{"list":"other","total":59,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"2206.04615","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","created":"2022-06-09","cited_by_count":1998},{"id":"2503.19786","title":"Gemma 3 Technical Report","created":"2025-03-25","cited_by_count":1824},{"id":"2306.03341","title":"Inference-Time Intervention: Eliciting Truthful Answers from a Language Model","created":"2023-06-06","cited_by_count":1302},{"id":"2303.12528","title":"MEGA: Multilingual Evaluation of Generative AI","created":"2023-03-22","cited_by_count":293},{"id":"2111.07997","title":"Annotators with Attitudes: How Annotator Beliefs And Identities Bias Toxic Language Detection","created":"2021-11-15","cited_by_count":264},{"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":"2402.18815","title":"How do Large Language Models Handle Multilingualism?","created":"2024-02-29","cited_by_count":150},{"id":"2012.15738","title":"Moral Stories: Situated Reasoning about Norms, Intents, Actions, and their Consequences","created":"2020-12-31","cited_by_count":135},{"id":"2402.16438","title":"Language-Specific Neurons: The Key to Multilingual Capabilities in Large Language Models","created":"2024-02-26","cited_by_count":126},{"id":"2406.05967","title":"CVQA: Culturally-diverse Multilingual Visual Question Answering Benchmark","created":"2024-06-10","cited_by_count":120},{"id":"2407.10920","title":"Benchmarking Vision Language Models for Cultural Understanding","created":"2024-07-15","cited_by_count":101},{"id":"2404.15238","title":"CultureBank: An Online Community-Driven Knowledge Base Towards Culturally Aware Language Technologies","created":"2024-04-23","cited_by_count":98},{"id":"2306.01943","title":"NLPositionality: Characterizing Design Biases of Datasets and Models","created":"2023-06-02","cited_by_count":94},{"id":"2309.04766","title":"SeaEval for Multilingual Foundation Models: From Cross-Lingual Alignment to Cultural Reasoning","created":"2023-09-09","cited_by_count":94},{"id":"2404.02431","title":"On the Multilingual Ability of Decoder-based Pre-trained Language Models: Finding and Controlling Language-Specific Neurons","created":"2024-04-03","cited_by_count":83},{"id":"2205.12404","title":"FLUTE: Figurative Language Understanding through Textual Explanations","created":"2022-05-24","cited_by_count":79},{"id":"2402.09369","title":"Massively Multi-Cultural Knowledge Acquisition & LM Benchmarking","created":"2024-02-14","cited_by_count":63},{"id":"2305.17008","title":"NormBank: A Knowledge Bank of Situational Social Norms","created":"2023-05-26","cited_by_count":60},{"id":"2407.02996","title":"Are Large Language Models Consistent over Value-laden Questions?","created":"2024-07-03","cited_by_count":58},{"id":"2406.16254","title":"Confidence Regulation Neurons in Language Models","created":"2024-06-24","cited_by_count":57},{"id":"2411.16508","title":"All Languages Matter: Evaluating LMMs on Culturally Diverse 100 Languages","created":"2024-11-25","cited_by_count":55},{"id":"2306.06826","title":"When Do Annotator Demographics Matter? Measuring the Influence of Annotator Demographics with the POPQUORN Dataset","created":"2023-06-12","cited_by_count":52},{"id":"2310.14491","title":"Towards a Mechanistic Interpretation of Multi-Step Reasoning Capabilities of Language Models","created":"2023-10-23","cited_by_count":50},{"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":"2305.16171","title":"Multi-lingual and Multi-cultural Figurative Language Understanding","created":"2023-05-25","cited_by_count":47},{"id":"2308.16705","title":"Exploring Cross-Cultural Differences in English Hate Speech Annotations: From Dataset Construction to Analysis","created":"2023-08-31","cited_by_count":45},{"id":"2012.06154","title":"ParsiNLU: A Suite of Language Understanding Challenges for Persian","created":"2020-12-11","cited_by_count":42},{"id":"2109.00087","title":"It's not Rocket Science : Interpreting Figurative Language in Narratives","created":"2021-08-31","cited_by_count":39},{"id":"2404.01854","title":"IndoCulture: Exploring Geographically-Influenced Cultural Commonsense Reasoning Across Eleven Indonesian Provinces","created":"2024-04-02","cited_by_count":39},{"id":"2310.18974","title":"EtiCor: Corpus for Analyzing LLMs for Etiquettes","created":"2023-10-29","cited_by_count":33},{"id":"2403.01031","title":"Peacock: A Family of Arabic Multimodal Large Language Models and Benchmarks","created":"2024-03-01","cited_by_count":32},{"id":"2404.06833","title":"Does Mapo Tofu Contain Coffee? Probing LLMs for Food-related Cultural Knowledge","created":"2024-04-10","cited_by_count":29},{"id":"2006.09479","title":"EPIE Dataset: A Corpus For Possible Idiomatic Expressions","created":"2020-06-16","cited_by_count":24},{"id":"2205.04022","title":"CoCoA-MT: A Dataset and Benchmark for Contrastive Controlled MT with Application to Formality","created":"2022-05-09","cited_by_count":24},{"id":"2310.14563","title":"NormDial: A Comparable Bilingual Synthetic Dialog Dataset for Modeling Social Norm Adherence and Violation","created":"2023-10-23","cited_by_count":24},{"id":"2406.11565","title":"Extrinsic Evaluation of Cultural Competence in Large Language Models","created":"2024-06-17","cited_by_count":24},{"id":"2305.14492","title":"Sociocultural Norm Similarities and Differences via Situational Alignment and Explainable Textual Entailment","created":"2023-05-23","cited_by_count":22},{"id":"2405.20089","title":"The Fine-Tuning Paradox: Boosting Translation Quality Without Sacrificing LLM Abilities","created":"2024-05-30","cited_by_count":22},{"id":"2310.12127","title":"A Tale of Pronouns: Interpretability Informs Gender Bias Mitigation for Fairer Instruction-Tuned Machine Translation","created":"2023-10-18","cited_by_count":19},{"id":"2305.18855","title":"STT4SG-350: A Speech Corpus for All Swiss German Dialect Regions","created":"2023-05-30","cited_by_count":18},{"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},{"id":"1802.08148","title":"LIDIOMS: A Multilingual Linked Idioms Data Set","created":"2018-02-22","cited_by_count":15},{"id":"2105.03280","title":"Potential Idiomatic Expression (PIE)-English: Corpus for Classes of Idioms","created":"2021-04-25","cited_by_count":15},{"id":"2109.02972","title":"Don't Go Far Off: An Empirical Study on Neural Poetry Translation","created":"2021-09-07","cited_by_count":15},{"id":"2402.11178","title":"RENOVI: A Benchmark Towards Remediating Norm Violations in Socio-Cultural Conversations","created":"2024-02-17","cited_by_count":14},{"id":"2406.15362","title":"Diverse Perspectives, Divergent Models: Cross-Cultural Evaluation of Depression Detection on Twitter","created":"2024-04-01","cited_by_count":12},{"id":"2305.16816","title":"Songs Across Borders: Singable and Controllable Neural Lyric Translation","created":"2023-05-26","cited_by_count":11},{"id":"2404.02403","title":"Benchmarking Large Language Models for Persian: A Preliminary Study Focusing on ChatGPT","created":"2024-04-03","cited_by_count":11},{"id":"2408.09819","title":"CMoralEval: A Moral Evaluation Benchmark for Chinese Large Language Models","created":"2024-08-19","cited_by_count":10},{"id":"2410.16461","title":"Comparative Study of Multilingual Idioms and Similes in Large Language Models","created":"2024-10-21","cited_by_count":10},{"id":"2310.09088","title":"Dialect Transfer for Swiss German Speech Translation","created":"2023-10-13","cited_by_count":7},{"id":"1909.00279","title":"Generating Classical Chinese Poems from Vernacular Chinese","created":"2019-08-31","cited_by_count":6},{"id":"2504.02403","title":"DaKultur: Evaluating the Cultural Awareness of Language Models for Danish with Native Speakers","created":"2025-04-03","cited_by_count":3},{"id":"2507.09701","title":"MCEval: A Dynamic Framework for Fair Multilingual Cultural Evaluation of LLMs","created":"2025-07-13","cited_by_count":3},{"id":"1807.08230","title":"German Dialect Identification Using Classifier Ensembles","created":"2018-07-22","cited_by_count":1}],"next_cursor":null}