{"total":110,"rows":[{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780,"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":"2112.04359","title":"Ethical and social risks of harm from Language Models","created":"2021-12-08","cited_by_count":966,"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":"2306.16388","title":"Towards Measuring the Representation of Subjective Global Opinions in Language Models","created":"2023-06-28","cited_by_count":437,"area":null},{"id":"2201.10005","title":"Text and Code Embeddings by Contrastive Pre-Training","created":"2022-01-24","cited_by_count":361,"area":null},{"id":"2210.09150","title":"Prompting GPT-3 To Be Reliable","created":"2022-10-17","cited_by_count":260,"area":null},{"id":"2305.03514","title":"Can Large Language Models Transform Computational Social Science?","created":"2023-04-12","cited_by_count":250,"area":null},{"id":"2203.10020","title":"Challenges and Strategies in Cross-Cultural NLP","created":"2022-03-18","cited_by_count":218,"area":null},{"id":"2307.14324","title":"Evaluating the Moral Beliefs Encoded in LLMs","created":"2023-07-26","cited_by_count":215,"area":null},{"id":"2306.09479","title":"Inverse Scaling: When Bigger Isn't Better","created":"2023-06-15","cited_by_count":207,"area":null},{"id":"2111.10952","title":"ExT5: Towards Extreme Multi-Task Scaling for Transfer Learning","created":"2021-11-22","cited_by_count":161,"area":null},{"id":"2401.16380","title":"Rephrasing the Web: A Recipe for Compute and Data-Efficient Language Modeling","created":"2024-01-29","cited_by_count":161,"area":null},{"id":"2308.06259","title":"Self-Alignment with Instruction Backtranslation","created":"2023-08-11","cited_by_count":151,"area":null},{"id":"2203.13722","title":"Probing Pre-Trained Language Models for Cross-Cultural Differences in Values","created":"2022-03-25","cited_by_count":149,"area":null},{"id":"2312.03718","title":"Large Language Models in Law: A Survey","created":"2023-11-26","cited_by_count":128,"area":null},{"id":"2203.07785","title":"The Ghost in the Machine has an American accent: value conflict in GPT-3","created":"2022-03-15","cited_by_count":105,"area":null},{"id":"2310.11501","title":"CoMPosT: Characterizing and Evaluating Caricature in LLM Simulations","created":"2023-10-17","cited_by_count":97,"area":null},{"id":"2306.05949","title":"Evaluating the Social Impact of Generative AI Systems in Systems and Society","created":"2023-06-09","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":"2403.18932","title":"Measuring Political Bias in Large Language Models: What Is Said and How It Is Said","created":"2024-03-27","cited_by_count":89,"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":"2407.09121","title":"Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training","created":"2024-07-12","cited_by_count":69,"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":"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":"2302.04844","title":"The Gradient of Generative AI Release: Methods and Considerations","created":"2023-02-05","cited_by_count":63,"area":null},{"id":"2402.04105","title":"Measuring Implicit Bias in Explicitly Unbiased Large Language Models","created":"2024-02-06","cited_by_count":51,"area":null},{"id":"2206.08325","title":"Characteristics of Harmful Text: Towards Rigorous Benchmarking of Language Models","created":"2022-06-16","cited_by_count":49,"area":null},{"id":"2210.08604","title":"NormSAGE: Multi-Lingual Multi-Cultural Norm Discovery from Conversations On-the-Fly","created":"2022-10-16","cited_by_count":48,"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":"2108.07790","title":"Mitigating harm in language models with conditional-likelihood filtration","created":"2021-08-04","cited_by_count":40,"area":null},{"id":"2108.01250","title":"Your fairness may vary: Pretrained language model fairness in toxic text classification","created":"2021-08-03","cited_by_count":39,"area":null},{"id":"2310.18362","title":"SoK: Memorization in General-Purpose Large Language Models","created":"2023-10-24","cited_by_count":37,"area":null},{"id":"2412.13879","title":"Crabs: Consuming Resource via Auto-generation for LLM-DoS Attack under Black-box Settings","created":"2024-12-18","cited_by_count":35,"area":null},{"id":"2211.07733","title":"Speaking Multiple Languages Affects the Moral Bias of Language Models","created":"2022-11-14","cited_by_count":34,"area":null},{"id":"2410.04332","title":"Gradient Routing: Masking Gradients to Localize Computation in Neural Networks","created":"2024-10-06","cited_by_count":34,"area":null},{"id":"2303.06167","title":"Overwriting Pretrained Bias with Finetuning Data","created":"2023-03-10","cited_by_count":32,"area":null},{"id":"2406.18678","title":"Few-shot Personalization of LLMs with Mis-aligned Responses","created":"2024-06-26","cited_by_count":32,"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":"2303.10464","title":"SPDF: Sparse Pre-training and Dense Fine-tuning for Large Language Models","created":"2023-03-18","cited_by_count":28,"area":null},{"id":"2402.15350","title":"Farsight: Fostering Responsible AI Awareness During AI Application Prototyping","created":"2024-02-23","cited_by_count":28,"area":null},{"id":"2407.19096","title":"AI Companions Reduce Loneliness","created":"2024-07-09","cited_by_count":28,"area":null},{"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":"2305.17701","title":"KoSBi: A Dataset for Mitigating Social Bias Risks Towards Safer Large Language Model Application","created":"2023-05-28","cited_by_count":24,"area":null},{"id":"2306.16244","title":"CBBQ: A Chinese Bias Benchmark Dataset Curated with Human-AI Collaboration for Large Language Models","created":"2023-06-28","cited_by_count":23,"area":null},{"id":"2207.14157","title":"A Hazard Analysis Framework for Code Synthesis Large Language Models","created":"2022-07-25","cited_by_count":22,"area":null},{"id":"2310.12611","title":"Identifying and Adapting Transformer-Components Responsible for Gender Bias in an English Language Model","created":"2023-10-19","cited_by_count":22,"area":null},{"id":"2205.11374","title":"Looking for a Handsome Carpenter! Debiasing GPT-3 Job Advertisements","created":"2022-05-23","cited_by_count":21,"area":null},{"id":"2211.05414","title":"ADEPT: A DEbiasing PrompT Framework","created":"2022-11-10","cited_by_count":21,"area":null},{"id":"2111.06467","title":"SynthBio: A Case Study in Human-AI Collaborative Curation of Text Datasets","created":"2021-11-11","cited_by_count":18,"area":null},{"id":"2508.18765","title":"Governance-as-a-Service: A Multi-Agent Framework for AI System Compliance and Policy Enforcement","created":"2025-08-26","cited_by_count":17,"area":null},{"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":"2410.17519","title":"Large Language Models Still Exhibit Bias in Long Text","created":"2024-10-23","cited_by_count":16,"area":null},{"id":"2402.01874","title":"The RL/LLM Taxonomy Tree: Reviewing Synergies Between Reinforcement Learning and Large Language Models","created":"2024-02-02","cited_by_count":15,"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":"2210.09306","title":"Mitigating Covertly Unsafe Text within Natural Language Systems","created":"2022-10-17","cited_by_count":13,"area":null},{"id":"2305.13406","title":"DADA: Dialect Adaptation via Dynamic Aggregation of Linguistic Rules","created":"2023-05-22","cited_by_count":13,"area":null},{"id":"2305.17696","title":"SQuARe: A Large-Scale Dataset of Sensitive Questions and Acceptable Responses Created Through Human-Machine Collaboration","created":"2023-05-28","cited_by_count":13,"area":null},{"id":"2307.03201","title":"Scaling Laws Do Not Scale","created":"2023-07-05","cited_by_count":13,"area":null},{"id":"2407.09241","title":"The Sociolinguistic Foundations of Language Modeling","created":"2024-07-12","cited_by_count":13,"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":"2312.07751","title":"Large Human Language Models: A Need and the Challenges","created":"2023-11-09","cited_by_count":11,"area":null},{"id":"2205.07233","title":"Mitigating Toxic Degeneration with Empathetic Data: Exploring the Relationship Between Toxicity and Empathy","created":"2022-05-15","cited_by_count":8,"area":null},{"id":"2304.08968","title":"Stochastic Parrots Looking for Stochastic Parrots: LLMs are Easy to Fine-Tune and Hard to Detect with other LLMs","created":"2023-04-18","cited_by_count":8,"area":null},{"id":"2402.10353","title":"Prompt-Based Bias Calibration for Better Zero/Few-Shot Learning of Language Models","created":"2024-02-15","cited_by_count":8,"area":null},{"id":"2504.07801","title":"FairEval: Evaluating Fairness in LLM-Based Recommendations with Personality Awareness","created":"2025-04-10","cited_by_count":8,"area":null},{"id":"2402.06287","title":"AI, Meet Human: Learning Paradigms for Hybrid Decision Making Systems","created":"2024-02-09","cited_by_count":7,"area":null},{"id":"2406.06559","title":"Harnessing Business and Media Insights with Large Language Models","created":"2024-06-02","cited_by_count":7,"area":null},{"id":"2501.06911","title":"Risk-Averse Finetuning of Large Language Models","created":"2025-01-12","cited_by_count":7,"area":null},{"id":"2208.01009","title":"Few-shot Adaptation Works with UnpredicTable Data","created":"2022-08-01","cited_by_count":6,"area":null},{"id":"2303.08956","title":"Exploring the Relevance of Data Privacy-Enhancing Technologies for AI Governance Use Cases","created":"2023-03-15","cited_by_count":6,"area":null},{"id":"2306.03423","title":"I'm Afraid I Can't Do That: Predicting Prompt Refusal in Black-Box Generative Language Models","created":"2023-06-06","cited_by_count":6,"area":null},{"id":"2308.08295","title":"CMD: a framework for Context-aware Model self-Detoxification","created":"2023-08-16","cited_by_count":6,"area":null},{"id":"2306.02294","title":"Exposing Bias in Online Communities through Large-Scale Language Models","created":"2023-06-04","cited_by_count":5,"area":null},{"id":"2406.17566","title":"FrenchToxicityPrompts: a Large Benchmark for Evaluating and Mitigating Toxicity in French Texts","created":"2024-06-25","cited_by_count":5,"area":null},{"id":"2602.04398","title":"Bi-directional Bias Attribution: Debiasing Large Language Models without Modifying Prompts","created":"2026-02-04","cited_by_count":5,"area":null},{"id":"2309.13218","title":"Language Models for Business Optimisation with a Real World Case Study in Production Scheduling","created":"2023-09-22","cited_by_count":4,"area":null},{"id":"2210.06245","title":"Back to the Future: On Potential Histories in NLP","created":"2022-10-12","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":"2311.05451","title":"All Should Be Equal in the Eyes of Language Models: Counterfactually Aware Fair Text Generation","created":"2023-11-09","cited_by_count":3,"area":null},{"id":"2405.18572","title":"Low-rank finetuning for LLMs: A fairness perspective","created":"2024-05-28","cited_by_count":3,"area":null},{"id":"2407.11203","title":"The Life Cycle of Large Language Models: A Review of Biases in Education","created":"2024-06-03","cited_by_count":3,"area":null},{"id":"2502.15873","title":"Practical Principles for AI Cost and Compute Accounting","created":"2025-02-21","cited_by_count":3,"area":null},{"id":"2505.18927","title":"Moderating Harm: Benchmarking Large Language Models for Cyberbullying Detection in YouTube Comments","created":"2025-05-25","cited_by_count":3,"area":null},{"id":"2507.19962","title":"KLAAD: Refining Attention Mechanisms to Reduce Societal Bias in Generative Language Models","created":"2025-07-26","cited_by_count":3,"area":null},{"id":"2208.07127","title":"Deception for Cyber Defence: Challenges and Opportunities","created":"2022-08-15","cited_by_count":2,"area":null},{"id":"2310.07225","title":"Do Large Language Models have Shared Weaknesses in Medical Question Answering?","created":"2023-10-11","cited_by_count":2,"area":null},{"id":"2403.11838","title":"Ensuring Safe and High-Quality Outputs: A Guideline Library Approach for Language Models","created":"2024-03-18","cited_by_count":2,"area":null},{"id":"2411.03287","title":"The Future of Intelligent Healthcare: A Systematic Analysis and Discussion on the Integration and Impact of Robots Using Large Language Models for Healthcare","created":"2024-11-05","cited_by_count":2,"area":null},{"id":"2503.00020","title":"A Systematic Review of Open Datasets Used in Text-to-Image (T2I) Gen AI Model Safety","created":"2025-02-23","cited_by_count":2,"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":"2308.06095","title":"Neural Conversation Models and How to Rein Them in: A Survey of Failures and Fixes","created":"2023-08-11","cited_by_count":1,"area":null},{"id":"2309.05981","title":"Learning Unbiased News Article Representations: A Knowledge-Infused Approach","created":"2023-09-12","cited_by_count":1,"area":null},{"id":"2404.08672","title":"Taxonomy and Analysis of Sensitive User Queries in Generative AI Search","created":"2024-04-05","cited_by_count":1,"area":null},{"id":"2407.11613","title":"Bringing AI Participation Down to Scale: A Comment on Open AIs Democratic Inputs to AI Project","created":"2024-07-16","cited_by_count":1,"area":null},{"id":"2502.07072","title":"IRepair: An Intent-Aware Approach to Repair Data-Driven Errors in Large Language Models","created":"2025-02-10","cited_by_count":1,"area":null},{"id":"2602.01558","title":"How Implicit Bias Accumulates and Propagates in LLM Long-term Memory","created":"2026-02-02","cited_by_count":1,"area":null},{"id":"2603.11299","title":"Counterweights and Complementarities: The Convergence of AI and Blockchain Powering a Decentralized Future","created":"2026-03-11","cited_by_count":1,"area":null},{"id":"2607.19834","title":"D2VBench: Benchmarking Large Language Models with Value Dilemmas in Daily Scenarios","created":"2026-07-22","cited_by_count":1,"area":null}],"next_cursor":"100"}