Kubrick's The Shining is a good movie, and a good prompt too?","created":"2022-12-20","cited_by_count":49},{"id":"2403.08424","title":"Distract Large Language Models for Automatic Jailbreak Attack","created":"2024-03-13","cited_by_count":45},{"id":"2308.14367","title":"A Comprehensive Overview of Backdoor Attacks in Large Language Models within Communication Networks","created":"2023-08-28","cited_by_count":42},{"id":"1909.03510","title":"Bi-level Actor-Critic for Multi-agent Coordination","created":"2019-09-08","cited_by_count":39},{"id":"2309.17050","title":"Interpretable Long-Form Legal Question Answering with Retrieval-Augmented Large Language Models","created":"2023-09-29","cited_by_count":35},{"id":"2309.13256","title":"Defending Pre-trained Language Models as Few-shot Learners against Backdoor Attacks","created":"2023-09-23","cited_by_count":33},{"id":"2308.02816","title":"PromptCARE: Prompt Copyright Protection by Watermark Injection and Verification","created":"2023-08-05","cited_by_count":32},{"id":"2309.01686","title":"MathAttack: Attacking Large Language Models Towards Math Solving Ability","created":"2023-09-04","cited_by_count":32},{"id":"2311.09641","title":"RLHFPoison: Reward Poisoning Attack for Reinforcement Learning with Human Feedback in Large Language Models","created":"2023-11-16","cited_by_count":32},{"id":"2402.16006","title":"ASETF: A Novel Method for Jailbreak Attack on LLMs through Translate Suffix Embeddings","created":"2024-02-25","cited_by_count":32},{"id":"2106.04188","title":"Stability and Generalization of Bilevel Programming in Hyperparameter Optimization","created":"2021-06-08","cited_by_count":31},{"id":"2302.04116","title":"Training-free Lexical Backdoor Attacks on Language Models","created":"2023-02-08","cited_by_count":31},{"id":"2405.05524","title":"Universal Adversarial Perturbations for Vision-Language Pre-trained Models","created":"2024-05-09","cited_by_count":31},{"id":"2304.05263","title":"Prompt Learning for News Recommendation","created":"2023-04-11","cited_by_count":25},{"id":"2402.11194","title":"Evaluating LLMs' Mathematical Reasoning in Financial Document Question Answering","created":"2024-02-17","cited_by_count":25},{"id":"2405.00175","title":"Towards a Search Engine for Machines: Unified Ranking for Multiple Retrieval-Augmented Large Language Models","created":"2024-04-30","cited_by_count":23},{"id":"2402.19371","title":"OpenMedLM: Prompt engineering can out-perform fine-tuning in medical question-answering with open-source large language models","created":"2024-02-29","cited_by_count":20},{"id":"2402.11891","title":"FeB4RAG: Evaluating Federated Search in the Context of Retrieval Augmented Generation","created":"2024-02-19","cited_by_count":19},{"id":"2402.07179","title":"Prompt Perturbation in Retrieval-Augmented Generation based Large Language Models","created":"2024-02-11","cited_by_count":18},{"id":"2304.14856","title":"A Unified Generative Retriever for Knowledge-Intensive Language Tasks via Prompt Learning","created":"2023-04-28","cited_by_count":16},{"id":"2404.01574","title":"Multi-granular Adversarial Attacks against Black-box Neural Ranking Models","created":"2024-04-02","cited_by_count":14},{"id":"2405.17984","title":"Cross-Context Backdoor Attacks against Graph Prompt Learning","created":"2024-05-28","cited_by_count":14},{"id":"2104.09379","title":"BM-NAS: Bilevel Multimodal Neural Architecture Search","created":"2021-04-19","cited_by_count":13},{"id":"2407.12443","title":"Preventing Catastrophic Overfitting in Fast Adversarial Training: A Bi-level Optimization Perspective","created":"2024-07-17","cited_by_count":13},{"id":"2105.13954","title":"A Gradient Method for Multilevel Optimization","created":"2021-05-28","cited_by_count":12},{"id":"2410.07018","title":"Tri-Level Navigator: LLM-Empowered Tri-Level Learning for Time Series OOD Generalization","created":"2024-10-09","cited_by_count":12},{"id":"2312.12863","title":"Federated Learning While Providing Model as a Service: Joint Training and Inference Optimization","created":"2023-12-20","cited_by_count":8},{"id":"2404.13892","title":"Retrieval-Augmented Audio Deepfake Detection","created":"2024-04-22","cited_by_count":7},{"id":"2312.11835","title":"Provably Convergent Federated Trilevel Learning","created":"2023-12-19","cited_by_count":6},{"id":"2310.06268","title":"Bi-Level Offline Policy Optimization with Limited Exploration","created":"2023-10-10","cited_by_count":5},{"id":"2412.07138","title":"Unlocking TriLevel Learning with Level-Wise Zeroth Order Constraints: Distributed Algorithms and Provable Non-Asymptotic Convergence","created":"2024-12-10","cited_by_count":3}],"next_cursor":null}