{"list":"other","total":57,"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":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"1905.07830","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","created":"2019-05-19","cited_by_count":4100},{"id":"2307.15043","title":"Universal and Transferable Adversarial Attacks on Aligned Language Models","created":"2023-07-27","cited_by_count":3104},{"id":"2311.12022","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","created":"2023-11-20","cited_by_count":2879},{"id":"2307.02483","title":"Jailbroken: How Does LLM Safety Training Fail?","created":"2023-07-05","cited_by_count":1651},{"id":"2310.08419","title":"Jailbreaking Black Box Large Language Models in Twenty Queries","created":"2023-10-12","cited_by_count":1420},{"id":"2009.11462","title":"RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models","created":"2020-09-24","cited_by_count":1255},{"id":"2112.11446","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","created":"2021-12-08","cited_by_count":1202},{"id":"2211.09527","title":"Ignore Previous Prompt: Attack Techniques For Language Models","created":"2022-11-17","cited_by_count":832},{"id":"2008.02275","title":"Aligning AI With Shared Human Values","created":"2020-08-05","cited_by_count":723},{"id":"2312.02119","title":"Tree of Attacks: Jailbreaking Black-Box LLMs Automatically","created":"2023-12-04","cited_by_count":672},{"id":"2310.12773","title":"Safe RLHF: Safe Reinforcement Learning from Human Feedback","created":"2023-10-19","cited_by_count":656},{"id":"2309.00614","title":"Baseline Defenses for Adversarial Attacks Against Aligned Language Models","created":"2023-09-01","cited_by_count":651},{"id":"1905.12616","title":"Defending Against Neural Fake News","created":"2019-05-29","cited_by_count":559},{"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":"2308.14132","title":"Detecting Language Model Attacks with Perplexity","created":"2023-08-27","cited_by_count":431},{"id":"2308.05374","title":"Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment","created":"2023-08-10","cited_by_count":401},{"id":"2304.05197","title":"Multi-step Jailbreaking Privacy Attacks on ChatGPT","created":"2023-04-11","cited_by_count":333},{"id":"2305.00944","title":"Poisoning Language Models During Instruction Tuning","created":"2023-05-01","cited_by_count":269},{"id":"2309.02705","title":"Certifying LLM Safety against Adversarial Prompting","created":"2023-09-06","cited_by_count":266},{"id":"2308.07308","title":"LLM Self Defense: By Self Examination, LLMs Know They Are Being Tricked","created":"2023-08-14","cited_by_count":244},{"id":"2410.02355","title":"AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models","created":"2024-10-03","cited_by_count":236},{"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":"2204.05149","title":"The Carbon Footprint of Machine Learning Training Will Plateau, Then Shrink","created":"2022-04-11","cited_by_count":184},{"id":"2502.04180","title":"Multi-agent Architecture Search via Agentic Supernet","created":"2025-02-06","cited_by_count":179},{"id":"2404.07921","title":"AmpleGCG: Learning a Universal and Transferable Generative Model of Adversarial Suffixes for Jailbreaking Both Open and Closed LLMs","created":"2024-04-11","cited_by_count":172},{"id":"2401.17263","title":"Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks","created":"2024-01-30","cited_by_count":156},{"id":"2410.12954","title":"A Note on Shumailov et al. (2024): `AI Models Collapse When Trained on Recursively Generated Data'","created":"2024-10-16","cited_by_count":115},{"id":"2306.09442","title":"Explore, Establish, Exploit: Red Teaming Language Models from Scratch","created":"2023-06-15","cited_by_count":114},{"id":"2006.03463","title":"Sponge Examples: Energy-Latency Attacks on Neural Networks","created":"2020-06-05","cited_by_count":111},{"id":"2502.02542","title":"OverThink: Slowdown Attacks on Reasoning LLMs","created":"2025-02-04","cited_by_count":96},{"id":"2402.14020","title":"Coercing LLMs to do and reveal (almost) anything","created":"2024-02-21","cited_by_count":89},{"id":"2502.05628","title":"AnyEdit: Edit Any Knowledge Encoded in Language Models","created":"2025-02-08","cited_by_count":76},{"id":"2401.05778","title":"Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems","created":"2024-01-11","cited_by_count":66},{"id":"2402.17262","title":"Speak Out of Turn: Safety Vulnerability of Large Language Models in Multi-turn Dialogue","created":"2024-02-27","cited_by_count":66},{"id":"2402.08416","title":"Pandora: Jailbreak GPTs by Retrieval Augmented Generation Poisoning","created":"2024-02-13","cited_by_count":64},{"id":"2504.17704","title":"Safety in Large Reasoning Models: A Survey","created":"2025-04-24","cited_by_count":64},{"id":"2408.13457","title":"Make Every Penny Count: Difficulty-Adaptive Self-Consistency for Cost-Efficient Reasoning","created":"2024-08-24","cited_by_count":63},{"id":"2302.04237","title":"Black Box Adversarial Prompting for Foundation Models","created":"2023-02-08","cited_by_count":62},{"id":"2310.05707","title":"Guiding Language Model Reasoning with Planning Tokens","created":"2023-10-09","cited_by_count":58},{"id":"2402.12343","title":"Emulated Disalignment: Safety Alignment for Large Language Models May Backfire!","created":"2024-02-19","cited_by_count":37},{"id":"2412.13879","title":"Crabs: Consuming Resource via Auto-generation for LLM-DoS Attack under Black-box Settings","created":"2024-12-18","cited_by_count":35},{"id":"2307.16630","title":"Text-CRS: A Generalized Certified Robustness Framework against Textual Adversarial Attacks","created":"2023-07-31","cited_by_count":34},{"id":"2407.07064","title":"Prompting Techniques for Secure Code Generation: A Systematic Investigation","created":"2024-07-09","cited_by_count":34},{"id":"2412.19394","title":"An Engorgio Prompt Makes Large Language Model Babble on","created":"2024-12-27","cited_by_count":30},{"id":"2504.08813","title":"SafeMLRM: Demystifying Safety in Multi-modal Large Reasoning Models","created":"2025-04-09","cited_by_count":29},{"id":"2502.12575","title":"DemonAgent: Dynamically Encrypted Multi-Backdoor Implantation Attack on LLM-based Agent","created":"2025-02-18","cited_by_count":23},{"id":"2502.20968","title":"Beware of Your Po! Measuring and Mitigating AI Safety Risks in Role-Play Fine-Tuning of LLMs","created":"2025-02-28","cited_by_count":22},{"id":"2408.03515","title":"A Study on Prompt Injection Attack Against LLM-Integrated Mobile Robotic Systems","created":"2024-08-07","cited_by_count":15},{"id":"2503.08195","title":"Dialogue Injection Attack: Jailbreaking LLMs through Context Manipulation","created":"2025-03-11","cited_by_count":14},{"id":"2404.02637","title":"Vocabulary Attack to Hijack Large Language Model Applications","created":"2024-04-03","cited_by_count":12},{"id":"2411.12762","title":"Playing Language Game with LLMs Leads to Jailbreaking","created":"2024-11-16","cited_by_count":11},{"id":"2502.00580","title":"Defense Against the Dark Prompts: Mitigating Best-of-N Jailbreaking with Prompt Evaluation","created":"2025-02-01","cited_by_count":8}],"next_cursor":null}