spb/wpai0002_uqo

1{"bibkey": "liang2025quantifying", "title": "Quantifying large language model usage in scientific papers", "first_author": "Weixin Liang", "year": 2025, "venue": "Nature Human Behaviour", "doi": "10.1038/s41562-025-02273-8", "arxiv_id": null, "verified_via": "https://api.openalex.org/works?filter=doi:10.1038/s41562-025-02273-8", "verified_at": "2026-11-09T17:12:41Z", "theme": "LLM influence on scientific writing"}2{"bibkey": "kobak2025delving", "title": "Delving into LLM-assisted writing in biomedical publications through excess vocabulary", "first_author": "Dmitry Kobak", "year": 2025, "venue": "Science Advances", "doi": "10.1126/sciadv.adt3813", "arxiv_id": null, "verified_via": "https://api.openalex.org/works?filter=doi:10.1126/sciadv.adt3813", "verified_at": "2026-11-09T17:12:41Z", "theme": "LLM influence on scientific writing"}3{"bibkey": "geng2024chatgpt", "title": "Is ChatGPT Transforming Academics' Writing Style?", "first_author": "Mingmeng Geng", "year": 2024, "venue": "arXiv preprint arXiv:2404.08627", "doi": null, "arxiv_id": "2404.08627", "verified_via": "http://export.arxiv.org/api/query?id_list=2404.08627", "verified_at": "2026-11-09T17:09:49Z", "theme": "LLM influence on scientific writing"}4{"bibkey": "geng2025humanllm", "title": "Human-LLM Coevolution: Evidence from Academic Writing", "first_author": "Mingmeng Geng", "year": 2025, "venue": "arXiv preprint arXiv:2502.09606", "doi": null, "arxiv_id": "2502.09606", "verified_via": "http://export.arxiv.org/api/query?id_list=2502.09606", "verified_at": "2026-11-09T17:09:49Z", "theme": "LLM influence on scientific writing"}5{"bibkey": "gray2024chatgpt", "title": "ChatGPT \"contamination\": estimating the prevalence of LLMs in the scholarly literature", "first_author": "Andrew Gray", "year": 2024, "venue": "arXiv preprint arXiv:2403.16887", "doi": null, "arxiv_id": "2403.16887", "verified_via": "http://export.arxiv.org/api/query?id_list=2403.16887", "verified_at": "2026-11-09T17:09:49Z", "theme": "LLM influence on scientific writing"}6{"bibkey": "liang2024monitoring", "title": "Monitoring AI-Modified Content at Scale: A Case Study on the Impact of ChatGPT on AI Conference Peer Reviews", "first_author": "Weixin Liang", "year": 2024, "venue": "arXiv preprint arXiv:2403.07183", "doi": null, "arxiv_id": "2403.07183", "verified_via": "http://export.arxiv.org/api/query?id_list=2403.07183", "verified_at": "2026-11-09T17:09:49Z", "theme": "LLM influence on scientific writing"}7{"bibkey": "bao2025examining", "title": "Examining Linguistic Shifts in Academic Writing Before and After the Launch of ChatGPT: A Study on Preprint Papers", "first_author": "Tong Bao", "year": 2025, "venue": "Scientometrics,2025", "doi": null, "arxiv_id": "2505.12218", "verified_via": "http://export.arxiv.org/api/query?id_list=2505.12218", "verified_at": "2026-11-09T17:09:49Z", "theme": "LLM influence on scientific writing"}8{"bibkey": "juzek2024delve", "title": "Why Does ChatGPT \"Delve\" So Much? Exploring the Sources of Lexical Overrepresentation in Large Language Models", "first_author": "Tom S. Juzek", "year": 2024, "venue": "arXiv preprint arXiv:2412.11385", "doi": null, "arxiv_id": "2412.11385", "verified_via": "http://export.arxiv.org/api/query?id_list=2412.11385", "verified_at": "2026-11-09T17:09:56Z", "theme": "LLM influence on scientific writing"}9{"bibkey": "reinhart2025llms", "title": "Do LLMs write like humans? Variation in grammatical and rhetorical styles", "first_author": "Alex Reinhart", "year": 2025, "venue": "Proceedings of the National Academy of Sciences", "doi": "10.1073/pnas.2422455122", "arxiv_id": null, "verified_via": "https://api.openalex.org/works?filter=doi:10.1073/pnas.2422455122", "verified_at": "2026-11-09T17:12:41Z", "theme": "LLM influence on scientific writing"}10{"bibkey": "munozortiz2023contrasting", "title": "Contrasting Linguistic Patterns in Human and LLM-Generated News Text", "first_author": "Alberto Muñoz-Ortiz", "year": 2023, "venue": "Artificial Intelligence Review 57, 265 (2024)", "doi": "10.1007/s10462-024-10903-2", "arxiv_id": "2308.09067", "verified_via": "http://export.arxiv.org/api/query?id_list=2308.09067", "verified_at": "2026-11-09T17:09:56Z", "theme": "LLM influence on scientific writing"}11{"bibkey": "padmakumar2023writing", "title": "Does Writing with Language Models Reduce Content Diversity?", "first_author": "Vishakh Padmakumar", "year": 2023, "venue": "arXiv preprint arXiv:2309.05196", "doi": null, "arxiv_id": "2309.05196", "verified_via": "http://export.arxiv.org/api/query?id_list=2309.05196", "verified_at": "2026-11-09T17:09:49Z", "theme": "LLM influence on scientific writing"}12{"bibkey": "jang2026scizoom", "title": "SciZoom: A Large-scale Benchmark for Hierarchical Scientific Summarization across the LLM Era", "first_author": "Han Jang", "year": 2026, "venue": "arXiv preprint arXiv:2603.16131", "doi": null, "arxiv_id": "2603.16131", "verified_via": "http://export.arxiv.org/api/query?id_list=2603.16131", "verified_at": "2026-11-09T17:12:04Z", "theme": "LLM influence on scientific writing"}13{"bibkey": "kosch2026chi", "title": "How Did Writing Change At CHI? Analyzing 44 Years of CHI Writing Before and After the Introduction of Large Language Models", "first_author": "Thomas Kosch", "year": 2026, "venue": "arXiv preprint arXiv:2609.23090", "doi": null, "arxiv_id": "2609.23090", "verified_via": "http://export.arxiv.org/api/query?id_list=2609.23090", "verified_at": "2026-11-09T17:12:04Z", "theme": "LLM influence on scientific writing"}14{"bibkey": "gao2023comparing", "title": "Comparing scientific abstracts generated by ChatGPT to real abstracts with detectors and blinded human reviewers", "first_author": "Catherine A. Gao", "year": 2023, "venue": "npj Digital Medicine", "doi": "10.1038/s41746-023-00819-6", "arxiv_id": null, "verified_via": "https://api.openalex.org/works?filter=doi:10.1038/s41746-023-00819-6", "verified_at": "2026-11-09T17:12:41Z", "theme": "LLM influence on scientific writing"}15{"bibkey": "krishna2023paraphrasing", "title": "Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense", "first_author": "Kalpesh Krishna", "year": 2023, "venue": "arXiv preprint arXiv:2303.13408", "doi": null, "arxiv_id": "2303.13408", "verified_via": "http://export.arxiv.org/api/query?id_list=2303.13408", "verified_at": "2026-11-09T17:09:49Z", "theme": "AI-text detection and paraphrase attacks"}16{"bibkey": "sadasivan2023reliably", "title": "Can AI-Generated Text be Reliably Detected?", "first_author": "Vinu Sankar Sadasivan", "year": 2023, "venue": "arXiv preprint arXiv:2303.11156", "doi": null, "arxiv_id": "2303.11156", "verified_via": "http://export.arxiv.org/api/query?id_list=2303.11156", "verified_at": "2026-11-09T17:09:49Z", "theme": "AI-text detection and paraphrase attacks"}17{"bibkey": "mitchell2023detectgpt", "title": "DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature", "first_author": "Eric Mitchell", "year": 2023, "venue": "arXiv preprint arXiv:2301.11305", "doi": null, "arxiv_id": "2301.11305", "verified_via": "http://export.arxiv.org/api/query?id_list=2301.11305", "verified_at": "2026-11-09T17:09:49Z", "theme": "AI-text detection and paraphrase attacks"}18{"bibkey": "bao2023fastdetectgpt", "title": "Fast-DetectGPT: Efficient Zero-Shot Detection of Machine-Generated Text via Conditional Probability Curvature", "first_author": "Guangsheng Bao", "year": 2023, "venue": "arXiv preprint arXiv:2310.05130", "doi": null, "arxiv_id": "2310.05130", "verified_via": "http://export.arxiv.org/api/query?id_list=2310.05130", "verified_at": "2026-11-09T17:09:49Z", "theme": "AI-text detection and paraphrase attacks"}19{"bibkey": "hans2024binoculars", "title": "Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Text", "first_author": "Abhimanyu Hans", "year": 2024, "venue": "arXiv preprint arXiv:2401.12070", "doi": null, "arxiv_id": "2401.12070", "verified_via": "http://export.arxiv.org/api/query?id_list=2401.12070", "verified_at": "2026-11-09T17:09:49Z", "theme": "AI-text detection and paraphrase attacks"}20{"bibkey": "liang2023detectors", "title": "GPT detectors are biased against non-native English writers", "first_author": "Weixin Liang", "year": 2023, "venue": "arXiv preprint arXiv:2304.02819", "doi": null, "arxiv_id": "2304.02819", "verified_via": "http://export.arxiv.org/api/query?id_list=2304.02819", "verified_at": "2026-11-09T17:09:49Z", "theme": "AI-text detection and paraphrase attacks"}21{"bibkey": "kirchenbauer2023watermark", "title": "A Watermark for Large Language Models", "first_author": "John Kirchenbauer", "year": 2023, "venue": "arXiv preprint arXiv:2301.10226", "doi": null, "arxiv_id": "2301.10226", "verified_via": "http://export.arxiv.org/api/query?id_list=2301.10226", "verified_at": "2026-11-09T17:09:49Z", "theme": "AI-text detection and paraphrase attacks"}22{"bibkey": "dugan2024raid", "title": "RAID: A Shared Benchmark for Robust Evaluation of Machine-Generated Text Detectors", "first_author": "Liam Dugan", "year": 2024, "venue": "arXiv preprint arXiv:2405.07940", "doi": null, "arxiv_id": "2405.07940", "verified_via": "http://export.arxiv.org/api/query?id_list=2405.07940", "verified_at": "2026-11-09T17:09:52Z", "theme": "AI-text detection and paraphrase attacks"}23{"bibkey": "saha2025polished", "title": "Almost AI, Almost Human: The Challenge of Detecting AI-Polished Writing", "first_author": "Shoumik Saha", "year": 2025, "venue": "arXiv preprint arXiv:2502.15666", "doi": null, "arxiv_id": "2502.15666", "verified_via": "http://export.arxiv.org/api/query?id_list=2502.15666", "verified_at": "2026-11-09T17:09:49Z", "theme": "AI-text detection and paraphrase attacks"}24{"bibkey": "chen2024imitate", "title": "Imitate Before Detect: Aligning Machine Stylistic Preference for Machine-Revised Text Detection", "first_author": "Jiaqi Chen", "year": 2024, "venue": "arXiv preprint arXiv:2412.10432", "doi": null, "arxiv_id": "2412.10432", "verified_via": "http://export.arxiv.org/api/query?id_list=2412.10432", "verified_at": "2026-11-09T17:12:04Z", "theme": "AI-text detection and paraphrase attacks"}25{"bibkey": "artemova2024beemo", "title": "Beemo: Benchmark of Expert-edited Machine-generated Outputs", "first_author": "Ekaterina Artemova", "year": 2024, "venue": "arXiv preprint arXiv:2411.04032", "doi": null, "arxiv_id": "2411.04032", "verified_via": "http://export.arxiv.org/api/query?id_list=2411.04032", "verified_at": "2026-11-09T17:12:04Z", "theme": "AI-text detection and paraphrase attacks"}26{"bibkey": "zheng2025thbench", "title": "TH-Bench: Evaluating Evading Attacks via Humanizing AI Text on Machine-Generated Text Detectors", "first_author": "Jingyi Zheng", "year": 2025, "venue": "arXiv preprint arXiv:2503.08708", "doi": null, "arxiv_id": "2503.08708", "verified_via": "http://export.arxiv.org/api/query?id_list=2503.08708", "verified_at": "2026-11-09T17:09:49Z", "theme": "AI-text detection and paraphrase attacks"}27{"bibkey": "stamatatos2008survey", "title": "A survey of modern authorship attribution methods", "first_author": "Efstathios Stamatatos", "year": 2008, "venue": "Journal of the American Society for Information Science and Technology", "doi": "10.1002/asi.21001", "arxiv_id": null, "verified_via": "https://api.openalex.org/works?filter=doi:10.1002/asi.21001", "verified_at": "2026-11-09T17:12:41Z", "theme": "Stylometry and authorship"}28{"bibkey": "juola2008authorship", "title": "Authorship Attribution", "first_author": "Patrick Juola", "year": 2008, "venue": "Foundations and Trends® in Information Retrieval", "doi": "10.1561/1500000005", "arxiv_id": null, "verified_via": "https://api.openalex.org/works?filter=doi:10.1561/1500000005", "verified_at": "2026-11-09T17:12:41Z", "theme": "Stylometry and authorship"}29{"bibkey": "koppel2008computational", "title": "Computational methods in authorship attribution", "first_author": "Moshe Koppel", "year": 2008, "venue": "Journal of the American Society for Information Science and Technology", "doi": "10.1002/asi.20961", "arxiv_id": null, "verified_via": "https://api.openalex.org/works?filter=doi:10.1002/asi.20961", "verified_at": "2026-11-09T17:12:41Z", "theme": "Stylometry and authorship"}30{"bibkey": "burrows2002delta", "title": "'Delta': a Measure of Stylistic Difference and a Guide to Likely Authorship", "first_author": "J. F. Burrows", "year": 2002, "venue": "Literary and Linguistic Computing", "doi": "10.1093/llc/17.3.267", "arxiv_id": null, "verified_via": "https://api.openalex.org/works?filter=doi:10.1093/llc/17.3.267", "verified_at": "2026-11-09T17:12:41Z", "theme": "Stylometry and authorship"}31{"bibkey": "riverasoto2021luar", "title": "Learning Universal Authorship Representations", "first_author": "Rafael Rivera Soto", "year": 2021, "venue": "Conference on Empirical Methods in Natural Language Processing (EMNLP)", "doi": "10.18653/v1/2021.emnlp-main.70", "arxiv_id": null, "verified_via": "https://api.openalex.org/works?filter=doi:10.18653/v1/2021.emnlp-main.70", "verified_at": "2026-11-09T17:12:41Z", "theme": "Stylometry and authorship"}32{"bibkey": "wegmann2022same", "title": "Same Author or Just Same Topic? Towards Content-Independent Style Representations", "first_author": "Anna Wegmann", "year": 2022, "venue": "arXiv preprint arXiv:2204.04907", "doi": null, "arxiv_id": "2204.04907", "verified_via": "http://export.arxiv.org/api/query?id_list=2204.04907", "verified_at": "2026-11-09T17:09:49Z", "theme": "Stylometry and authorship"}33{"bibkey": "fisher2024styleremix", "title": "StyleRemix: Interpretable Authorship Obfuscation via Distillation and Perturbation of Style Elements", "first_author": "Jillian Fisher", "year": 2024, "venue": "arXiv preprint arXiv:2408.15666", "doi": null, "arxiv_id": "2408.15666", "verified_via": "http://export.arxiv.org/api/query?id_list=2408.15666", "verified_at": "2026-11-09T17:09:49Z", "theme": "Stylometry and authorship"}34{"bibkey": "shen2017style", "title": "Style Transfer from Non-Parallel Text by Cross-Alignment", "first_author": "Tianxiao Shen", "year": 2017, "venue": "arXiv preprint arXiv:1705.09655", "doi": null, "arxiv_id": "1705.09655", "verified_via": "http://export.arxiv.org/api/query?id_list=1705.09655", "verified_at": "2026-11-09T17:09:49Z", "theme": "Style transfer, paraphrase and inversion"}35{"bibkey": "fu2017style", "title": "Style Transfer in Text: Exploration and Evaluation", "first_author": "Zhenxin Fu", "year": 2017, "venue": "arXiv preprint arXiv:1711.06861", "doi": null, "arxiv_id": "1711.06861", "verified_via": "http://export.arxiv.org/api/query?id_list=1711.06861", "verified_at": "2026-11-09T17:09:49Z", "theme": "Style transfer, paraphrase and inversion"}36{"bibkey": "john2018disentangled", "title": "Disentangled Representation Learning for Non-Parallel Text Style Transfer", "first_author": "Vineet John", "year": 2018, "venue": "arXiv preprint arXiv:1808.04339", "doi": null, "arxiv_id": "1808.04339", "verified_via": "http://export.arxiv.org/api/query?id_list=1808.04339", "verified_at": "2026-11-09T17:09:49Z", "theme": "Style transfer, paraphrase and inversion"}37{"bibkey": "krishna2020reformulating", "title": "Reformulating Unsupervised Style Transfer as Paraphrase Generation", "first_author": "Kalpesh Krishna", "year": 2020, "venue": "arXiv preprint arXiv:2010.05700", "doi": null, "arxiv_id": "2010.05700", "verified_via": "http://export.arxiv.org/api/query?id_list=2010.05700", "verified_at": "2026-11-09T17:09:49Z", "theme": "Style transfer, paraphrase and inversion"}38{"bibkey": "riley2020textsettr", "title": "TextSETTR: Few-Shot Text Style Extraction and Tunable Targeted Restyling", "first_author": "Parker Riley", "year": 2020, "venue": "arXiv preprint arXiv:2010.03802", "doi": null, "arxiv_id": "2010.03802", "verified_via": "http://export.arxiv.org/api/query?id_list=2010.03802", "verified_at": "2026-11-09T17:09:49Z", "theme": "Style transfer, paraphrase and inversion"}39{"bibkey": "patel2022lowresource", "title": "Low-Resource Authorship Style Transfer: Can Non-Famous Authors Be Imitated?", "first_author": "Ajay Patel", "year": 2022, "venue": "arXiv preprint arXiv:2212.08986", "doi": null, "arxiv_id": "2212.08986", "verified_via": "http://export.arxiv.org/api/query?id_list=2212.08986", "verified_at": "2026-11-09T17:09:49Z", "theme": "Style transfer, paraphrase and inversion"}40{"bibkey": "mir2019evaluating", "title": "Evaluating Style Transfer for Text", "first_author": "Remi Mir", "year": 2019, "venue": "arXiv preprint arXiv:1904.02295", "doi": null, "arxiv_id": "1904.02295", "verified_via": "http://export.arxiv.org/api/query?id_list=1904.02295", "verified_at": "2026-11-09T17:09:49Z", "theme": "Style transfer, paraphrase and inversion"}41{"bibkey": "jin2020survey", "title": "Deep Learning for Text Style Transfer: A Survey", "first_author": "Di Jin", "year": 2020, "venue": "arXiv preprint arXiv:2011.00416", "doi": null, "arxiv_id": "2011.00416", "verified_via": "http://export.arxiv.org/api/query?id_list=2011.00416", "verified_at": "2026-11-09T17:09:49Z", "theme": "Style transfer, paraphrase and inversion"}42{"bibkey": "rao2018gyafc", "title": "Dear Sir or Madam, May I introduce the GYAFC Dataset: Corpus, Benchmarks and Metrics for Formality Style Transfer", "first_author": "Sudha Rao", "year": 2018, "venue": "arXiv preprint arXiv:1803.06535", "doi": null, "arxiv_id": "1803.06535", "verified_via": "http://export.arxiv.org/api/query?id_list=1803.06535", "verified_at": "2026-11-09T17:09:52Z", "theme": "Style transfer, paraphrase and inversion"}43{"bibkey": "riverasoto2024paraphrase", "title": "Mitigating Paraphrase Attacks on Machine-Text Detectors via Paraphrase Inversion", "first_author": "Rafael Rivera Soto", "year": 2024, "venue": "arXiv preprint arXiv:2410.21637", "doi": null, "arxiv_id": "2410.21637", "verified_via": "http://export.arxiv.org/api/query?id_list=2410.21637", "verified_at": "2026-11-09T17:09:49Z", "theme": "Style transfer, paraphrase and inversion"}44{"bibkey": "riverasoto2026unsupervised", "title": "Unsupervised Style Representation Learning for AI-Text Detection via Paraphrase Inversion", "first_author": "Rafael Rivera Soto", "year": 2026, "venue": "arXiv preprint arXiv:2606.10099", "doi": null, "arxiv_id": "2606.10099", "verified_via": "http://export.arxiv.org/api/query?id_list=2606.10099", "verified_at": "2026-11-09T17:09:49Z", "theme": "Style transfer, paraphrase and inversion"}45{"bibkey": "morris2023lminversion", "title": "Language Model Inversion", "first_author": "John X. Morris", "year": 2023, "venue": "arXiv preprint arXiv:2311.13647", "doi": null, "arxiv_id": "2311.13647", "verified_via": "http://export.arxiv.org/api/query?id_list=2311.13647", "verified_at": "2026-11-09T17:09:49Z", "theme": "Style transfer, paraphrase and inversion"}46{"bibkey": "morris2023embeddings", "title": "Text Embeddings Reveal (Almost) As Much As Text", "first_author": "John X. Morris", "year": 2023, "venue": "arXiv preprint arXiv:2310.06816", "doi": null, "arxiv_id": "2310.06816", "verified_via": "http://export.arxiv.org/api/query?id_list=2310.06816", "verified_at": "2026-11-09T17:09:49Z", "theme": "Style transfer, paraphrase and inversion"}47{"bibkey": "ganin2014unsupervised", "title": "Unsupervised Domain Adaptation by Backpropagation", "first_author": "Yaroslav Ganin", "year": 2014, "venue": "arXiv preprint arXiv:1409.7495", "doi": null, "arxiv_id": "1409.7495", "verified_via": "http://export.arxiv.org/api/query?id_list=1409.7495", "verified_at": "2026-11-09T17:09:49Z", "theme": "Disentanglement and identifiability"}48{"bibkey": "bousmalis2016domain", "title": "Domain Separation Networks", "first_author": "Konstantinos Bousmalis", "year": 2016, "venue": "arXiv preprint arXiv:1608.06019", "doi": null, "arxiv_id": "1608.06019", "verified_via": "http://export.arxiv.org/api/query?id_list=1608.06019", "verified_at": "2026-11-09T17:09:49Z", "theme": "Disentanglement and identifiability"}49{"bibkey": "hu2017controlled", "title": "Toward Controlled Generation of Text", "first_author": "Zhiting Hu", "year": 2017, "venue": "arXiv preprint arXiv:1703.00955", "doi": null, "arxiv_id": "1703.00955", "verified_via": "http://export.arxiv.org/api/query?id_list=1703.00955", "verified_at": "2026-11-09T17:09:52Z", "theme": "Disentanglement and identifiability"}50{"bibkey": "chen2020simclr", "title": "A Simple Framework for Contrastive Learning of Visual Representations", "first_author": "Ting Chen", "year": 2020, "venue": "arXiv preprint arXiv:2002.05709", "doi": null, "arxiv_id": "2002.05709", "verified_via": "http://export.arxiv.org/api/query?id_list=2002.05709", "verified_at": "2026-11-09T17:09:52Z", "theme": "Disentanglement and identifiability"}51{"bibkey": "oord2018cpc", "title": "Representation Learning with Contrastive Predictive Coding", "first_author": "Aaron van den Oord", "year": 2018, "venue": "arXiv preprint arXiv:1807.03748", "doi": null, "arxiv_id": "1807.03748", "verified_via": "http://export.arxiv.org/api/query?id_list=1807.03748", "verified_at": "2026-11-09T17:09:52Z", "theme": "Disentanglement and identifiability"}52{"bibkey": "elazar2018adversarial", "title": "Adversarial Removal of Demographic Attributes from Text Data", "first_author": "Yanai Elazar", "year": 2018, "venue": "arXiv preprint arXiv:1808.06640", "doi": null, "arxiv_id": "1808.06640", "verified_via": "http://export.arxiv.org/api/query?id_list=1808.06640", "verified_at": "2026-11-09T17:09:52Z", "theme": "Disentanglement and identifiability"}53{"bibkey": "locatello2018challenging", "title": "Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations", "first_author": "Francesco Locatello", "year": 2018, "venue": "Proceedings of the 36th International Conference on Machine Learning (ICML 2019)", "doi": null, "arxiv_id": "1811.12359", "verified_via": "http://export.arxiv.org/api/query?id_list=1811.12359", "verified_at": "2026-11-09T17:09:52Z", "theme": "Disentanglement and identifiability"}54{"bibkey": "hyvarinen1999nonlinear", "title": "Nonlinear independent component analysis: Existence and uniqueness results", "first_author": "Aapo Hyvärinen", "year": 1999, "venue": "Neural Networks", "doi": "10.1016/s0893-6080(98)00140-3", "arxiv_id": null, "verified_via": "https://api.openalex.org/works?filter=doi:10.1016/s0893-6080(98)00140-3", "verified_at": "2026-11-09T17:12:41Z", "theme": "Disentanglement and identifiability"}55{"bibkey": "vonkugelgen2021selfsupervised", "title": "Self-Supervised Learning with Data Augmentations Provably Isolates Content from Style", "first_author": "Julius von Kügelgen", "year": 2021, "venue": "arXiv preprint arXiv:2106.04619", "doi": null, "arxiv_id": "2106.04619", "verified_via": "http://export.arxiv.org/api/query?id_list=2106.04619", "verified_at": "2026-11-09T17:09:52Z", "theme": "Disentanglement and identifiability"}56{"bibkey": "zimmermann2021contrastive", "title": "Contrastive Learning Inverts the Data Generating Process", "first_author": "Roland S. Zimmermann", "year": 2021, "venue": "arXiv preprint arXiv:2102.08850", "doi": null, "arxiv_id": "2102.08850", "verified_via": "http://export.arxiv.org/api/query?id_list=2102.08850", "verified_at": "2026-11-09T17:09:52Z", "theme": "Disentanglement and identifiability"}57{"bibkey": "vaswani2017attention", "title": "Attention Is All You Need", "first_author": "Ashish Vaswani", "year": 2017, "venue": "arXiv preprint arXiv:1706.03762", "doi": null, "arxiv_id": "1706.03762", "verified_via": "http://export.arxiv.org/api/query?id_list=1706.03762", "verified_at": "2026-11-09T17:09:52Z", "theme": "Sequence-to-sequence architectures"}58{"bibkey": "raffel2019t5", "title": "Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer", "first_author": "Colin Raffel", "year": 2019, "venue": "arXiv preprint arXiv:1910.10683", "doi": null, "arxiv_id": "1910.10683", "verified_via": "http://export.arxiv.org/api/query?id_list=1910.10683", "verified_at": "2026-11-09T17:09:52Z", "theme": "Sequence-to-sequence architectures"}59{"bibkey": "lewis2019bart", "title": "BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension", "first_author": "Mike Lewis", "year": 2019, "venue": "arXiv preprint arXiv:1910.13461", "doi": null, "arxiv_id": "1910.13461", "verified_via": "http://export.arxiv.org/api/query?id_list=1910.13461", "verified_at": "2026-11-09T17:09:52Z", "theme": "Sequence-to-sequence architectures"}60{"bibkey": "see2017pointer", "title": "Get To The Point: Summarization with Pointer-Generator Networks", "first_author": "Abigail See", "year": 2017, "venue": "arXiv preprint arXiv:1704.04368", "doi": null, "arxiv_id": "1704.04368", "verified_via": "http://export.arxiv.org/api/query?id_list=1704.04368", "verified_at": "2026-11-09T17:09:52Z", "theme": "Sequence-to-sequence architectures"}61{"bibkey": "gu2016copying", "title": "Incorporating Copying Mechanism in Sequence-to-Sequence Learning", "first_author": "Jiatao Gu", "year": 2016, "venue": "arXiv preprint arXiv:1603.06393", "doi": null, "arxiv_id": "1603.06393", "verified_via": "http://export.arxiv.org/api/query?id_list=1603.06393", "verified_at": "2026-11-09T17:09:52Z", "theme": "Sequence-to-sequence architectures"}62{"bibkey": "kudo2018sentencepiece", "title": "SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing", "first_author": "Taku Kudo", "year": 2018, "venue": "arXiv preprint arXiv:1808.06226", "doi": null, "arxiv_id": "1808.06226", "verified_via": "http://export.arxiv.org/api/query?id_list=1808.06226", "verified_at": "2026-11-09T17:09:52Z", "theme": "Sequence-to-sequence architectures"}63{"bibkey": "xiong2020layernorm", "title": "On Layer Normalization in the Transformer Architecture", "first_author": "Ruibin Xiong", "year": 2020, "venue": "Published on ICML 2020", "doi": null, "arxiv_id": "2002.04745", "verified_via": "http://export.arxiv.org/api/query?id_list=2002.04745", "verified_at": "2026-11-09T17:09:52Z", "theme": "Sequence-to-sequence architectures"}64{"bibkey": "su2021roformer", "title": "RoFormer: Enhanced Transformer with Rotary Position Embedding", "first_author": "Jianlin Su", "year": 2021, "venue": "arXiv preprint arXiv:2104.09864", "doi": null, "arxiv_id": "2104.09864", "verified_via": "http://export.arxiv.org/api/query?id_list=2104.09864", "verified_at": "2026-11-09T17:09:52Z", "theme": "Sequence-to-sequence architectures"}65{"bibkey": "popovic2015chrf", "title": "chrF: character n-gram F-score for automatic MT evaluation", "first_author": "Maja Popović", "year": 2015, "venue": "Conference on Machine Translation (WMT)", "doi": "10.18653/v1/w15-3049", "arxiv_id": null, "verified_via": "https://api.openalex.org/works?filter=doi:10.18653/v1/w15-3049", "verified_at": "2026-11-09T17:12:41Z", "theme": "Evaluation metrics"}66{"bibkey": "papineni2002bleu", "title": "BLEU", "first_author": "Kishore Papineni", "year": 2001, "venue": "Proceedings of the conference - Association for Computational Linguistics. Meeting", "doi": "10.3115/1073083.1073135", "arxiv_id": null, "verified_via": "https://api.openalex.org/works?filter=doi:10.3115/1073083.1073135", "verified_at": "2026-11-09T17:12:41Z", "theme": "Evaluation metrics", "note": "OpenAlex/Crossref title \"BLEU\", issued 2001; proceedings of ACL-02 (bib year 2002)"}67{"bibkey": "lin2004rouge", "title": "ROUGE: A Package for Automatic Evaluation of Summaries", "first_author": "Chin-Yew Lin", "year": 2004, "venue": null, "doi": null, "arxiv_id": null, "verified_via": "https://api.openalex.org/works/W2154652894", "verified_at": "2026-11-09T17:12:41Z", "theme": "Evaluation metrics"}68{"bibkey": "zhang2019bertscore", "title": "BERTScore: Evaluating Text Generation with BERT", "first_author": "Tianyi Zhang", "year": 2019, "venue": "arXiv preprint arXiv:1904.09675", "doi": null, "arxiv_id": "1904.09675", "verified_via": "http://export.arxiv.org/api/query?id_list=1904.09675", "verified_at": "2026-11-09T17:09:52Z", "theme": "Evaluation metrics"}69{"bibkey": "reimers2019sentencebert", "title": "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks", "first_author": "Nils Reimers", "year": 2019, "venue": "arXiv preprint arXiv:1908.10084", "doi": null, "arxiv_id": "1908.10084", "verified_via": "http://export.arxiv.org/api/query?id_list=1908.10084", "verified_at": "2026-11-09T17:09:52Z", "theme": "Evaluation metrics"}70{"bibkey": "carlini2020extracting", "title": "Extracting Training Data from Large Language Models", "first_author": "Nicholas Carlini", "year": 2020, "venue": "arXiv preprint arXiv:2012.07805", "doi": null, "arxiv_id": "2012.07805", "verified_via": "http://export.arxiv.org/api/query?id_list=2012.07805", "verified_at": "2026-11-09T17:09:52Z", "theme": "Memorisation and contamination"}71{"bibkey": "carlini2022quantifying", "title": "Quantifying Memorization Across Neural Language Models", "first_author": "Nicholas Carlini", "year": 2022, "venue": "arXiv preprint arXiv:2202.07646", "doi": null, "arxiv_id": "2202.07646", "verified_via": "http://export.arxiv.org/api/query?id_list=2202.07646", "verified_at": "2026-11-09T17:09:52Z", "theme": "Memorisation and contamination"}72{"bibkey": "lee2021dedup", "title": "Deduplicating Training Data Makes Language Models Better", "first_author": "Katherine Lee", "year": 2021, "venue": "arXiv preprint arXiv:2107.06499", "doi": null, "arxiv_id": "2107.06499", "verified_via": "http://export.arxiv.org/api/query?id_list=2107.06499", "verified_at": "2026-11-09T17:09:52Z", "theme": "Memorisation and contamination"}73{"bibkey": "magar2022contamination", "title": "Data Contamination: From Memorization to Exploitation", "first_author": "Inbal Magar", "year": 2022, "venue": "arXiv preprint arXiv:2203.08242", "doi": null, "arxiv_id": "2203.08242", "verified_via": "http://export.arxiv.org/api/query?id_list=2203.08242", "verified_at": "2026-11-09T17:09:52Z", "theme": "Memorisation and contamination"}74{"bibkey": "sainz2023contamination", "title": "NLP Evaluation in trouble: On the Need to Measure LLM Data Contamination for each Benchmark", "first_author": "Oscar Sainz", "year": 2023, "venue": "arXiv preprint arXiv:2310.18018", "doi": null, "arxiv_id": "2310.18018", "verified_via": "http://export.arxiv.org/api/query?id_list=2310.18018", "verified_at": "2026-11-09T17:09:52Z", "theme": "Memorisation and contamination"}75{"bibkey": "shumailov2024collapse", "title": "AI models collapse when trained on recursively generated data", "first_author": "Ilia Shumailov", "year": 2024, "venue": "Nature", "doi": "10.1038/s41586-024-07566-y", "arxiv_id": null, "verified_via": "https://api.openalex.org/works?filter=doi:10.1038/s41586-024-07566-y", "verified_at": "2026-11-09T17:12:41Z", "theme": "Synthetic data and model collapse"}76{"bibkey": "alemohammad2023mad", "title": "Self-Consuming Generative Models Go MAD", "first_author": "Sina Alemohammad", "year": 2023, "venue": "arXiv preprint arXiv:2307.01850", "doi": null, "arxiv_id": "2307.01850", "verified_via": "http://export.arxiv.org/api/query?id_list=2307.01850", "verified_at": "2026-11-09T17:09:52Z", "theme": "Synthetic data and model collapse"}77{"bibkey": "dohmatob2024tails", "title": "A Tale of Tails: Model Collapse as a Change of Scaling Laws", "first_author": "Elvis Dohmatob", "year": 2024, "venue": "ICML 2024", "doi": null, "arxiv_id": "2402.07043", "verified_via": "http://export.arxiv.org/api/query?id_list=2402.07043", "verified_at": "2026-11-09T17:09:52Z", "theme": "Synthetic data and model collapse"}78{"bibkey": "lo2019s2orc", "title": "S2ORC: The Semantic Scholar Open Research Corpus", "first_author": "Kyle Lo", "year": 2019, "venue": "arXiv preprint arXiv:1911.02782", "doi": null, "arxiv_id": "1911.02782", "verified_via": "http://export.arxiv.org/api/query?id_list=1911.02782", "verified_at": "2026-11-09T17:09:52Z", "theme": "Corpora and licensing"}79{"bibkey": "saier2023unarxive", "title": "unarXive 2022: All arXiv Publications Pre-Processed for NLP, Including Structured Full-Text and Citation Network", "first_author": "Tarek Saier", "year": 2023, "venue": "arXiv preprint arXiv:2303.14957", "doi": "10.1109/JCDL57899.2023.00020", "arxiv_id": "2303.14957", "verified_via": "http://export.arxiv.org/api/query?id_list=2303.14957", "verified_at": "2026-11-09T17:09:52Z", "theme": "Corpora and licensing"}80{"bibkey": "gao2020pile", "title": "The Pile: An 800GB Dataset of Diverse Text for Language Modeling", "first_author": "Leo Gao", "year": 2020, "venue": "arXiv preprint arXiv:2101.00027", "doi": null, "arxiv_id": "2101.00027", "verified_via": "http://export.arxiv.org/api/query?id_list=2101.00027", "verified_at": "2026-11-09T17:09:52Z", "theme": "Corpora and licensing"}81{"bibkey": "soldaini2024dolma", "title": "Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research", "first_author": "Luca Soldaini", "year": 2024, "venue": "arXiv preprint arXiv:2402.00159", "doi": null, "arxiv_id": "2402.00159", "verified_via": "http://export.arxiv.org/api/query?id_list=2402.00159", "verified_at": "2026-11-09T17:09:52Z", "theme": "Corpora and licensing"}82{"bibkey": "longpre2023provenance", "title": "The Data Provenance Initiative: A Large Scale Audit of Dataset Licensing & Attribution in AI", "first_author": "Shayne Longpre", "year": 2023, "venue": "arXiv preprint arXiv:2310.16787", "doi": null, "arxiv_id": "2310.16787", "verified_via": "http://export.arxiv.org/api/query?id_list=2310.16787", "verified_at": "2026-11-09T17:09:52Z", "theme": "Corpora and licensing"}83{"bibkey": "plavensigray2017readability", "title": "The readability of scientific texts is decreasing over time", "first_author": "Pontus Plavén‐Sigray", "year": 2017, "venue": "eLife", "doi": "10.7554/elife.27725", "arxiv_id": null, "verified_via": "https://api.openalex.org/works?filter=doi:10.7554/elife.27725", "verified_at": "2026-11-09T17:12:41Z", "theme": "Scientific style change over time"}84{"bibkey": "hyland2016stance", "title": "Change of Attitude? A Diachronic Study of Stance", "first_author": "Ken Hyland", "year": 2016, "venue": "Written Communication", "doi": "10.1177/0741088316650399", "arxiv_id": null, "verified_via": "https://api.openalex.org/works?filter=doi:10.1177/0741088316650399", "verified_at": "2026-11-09T17:12:41Z", "theme": "Scientific style change over time"}85{"bibkey": "hyland2016informal", "title": "Is academic writing becoming more informal?", "first_author": "Ken Hyland", "year": 2016, "venue": "English for Specific Purposes", "doi": "10.1016/j.esp.2016.09.001", "arxiv_id": null, "verified_via": "https://api.openalex.org/works?filter=doi:10.1016/j.esp.2016.09.001", "verified_at": "2026-11-09T17:12:41Z", "theme": "Scientific style change over time"}86