{"total":117,"rows":[{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028,"area":null},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512,"area":null},{"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":"2309.00770","title":"Bias and Fairness in Large Language Models: A Survey","created":"2023-09-02","cited_by_count":639,"area":null},{"id":"2207.01780","title":"CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning","created":"2022-07-05","cited_by_count":358,"area":null},{"id":"2305.07922","title":"CodeT5+: Open Code Large Language Models for Code Understanding and Generation","created":"2023-05-13","cited_by_count":333,"area":null},{"id":"2107.07567","title":"Beyond Goldfish Memory: Long-Term Open-Domain Conversation","created":"2021-07-15","cited_by_count":267,"area":null},{"id":"2107.07566","title":"Internet-Augmented Dialogue Generation","created":"2021-07-15","cited_by_count":217,"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":"2106.10328","title":"Process for Adapting Language Models to Society (PALMS) with Values-Targeted Datasets","created":"2021-06-18","cited_by_count":181,"area":null},{"id":"2109.07445","title":"Challenges in Detoxifying Language Models","created":"2021-09-15","cited_by_count":169,"area":null},{"id":"2205.11275","title":"RL with KL penalties is better viewed as Bayesian inference","created":"2022-05-23","cited_by_count":135,"area":null},{"id":"2108.05036","title":"DEMix Layers: Disentangling Domains for Modular Language Modeling","created":"2021-08-11","cited_by_count":132,"area":null},{"id":"2104.06390","title":"Detoxifying Language Models Risks Marginalizing Minority Voices","created":"2021-04-13","cited_by_count":107,"area":null},{"id":"2203.13224","title":"Language Models that Seek for Knowledge: Modular Search & Generation for Dialogue and Prompt Completion","created":"2022-03-24","cited_by_count":102,"area":null},{"id":"2212.09746","title":"Evaluating Human-Language Model Interaction","created":"2022-12-19","cited_by_count":92,"area":null},{"id":"2308.14840","title":"Identifying and Mitigating the Security Risks of Generative AI","created":"2023-08-28","cited_by_count":91,"area":null},{"id":"2107.02794","title":"Improving Coherence and Consistency in Neural Sequence Models with Dual-System, Neuro-Symbolic Reasoning","created":"2021-07-06","cited_by_count":85,"area":null},{"id":"2304.10436","title":"Safety Assessment of Chinese Large Language Models","created":"2023-04-20","cited_by_count":85,"area":null},{"id":"2210.07700","title":"Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Survey","created":"2022-10-14","cited_by_count":80,"area":null},{"id":"2202.13047","title":"AugESC: Dialogue Augmentation with Large Language Models for Emotional Support Conversation","created":"2022-02-26","cited_by_count":79,"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":"2201.06025","title":"COLD: A Benchmark for Chinese Offensive Language Detection","created":"2022-01-16","cited_by_count":76,"area":null},{"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":"2401.05778","title":"Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems","created":"2024-01-11","cited_by_count":66,"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":"2305.04533","title":"Prompted LLMs as Chatbot Modules for Long Open-domain Conversation","created":"2023-05-08","cited_by_count":61,"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":"2202.01994","title":"Data Scaling Laws in NMT: The Effect of Noise and Architecture","created":"2022-02-04","cited_by_count":55,"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":"2402.16444","title":"ShieldLM: Empowering LLMs as Aligned, Customizable and Explainable Safety Detectors","created":"2024-02-26","cited_by_count":51,"area":null},{"id":"2410.03415","title":"Surgical, Cheap, and Flexible: Mitigating False Refusal in Language Models via Single Vector Ablation","created":"2024-10-04","cited_by_count":48,"area":null},{"id":"2212.01588","title":"RHO ($\\rho$): Reducing Hallucination in Open-domain Dialogues with Knowledge Grounding","created":"2022-12-03","cited_by_count":47,"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":"2302.00871","title":"Using In-Context Learning to Improve Dialogue Safety","created":"2023-02-02","cited_by_count":42,"area":null},{"id":"2206.07694","title":"DIRECTOR: Generator-Classifiers For Supervised Language Modeling","created":"2022-06-15","cited_by_count":38,"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":"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":"2407.12824","title":"Whispering Experts: Neural Interventions for Toxicity Mitigation in Language Models","created":"2024-07-02","cited_by_count":32,"area":null},{"id":"2203.09313","title":"EVA2.0: Investigating Open-Domain Chinese Dialogue Systems with Large-Scale Pre-Training","created":"2022-03-17","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":"2305.09800","title":"Mirages: On Anthropomorphism in Dialogue Systems","created":"2023-05-16","cited_by_count":30,"area":null},{"id":"2312.00029","title":"Bergeron: Combating Adversarial Attacks through a Conscience-Based Alignment Framework","created":"2023-11-16","cited_by_count":30,"area":null},{"id":"2111.02110","title":"Automatic Evaluation and Moderation of Open-domain Dialogue Systems","created":"2021-11-03","cited_by_count":28,"area":null},{"id":"2311.04124","title":"Unveiling Safety Vulnerabilities of Large Language Models","created":"2023-11-07","cited_by_count":27,"area":null},{"id":"2201.06657","title":"A Literature Survey of Recent Advances in Chatbots","created":"2022-01-17","cited_by_count":26,"area":null},{"id":"2110.08514","title":"Analyzing Dynamic Adversarial Training Data in the Limit","created":"2021-10-16","cited_by_count":24,"area":null},{"id":"2109.03300","title":"Hi, my name is Martha: Using names to measure and mitigate bias in generative dialogue models","created":"2021-09-07","cited_by_count":23,"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":"2106.06157","title":"Assessing Political Prudence of Open-domain Chatbots","created":"2021-06-11","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":"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":"2303.11257","title":"Unit Scaling: Out-of-the-Box Low-Precision Training","created":"2023-03-20","cited_by_count":17,"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":"2306.06135","title":"Safety and Fairness for Content Moderation in Generative Models","created":"2023-06-09","cited_by_count":16,"area":null},{"id":"2309.16459","title":"Augmenting LLMs with Knowledge: A survey on hallucination prevention","created":"2023-09-28","cited_by_count":16,"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":"2310.02469","title":"PrivacyMind: Large Language Models Can Be Contextual Privacy Protection Learners","created":"2023-10-03","cited_by_count":14,"area":null},{"id":"2411.07213","title":"Comparing Bottom-Up and Top-Down Steering Approaches on In-Context Learning Tasks","created":"2024-11-11","cited_by_count":14,"area":null},{"id":"2208.03295","title":"Learning from data in the mixed adversarial non-adversarial case: Finding the helpers and ignoring the trolls","created":"2022-08-05","cited_by_count":11,"area":null},{"id":"2210.00572","title":"Risk-graded Safety for Handling Medical Queries in Conversational AI","created":"2022-10-02","cited_by_count":11,"area":null},{"id":"2312.01509","title":"Tackling Bias in Pre-trained Language Models: Current Trends and Under-represented Societies","created":"2023-12-03","cited_by_count":11,"area":null},{"id":"2306.04707","title":"Improving Open Language Models by Learning from Organic Interactions","created":"2023-06-07","cited_by_count":10,"area":null},{"id":"2203.17090","title":"PanGu-Bot: Efficient Generative Dialogue Pre-training from Pre-trained Language Model","created":"2022-03-31","cited_by_count":9,"area":null},{"id":"2406.07736","title":"MultiPragEval: Multilingual Pragmatic Evaluation of Large Language Models","created":"2024-06-11","cited_by_count":9,"area":null},{"id":"2406.16714","title":"AutoDetect: Towards a Unified Framework for Automated Weakness Detection in Large Language Models","created":"2024-06-24","cited_by_count":9,"area":null},{"id":"2205.09314","title":"Target-Guided Dialogue Response Generation Using Commonsense and Data Augmentation","created":"2022-05-19","cited_by_count":8,"area":null},{"id":"2210.12429","title":"Robots-Dont-Cry: Understanding Falsely Anthropomorphic Utterances in Dialog Systems","created":"2022-10-22","cited_by_count":8,"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":"2304.11220","title":"Learn What NOT to Learn: Towards Generative Safety in Chatbots","created":"2023-04-21","cited_by_count":8,"area":null},{"id":"2301.05154","title":"Mephisto: A Framework for Portable, Reproducible, and Iterative Crowdsourcing","created":"2023-01-12","cited_by_count":7,"area":null},{"id":"2204.03262","title":"Korean Online Hate Speech Dataset for Multilabel Classification: How Can Social Science Improve Dataset on Hate Speech?","created":"2022-04-07","cited_by_count":6,"area":null},{"id":"2306.10645","title":"Developing Effective Educational Chatbots with ChatGPT prompts: Insights from Preliminary Tests in a Case Study on Social Media Literacy (with appendix)","created":"2023-06-18","cited_by_count":6,"area":null},{"id":"2109.02513","title":"Proto: A Neural Cocktail for Generating Appealing Conversations","created":"2021-09-06","cited_by_count":5,"area":null},{"id":"2109.06950","title":"Automatically Exposing Problems with Neural Dialog Models","created":"2021-09-14","cited_by_count":5,"area":null},{"id":"2209.07634","title":"Stateful Memory-Augmented Transformers for Efficient Dialogue Modeling","created":"2022-09-15","cited_by_count":5,"area":null},{"id":"2108.12582","title":"Distilling the Knowledge of Large-scale Generative Models into Retrieval Models for Efficient Open-domain Conversation","created":"2021-08-28","cited_by_count":4,"area":null},{"id":"2201.03239","title":"There is no rose without a thorn: Finding weaknesses on BlenderBot 2.0 in terms of Model, Data and User-Centric Approach","created":"2022-01-10","cited_by_count":4,"area":null},{"id":"2207.11862","title":"Improving Bot Response Contradiction Detection via Utterance Rewriting","created":"2022-07-25","cited_by_count":4,"area":null},{"id":"2207.12021","title":"Neural Generation Meets Real People: Building a Social, Informative Open-Domain Dialogue Agent","created":"2022-07-25","cited_by_count":4,"area":null},{"id":"2212.10557","title":"DialGuide: Aligning Dialogue Model Behavior with Developer Guidelines","created":"2022-12-20","cited_by_count":4,"area":null},{"id":"2405.03735","title":"Select to Perfect: Imitating desired behavior from large multi-agent data","created":"2024-05-06","cited_by_count":4,"area":null},{"id":"2408.10437","title":"Understanding Generative AI Content with Embedding Models","created":"2024-08-19","cited_by_count":4,"area":null},{"id":"2212.11219","title":"On Safe and Usable Chatbots for Promoting Voter Participation","created":"2022-12-16","cited_by_count":3,"area":null},{"id":"2305.11761","title":"ReSeTOX: Re-learning attention weights for toxicity mitigation in machine translation","created":"2023-05-19","cited_by_count":3,"area":null},{"id":"2308.06507","title":"AutoConv: Automatically Generating Information-seeking Conversations with Large Language Models","created":"2023-08-12","cited_by_count":3,"area":null},{"id":"2408.15244","title":"Misrepresented Technological Solutions in Imagined Futures: The Origins and Dangers of AI Hype in the Research Community","created":"2024-08-08","cited_by_count":3,"area":null},{"id":"2410.03870","title":"From Pixels to Personas: Investigating and Modeling Self-Anthropomorphism in Human-Robot Dialogues","created":"2024-10-04","cited_by_count":3,"area":null},{"id":"2412.03824","title":"Towards Data Governance of Frontier AI Models","created":"2024-12-05","cited_by_count":3,"area":null},{"id":"2105.02482","title":"A Unified Pre-training Framework for Conversational AI","created":"2021-05-06","cited_by_count":2,"area":null},{"id":"2108.11063","title":"Viola: A Topic Agnostic Generate-and-Rank Dialogue System","created":"2021-08-25","cited_by_count":2,"area":null},{"id":"2304.07258","title":"Learn What Is Possible, Then Choose What Is Best: Disentangling One-To-Many Relations in Language Through Text-based Games","created":"2023-04-14","cited_by_count":2,"area":null},{"id":"2304.09865","title":"Safer Conversational AI as a Source of User Delight","created":"2023-04-18","cited_by_count":2,"area":null},{"id":"2304.13191","title":"Towards Explainable and Safe Conversational Agents for Mental Health: A Survey","created":"2023-04-25","cited_by_count":2,"area":null},{"id":"2304.14553","title":"Appropriateness is all you need!","created":"2023-04-27","cited_by_count":2,"area":null},{"id":"2311.04921","title":"Successor Features for Efficient Multisubject Controlled Text Generation","created":"2023-11-03","cited_by_count":2,"area":null},{"id":"2412.18672","title":"From Hallucinations to Facts: Enhancing Language Models with Curated Knowledge Graphs","created":"2024-12-24","cited_by_count":2,"area":null},{"id":"2602.02498","title":"Test-Time Detoxification without Training or Learning Anything","created":"2026-01-14","cited_by_count":2,"area":null},{"id":"2203.02392","title":"Beyond Plain Toxic: Detection of Inappropriate Statements on Flammable Topics for the Russian Language","created":"2022-03-04","cited_by_count":1,"area":null}],"next_cursor":"100"}