{"total":76,"rows":[{"id":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975,"area":null},{"id":"2201.08239","title":"LaMDA: Language Models for Dialog Applications","created":"2022-01-20","cited_by_count":1220,"area":null},{"id":"2112.04359","title":"Ethical and social risks of harm from Language Models","created":"2021-12-08","cited_by_count":966,"area":null},{"id":"2211.09527","title":"Ignore Previous Prompt: Attack Techniques For Language Models","created":"2022-11-17","cited_by_count":832,"area":null},{"id":"2301.13688","title":"The Flan Collection: Designing Data and Methods for Effective Instruction Tuning","created":"2023-01-31","cited_by_count":739,"area":null},{"id":"2209.07858","title":"Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned","created":"2022-08-23","cited_by_count":729,"area":"alignment"},{"id":"2203.14680","title":"Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space","created":"2022-03-28","cited_by_count":532,"area":null},{"id":"2209.14375","title":"Improving alignment of dialogue agents via targeted human judgements","created":"2022-09-28","cited_by_count":531,"area":"agents"},{"id":"2105.03023","title":"DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts","created":"2021-05-07","cited_by_count":441,"area":null},{"id":"2302.05733","title":"Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks","created":"2023-02-11","cited_by_count":278,"area":null},{"id":"2111.07997","title":"Annotators with Attitudes: How Annotator Beliefs And Identities Bias Toxic Language Detection","created":"2021-11-15","cited_by_count":264,"area":null},{"id":"2401.17263","title":"Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks","created":"2024-01-30","cited_by_count":156,"area":"safety"},{"id":"2112.08726","title":"NeuroLogic A*esque Decoding: Constrained Text Generation with Lookahead Heuristics","created":"2021-12-16","cited_by_count":154,"area":null},{"id":"2408.00761","title":"Tamper-Resistant Safeguards for Open-Weight LLMs","created":"2024-08-01","cited_by_count":138,"area":"safety"},{"id":"2108.05036","title":"DEMix Layers: Disentangling Domains for Modular Language Modeling","created":"2021-08-11","cited_by_count":132,"area":null},{"id":"2106.15115","title":"Neural Machine Translation for Low-Resource Languages: A Survey","created":"2021-06-29","cited_by_count":109,"area":null},{"id":"2301.12867","title":"Red teaming ChatGPT via Jailbreaking: Bias, Robustness, Reliability and Toxicity","created":"2023-01-30","cited_by_count":89,"area":"safety"},{"id":"2210.07321","title":"Machine Generated Text: A Comprehensive Survey of Threat Models and Detection Methods","created":"2022-10-13","cited_by_count":79,"area":null},{"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,"area":null},{"id":"2302.04844","title":"The Gradient of Generative AI Release: Methods and Considerations","created":"2023-02-05","cited_by_count":63,"area":null},{"id":"2103.12407","title":"Detecting Hate Speech with GPT-3","created":"2021-03-23","cited_by_count":56,"area":null},{"id":"2311.16153","title":"Identifying and Mitigating Vulnerabilities in LLM-Integrated Applications","created":"2023-11-07","cited_by_count":54,"area":null},{"id":"2201.10474","title":"Whose Language Counts as High Quality? Measuring Language Ideologies in Text Data Selection","created":"2022-01-25","cited_by_count":53,"area":null},{"id":"2304.14670","title":"Prompt Engineering for Healthcare: Methodologies and Applications","created":"2023-04-28","cited_by_count":52,"area":null},{"id":"2109.04825","title":"Artificial Text Detection via Examining the Topology of Attention Maps","created":"2021-09-10","cited_by_count":49,"area":null},{"id":"2306.03350","title":"Click: Controllable Text Generation with Sequence Likelihood Contrastive Learning","created":"2023-06-06","cited_by_count":41,"area":null},{"id":"2210.09421","title":"Deepfake Text Detection: Limitations and Opportunities","created":"2022-10-17","cited_by_count":37,"area":null},{"id":"2212.10543","title":"Detoxifying Text with MaRCo: Controllable Revision with Experts and Anti-Experts","created":"2022-12-20","cited_by_count":36,"area":null},{"id":"2405.02774","title":"Get more for less: Principled Data Selection for Warming Up Fine-Tuning in LLMs","created":"2024-05-05","cited_by_count":32,"area":null},{"id":"2205.12771","title":"Does Moral Code Have a Moral Code? Probing Delphi's Moral Philosophy","created":"2022-05-25","cited_by_count":31,"area":null},{"id":"2405.10313","title":"How Far Are We From AGI: Are LLMs All We Need?","created":"2024-05-16","cited_by_count":31,"area":null},{"id":"2206.01583","title":"Findings of the The RuATD Shared Task 2022 on Artificial Text Detection in Russian","created":"2022-06-03","cited_by_count":29,"area":null},{"id":"2307.03214","title":"PREADD: Prefix-Adaptive Decoding for Controlled Text Generation","created":"2023-07-06","cited_by_count":29,"area":null},{"id":"2204.12130","title":"LM-Debugger: An Interactive Tool for Inspection and Intervention in Transformer-Based Language Models","created":"2022-04-26","cited_by_count":28,"area":null},{"id":"2209.15259","title":"On the Impossible Safety of Large AI Models","created":"2022-09-30","cited_by_count":28,"area":null},{"id":"2309.13322","title":"From Text to Source: Results in Detecting Large Language Model-Generated Content","created":"2023-09-23","cited_by_count":26,"area":"safety"},{"id":"2311.11202","title":"Unmasking and Improving Data Credibility: A Study with Datasets for Training Harmless Language Models","created":"2023-11-19","cited_by_count":26,"area":null},{"id":"2203.04940","title":"Data-Efficient Structured Pruning via Submodular Optimization","created":"2022-03-09","cited_by_count":23,"area":null},{"id":"2306.05871","title":"Towards a Robust Detection of Language Model Generated Text: Is ChatGPT that Easy to Detect?","created":"2023-06-09","cited_by_count":23,"area":null},{"id":"2108.13349","title":"On the Multilingual Capabilities of Very Large-Scale English Language Models","created":"2021-08-30","cited_by_count":22,"area":null},{"id":"2311.12997","title":"Compositional Capabilities of Autoregressive Transformers: A Study on Synthetic, Interpretable Tasks","created":"2023-11-21","cited_by_count":22,"area":null},{"id":"2311.02805","title":"Tailoring Self-Rationalizers with Multi-Reward Distillation","created":"2023-11-06","cited_by_count":21,"area":null},{"id":"2304.08637","title":"An Evaluation on Large Language Model Outputs: Discourse and Memorization","created":"2023-04-17","cited_by_count":20,"area":null},{"id":"2108.01764","title":"Q-Pain: A Question Answering Dataset to Measure Social Bias in Pain Management","created":"2021-08-03","cited_by_count":16,"area":null},{"id":"2202.08578","title":"An Equivalence Between Data Poisoning and Byzantine Gradient Attacks","created":"2022-02-17","cited_by_count":16,"area":"safety"},{"id":"2302.07388","title":"Adding Instructions during Pretraining: Effective Way of Controlling Toxicity in Language Models","created":"2023-02-14","cited_by_count":16,"area":null},{"id":"2101.00379","title":"Investigating Memorization of Conspiracy Theories in Text Generation","created":"2021-01-02","cited_by_count":15,"area":null},{"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":"2303.12132","title":"Fundamentals of Generative Large Language Models and Perspectives in Cyber-Defense","created":"2023-03-21","cited_by_count":13,"area":null},{"id":"2312.05180","title":"PathFinder: Guided Search over Multi-Step Reasoning Paths","created":"2023-12-08","cited_by_count":12,"area":"lr"},{"id":"2107.07334","title":"Tournesol: A quest for a large, secure and trustworthy database of reliable human judgments","created":"2021-05-29","cited_by_count":11,"area":null},{"id":"2212.01810","title":"Constructing Highly Inductive Contexts for Dialogue Safety through Controllable Reverse Generation","created":"2022-12-04","cited_by_count":8,"area":null},{"id":"2212.11126","title":"Chatbots in a Botnet World","created":"2022-12-18","cited_by_count":8,"area":null},{"id":"2305.11351","title":"Data Redaction from Conditional Generative Models","created":"2023-05-18","cited_by_count":8,"area":"safety"},{"id":"2404.05783","title":"A Survey on Responsible Generative AI: What to Generate and What Not","created":"2024-04-08","cited_by_count":8,"area":null},{"id":"2306.00374","title":"CFL: Causally Fair Language Models Through Token-level Attribute Controlled Generation","created":"2023-06-01","cited_by_count":7,"area":null},{"id":"2306.13671","title":"Deceptive AI Ecosystems: The Case of ChatGPT","created":"2023-06-18","cited_by_count":7,"area":null},{"id":"2304.11079","title":"Academic Writing with GPT-3.5: Reflections on Practices, Efficacy and Transparency","created":"2023-02-12","cited_by_count":6,"area":null},{"id":"2104.10259","title":"Analyzing COVID-19 Tweets with Transformer-based Language Models","created":"2021-04-20","cited_by_count":5,"area":null},{"id":"2204.07289","title":"Identifying and Measuring Token-Level Sentiment Bias in Pre-trained Language Models with Prompts","created":"2022-04-15","cited_by_count":4,"area":null},{"id":"2212.07877","title":"Manifestations of Xenophobia in AI Systems","created":"2022-12-15","cited_by_count":4,"area":null},{"id":"2312.15478","title":"A Group Fairness Lens for Large Language Models","created":"2023-12-24","cited_by_count":4,"area":null},{"id":"2402.08467","title":"Lying Blindly: Bypassing ChatGPT's Safeguards to Generate Hard-to-Detect Disinformation Claims","created":"2024-02-13","cited_by_count":3,"area":null},{"id":"2311.02733","title":"AV-Lip-Sync+: Leveraging AV-HuBERT to Exploit Multimodal Inconsistency for Deepfake Detection of Frontal Face Videos","created":"2023-11-05","cited_by_count":2,"area":null},{"id":"2106.02398","title":"Strategyproof Learning: Building Trustworthy User-Generated Datasets","created":"2021-06-04","cited_by_count":1,"area":null},{"id":"2112.07041","title":"Survey of Generative Methods for Social Media Analysis","created":"2021-12-13","cited_by_count":1,"area":null},{"id":"2202.02647","title":"Ethics, Rules of Engagement, and AI: Neural Narrative Mapping Using Large Transformer Language Models","created":"2022-02-05","cited_by_count":1,"area":null},{"id":"2204.07483","title":"Polling Latent Opinions: A Method for Computational Sociolinguistics Using Transformer Language Models","created":"2022-04-15","cited_by_count":1,"area":null},{"id":"2402.01663","title":"Killer Apps: Low-Speed, Large-Scale AI Weapons","created":"2024-01-14","cited_by_count":1,"area":null},{"id":"2402.03607","title":"Enhancing Cross-Modal Contextual Congruence for Crowdfunding Success using Knowledge-infused Learning","created":"2024-02-06","cited_by_count":1,"area":null},{"id":"2405.20806","title":"The AI Alignment Paradox","created":"2024-05-31","cited_by_count":1,"area":null},{"id":"2410.15212","title":"Boardwalk Empire: How Generative AI is Revolutionizing Economic Paradigms","created":"2024-10-19","cited_by_count":1,"area":null},{"id":"2104.08359","title":"In Defense of the Paper","created":"2021-04-16","cited_by_count":0,"area":null},{"id":"2412.01711","title":"Towards Resource Efficient and Interpretable Bias Mitigation in Large Language Models","created":"2024-12-02","cited_by_count":0,"area":null},{"id":"2506.06391","title":"From Rogue to Safe AI: The Role of Explicit Refusals in Aligning LLMs with International Humanitarian Law","created":"2025-06-05","cited_by_count":0,"area":null},{"id":"2510.09471","title":"Getting Your Indices in a Row: Full-Text Search for LLM Training Data for Real World","created":"2025-10-10","cited_by_count":0,"area":"safety"}],"next_cursor":null}