{"list":"other","total":65,"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":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"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":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"2403.13372","title":"LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models","created":"2024-03-20","cited_by_count":1464},{"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":"1902.02918","title":"Certified Adversarial Robustness via Randomized Smoothing","created":"2019-02-08","cited_by_count":1340},{"id":"2306.03341","title":"Inference-Time Intervention: Eliciting Truthful Answers from a Language Model","created":"2023-06-06","cited_by_count":1302},{"id":"2312.06674","title":"Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations","created":"2023-12-07","cited_by_count":1207},{"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":"2004.09297","title":"MPNet: Masked and Permuted Pre-training for Language Understanding","created":"2020-04-20","cited_by_count":981},{"id":"2412.08905","title":"Phi-4 Technical Report","created":"2024-12-12","cited_by_count":711},{"id":"2308.01263","title":"XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models","created":"2023-08-02","cited_by_count":505},{"id":"2406.18495","title":"WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs","created":"2024-06-26","cited_by_count":496},{"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":"1903.11199","title":"Control Barrier Functions: Theory and Applications","created":"2019-03-27","cited_by_count":372},{"id":"2208.03274","title":"A Holistic Approach to Undesired Content Detection in the Real World","created":"2022-08-05","cited_by_count":356},{"id":"2406.04313","title":"Improving Alignment and Robustness with Circuit Breakers","created":"2024-06-06","cited_by_count":322},{"id":"2401.05561","title":"TrustLLM: Trustworthiness in Large Language Models","created":"2024-01-10","cited_by_count":285},{"id":"2407.21772","title":"ShieldGemma: Generative AI Content Moderation Based on Gemma","created":"2024-07-31","cited_by_count":243},{"id":"2404.09932","title":"Foundational Challenges in Assuring Alignment and Safety of Large Language Models","created":"2024-04-15","cited_by_count":199},{"id":"2005.00611","title":"Neural Lyapunov Control","created":"2020-05-01","cited_by_count":142},{"id":"2404.05993","title":"AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts","created":"2024-04-09","cited_by_count":136},{"id":"2404.01099","title":"What is in Your Safe Data? Identifying Benign Data that Breaks Safety","created":"2024-04-01","cited_by_count":118},{"id":"2501.18492","title":"GuardReasoner: Towards Reasoning-based LLM Safeguards","created":"2025-01-30","cited_by_count":100},{"id":"2109.06697","title":"Safe Nonlinear Control Using Robust Neural Lyapunov-Barrier Functions","created":"2021-09-14","cited_by_count":94},{"id":"2004.03315","title":"Learning Control Barrier Functions from Expert Demonstrations","created":"2020-04-07","cited_by_count":92},{"id":"2406.09714","title":"Large language model validity via enhanced conformal prediction methods","created":"2024-06-14","cited_by_count":92},{"id":"2405.05610","title":"Chain of Attack: a Semantic-Driven Contextual Multi-Turn attacker for LLM","created":"2024-05-09","cited_by_count":77},{"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":"2406.05954","title":"Aligning Large Language Models with Representation Editing: A Control Perspective","created":"2024-06-10","cited_by_count":64},{"id":"2501.18841","title":"Trading Inference-Time Compute for Adversarial Robustness","created":"2025-01-31","cited_by_count":61},{"id":"2406.17626","title":"CoSafe: Evaluating Large Language Model Safety in Multi-Turn Dialogue Coreference","created":"2024-06-25","cited_by_count":51},{"id":"2008.05952","title":"Learning Stability Certificates from Data","created":"2020-08-13","cited_by_count":45},{"id":"2410.01606","title":"Automated Red Teaming with GOAT: the Generative Offensive Agent Tester","created":"2024-10-02","cited_by_count":45},{"id":"2310.15478","title":"How to Train Your Neural Control Barrier Function: Learning Safety Filters for Complex Input-Constrained Systems","created":"2023-10-24","cited_by_count":44},{"id":"2407.05557","title":"$R^2$-Guard: Robust Reasoning Enabled LLM Guardrail via Knowledge-Enhanced Logical Reasoning","created":"2024-07-08","cited_by_count":43},{"id":"2409.00598","title":"Automatic Pseudo-Harmful Prompt Generation for Evaluating False Refusals in Large Language Models","created":"2024-09-01","cited_by_count":35},{"id":"2011.04112","title":"Learning Hybrid Control Barrier Functions from Data","created":"2020-11-08","cited_by_count":24},{"id":"2110.01110","title":"Safe Control with Neural Network Dynamic Models","created":"2021-10-03","cited_by_count":22},{"id":"2206.01463","title":"Safety Certification for Stochastic Systems via Neural Barrier Functions","created":"2022-06-03","cited_by_count":22},{"id":"2305.18449","title":"Taming AI Bots: Controllability of Neural States in Large Language Models","created":"2023-05-29","cited_by_count":22},{"id":"2410.01174","title":"Towards Inference-time Category-wise Safety Steering for Large Language Models","created":"2024-10-02","cited_by_count":18},{"id":"2312.12791","title":"Model-Based Control with Sparse Neural Dynamics","created":"2023-12-20","cited_by_count":16},{"id":"2101.05916","title":"Scalable Learning of Safety Guarantees for Autonomous Systems using Hamilton-Jacobi Reachability","created":"2021-01-15","cited_by_count":14},{"id":"2206.07811","title":"Safety Guarantees for Neural Network Dynamic Systems via Stochastic Barrier Functions","created":"2022-06-15","cited_by_count":14},{"id":"2410.16281","title":"Verification of Neural Control Barrier Functions with Symbolic Derivative Bounds Propagation","created":"2024-10-04","cited_by_count":12},{"id":"2408.15625","title":"CBF-LLM: Safe Control for LLM Alignment","created":"2024-08-28","cited_by_count":9},{"id":"2301.13039","title":"Representation biases in sentence transformers","created":"2023-01-30","cited_by_count":7},{"id":"2405.09794","title":"Human-AI Safety: A Descendant of Generative AI and Control Systems Safety","created":"2024-05-16","cited_by_count":7},{"id":"2407.15399","title":"Imposter.AI: Adversarial Attacks with Hidden Intentions towards Aligned Large Language Models","created":"2024-07-22","cited_by_count":7},{"id":"2205.05429","title":"Learning a Better Control Barrier Function","created":"2022-05-11","cited_by_count":6},{"id":"2311.10438","title":"Simultaneous Synthesis and Verification of Neural Control Barrier Functions through Branch-and-Bound Verification-in-the-loop Training","created":"2023-11-17","cited_by_count":6},{"id":"2312.06810","title":"System-level Safety Guard: Safe Tracking Control through Uncertain Neural Network Dynamics Models","created":"2023-12-11","cited_by_count":5},{"id":"2404.13456","title":"Real-Time Safe Control of Neural Network Dynamic Models with Sound Approximation","created":"2024-04-20","cited_by_count":5},{"id":"2405.14061","title":"Meanings and Feelings of Large Language Models: Observability of Latent States in Generative AI","created":"2024-05-22","cited_by_count":5},{"id":"2412.09584","title":"BaB-ND: Long-Horizon Motion Planning with Branch-and-Bound and Neural Dynamics","created":"2024-12-12","cited_by_count":5},{"id":"2401.05629","title":"Learning Performance-Oriented Control Barrier Functions Under Complex Safety Constraints and Limited Actuation","created":"2024-01-11","cited_by_count":4},{"id":"2312.07345","title":"Neural Differentiable Integral Control Barrier Functions for Unknown Nonlinear Systems with Input Constraints","created":"2023-12-12","cited_by_count":3},{"id":"2410.10387","title":"Robust Tracking Control with Neural Network Dynamic Models under Input Perturbations","created":"2024-10-14","cited_by_count":2}],"next_cursor":null}