{"list":"other","total":53,"rows":[{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"id":"1609.07843","title":"Pointer Sentinel Mixture Models","created":"2016-09-26","cited_by_count":3096},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"2010.11934","title":"mT5: A massively multilingual pre-trained text-to-text transformer","created":"2020-10-22","cited_by_count":1818},{"id":"1607.06520","title":"Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings","created":"2016-07-21","cited_by_count":1312},{"id":"2207.04672","title":"No Language Left Behind: Scaling Human-Centered Machine Translation","created":"2022-07-11","cited_by_count":1312},{"id":"2009.11462","title":"RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models","created":"2020-09-24","cited_by_count":1255},{"id":"2004.09456","title":"StereoSet: Measuring stereotypical bias in pretrained language models","created":"2020-04-20","cited_by_count":924},{"id":"1607.01759","title":"Bag of Tricks for Efficient Text Classification","created":"2016-07-06","cited_by_count":876},{"id":"2010.00133","title":"CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models","created":"2020-09-30","cited_by_count":710},{"id":"2110.08193","title":"BBQ: A Hand-Built Bias Benchmark for Question Answering","created":"2021-10-15","cited_by_count":701},{"id":"1906.01502","title":"How multilingual is Multilingual BERT?","created":"2019-06-04","cited_by_count":645},{"id":"1910.11856","title":"On the Cross-lingual Transferability of Monolingual Representations","created":"2019-10-25","cited_by_count":578},{"id":"2106.03193","title":"The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translation","created":"2021-06-06","cited_by_count":560},{"id":"2309.11998","title":"LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset","created":"2023-09-21","cited_by_count":461},{"id":"1707.09457","title":"Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints","created":"2017-07-29","cited_by_count":420},{"id":"2402.07827","title":"Aya Model: An Instruction Finetuned Open-Access Multilingual Language Model","created":"2024-02-12","cited_by_count":295},{"id":"2310.17389","title":"ToxicChat: Unveiling Hidden Challenges of Toxicity Detection in Real-World User-AI Conversation","created":"2023-10-26","cited_by_count":231},{"id":"2202.11176","title":"A New Generation of Perspective API: Efficient Multilingual Character-level Transformers","created":"2022-02-22","cited_by_count":185},{"id":"2401.01967","title":"A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity","created":"2024-01-03","cited_by_count":185},{"id":"2402.06619","title":"Aya Dataset: An Open-Access Collection for Multilingual Instruction Tuning","created":"2024-02-09","cited_by_count":177},{"id":"2309.16240","title":"Beyond Reverse KL: Generalizing Direct Preference Optimization with Diverse Divergence Constraints","created":"2023-09-28","cited_by_count":174},{"id":"2010.12858","title":"When Being Unseen from mBERT is just the Beginning: Handling New Languages With Multilingual Language Models","created":"2020-10-24","cited_by_count":131},{"id":"2405.15032","title":"Aya 23: Open Weight Releases to Further Multilingual Progress","created":"2024-05-23","cited_by_count":123},{"id":"2310.10378","title":"Cross-Lingual Consistency of Factual Knowledge in Multilingual Language Models","created":"2023-10-16","cited_by_count":118},{"id":"2012.15562","title":"UNKs Everywhere: Adapting Multilingual Language Models to New Scripts","created":"2020-12-31","cited_by_count":113},{"id":"2104.06390","title":"Detoxifying Language Models Risks Marginalizing Minority Voices","created":"2021-04-13","cited_by_count":107},{"id":"2109.03646","title":"Sustainable Modular Debiasing of Language Models","created":"2021-09-08","cited_by_count":100},{"id":"2108.03362","title":"On Measures of Biases and Harms in NLP","created":"2021-08-07","cited_by_count":81},{"id":"2406.20052","title":"Understanding and Mitigating Language Confusion in LLMs","created":"2024-06-28","cited_by_count":75},{"id":"2307.16778","title":"KoBBQ: Korean Bias Benchmark for Question Answering","created":"2023-07-31","cited_by_count":71},{"id":"2406.18682","title":"The Multilingual Alignment Prism: Aligning Global and Local Preferences to Reduce Harm","created":"2024-06-26","cited_by_count":70},{"id":"2005.00699","title":"Gender Bias in Multilingual Embeddings and Cross-Lingual Transfer","created":"2020-05-02","cited_by_count":55},{"id":"2304.12397","title":"On the Challenges of Using Black-Box APIs for Toxicity Evaluation in Research","created":"2023-04-24","cited_by_count":44},{"id":"2407.02552","title":"RLHF Can Speak Many Languages: Unlocking Multilingual Preference Optimization for LLMs","created":"2024-07-02","cited_by_count":43},{"id":"2305.11242","title":"Comparing Biases and the Impact of Multilingual Training across Multiple Languages","created":"2023-05-18","cited_by_count":36},{"id":"2404.14397","title":"RTP-LX: Can LLMs Evaluate Toxicity in Multilingual Scenarios?","created":"2024-04-22","cited_by_count":36},{"id":"2110.05367","title":"Improving Gender Fairness of Pre-Trained Language Models without Catastrophic Forgetting","created":"2021-10-11","cited_by_count":35},{"id":"2406.07243","title":"MBBQ: A Dataset for Cross-Lingual Comparison of Stereotypes in Generative LLMs","created":"2024-06-11","cited_by_count":35},{"id":"2305.13862","title":"A Trip Towards Fairness: Bias and De-Biasing in Large Language Models","created":"2023-05-23","cited_by_count":32},{"id":"2307.01503","title":"On Evaluating and Mitigating Gender Biases in Multilingual Settings","created":"2023-07-04","cited_by_count":31},{"id":"2406.16235","title":"Preference Tuning For Toxicity Mitigation Generalizes Across Languages","created":"2024-06-23","cited_by_count":31},{"id":"2403.03893","title":"From One to Many: Expanding the Scope of Toxicity Mitigation in Language Models","created":"2024-03-06","cited_by_count":18},{"id":"2407.13928","title":"BiasDPO: Mitigating Bias in Language Models through Direct Preference Optimization","created":"2024-07-18","cited_by_count":18},{"id":"2311.13937","title":"Exploring Methods for Cross-lingual Text Style Transfer: The Case of Text Detoxification","created":"2023-11-23","cited_by_count":15},{"id":"2407.04434","title":"From 'Showgirls' to 'Performers': Fine-tuning with Gender-inclusive Language for Bias Reduction in LLMs","created":"2024-07-05","cited_by_count":15},{"id":"2310.10310","title":"Investigating Bias in Multilingual Language Models: Cross-Lingual Transfer of Debiasing Techniques","created":"2023-10-16","cited_by_count":14},{"id":"2404.02037","title":"MultiParaDetox: Extending Text Detoxification with Parallel Data to New Languages","created":"2024-04-02","cited_by_count":14},{"id":"2407.16607","title":"Data Mixture Inference: What do BPE Tokenizers Reveal about their Training Data?","created":"2024-07-23","cited_by_count":13},{"id":"2406.05918","title":"Why Don't Prompt-Based Fairness Metrics Correlate?","created":"2024-06-09","cited_by_count":4}],"next_cursor":null}