{"total":117,"rows":[{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512,"area":null},{"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":"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":"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":"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":"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":"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":"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":"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":"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":"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":"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":"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":"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":"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":"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":"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":"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":"2308.07902","title":"Through the Lens of Core Competency: Survey on Evaluation of Large Language Models","created":"2023-08-15","cited_by_count":12,"area":null},{"id":"2205.04238","title":"Counterfactually Augmented Data and Unintended Bias: The Case of Sexism and Hate Speech Detection","created":"2022-05-09","cited_by_count":11,"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":"2306.04707","title":"Improving Open Language Models by Learning from Organic Interactions","created":"2023-06-07","cited_by_count":10,"area":null},{"id":"2104.06393","title":"Bridging the Gap Between Clean Data Training and Real-World Inference for Spoken Language Understanding","created":"2021-04-13","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":"2111.12447","title":"Revisiting Contextual Toxicity Detection in Conversations","created":"2021-11-24","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":"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":"2305.13589","title":"BiasX: \"Thinking Slow\" in Toxic Content Moderation with Explanations of Implied Social Biases","created":"2023-05-23","cited_by_count":7,"area":null},{"id":"2109.06950","title":"Automatically Exposing Problems with Neural Dialog Models","created":"2021-09-14","cited_by_count":5,"area":null},{"id":"2302.06598","title":"Gradient-Based Automated Iterative Recovery for Parameter-Efficient Tuning","created":"2023-02-13","cited_by_count":5,"area":null},{"id":"2308.09720","title":"On the Unexpected Abilities of Large Language Models","created":"2023-08-09","cited_by_count":5,"area":null},{"id":"2310.16955","title":"Break it, Imitate it, Fix it: Robustness by Generating Human-Like Attacks","created":"2023-10-25","cited_by_count":5,"area":null},{"id":"2505.00147","title":"AdaptMI: Adaptive Skill-based In-context Math Instruction for Small Language Models","created":"2025-04-30","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":"2111.02519","title":"Athena 2.0: Contextualized Dialogue Management for an Alexa Prize SocialBot","created":"2021-11-03","cited_by_count":4,"area":null},{"id":"2201.08555","title":"Identifying Adversarial Attacks on Text Classifiers","created":"2022-01-21","cited_by_count":4,"area":null},{"id":"2311.17376","title":"CESAR: Automatic Induction of Compositional Instructions for Multi-turn Dialogs","created":"2023-11-29","cited_by_count":3,"area":null},{"id":"2406.17104","title":"Automated Adversarial Discovery for Safety Classifiers","created":"2024-06-24","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":"2604.14602","title":"CausalDetox: Causal Head Selection and Intervention for Language Model Detoxification","created":"2026-04-16","cited_by_count":3,"area":null},{"id":"2104.08231","title":"An Adversarially-Learned Turing Test for Dialog Generation Models","created":"2021-04-16","cited_by_count":2,"area":null},{"id":"2107.10204","title":"Characterizing Social Imaginaries and Self-Disclosures of Dissonance in Online Conspiracy Discussion Communities","created":"2021-07-21","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":"2402.13372","title":"EvoGrad: A Dynamic Take on the Winograd Schema Challenge with Human Adversaries","created":"2024-02-20","cited_by_count":2,"area":null},{"id":"2412.18551","title":"Libra-Leaderboard: Towards Responsible AI through a Balanced Leaderboard of Safety and Capability","created":"2024-12-24","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},{"id":"2204.08083","title":"AfriWOZ: Corpus for Exploiting Cross-Lingual Transferability for Generation of Dialogues in Low-Resource, African Languages","created":"2022-04-17","cited_by_count":1,"area":null},{"id":"2208.05757","title":"A Comprehensive Survey of Natural Language Generation Advances from the Perspective of Digital Deception","created":"2022-08-11","cited_by_count":1,"area":null}],"next_cursor":"100"}