{"total":176,"rows":[{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971,"area":"alignment"},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512,"area":null},{"id":"2310.08419","title":"Jailbreaking Black Box Large Language Models in Twenty Queries","created":"2023-10-12","cited_by_count":1420,"area":"safety"},{"id":"2312.06674","title":"Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations","created":"2023-12-07","cited_by_count":1207,"area":null},{"id":"2305.10403","title":"PaLM 2 Technical Report","created":"2023-05-17","cited_by_count":1162,"area":"lr"},{"id":"2202.03286","title":"Red Teaming Language Models with Language Models","created":"2022-02-07","cited_by_count":1026,"area":"safety"},{"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":"2209.14375","title":"Improving alignment of dialogue agents via targeted human judgements","created":"2022-09-28","cited_by_count":531,"area":"agents"},{"id":"2104.08758","title":"Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpus","created":"2021-04-18","cited_by_count":492,"area":null},{"id":"2104.14337","title":"Dynabench: Rethinking Benchmarking in NLP","created":"2021-04-07","cited_by_count":459,"area":null},{"id":"2203.09509","title":"ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection","created":"2022-03-17","cited_by_count":422,"area":null},{"id":"2208.03274","title":"A Holistic Approach to Undesired Content Detection in the Real World","created":"2022-08-05","cited_by_count":356,"area":null},{"id":"2110.08420","title":"Understanding Dataset Difficulty with $\\mathcal{V}$-Usable Information","created":"2021-10-16","cited_by_count":291,"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":"2406.14598","title":"SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal","created":"2024-06-20","cited_by_count":240,"area":"alignment"},{"id":"2402.11753","title":"ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs","created":"2024-02-19","cited_by_count":216,"area":"safety"},{"id":"2201.05955","title":"WANLI: Worker and AI Collaboration for Natural Language Inference Dataset Creation","created":"2022-01-16","cited_by_count":202,"area":null},{"id":"2309.07045","title":"SafetyBench: Evaluating the Safety of Large Language Models","created":"2023-09-13","cited_by_count":199,"area":null},{"id":"2208.03188","title":"BlenderBot 3: a deployed conversational agent that continually learns to responsibly engage","created":"2022-08-05","cited_by_count":198,"area":null},{"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":"2311.07689","title":"MART: Improving LLM Safety with Multi-round Automatic Red-Teaming","created":"2023-11-13","cited_by_count":163,"area":"safety"},{"id":"2403.04783","title":"AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks","created":"2024-03-02","cited_by_count":145,"area":"agents"},{"id":"2407.18418","title":"Know Your Limits: A Survey of Abstention in Large Language Models","created":"2024-07-25","cited_by_count":121,"area":null},{"id":"2205.12688","title":"ProsocialDialog: A Prosocial Backbone for Conversational Agents","created":"2022-05-25","cited_by_count":109,"area":"agents"},{"id":"2102.00086","title":"Challenges in Automated Debiasing for Toxic Language Detection","created":"2021-01-29","cited_by_count":96,"area":null},{"id":"2107.08720","title":"Human-in-the-Loop for Data Collection: a Multi-Target Counter Narrative Dataset to Fight Online Hate Speech","created":"2021-07-19","cited_by_count":82,"area":null},{"id":"2108.03362","title":"On Measures of Biases and Harms in NLP","created":"2021-08-07","cited_by_count":81,"area":null},{"id":"2107.03451","title":"Anticipating Safety Issues in E2E Conversational AI: Framework and Tooling","created":"2021-07-07","cited_by_count":78,"area":null},{"id":"2406.02622","title":"Safeguarding Large Language Models: A Survey","created":"2024-06-03","cited_by_count":78,"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":"2201.06025","title":"COLD: A Benchmark for Chinese Offensive Language Detection","created":"2022-01-16","cited_by_count":76,"area":null},{"id":"2403.07865","title":"CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion","created":"2024-03-12","cited_by_count":76,"area":"safety"},{"id":"2110.08466","title":"On the Safety of Conversational Models: Taxonomy, Dataset, and Benchmark","created":"2021-10-16","cited_by_count":73,"area":null},{"id":"2304.00612","title":"Eight Things to Know about Large Language Models","created":"2023-04-02","cited_by_count":73,"area":null},{"id":"2302.03269","title":"PLACES: Prompting Language Models for Social Conversation Synthesis","created":"2023-02-07","cited_by_count":72,"area":null},{"id":"2305.02750","title":"A Survey on Proactive Dialogue Systems: Problems, Methods, and Prospects","created":"2023-05-04","cited_by_count":66,"area":null},{"id":"2110.08118","title":"Few-Shot Bot: Prompt-Based Learning for Dialogue Systems","created":"2021-10-15","cited_by_count":64,"area":null},{"id":"2201.04723","title":"Human Evaluation of Conversations is an Open Problem: comparing the sensitivity of various methods for evaluating dialogue agents","created":"2022-01-12","cited_by_count":62,"area":null},{"id":"2404.12241","title":"Introducing v0.5 of the AI Safety Benchmark from MLCommons","created":"2024-04-18","cited_by_count":62,"area":null},{"id":"2205.01663","title":"Adversarial Training for High-Stakes Reliability","created":"2022-05-03","cited_by_count":60,"area":null},{"id":"2106.02280","title":"Human-Adversarial Visual Question Answering","created":"2021-06-04","cited_by_count":57,"area":null},{"id":"2208.01448","title":"AlexaTM 20B: Few-Shot Learning Using a Large-Scale Multilingual Seq2Seq Model","created":"2022-08-02","cited_by_count":57,"area":null},{"id":"2108.11830","title":"Just Say No: Analyzing the Stance of Neural Dialogue Generation in Offensive Contexts","created":"2021-08-26","cited_by_count":56,"area":null},{"id":"2310.07629","title":"The Past, Present and Better Future of Feedback Learning in Large Language Models for Subjective Human Preferences and Values","created":"2023-10-11","cited_by_count":54,"area":"alignment"},{"id":"2311.08592","title":"AART: AI-Assisted Red-Teaming with Diverse Data Generation for New LLM-powered Applications","created":"2023-11-14","cited_by_count":54,"area":"safety"},{"id":"2405.18540","title":"Learning diverse attacks on large language models for robust red-teaming and safety tuning","created":"2024-05-28","cited_by_count":54,"area":"safety"},{"id":"2205.12586","title":"Perturbation Augmentation for Fairer NLP","created":"2022-05-25","cited_by_count":52,"area":null},{"id":"2311.17391","title":"Unveiling the Implicit Toxicity in Large Language Models","created":"2023-11-29","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":"2106.05555","title":"Shades of BLEU, Flavours of Success: The Case of MultiWOZ","created":"2021-06-10","cited_by_count":48,"area":null},{"id":"2109.09483","title":"ConvAbuse: Data, Analysis, and Benchmarks for Nuanced Abuse Detection in Conversational AI","created":"2021-09-20","cited_by_count":46,"area":null},{"id":"2405.17374","title":"Navigating the Safety Landscape: Measuring Risks in Finetuning Large Language Models","created":"2024-05-27","cited_by_count":46,"area":"alignment"},{"id":"2507.21206","title":"Agentic Web: Weaving the Next Web with AI Agents","created":"2025-07-28","cited_by_count":45,"area":"agents"},{"id":"2407.08351","title":"AutoBencher: Towards Declarative Benchmark Construction","created":"2024-07-11","cited_by_count":44,"area":null},{"id":"2302.00871","title":"Using In-Context Learning to Improve Dialogue Safety","created":"2023-02-02","cited_by_count":42,"area":null},{"id":"2211.03433","title":"Human-Machine Collaboration Approaches to Build a Dialogue Dataset for Hate Speech Countering","created":"2022-11-07","cited_by_count":40,"area":null},{"id":"2205.12673","title":"InstructDial: Improving Zero and Few-shot Generalization in Dialogue through Instruction Tuning","created":"2022-05-25","cited_by_count":39,"area":null},{"id":"2211.05826","title":"The CRINGE Loss: Learning what language not to model","created":"2022-11-10","cited_by_count":39,"area":null},{"id":"2206.07694","title":"DIRECTOR: Generator-Classifiers For Supervised Language Modeling","created":"2022-06-15","cited_by_count":38,"area":null},{"id":"2110.07518","title":"SaFeRDialogues: Taking Feedback Gracefully after Conversational Safety Failures","created":"2021-10-14","cited_by_count":37,"area":null},{"id":"2202.08011","title":"Towards Identifying Social Bias in Dialog Systems: Frame, Datasets, and Benchmarks","created":"2022-02-16","cited_by_count":36,"area":null},{"id":"2310.10477","title":"Gaining Wisdom from Setbacks: Aligning Large Language Models via Mistake Analysis","created":"2023-10-16","cited_by_count":35,"area":"alignment"},{"id":"2110.06800","title":"SGD-X: A Benchmark for Robust Generalization in Schema-Guided Dialogue Systems","created":"2021-10-13","cited_by_count":34,"area":null},{"id":"2104.08728","title":"Revealing Persona Biases in Dialogue Systems","created":"2021-04-18","cited_by_count":33,"area":null},{"id":"2209.03463","title":"Why So Toxic? Measuring and Triggering Toxic Behavior in Open-Domain Chatbots","created":"2022-09-07","cited_by_count":33,"area":null},{"id":"2305.17444","title":"Query-Efficient Black-Box Red Teaming via Bayesian Optimization","created":"2023-05-27","cited_by_count":32,"area":"safety"},{"id":"2106.00872","title":"On the Efficacy of Adversarial Data Collection for Question Answering: Results from a Large-Scale Randomized Study","created":"2021-06-02","cited_by_count":31,"area":null},{"id":"2112.09062","title":"Models in the Loop: Aiding Crowdworkers with Generative Annotation Assistants","created":"2021-12-16","cited_by_count":31,"area":null},{"id":"2311.01677","title":"DialogBench: Evaluating LLMs as Human-like Dialogue Systems","created":"2023-11-03","cited_by_count":31,"area":null},{"id":"2204.01440","title":"Using Pre-Trained Language Models for Producing Counter Narratives Against Hate Speech: a Comparative Study","created":"2022-04-04","cited_by_count":30,"area":null},{"id":"2406.12935","title":"ChatBug: A Common Vulnerability of Aligned LLMs Induced by Chat Templates","created":"2024-06-17","cited_by_count":30,"area":"alignment"},{"id":"2310.03400","title":"Adapting Large Language Models for Content Moderation: Pitfalls in Data Engineering and Supervised Fine-tuning","created":"2023-10-05","cited_by_count":29,"area":null},{"id":"2310.13522","title":"Teaching Language Models to Self-Improve through Interactive Demonstrations","created":"2023-10-20","cited_by_count":26,"area":"synth"},{"id":"2311.00172","title":"Robust Safety Classifier for Large Language Models: Adversarial Prompt Shield","created":"2023-10-31","cited_by_count":25,"area":"safety"},{"id":"2412.18693","title":"Diverse and Effective Red Teaming with Auto-generated Rewards and Multi-step Reinforcement Learning","created":"2024-12-24","cited_by_count":25,"area":"safety"},{"id":"2110.08514","title":"Analyzing Dynamic Adversarial Training Data in the Limit","created":"2021-10-16","cited_by_count":24,"area":null},{"id":"2203.06414","title":"A Survey of Adversarial Defences and Robustness in NLP","created":"2022-03-12","cited_by_count":23,"area":null},{"id":"2205.02392","title":"Robust Conversational Agents against Imperceptible Toxicity Triggers","created":"2022-05-05","cited_by_count":23,"area":"agents"},{"id":"2410.20245","title":"Improving Model Evaluation using SMART Filtering of Benchmark Datasets","created":"2024-10-26","cited_by_count":21,"area":null},{"id":"2106.06157","title":"Assessing Political Prudence of Open-domain Chatbots","created":"2021-06-11","cited_by_count":20,"area":null},{"id":"2109.05925","title":"Adversarial Examples for Evaluating Math Word Problem Solvers","created":"2021-09-13","cited_by_count":20,"area":null},{"id":"2302.07346","title":"ScatterShot: Interactive In-context Example Curation for Text Transformation","created":"2023-02-14","cited_by_count":20,"area":null},{"id":"2110.00687","title":"Investigating Robustness of Dialog Models to Popular Figurative Language Constructs","created":"2021-10-01","cited_by_count":19,"area":null},{"id":"2204.10817","title":"Reward Reports for Reinforcement Learning","created":"2022-04-22","cited_by_count":18,"area":null},{"id":"2402.14147","title":"Wikibench: Community-Driven Data Curation for AI Evaluation on Wikipedia","created":"2024-02-21","cited_by_count":18,"area":null},{"id":"2405.09113","title":"Efficient LLM Jailbreak via Adaptive Dense-to-sparse Constrained Optimization","created":"2024-05-15","cited_by_count":18,"area":"safety"},{"id":"2212.10720","title":"MoralDial: A Framework to Train and Evaluate Moral Dialogue Systems via Moral Discussions","created":"2022-12-21","cited_by_count":17,"area":null},{"id":"2310.00322","title":"Evolving Diverse Red-team Language Models in Multi-round Multi-agent Games","created":"2023-09-30","cited_by_count":17,"area":"agents"},{"id":"2106.02692","title":"The R-U-A-Robot Dataset: Helping Avoid Chatbot Deception by Detecting User Questions About Human or Non-Human Identity","created":"2021-06-04","cited_by_count":16,"area":null},{"id":"2210.03165","title":"A Theory of Dynamic Benchmarks","created":"2022-10-06","cited_by_count":16,"area":null},{"id":"2302.14003","title":"Systematic Rectification of Language Models via Dead-end Analysis","created":"2023-02-27","cited_by_count":16,"area":null},{"id":"2307.09579","title":"Understanding Multi-Turn Toxic Behaviors in Open-Domain Chatbots","created":"2023-07-14","cited_by_count":15,"area":null},{"id":"2302.09270","title":"Towards Safer Generative Language Models: A Survey on Safety Risks, Evaluations, and Improvements","created":"2023-02-18","cited_by_count":14,"area":null},{"id":"2502.06207","title":"Is LLM an Overconfident Judge? Unveiling the Capabilities of LLMs in Detecting Offensive Language with Annotation Disagreement","created":"2025-02-10","cited_by_count":14,"area":null},{"id":"2208.13078","title":"MDIA: A Benchmark for Multilingual Dialogue Generation in 46 Languages","created":"2022-08-27","cited_by_count":13,"area":null},{"id":"2302.06541","title":"Towards Agile Text Classifiers for Everyone","created":"2023-02-13","cited_by_count":13,"area":null},{"id":"2307.16457","title":"A Benchmark for Understanding Dialogue Safety in Mental Health Support","created":"2023-07-31","cited_by_count":13,"area":null},{"id":"2403.19559","title":"Improving Adversarial Data Collection by Supporting Annotators: Lessons from GAHD, a German Hate Speech Dataset","created":"2024-03-28","cited_by_count":13,"area":null},{"id":"2406.10977","title":"Toward Optimal LLM Alignments Using Two-Player Games","created":"2024-06-16","cited_by_count":13,"area":"alignment"},{"id":"2408.15488","title":"Legilimens: Practical and Unified Content Moderation for Large Language Model Services","created":"2024-08-28","cited_by_count":13,"area":"safety"}],"next_cursor":"100"}