{"list":"other","total":51,"rows":[{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"2101.00027","title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","created":"2020-12-31","cited_by_count":2411},{"id":"2210.09261","title":"Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them","created":"2022-10-17","cited_by_count":1807},{"id":"1703.04009","title":"Automated Hate Speech Detection and the Problem of Offensive Language","created":"2017-03-11","cited_by_count":736},{"id":"2309.12284","title":"MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models","created":"2023-09-21","cited_by_count":735},{"id":"2401.01335","title":"Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models","created":"2024-01-02","cited_by_count":557},{"id":"2401.00368","title":"Improving Text Embeddings with Large Language Models","created":"2023-12-31","cited_by_count":303},{"id":"2303.12528","title":"MEGA: Multilingual Evaluation of Generative AI","created":"2023-03-22","cited_by_count":293},{"id":"2310.19852","title":"AI Alignment: A Comprehensive Survey","created":"2023-10-30","cited_by_count":263},{"id":"2309.15025","title":"Large Language Model Alignment: A Survey","created":"2023-09-26","cited_by_count":243},{"id":"2303.17466","title":"Assessing Cross-Cultural Alignment between ChatGPT and Human Societies: An Empirical Study","created":"2023-03-30","cited_by_count":206},{"id":"2305.14456","title":"Having Beer after Prayer? Measuring Cultural Bias in Large Language Models","created":"2023-05-23","cited_by_count":153},{"id":"2308.06259","title":"Self-Alignment with Instruction Backtranslation","created":"2023-08-11","cited_by_count":151},{"id":"2006.07235","title":"SemEval-2020 Task 12: Multilingual Offensive Language Identification in Social Media (OffensEval 2020)","created":"2020-06-12","cited_by_count":138},{"id":"1908.11049","title":"Multilingual and Multi-Aspect Hate Speech Analysis","created":"2019-08-29","cited_by_count":133},{"id":"2309.12342","title":"Cultural Alignment in Large Language Models: An Explanatory Analysis Based on Hofstede's Cultural Dimensions","created":"2023-08-25","cited_by_count":112},{"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},{"id":"2312.00738","title":"SeaLLMs -- Large Language Models for Southeast Asia","created":"2023-12-01","cited_by_count":104},{"id":"1701.08118","title":"Measuring the Reliability of Hate Speech Annotations: The Case of the European Refugee Crisis","created":"2017-01-27","cited_by_count":96},{"id":"2307.09705","title":"CValues: Measuring the Values of Chinese Large Language Models from Safety to Responsibility","created":"2023-07-19","cited_by_count":85},{"id":"2310.13132","title":"Better to Ask in English: Cross-Lingual Evaluation of Large Language Models for Healthcare Queries","created":"2023-10-19","cited_by_count":82},{"id":"2210.07763","title":"Extracting Cultural Commonsense Knowledge at Scale","created":"2022-10-14","cited_by_count":76},{"id":"2312.09241","title":"TinyGSM: achieving >80% on GSM8k with small language models","created":"2023-12-14","cited_by_count":70},{"id":"2310.07251","title":"Ethical Reasoning over Moral Alignment: A Case and Framework for In-Context Ethical Policies in LLMs","created":"2023-10-11","cited_by_count":64},{"id":"2309.02144","title":"Making Large Language Models Better Reasoners with Alignment","created":"2023-09-05","cited_by_count":63},{"id":"2004.14454","title":"SOLID: A Large-Scale Semi-Supervised Dataset for Offensive Language Identification","created":"2020-04-29","cited_by_count":53},{"id":"2206.09917","title":"Multilingual HateCheck: Functional Tests for Multilingual Hate Speech Detection Models","created":"2022-06-20","cited_by_count":51},{"id":"2003.07459","title":"Offensive Language Identification in Greek","created":"2020-03-16","cited_by_count":50},{"id":"2307.07870","title":"Large Language Models as Superpositions of Cultural Perspectives","created":"2023-07-15","cited_by_count":49},{"id":"2210.08604","title":"NormSAGE: Multi-Lingual Multi-Cultural Norm Discovery from Conversations On-the-Fly","created":"2022-10-16","cited_by_count":48},{"id":"2010.04543","title":"Toxic Language Detection in Social Media for Brazilian Portuguese: New Dataset and Multilingual Analysis","created":"2020-10-09","cited_by_count":45},{"id":"2308.12014","title":"From Instructions to Intrinsic Human Values -- A Survey of Alignment Goals for Big Models","created":"2023-08-23","cited_by_count":45},{"id":"2310.12481","title":"Not All Countries Celebrate Thanksgiving: On the Cultural Dominance in Large Language Models","created":"2023-10-19","cited_by_count":43},{"id":"2005.12503","title":"BEEP! Korean Corpus of Online News Comments for Toxic Speech Detection","created":"2020-05-26","cited_by_count":39},{"id":"2202.00132","title":"Submodularity In Machine Learning and Artificial Intelligence","created":"2022-01-31","cited_by_count":38},{"id":"2012.09686","title":"Hate Speech detection in the Bengali language: A dataset and its baseline evaluation","created":"2020-12-17","cited_by_count":37},{"id":"2003.07428","title":"Developing a Multilingual Annotated Corpus of Misogyny and Aggression","created":"2020-03-16","cited_by_count":33},{"id":"2309.08591","title":"Are Multilingual LLMs Culturally-Diverse Reasoners? An Investigation into Multicultural Proverbs and Sayings","created":"2023-09-15","cited_by_count":32},{"id":"2310.13671","title":"Let's Synthesize Step by Step: Iterative Dataset Synthesis with Large Language Models by Extrapolating Errors from Small Models","created":"2023-10-20","cited_by_count":30},{"id":"2312.13951","title":"Typhoon: Thai Large Language Models","created":"2023-12-21","cited_by_count":30},{"id":"2311.17487","title":"Taiwan LLM: Bridging the Linguistic Divide with a Culturally Aligned Language Model","created":"2023-11-29","cited_by_count":29},{"id":"1311.3475","title":"Social Influence and the Collective Dynamics of Opinion Formation","created":"2013-11-14","cited_by_count":16},{"id":"2103.14972","title":"HateBR: A Large Expert Annotated Corpus of Brazilian Instagram Comments for Offensive Language and Hate Speech Detection","created":"2021-03-27","cited_by_count":15},{"id":"2312.15713","title":"PersianLLaMA: Towards Building First Persian Large Language Model","created":"2023-12-25","cited_by_count":14},{"id":"2208.10684","title":"K-MHaS: A Multi-label Hate Speech Detection Dataset in Korean Online News Comment","created":"2022-08-23","cited_by_count":13},{"id":"2005.07297","title":"OSACT4 Shared Task on Offensive Language Detection: Intensive Preprocessing-Based Approach","created":"2020-05-14","cited_by_count":11},{"id":"2111.04530","title":"AI-UPV at IberLEF-2021 DETOXIS task: Toxicity Detection in Immigration-Related Web News Comments Using Transformers and Statistical Models","created":"2021-11-08","cited_by_count":8},{"id":"2310.10679","title":"Large language models can replicate cross-cultural differences in personality","created":"2023-10-12","cited_by_count":8},{"id":"1908.11561","title":"Detect Camouflaged Spam Content via StoneSkipping: Graph and Text Joint Embedding for Chinese Character Variation Representation","created":"2019-08-30","cited_by_count":7}],"next_cursor":null}