{"total":200,"rows":[{"id":"2304.01373","title":"Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling","created":"2023-04-03","cited_by_count":1786,"area":null},{"id":"2212.10511","title":"When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories","created":"2022-12-20","cited_by_count":1128,"area":"rag"},{"id":"2310.01798","title":"Large Language Models Cannot Self-Correct Reasoning Yet","created":"2023-10-03","cited_by_count":1017,"area":"lr"},{"id":"2305.03111","title":"Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs","created":"2023-05-04","cited_by_count":688,"area":null},{"id":"2212.10403","title":"Towards Reasoning in Large Language Models: A Survey","created":"2022-12-20","cited_by_count":596,"area":"lr"},{"id":"2401.06121","title":"TOFU: A Task of Fictitious Unlearning for LLMs","created":"2024-01-11","cited_by_count":533,"area":"safety"},{"id":"2404.05868","title":"Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning","created":"2024-04-08","cited_by_count":504,"area":"alignment"},{"id":"2210.01504","title":"Knowledge Unlearning for Mitigating Privacy Risks in Language Models","created":"2022-10-04","cited_by_count":437,"area":"safety"},{"id":"2312.02003","title":"A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly","created":"2023-12-04","cited_by_count":387,"area":null},{"id":"2304.05197","title":"Multi-step Jailbreaking Privacy Attacks on ChatGPT","created":"2023-04-11","cited_by_count":333,"area":"safety"},{"id":"2302.00539","title":"Analyzing Leakage of Personally Identifiable Information in Language Models","created":"2023-02-01","cited_by_count":285,"area":"safety"},{"id":"2406.01171","title":"Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalization","created":"2024-06-03","cited_by_count":208,"area":null},{"id":"2503.21460","title":"Large Language Model Agent: A Survey on Methodology, Applications and Challenges","created":"2025-03-27","cited_by_count":205,"area":"agents"},{"id":"2310.10844","title":"Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attacks","created":"2023-10-16","cited_by_count":194,"area":"safety"},{"id":"2402.00888","title":"Security and Privacy Challenges of Large Language Models: A Survey","created":"2024-01-30","cited_by_count":186,"area":"safety"},{"id":"2310.05694","title":"A Survey of Large Language Models for Healthcare: from Data, Technology, and Applications to Accountability and Ethics","created":"2023-10-09","cited_by_count":163,"area":null},{"id":"2403.12313","title":"Improving LoRA in Privacy-preserving Federated Learning","created":"2024-03-18","cited_by_count":161,"area":null},{"id":"2401.06855","title":"Fine-grained Hallucination Detection and Editing for Language Models","created":"2024-01-12","cited_by_count":149,"area":null},{"id":"2406.04244","title":"Benchmark Data Contamination of Large Language Models: A Survey","created":"2024-06-06","cited_by_count":147,"area":null},{"id":"2307.01881","title":"ProPILE: Probing Privacy Leakage in Large Language Models","created":"2023-07-04","cited_by_count":129,"area":null},{"id":"2305.00118","title":"Speak, Memory: An Archaeology of Books Known to ChatGPT/GPT-4","created":"2023-04-28","cited_by_count":125,"area":"safety"},{"id":"2306.10070","title":"Opportunities and Challenges for ChatGPT and Large Language Models in Biomedicine and Health","created":"2023-06-15","cited_by_count":118,"area":null},{"id":"2504.15585","title":"A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment","created":"2025-04-22","cited_by_count":116,"area":"lr"},{"id":"2407.12043","title":"The Art of Saying No: Contextual Noncompliance in Language Models","created":"2024-07-02","cited_by_count":105,"area":null},{"id":"2303.11504","title":"Language Model Behavior: A Comprehensive Survey","created":"2023-03-20","cited_by_count":92,"area":null},{"id":"2404.14851","title":"From Matching to Generation: A Survey on Generative Information Retrieval","created":"2024-04-23","cited_by_count":89,"area":null},{"id":"2409.10102","title":"Trustworthiness in Retrieval-Augmented Generation Systems: A Survey","created":"2024-09-16","cited_by_count":83,"area":"rag"},{"id":"2410.16454","title":"Catastrophic Failure of LLM Unlearning via Quantization","created":"2024-10-21","cited_by_count":81,"area":"safety"},{"id":"2404.05399","title":"SafetyPrompts: a Systematic Review of Open Datasets for Evaluating and Improving Large Language Model Safety","created":"2024-04-08","cited_by_count":77,"area":"safety"},{"id":"2402.12483","title":"Artifacts or Abduction: How Do LLMs Answer Multiple-Choice Questions Without the Question?","created":"2024-02-19","cited_by_count":71,"area":null},{"id":"2401.05778","title":"Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems","created":"2024-01-11","cited_by_count":66,"area":null},{"id":"2402.01822","title":"Building Guardrails for Large Language Models","created":"2024-02-02","cited_by_count":65,"area":"safety"},{"id":"2410.08109","title":"A Closer Look at Machine Unlearning for Large Language Models","created":"2024-10-10","cited_by_count":56,"area":"safety"},{"id":"2304.10513","title":"Why Does ChatGPT Fall Short in Providing Truthful Answers?","created":"2023-04-20","cited_by_count":54,"area":null},{"id":"2310.10383","title":"Privacy in Large Language Models: Attacks, Defenses and Future Directions","created":"2023-10-16","cited_by_count":51,"area":null},{"id":"2406.17626","title":"CoSafe: Evaluating Large Language Model Safety in Multi-Turn Dialogue Coreference","created":"2024-06-25","cited_by_count":51,"area":"safety"},{"id":"2305.14965","title":"Tricking LLMs into Disobedience: Formalizing, Analyzing, and Detecting Jailbreaks","created":"2023-05-24","cited_by_count":49,"area":"safety"},{"id":"2311.09538","title":"Reducing Privacy Risks in Online Self-Disclosures with Language Models","created":"2023-11-16","cited_by_count":47,"area":null},{"id":"2306.11547","title":"Event Stream GPT: A Data Pre-processing and Modeling Library for Generative, Pre-trained Transformers over Continuous-time Sequences of Complex Events","created":"2023-06-20","cited_by_count":46,"area":null},{"id":"2305.16157","title":"Training Data Extraction From Pre-trained Language Models: A Survey","created":"2023-05-25","cited_by_count":45,"area":null},{"id":"2503.17003","title":"A Survey on Personalized Alignment -- The Missing Piece for Large Language Models in Real-World Applications","created":"2025-03-21","cited_by_count":42,"area":"alignment"},{"id":"2408.12787","title":"LLM-PBE: Assessing Data Privacy in Large Language Models","created":"2024-08-23","cited_by_count":41,"area":null},{"id":"2308.07922","title":"RAVEN: In-Context Learning with Retrieval-Augmented Encoder-Decoder Language Models","created":"2023-08-15","cited_by_count":37,"area":"rag"},{"id":"2309.11852","title":"Knowledge Sanitization of Large Language Models","created":"2023-09-21","cited_by_count":37,"area":null},{"id":"2311.04044","title":"PrivLM-Bench: A Multi-level Privacy Evaluation Benchmark for Language Models","created":"2023-11-07","cited_by_count":37,"area":null},{"id":"2403.12503","title":"Securing Large Language Models: Threats, Vulnerabilities and Responsible Practices","created":"2024-03-19","cited_by_count":37,"area":null},{"id":"2411.14110","title":"Feedback-Guided Extraction of Knowledge Base from Retrieval-Augmented LLM Applications","created":"2024-11-21","cited_by_count":37,"area":"rag"},{"id":"2310.15469","title":"The Janus Interface: How Fine-Tuning in Large Language Models Amplifies the Privacy Risks","created":"2023-10-24","cited_by_count":36,"area":null},{"id":"2407.16997","title":"Revisiting Who's Harry Potter: Towards Targeted Unlearning from a Causal Intervention Perspective","created":"2024-07-24","cited_by_count":36,"area":"safety"},{"id":"2404.14928","title":"Graph Machine Learning in the Era of Large Language Models (LLMs)","created":"2024-04-23","cited_by_count":33,"area":null},{"id":"2305.14888","title":"Privacy Implications of Retrieval-Based Language Models","created":"2023-05-24","cited_by_count":32,"area":null},{"id":"2403.00871","title":"Teach LLMs to Phish: Stealing Private Information from Language Models","created":"2024-03-01","cited_by_count":32,"area":null},{"id":"2302.14035","title":"The ROOTS Search Tool: Data Transparency for LLMs","created":"2023-02-27","cited_by_count":31,"area":null},{"id":"2309.16595","title":"Can LLMs Effectively Leverage Graph Structural Information through Prompts, and Why?","created":"2023-09-28","cited_by_count":31,"area":null},{"id":"2402.04013","title":"Privacy Leakage on DNNs: A Survey of Model Inversion Attacks and Defenses","created":"2024-02-06","cited_by_count":30,"area":null},{"id":"2312.11658","title":"Traces of Memorisation in Large Language Models for Code","created":"2023-12-18","cited_by_count":29,"area":"safety"},{"id":"2410.02650","title":"Undesirable Memorization in Large Language Models: A Survey","created":"2024-10-03","cited_by_count":29,"area":null},{"id":"2501.18624","title":"Membership Inference Attacks Against Vision-Language Models","created":"2025-01-27","cited_by_count":29,"area":"mllm"},{"id":"2305.12707","title":"Quantifying Association Capabilities of Large Language Models and Its Implications on Privacy Leakage","created":"2023-05-22","cited_by_count":28,"area":null},{"id":"2406.05948","title":"Chain-of-Scrutiny: Detecting Backdoor Attacks for Large Language Models","created":"2024-06-10","cited_by_count":28,"area":"safety"},{"id":"2510.23883","title":"Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges","created":"2025-10-27","cited_by_count":28,"area":"agents"},{"id":"2405.10989","title":"Learnable Privacy Neurons Localization in Language Models","created":"2024-05-16","cited_by_count":27,"area":null},{"id":"2406.08689","title":"Security of AI Agents","created":"2024-06-12","cited_by_count":26,"area":"agents"},{"id":"2409.14457","title":"Large Model Based Agents: State-of-the-Art, Cooperation Paradigms, Security and Privacy, and Future Trends","created":"2024-09-22","cited_by_count":26,"area":null},{"id":"2312.12736","title":"Learning and Forgetting Unsafe Examples in Large Language Models","created":"2023-12-20","cited_by_count":24,"area":null},{"id":"2407.02943","title":"PII-Compass: Guiding LLM training data extraction prompts towards the target PII via grounding","created":"2024-07-03","cited_by_count":24,"area":null},{"id":"2410.07959","title":"COMPL-AI Framework: A Technical Interpretation and LLM Benchmarking Suite for the EU Artificial Intelligence Act","created":"2024-10-10","cited_by_count":24,"area":null},{"id":"2503.10566","title":"ASIDE: Architectural Separation of Instructions and Data in Language Models","created":"2025-03-13","cited_by_count":24,"area":"safety"},{"id":"2407.10058","title":"Learning to Refuse: Towards Mitigating Privacy Risks in LLMs","created":"2024-07-14","cited_by_count":23,"area":"safety"},{"id":"2502.11090","title":"SafeDialBench: A Fine-Grained Safety Evaluation Benchmark for Large Language Models in Multi-Turn Dialogues with Diverse Jailbreak Attacks","created":"2025-02-16","cited_by_count":23,"area":"safety"},{"id":"2503.06808","title":"Privacy Auditing of Large Language Models","created":"2025-03-09","cited_by_count":23,"area":"safety"},{"id":"2409.11423","title":"Generated Data with Fake Privacy: Hidden Dangers of Fine-tuning Large Language Models on Generated Data","created":"2024-09-12","cited_by_count":22,"area":"synth"},{"id":"2307.02185","title":"Citation: A Key to Building Responsible and Accountable Large Language Models","created":"2023-07-05","cited_by_count":20,"area":null},{"id":"2404.11262","title":"Sampling-based Pseudo-Likelihood for Membership Inference Attacks","created":"2024-04-17","cited_by_count":20,"area":"safety"},{"id":"2408.12880","title":"Has Multimodal Learning Delivered Universal Intelligence in Healthcare? A Comprehensive Survey","created":"2024-08-23","cited_by_count":20,"area":null},{"id":"2402.08323","title":"Mapping the Ethics of Generative AI: A Comprehensive Scoping Review","created":"2024-02-13","cited_by_count":19,"area":null},{"id":"2506.22521","title":"A Survey on Model Extraction Attacks and Defenses for Large Language Models","created":"2025-06-26","cited_by_count":19,"area":null},{"id":"2308.15727","title":"Quantifying and Analyzing Entity-level Memorization in Large Language Models","created":"2023-08-30","cited_by_count":18,"area":null},{"id":"2312.11518","title":"User Modeling in the Era of Large Language Models: Current Research and Future Directions","created":"2023-12-11","cited_by_count":18,"area":null},{"id":"2410.09432","title":"FedEx-LoRA: Exact Aggregation for Federated and Efficient Fine-Tuning of Foundation Models","created":"2024-10-12","cited_by_count":18,"area":null},{"id":"2405.19524","title":"AI Risk Management Should Incorporate Both Safety and Security","created":"2024-05-29","cited_by_count":17,"area":null},{"id":"2306.14583","title":"Exploring the Robustness of Large Language Models for Solving Programming Problems","created":"2023-06-26","cited_by_count":16,"area":null},{"id":"2408.11006","title":"Security Attacks on LLM-based Code Completion Tools","created":"2024-08-20","cited_by_count":16,"area":"safety"},{"id":"2307.10476","title":"What can we learn from Data Leakage and Unlearning for Law?","created":"2023-07-19","cited_by_count":15,"area":"safety"},{"id":"2307.16680","title":"On the Trustworthiness Landscape of State-of-the-art Generative Models: A Survey and Outlook","created":"2023-07-31","cited_by_count":15,"area":"diffusion"},{"id":"2410.17050","title":"UnStar: Unlearning with Self-Taught Anti-Sample Reasoning for LLMs","created":"2024-10-22","cited_by_count":15,"area":"lr"},{"id":"2501.18532","title":"Differentially Private Steering for Large Language Model Alignment","created":"2025-01-30","cited_by_count":15,"area":"alignment"},{"id":"2501.05078","title":"Analyzing Memorization in Large Language Models through the Lens of Model Attribution","created":"2025-01-09","cited_by_count":14,"area":null},{"id":"2503.13222","title":"Can Language Models Follow Multiple Turns of Entangled Instructions?","created":"2025-03-17","cited_by_count":14,"area":null},{"id":"2505.00976","title":"Attack and defense techniques in large language models: A survey and new perspectives","created":"2025-05-02","cited_by_count":14,"area":null},{"id":"2505.19504","title":"DOGe: Defensive Output Generation for LLM Protection Against Knowledge Distillation","created":"2025-05-26","cited_by_count":14,"area":"distill"},{"id":"2506.11680","title":"Malicious LLM-Based Conversational AI Makes Users Reveal Personal Information","created":"2025-06-13","cited_by_count":13,"area":null},{"id":"2505.23847","title":"Seven Security Challenges in Cross-domain Multi-agent LLM Systems","created":"2025-05-28","cited_by_count":12,"area":"agents"},{"id":"2506.10139","title":"Unsupervised Elicitation of Language Models","created":"2025-06-11","cited_by_count":11,"area":null},{"id":"2502.15680","title":"Privacy Ripple Effects from Adding or Removing Personal Information in Language Model Training","created":"2025-02-21","cited_by_count":10,"area":null},{"id":"2503.04693","title":"UIPE: Enhancing LLM Unlearning by Removing Knowledge Related to Forgetting Targets","created":"2025-03-06","cited_by_count":10,"area":"safety"},{"id":"2506.05104","title":"Survey on the Evaluation of Generative Models in Music","created":"2025-06-05","cited_by_count":10,"area":null},{"id":"2310.16152","title":"Gradient-Free Privacy Leakage in Federated Language Models through Selective Weight Tampering","created":"2023-10-24","cited_by_count":9,"area":null},{"id":"2410.01322","title":"Forte : Finding Outliers with Representation Typicality Estimation","created":"2024-10-02","cited_by_count":9,"area":null},{"id":"2306.01481","title":"GAIA Search: Hugging Face and Pyserini Interoperability for NLP Training Data Exploration","created":"2023-06-02","cited_by_count":8,"area":null}],"next_cursor":"100"}