{"list":"other","total":64,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"1803.05457","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","created":"2018-03-14","cited_by_count":4886},{"id":"1905.07830","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","created":"2019-05-19","cited_by_count":4100},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"1609.07843","title":"Pointer Sentinel Mixture Models","created":"2016-09-26","cited_by_count":3096},{"id":"2202.05262","title":"Locating and Editing Factual Associations in GPT","created":"2022-02-10","cited_by_count":2691},{"id":"1905.10044","title":"BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions","created":"2019-05-24","cited_by_count":2183},{"id":"1809.02789","title":"Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering","created":"2018-09-08","cited_by_count":2164},{"id":"1909.08593","title":"Fine-Tuning Language Models from Human Preferences","created":"2019-09-18","cited_by_count":2150},{"id":"2004.10964","title":"Don't Stop Pretraining: Adapt Language Models to Domains and Tasks","created":"2020-04-23","cited_by_count":1565},{"id":"2009.11462","title":"RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models","created":"2020-09-24","cited_by_count":1255},{"id":"2312.06681","title":"Steering Llama 2 via Contrastive Activation Addition","created":"2023-12-09","cited_by_count":1085},{"id":"1912.02164","title":"Plug and Play Language Models: A Simple Approach to Controlled Text Generation","created":"2019-12-04","cited_by_count":799},{"id":"2311.03658","title":"The Linear Representation Hypothesis and the Geometry of Large Language Models","created":"2023-11-07","cited_by_count":716},{"id":"2310.03684","title":"SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks","created":"2023-10-05","cited_by_count":469},{"id":"2105.03023","title":"DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts","created":"2021-05-07","cited_by_count":441},{"id":"2009.06367","title":"GeDi: Generative Discriminator Guided Sequence Generation","created":"2020-09-14","cited_by_count":378},{"id":"2304.05335","title":"Toxicity in ChatGPT: Analyzing Persona-assigned Language Models","created":"2023-04-11","cited_by_count":360},{"id":"2309.00941","title":"Emergent Linear Representations in World Models of Self-Supervised Sequence Models","created":"2023-09-02","cited_by_count":319},{"id":"2401.05561","title":"TrustLLM: Trustworthiness in Large Language Models","created":"2024-01-10","cited_by_count":285},{"id":"2311.06668","title":"In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering","created":"2023-11-11","cited_by_count":245},{"id":"2401.06080","title":"Secrets of RLHF in Large Language Models Part II: Reward Modeling","created":"2024-01-11","cited_by_count":171},{"id":"2406.01506","title":"The Geometry of Categorical and Hierarchical Concepts in Large Language Models","created":"2024-06-03","cited_by_count":159},{"id":"1404.1100","title":"A Tutorial on Principal Component Analysis","created":"2014-04-03","cited_by_count":141},{"id":"2302.08215","title":"Aligning Language Models with Preferences through f-divergence Minimization","created":"2023-02-16","cited_by_count":120},{"id":"2406.04031","title":"Jailbreak Vision Language Models via Bi-Modal Adversarial Prompt","created":"2024-06-06","cited_by_count":109},{"id":"2401.04700","title":"Model Editing Harms General Abilities of Large Language Models: Regularization to the Rescue","created":"2024-01-09","cited_by_count":103},{"id":"2210.03162","title":"Prompt Compression and Contrastive Conditioning for Controllability and Toxicity Reduction in Language Models","created":"2022-10-06","cited_by_count":97},{"id":"2402.13851","title":"VL-Trojan: Multimodal Instruction Backdoor Attacks against Autoregressive Visual Language Models","created":"2024-02-21","cited_by_count":87},{"id":"2403.14472","title":"Detoxifying Large Language Models via Knowledge Editing","created":"2024-03-21","cited_by_count":87},{"id":"2310.09520","title":"Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model","created":"2023-10-14","cited_by_count":79},{"id":"2410.18927","title":"SafeBench: A Safety Evaluation Framework for Multimodal Large Language Models","created":"2024-10-24","cited_by_count":69},{"id":"2202.04173","title":"Exploring the Limits of Domain-Adaptive Training for Detoxifying Large-Scale Language Models","created":"2022-02-08","cited_by_count":68},{"id":"2406.05954","title":"Aligning Large Language Models with Representation Editing: A Control Perspective","created":"2024-06-10","cited_by_count":64},{"id":"2502.11054","title":"Reasoning-Augmented Conversation for Multi-Turn Jailbreak Attacks on Large Language Models","created":"2025-02-16","cited_by_count":64},{"id":"1909.09034","title":"Training Robust Deep Neural Networks via Adversarial Noise Propagation","created":"2019-09-19","cited_by_count":62},{"id":"2302.09491","title":"X-Adv: Physical Adversarial Object Attacks against X-ray Prohibited Item Detection","created":"2023-02-19","cited_by_count":59},{"id":"2312.01072","title":"A Survey of Temporal Credit Assignment in Deep Reinforcement Learning","created":"2023-12-02","cited_by_count":59},{"id":"2410.08193","title":"GenARM: Reward Guided Generation with Autoregressive Reward Model for Test-time Alignment","created":"2024-10-10","cited_by_count":54},{"id":"2501.04931","title":"Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency","created":"2025-01-09","cited_by_count":51},{"id":"2406.18844","title":"Revisiting Backdoor Attacks against Large Vision-Language Models from Domain Shift","created":"2024-06-27","cited_by_count":49},{"id":"2310.09573","title":"Self-Detoxifying Language Models via Toxification Reversal","created":"2023-10-14","cited_by_count":46},{"id":"2504.14348","title":"Manipulating Multimodal Agents via Cross-Modal Prompt Injection","created":"2025-04-19","cited_by_count":44},{"id":"2506.14697","title":"AGENTSAFE: Benchmarking the Safety of Embodied Agents on Hazardous Instructions","created":"2025-06-17","cited_by_count":38},{"id":"2403.16257","title":"Unlearning Backdoor Threats: Enhancing Backdoor Defense in Multimodal Contrastive Learning via Local Token Unlearning","created":"2024-03-24","cited_by_count":31},{"id":"2407.00600","title":"GenderBias-\\emph{VL}: Benchmarking Gender Bias in Vision Language Models via Counterfactual Probing","created":"2024-06-30","cited_by_count":31},{"id":"2305.11602","title":"Latent Imitator: Generating Natural Individual Discriminatory Instances for Black-Box Fairness Testing","created":"2023-05-19","cited_by_count":23},{"id":"2308.02350","title":"RobustMQ: Benchmarking Robustness of Quantized Models","created":"2023-08-04","cited_by_count":19},{"id":"2504.15512","title":"T2VShield: Model-Agnostic Jailbreak Defense for Text-to-Video Models","created":"2025-04-22","cited_by_count":18},{"id":"2505.06413","title":"Natural Reflection Backdoor Attack on Vision Language Model for Autonomous Driving","created":"2025-05-09","cited_by_count":18},{"id":"2507.00841","title":"SafeMobile: Chain-level Jailbreak Detection and Automated Evaluation for Multimodal Mobile Agents","created":"2025-07-01","cited_by_count":15},{"id":"2306.16170","title":"Mitigating Accuracy-Robustness Trade-off via Balanced Multi-Teacher Adversarial Distillation","created":"2023-06-28","cited_by_count":13},{"id":"2506.12430","title":"Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025","created":"2025-06-14","cited_by_count":12},{"id":"2412.00746","title":"BDefects4NN: A Backdoor Defect Database for Controlled Localization Studies in Neural Networks","created":"2024-12-01","cited_by_count":11},{"id":"2502.18511","title":"ELBA-Bench: An Efficient Learning Backdoor Attacks Benchmark for Large Language Models","created":"2025-02-22","cited_by_count":11},{"id":"2509.01444","title":"Strata-Sword: A Hierarchical Safety Evaluation towards LLMs based on Reasoning Complexity of Jailbreak Instructions","created":"2025-09-01","cited_by_count":11},{"id":"2406.13098","title":"DLP: towards active defense against backdoor attacks with decoupled learning process","created":"2024-06-18","cited_by_count":10},{"id":"2404.10464","title":"DESTEIN: Navigating Detoxification of Language Models via Universal Steering Pairs and Head-wise Activation Fusion","created":"2024-04-16","cited_by_count":9},{"id":"2504.07787","title":"Fairness Mediator: Neutralize Stereotype Associations to Mitigate Bias in Large Language Models","created":"2025-04-10","cited_by_count":8}],"next_cursor":null}