{"total":53,"rows":[{"id":"2305.03514","title":"Can Large Language Models Transform Computational Social Science?","created":"2023-04-12","cited_by_count":250,"area":null},{"id":"2402.15018","title":"Unintended Impacts of LLM Alignment on Global Representation","created":"2024-02-22","cited_by_count":66,"area":"alignment"},{"id":"2406.08818","title":"Linguistic Bias in ChatGPT: Language Models Reinforce Dialect Discrimination","created":"2024-06-13","cited_by_count":56,"area":null},{"id":"2403.11009","title":"DIALECTBENCH: A NLP Benchmark for Dialects, Varieties, and Closely-Related Languages","created":"2024-03-16","cited_by_count":50,"area":null},{"id":"2401.05632","title":"Natural Language Processing for Dialects of a Language: A Survey","created":"2024-01-11","cited_by_count":40,"area":null},{"id":"2502.12057","title":"Culture is Not Trivia: Sociocultural Theory for Cultural NLP","created":"2025-02-17","cited_by_count":40,"area":null},{"id":"2406.03930","title":"Culturally Aware and Adapted NLP: A Taxonomy and a Survey of the State of the Art","created":"2024-06-06","cited_by_count":26,"area":null},{"id":"2311.08391","title":"A Material Lens on Coloniality in NLP","created":"2023-11-14","cited_by_count":21,"area":null},{"id":"2308.07120","title":"Position: Key Claims in LLM Research Have a Long Tail of Footnotes","created":"2023-08-14","cited_by_count":20,"area":null},{"id":"2304.09805","title":"A Survey of Corpora for Germanic Low-Resource Languages and Dialects","created":"2023-04-19","cited_by_count":16,"area":null},{"id":"2305.16651","title":"TADA: Task-Agnostic Dialect Adapters for English","created":"2023-05-26","cited_by_count":15,"area":null},{"id":"2310.14607","title":"Confronting LLMs with Traditional ML: Rethinking the Fairness of Large Language Models in Tabular Classifications","created":"2023-10-23","cited_by_count":15,"area":"lr"},{"id":"2405.05688","title":"Evaluating Dialect Robustness of Language Models via Conversation Understanding","created":"2024-05-09","cited_by_count":14,"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":"2502.15343","title":"Tokenization is Sensitive to Language Variation","created":"2025-02-21","cited_by_count":13,"area":null},{"id":"2411.10954","title":"Dialectal Toxicity Detection: Evaluating LLM-as-a-Judge Consistency Across Language Varieties","created":"2024-11-17","cited_by_count":12,"area":null},{"id":"2406.19564","title":"Voices Unheard: NLP Resources and Models for Yor\\`ub\\'a Regional Dialects","created":"2024-06-27","cited_by_count":11,"area":null},{"id":"2504.08231","title":"Out of Style: RAG's Fragility to Linguistic Variation","created":"2025-04-11","cited_by_count":11,"area":"rag"},{"id":"2409.00358","title":"Predicting the Target Word of Game-playing Conversations using a Low-Rank Dialect Adapter for Decoder Models","created":"2024-08-31","cited_by_count":6,"area":null},{"id":"2403.01983","title":"Language and Speech Technology for Central Kurdish Varieties","created":"2024-03-04","cited_by_count":5,"area":null},{"id":"2406.17385","title":"Native Design Bias: Studying the Impact of English Nativeness on Language Model Performance","created":"2024-06-25","cited_by_count":5,"area":null},{"id":"2412.04726","title":"BESSTIE: A Benchmark for Sentiment and Sarcasm Classification for Varieties of English","created":"2024-12-06","cited_by_count":5,"area":null},{"id":"2510.00962","title":"Analyzing Dialectical Biases in LLMs for Knowledge and Reasoning Benchmarks","created":"2025-10-01","cited_by_count":5,"area":"lr"},{"id":"2402.02078","title":"Exploring the Robustness of Task-oriented Dialogue Systems for Colloquial German Varieties","created":"2024-02-03","cited_by_count":4,"area":null},{"id":"2505.20875","title":"Trans-EnV: A Framework for Evaluating the Linguistic Robustness of LLMs Against English Varieties","created":"2025-05-27","cited_by_count":4,"area":null},{"id":"2503.03417","title":"When Claims Evolve: Evaluating and Enhancing the Robustness of Embedding Models Against Misinformation Edits","created":"2025-03-05","cited_by_count":3,"area":null},{"id":"2510.14949","title":"DialectGen: Benchmarking and Improving Dialect Robustness in Multimodal Generation","created":"2025-10-16","cited_by_count":3,"area":null},{"id":"2604.04204","title":"How Does \"English (US)\" Become the Default? Triangulating Structural Bias Towards American English Across the LLM Pipeline","created":"2026-04-05","cited_by_count":3,"area":null},{"id":"2502.06004","title":"Analysis of LLM as a grammatical feature tagger for African American English","created":"2025-02-09","cited_by_count":2,"area":null},{"id":"2506.02998","title":"A Multi-Agent Framework for Mitigating Dialect Biases in Privacy Policy Question-Answering Systems","created":"2025-06-03","cited_by_count":2,"area":"agents"},{"id":"2510.27672","title":"Culture Cartography: Mapping the Landscape of Cultural Knowledge","created":"2025-10-31","cited_by_count":2,"area":null},{"id":"2410.14589","title":"Dialetto, ma Quanto Dialetto? Transcribing and Evaluating Dialects on a Continuum","created":"2024-10-18","cited_by_count":1,"area":null},{"id":"2501.03441","title":"Finding A Voice: Exploring the Potential of African American Dialect and Voice Generation for Chatbots","created":"2025-01-07","cited_by_count":1,"area":null},{"id":"2501.16581","title":"DialUp! Modeling the Language Continuum by Adapting Models to Dialects and Dialects to Models","created":"2025-01-27","cited_by_count":1,"area":null},{"id":"2503.12858","title":"Harnessing Test-time Adaptation for NLU tasks Involving Dialects of English","created":"2025-03-17","cited_by_count":1,"area":null},{"id":"2601.16623","title":"MultiLexNorm++: A Unified Benchmark and a Generative Model for Lexical Normalization for Asian Languages","created":"2026-01-23","cited_by_count":1,"area":null},{"id":"2604.05318","title":"DIA-HARM: Dialectal Disparities in Harmful Content Detection Across 50 English Dialects","created":"2026-04-07","cited_by_count":1,"area":"safety"},{"id":"2607.07669","title":"DiaLLM: An Investigation into the Robustness-Generation Gap in English Dialect Adaptation","created":"2026-07-08","cited_by_count":1,"area":null},{"id":"2609.17542","title":"Register Bias in Complexity-Based Large Language Model Routing","created":"2026-07-14","cited_by_count":1,"area":null},{"id":"2505.15095","title":"Nek Minit: Harnessing Pragmatic Metacognitive Prompting for Explainable Sarcasm Detection of Australian and Indian English","created":"2025-05-21","cited_by_count":0,"area":null},{"id":"2511.23041","title":"Social Perceptions of English Spelling Variation on Twitter: A Comparative Analysis of Human and LLM Responses","created":"2025-11-28","cited_by_count":0,"area":null},{"id":"2601.22888","title":"DialectLLM: A Dialect-Aware Dialog[ue] Generation Framework Beyond Standard American English","created":"2026-01-30","cited_by_count":0,"area":"mechinterp"},{"id":"2603.25189","title":"A Catalog of Basque Dialectal Resources: Online Collections and Standard-to-Dialectal Adaptations","created":"2026-03-26","cited_by_count":0,"area":null},{"id":"2604.23824","title":"Resource-Lean Lexicon Induction for German Dialects","created":"2026-04-26","cited_by_count":0,"area":null},{"id":"2604.25456","title":"An Investigation of Linguistic Biases in LLM-Based Recommendations","created":"2026-04-28","cited_by_count":0,"area":null},{"id":"2607.06845","title":"LLMs Silently Correct African American English: Auditing and Mitigating Dialect Bias via Activation Steering","created":"2026-07-07","cited_by_count":0,"area":"mechinterp"},{"id":"2608.22490","title":"Who Pays More for Safety? Measuring the Disparate Cost of Safety Alignment across Languages","created":"2026-08-23","cited_by_count":0,"area":"alignment"},{"id":"2608.24952","title":"The Dialect Tax: Dialectal Biases Persist throughout the Language Modeling Pipeline","created":"2026-08-24","cited_by_count":0,"area":"mechinterp"},{"id":"2608.29589","title":"Not Safe for All: Auditing the Dialect Penalty in Text-to-Image Safety Pipelines","created":"2026-08-30","cited_by_count":0,"area":"safety"},{"id":"2609.18156","title":"TeochewBench: A Human-Reviewed Benchmark for Teochew Hanzi Translation","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.25298","title":"FineWeb-CLaR: Culture, Language, and Region Annotations for Benchmark-Aligned Corpus Auditing","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2610.00164","title":"Metric-Construction Coupling Inflates Measured Synthetic Dialect Recovery","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2610.02627","title":"Lost in the Request: How Communication Variation Disrupts Retrieval and Action in Email Agents","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}