{"total":337,"rows":[{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512,"area":null},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024,"area":null},{"id":"2107.13586","title":"Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing","created":"2021-07-28","cited_by_count":2234,"area":null},{"id":"2112.11446","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","created":"2021-12-08","cited_by_count":1202,"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":"2308.10248","title":"Steering Language Models With Activation Engineering","created":"2023-08-20","cited_by_count":922,"area":"mechinterp"},{"id":"2210.02414","title":"GLM-130B: An Open Bilingual Pre-trained Model","created":"2022-10-05","cited_by_count":843,"area":null},{"id":"2310.11324","title":"Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting","created":"2023-10-17","cited_by_count":817,"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":"2201.11990","title":"Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Model","created":"2022-01-28","cited_by_count":559,"area":null},{"id":"2303.07345","title":"Erasing Concepts from Diffusion Models","created":"2023-03-13","cited_by_count":539,"area":"diffusion"},{"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":"2211.05105","title":"Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models","created":"2022-11-09","cited_by_count":513,"area":"diffusion"},{"id":"2111.01243","title":"Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey","created":"2021-11-01","cited_by_count":463,"area":null},{"id":"2304.05335","title":"Toxicity in ChatGPT: Analyzing Persona-assigned Language Models","created":"2023-04-11","cited_by_count":360,"area":null},{"id":"2306.13213","title":"Visual Adversarial Examples Jailbreak Aligned Large Language Models","created":"2023-06-22","cited_by_count":328,"area":"mllm"},{"id":"2410.21819","title":"Self-Preference Bias in LLM-as-a-Judge","created":"2024-10-29","cited_by_count":258,"area":null},{"id":"2311.06668","title":"In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering","created":"2023-11-11","cited_by_count":245,"area":null},{"id":"2309.15025","title":"Large Language Model Alignment: A Survey","created":"2023-09-26","cited_by_count":243,"area":"alignment"},{"id":"2406.01297","title":"When Can LLMs Actually Correct Their Own Mistakes? A Critical Survey of Self-Correction of LLMs","created":"2024-06-03","cited_by_count":240,"area":null},{"id":"2205.13636","title":"Quark: Controllable Text Generation with Reinforced Unlearning","created":"2022-05-26","cited_by_count":237,"area":"safety"},{"id":"2202.07922","title":"ZeroGen: Efficient Zero-shot Learning via Dataset Generation","created":"2022-02-16","cited_by_count":211,"area":null},{"id":"2305.18189","title":"Marked Personas: Using Natural Language Prompts to Measure Stereotypes in Language Models","created":"2023-05-29","cited_by_count":207,"area":null},{"id":"2105.04054","title":"Societal Biases in Language Generation: Progress and Challenges","created":"2021-05-10","cited_by_count":202,"area":null},{"id":"2104.07540","title":"Generating Datasets with Pretrained Language Models","created":"2021-04-15","cited_by_count":193,"area":null},{"id":"2104.08826","title":"GPT3Mix: Leveraging Large-scale Language Models for Text Augmentation","created":"2021-04-18","cited_by_count":187,"area":null},{"id":"2207.07051","title":"Language models show human-like content effects on reasoning tasks","created":"2022-07-14","cited_by_count":173,"area":"lr"},{"id":"2302.07459","title":"The Capacity for Moral Self-Correction in Large Language Models","created":"2023-02-15","cited_by_count":173,"area":"alignment"},{"id":"2109.07445","title":"Challenges in Detoxifying Language Models","created":"2021-09-15","cited_by_count":169,"area":null},{"id":"2205.09209","title":"\"I'm sorry to hear that\": Finding New Biases in Language Models with a Holistic Descriptor Dataset","created":"2022-05-18","cited_by_count":162,"area":null},{"id":"2202.06675","title":"Can Machines Help Us Answering Question 16 in Datasheets, and In Turn Reflecting on Inappropriate Content?","created":"2022-02-14","cited_by_count":155,"area":null},{"id":"2312.03689","title":"Evaluating and Mitigating Discrimination in Language Model Decisions","created":"2023-12-06","cited_by_count":124,"area":null},{"id":"2201.05273","title":"Pretrained Language Models for Text Generation: A Survey","created":"2022-01-14","cited_by_count":122,"area":null},{"id":"2403.00811","title":"Cognitive Bias in Decision-Making with LLMs","created":"2024-02-25","cited_by_count":106,"area":null},{"id":"2305.08844","title":"RL4F: Generating Natural Language Feedback with Reinforcement Learning for Repairing Model Outputs","created":"2023-05-15","cited_by_count":105,"area":null},{"id":"2110.08527","title":"An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language Models","created":"2021-10-16","cited_by_count":97,"area":null},{"id":"2204.03021","title":"The Moral Integrity Corpus: A Benchmark for Ethical Dialogue Systems","created":"2022-04-06","cited_by_count":93,"area":null},{"id":"2402.02680","title":"Large Language Models are Geographically Biased","created":"2024-02-05","cited_by_count":93,"area":"wm"},{"id":"2404.00929","title":"A Survey on Multilingual Large Language Models: Corpora, Alignment, and Bias","created":"2024-04-01","cited_by_count":84,"area":null},{"id":"2302.11529","title":"Modular Deep Learning","created":"2023-02-22","cited_by_count":83,"area":null},{"id":"2105.02732","title":"What's in the Box? A Preliminary Analysis of Undesirable Content in the Common Crawl Corpus","created":"2021-05-06","cited_by_count":80,"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":"2310.19596","title":"LLMaAA: Making Large Language Models as Active Annotators","created":"2023-10-30","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":"2411.10915","title":"Bias in Large Language Models: Origin, Evaluation, and Mitigation","created":"2024-11-16","cited_by_count":77,"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":"2406.12031","title":"Large Scale Transfer Learning for Tabular Data via Language Modeling","created":"2024-06-17","cited_by_count":76,"area":null},{"id":"2310.12560","title":"Fast Model Debias with Machine Unlearning","created":"2023-10-19","cited_by_count":72,"area":"safety"},{"id":"2305.12798","title":"Word Embeddings Are Steers for Language Models","created":"2023-05-22","cited_by_count":70,"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":"2210.13918","title":"Differentially Private Language Models for Secure Data Sharing","created":"2022-10-25","cited_by_count":68,"area":null},{"id":"2404.13081","title":"SuRe: Summarizing Retrievals using Answer Candidates for Open-domain QA of LLMs","created":"2024-04-17","cited_by_count":67,"area":null},{"id":"2104.07496","title":"Unmasking the Mask -- Evaluating Social Biases in Masked Language Models","created":"2021-04-15","cited_by_count":60,"area":null},{"id":"2402.01981","title":"Self-Debiasing Large Language Models: Zero-Shot Recognition and Reduction of Stereotypes","created":"2024-02-03","cited_by_count":59,"area":null},{"id":"2405.17894","title":"White-box Multimodal Jailbreaks Against Large Vision-Language Models","created":"2024-05-28","cited_by_count":59,"area":"mllm"},{"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":"2103.12407","title":"Detecting Hate Speech with GPT-3","created":"2021-03-23","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":"2105.13947","title":"Changing the World by Changing the Data","created":"2021-05-28","cited_by_count":51,"area":null},{"id":"2310.10383","title":"Privacy in Large Language Models: Attacks, Defenses and Future Directions","created":"2023-10-16","cited_by_count":51,"area":null},{"id":"2311.14479","title":"Controlled Text Generation via Language Model Arithmetic","created":"2023-11-24","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":"2307.07055","title":"Reward-Directed Conditional Diffusion: Provable Distribution Estimation and Reward Improvement","created":"2023-07-13","cited_by_count":49,"area":"diffusion"},{"id":"2402.11190","title":"Disclosure and Mitigation of Gender Bias in LLMs","created":"2024-02-17","cited_by_count":49,"area":null},{"id":"2401.12874","title":"From Understanding to Utilization: A Survey on Explainability for Large Language Models","created":"2024-01-23","cited_by_count":48,"area":null},{"id":"2310.09573","title":"Self-Detoxifying Language Models via Toxification Reversal","created":"2023-10-14","cited_by_count":46,"area":"safety"},{"id":"2310.16523","title":"Improving Diversity of Demographic Representation in Large Language Models via Collective-Critiques and Self-Voting","created":"2023-10-25","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":"2307.05977","title":"Towards Safe Self-Distillation of Internet-Scale Text-to-Image Diffusion Models","created":"2023-07-12","cited_by_count":41,"area":"diffusion"},{"id":"2108.07790","title":"Mitigating harm in language models with conditional-likelihood filtration","created":"2021-08-04","cited_by_count":40,"area":null},{"id":"2407.03129","title":"Social Bias Evaluation for Large Language Models Requires Prompt Variations","created":"2024-07-03","cited_by_count":40,"area":null},{"id":"2504.14492","title":"FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering","created":"2025-04-20","cited_by_count":40,"area":"mechinterp"},{"id":"2308.05596","title":"You Only Prompt Once: On the Capabilities of Prompt Learning on Large Language Models to Tackle Toxic Content","created":"2023-08-10","cited_by_count":39,"area":null},{"id":"2404.17218","title":"Prompting Techniques for Reducing Social Bias in LLMs through System 1 and System 2 Cognitive Processes","created":"2024-04-26","cited_by_count":39,"area":null},{"id":"2111.13440","title":"True Few-Shot Learning with Prompts -- A Real-World Perspective","created":"2021-11-26","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":"2305.08005","title":"Beyond the Safeguards: Exploring the Security Risks of ChatGPT","created":"2023-05-13","cited_by_count":36,"area":null},{"id":"2205.12390","title":"Toxicity Detection with Generative Prompt-based Inference","created":"2022-05-24","cited_by_count":35,"area":null},{"id":"2306.08107","title":"AutoML in the Age of Large Language Models: Current Challenges, Future Opportunities and Risks","created":"2023-06-13","cited_by_count":35,"area":null},{"id":"2210.04492","title":"Unified Detoxifying and Debiasing in Language Generation via Inference-time Adaptive Optimization","created":"2022-10-10","cited_by_count":33,"area":null},{"id":"2407.18369","title":"AI Safety in Generative AI Large Language Models: A Survey","created":"2024-07-06","cited_by_count":33,"area":null},{"id":"2210.14169","title":"Weakly Supervised Data Augmentation Through Prompting for Dialogue Understanding","created":"2022-10-25","cited_by_count":32,"area":null},{"id":"2307.01503","title":"On Evaluating and Mitigating Gender Biases in Multilingual Settings","created":"2023-07-04","cited_by_count":31,"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":"2309.03876","title":"OpinionGPT: Modelling Explicit Biases in Instruction-Tuned LLMs","created":"2023-09-07","cited_by_count":29,"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":"2210.03992","title":"Generative Language Models for Paragraph-Level Question Generation","created":"2022-10-08","cited_by_count":28,"area":null},{"id":"2212.10678","title":"Causally Testing Gender Bias in LLMs: A Case Study on Occupational Bias","created":"2022-12-20","cited_by_count":28,"area":null},{"id":"2306.04597","title":"Language Models Get a Gender Makeover: Mitigating Gender Bias with Few-Shot Data Interventions","created":"2023-06-07","cited_by_count":28,"area":null},{"id":"2306.08158","title":"Sociodemographic Bias in Language Models: A Survey and Forward Path","created":"2023-06-13","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":"2301.00355","title":"Second Thoughts are Best: Learning to Re-Align With Human Values from Text Edits","created":"2023-01-01","cited_by_count":27,"area":"lr"},{"id":"2109.07437","title":"Should We Be Pre-training? An Argument for End-task Aware Training as an Alternative","created":"2021-09-15","cited_by_count":26,"area":null},{"id":"2305.10703","title":"ReGen: Zero-Shot Text Classification via Training Data Generation with Progressive Dense Retrieval","created":"2023-05-18","cited_by_count":26,"area":null},{"id":"2309.14381","title":"Survey of Social Bias in Vision-Language Models","created":"2023-09-24","cited_by_count":26,"area":"mllm"},{"id":"2406.01285","title":"Large Language Models as Recommender Systems: A Study of Popularity Bias","created":"2024-06-03","cited_by_count":26,"area":null},{"id":"2302.06321","title":"Parameter-efficient Modularised Bias Mitigation via AdapterFusion","created":"2023-02-13","cited_by_count":25,"area":null},{"id":"2310.14192","title":"PromptMix: A Class Boundary Augmentation Method for Large Language Model Distillation","created":"2023-10-22","cited_by_count":25,"area":null},{"id":"2408.08656","title":"LLMs Are Biased Towards Output Formats! Systematically Evaluating and Mitigating Output Format Bias of LLMs","created":"2024-08-16","cited_by_count":25,"area":null}],"next_cursor":"100"}