% Key papers for Multilingual LLM data and culture (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages. @inproceedings{neurips2022_the_65074, title = {{The BigScience ROOTS Corpus: A 1.6TB Composite Multilingual Dataset}}, booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}, year = {2022}, url = {https://nips.cc/virtual/2022/poster/55667}, } @inproceedings{neurips2024_culturellm_74145, title = {{CultureLLM: Incorporating Cultural Differences into Large Language Models}}, booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}, year = {2024}, url = {https://neurips.cc/virtual/2024/poster/93396}, } @inproceedings{aaai2023_multispider_4212, title = {{MultiSpider: Towards Benchmarking Multilingual Text-to-SQL Semantic Parsing}}, booktitle = {AAAI Conference on Artificial Intelligence (AAAI)}, year = {2023}, url = {https://ojs.aaai.org/index.php/AAAI/article/view/26499}, } @inproceedings{aaai2025_language_9704, title = {{Language Ranker: A Metric for Quantifying LLM Performance Across High and Low-Resource Languages}}, booktitle = {AAAI Conference on Artificial Intelligence (AAAI)}, year = {2025}, url = {https://ojs.aaai.org/index.php/AAAI/article/view/35038}, } @inproceedings{neurips2022_multi_66485, title = {{Multi-LexSum: Real-world Summaries of Civil Rights Lawsuits at Multiple Granularities}}, booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}, year = {2022}, url = {https://nips.cc/virtual/2022/poster/55681}, } @inproceedings{neurips2023_post_66725, title = {{Post Hoc Explanations of Language Models Can Improve Language Models}}, booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}, year = {2023}, url = {https://nips.cc/virtual/2023/poster/72907}, } @inproceedings{aaai2022_from_2131, title = {{From Good to Best: Two-Stage Training for Cross-Lingual Machine Reading Comprehension}}, booktitle = {AAAI Conference on Artificial Intelligence (AAAI)}, year = {2022}, url = {https://aaai.org/papers/10501-from-good-to-best-two-stage-training-for-cross-lingual-machine-reading-comprehension/}, } @inproceedings{iclr2024_llm_35062, title = {{LLM Augmented LLMs: Expanding Capabilities through Composition}}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2024}, url = {https://iclr.cc/virtual/2024/poster/18011}, } @inproceedings{neurips2023_amazon_69799, title = {{Amazon-M2: A Multilingual Multi-locale Shopping Session Dataset for Recommendation and Text Generation}}, booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}, year = {2023}, url = {https://nips.cc/virtual/2023/poster/73435}, } @inproceedings{neurips2023_madlad_68511, title = {{MADLAD-400: A Multilingual And Document-Level Large Audited Dataset}}, booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}, year = {2023}, url = {https://nips.cc/virtual/2023/poster/73557}, } @inproceedings{aaai2025_mathspeech_9918, title = {{MathSpeech: Leveraging Small LMs for Accurate Conversion in Mathematical Speech-to-Formula}}, booktitle = {AAAI Conference on Artificial Intelligence (AAAI)}, year = {2025}, url = {https://ojs.aaai.org/index.php/AAAI/article/view/34595}, } @inproceedings{neurips2025_measuring_79178, title = {{Measuring what Matters: Construct Validity in Large Language Model Benchmarks}}, booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}, year = {2025}, url = {https://openreview.net/forum?id=mdA5lVvNcU}, } @inproceedings{aaai2024_consider_5354, title = {{CONSIDER: Commonalities and Specialties Driven Multilingual Code Retrieval Framework}}, booktitle = {AAAI Conference on Artificial Intelligence (AAAI)}, year = {2024}, url = {https://ojs.aaai.org/index.php/AAAI/article/view/28713}, } @inproceedings{aaai2025_distilling_8769, title = {{Distilling Structured Rationale from Large Language Models to Small Language Models for Abstractive Summarization}}, booktitle = {AAAI Conference on Artificial Intelligence (AAAI)}, year = {2025}, url = {https://ojs.aaai.org/index.php/AAAI/article/view/34727}, } @inproceedings{neurips2022_this_64297, title = {{This is the way: designing and compiling LEPISZCZE, a comprehensive NLP benchmark for Polish}}, booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}, year = {2022}, url = {https://nips.cc/virtual/2022/poster/55618}, } @inproceedings{neurips2024_how_73048, title = {{How do Large Language Models Handle Multilingualism?}}, booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}, year = {2024}, url = {https://neurips.cc/virtual/2024/poster/94375}, } @inproceedings{iclr2024_a_35464, title = {{A Benchmark for Learning to Translate a New Language from One Grammar Book}}, booktitle = {International Conference on Learning Representations (ICLR)}, year = {2024}, url = {https://iclr.cc/virtual/2024/poster/17609}, } @inproceedings{neurips2024_mindmerger_71965, title = {{MindMerger: Efficiently Boosting LLM Reasoning in non-English Languages}}, booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}, year = {2024}, url = {https://neurips.cc/virtual/2024/poster/95346}, } @inproceedings{neurips2024_end_72414, title = {{End-to-End Ontology Learning with Large Language Models}}, booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}, year = {2024}, url = {https://neurips.cc/virtual/2024/poster/94942}, } @inproceedings{aaai2025_adaptive_8031, title = {{Adaptive Few-shot Prompting for Machine Translation with Pre-trained Language Models}}, booktitle = {AAAI Conference on Artificial Intelligence (AAAI)}, year = {2025}, url = {https://ojs.aaai.org/index.php/AAAI/article/view/34712}, } @inproceedings{aaai2024_translate_7649, title = {{Translate Meanings, Not Just Words: IdiomKB’s Role in Optimizing Idiomatic Translation with Language Models}}, booktitle = {AAAI Conference on Artificial Intelligence (AAAI)}, year = {2024}, url = {https://ojs.aaai.org/index.php/AAAI/article/view/29817}, } @inproceedings{aaai2025_enhancing_8984, title = {{Enhancing Portuguese Variety Identification with Cross-Domain Approaches}}, booktitle = {AAAI Conference on Artificial Intelligence (AAAI)}, year = {2025}, url = {https://ojs.aaai.org/index.php/AAAI/article/view/34705}, } @inproceedings{aaai2025_multilingual_10062, title = {{Multilingual LLMs Inherently Reward In-Language Time-Sensitive Semantic Alignment for Low-Resource Languages}}, booktitle = {AAAI Conference on Artificial Intelligence (AAAI)}, year = {2025}, url = {https://ojs.aaai.org/index.php/AAAI/article/view/34515}, } @inproceedings{neurips2024_a_70236, title = {{A Synthetic Dataset for Personal Attribute Inference}}, booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}, year = {2024}, url = {https://neurips.cc/virtual/2024/poster/97872}, } @inproceedings{aaai2025_a_7879, title = {{A Compact Model for Mathematics Problem Representations Distilled from BERT}}, booktitle = {AAAI Conference on Artificial Intelligence (AAAI)}, year = {2025}, url = {https://ojs.aaai.org/index.php/AAAI/article/view/34669}, } @inproceedings{aaai2025_scholargec_10695, title = {{ScholarGEC: Enhancing Controllability of Large Language Model for Chinese Academic Grammatical Error Correction}}, booktitle = {AAAI Conference on Artificial Intelligence (AAAI)}, year = {2025}, url = {https://ojs.aaai.org/index.php/AAAI/article/view/34611}, } @inproceedings{neurips2024_glotcc_72835, title = {{GlotCC: An Open Broad-Coverage CommonCrawl Corpus and Pipeline for Minority Languages}}, booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}, year = {2024}, url = {https://neurips.cc/virtual/2024/poster/97624}, } @inproceedings{neurips2025_enhancing_79962, title = {{Enhancing Multilingual LLM Pretraining with Model-Based Data Selection}}, booktitle = {Advances in Neural Information Processing Systems (NeurIPS)}, year = {2025}, url = {https://openreview.net/forum?id=ufhH8YXxOB}, }