1% ============================================================================2% WP45 / JoF-250 — references.bib3% Every entry was verified on 2026-11-03 against Crossref (DOI resolution),4% the arXiv API (id resolution) or Open Library (ISBN). See5% paper/sections/literature_verification.md for the audit table.6% ============================================================================78% ---------------------------------------------------------------------------9% (a) Genre analysis, rhetorical moves, research-article structure10% ---------------------------------------------------------------------------1112@book{swales1990genre,13 author = {Swales, John M.},14 title = {Genre Analysis: {English} in Academic and Research Settings},15 publisher = {Cambridge University Press},16 address = {Cambridge},17 year = {1990},18 isbn = {0521338131},19 note = {verified Open Library (ISBN 0521338131) and Crossref-indexed reviews (10.2307/329786; 10.1017/s0272263100011773) 2026-11-03}20}2122@book{swales2004research,23 author = {Swales, John M.},24 title = {Research Genres: Explorations and Applications},25 publisher = {Cambridge University Press},26 address = {Cambridge},27 year = {2004},28 doi = {10.1017/CBO9781139524827},29 isbn = {9780521533348},30 note = {verified Crossref 2026-11-03}31}3233@book{hyland1998hedging,34 author = {Hyland, Ken},35 title = {Hedging in Scientific Research Articles},36 series = {Pragmatics \& Beyond New Series},37 publisher = {John Benjamins},38 address = {Amsterdam},39 year = {1998},40 doi = {10.1075/pbns.54},41 isbn = {9789027250674},42 note = {verified Crossref 2026-11-03}43}4445@article{hyland1996hedging,46 author = {Hyland, Ken},47 title = {Writing Without Conviction? {Hedging} in Science Research Articles},48 journal = {Applied Linguistics},49 year = {1996},50 volume = {17},51 number = {4},52 pages = {433--454},53 doi = {10.1093/applin/17.4.433},54 note = {verified Crossref 2026-11-03}55}5657@article{hyland2004metadiscourse,58 author = {Hyland, Ken and Tse, Polly},59 title = {Metadiscourse in Academic Writing: A Reappraisal},60 journal = {Applied Linguistics},61 year = {2004},62 volume = {25},63 number = {2},64 pages = {156--177},65 doi = {10.1093/applin/25.2.156},66 note = {verified Crossref 2026-11-03}67}6869@article{samraj2002introductions,70 author = {Samraj, Betty},71 title = {Introductions in Research Articles: Variations Across Disciplines},72 journal = {English for Specific Purposes},73 year = {2002},74 volume = {21},75 number = {1},76 pages = {1--17},77 doi = {10.1016/S0889-4906(00)00023-5},78 note = {verified Crossref 2026-11-03}79}8081@article{kanoksilapatham2005rhetorical,82 author = {Kanoksilapatham, Budsaba},83 title = {Rhetorical Structure of Biochemistry Research Articles},84 journal = {English for Specific Purposes},85 year = {2005},86 volume = {24},87 number = {3},88 pages = {269--292},89 doi = {10.1016/j.esp.2004.08.003},90 note = {verified Crossref 2026-11-03}91}9293@article{lin2012structural,94 author = {Lin, Ling and Evans, Stephen},95 title = {Structural Patterns in Empirical Research Articles: A Cross-Disciplinary Study},96 journal = {English for Specific Purposes},97 year = {2012},98 volume = {31},99 number = {3},100 pages = {150--160},101 doi = {10.1016/j.esp.2011.10.002},102 note = {verified Crossref 2026-11-03}103}104105@article{hyland2017informal,106 author = {Hyland, Ken and Jiang, Feng (Kevin)},107 title = {Is Academic Writing Becoming More Informal?},108 journal = {English for Specific Purposes},109 year = {2017},110 volume = {45},111 pages = {40--51},112 doi = {10.1016/j.esp.2016.09.001},113 note = {verified Crossref 2026-11-03}114}115116@article{teufel2002summarizing,117 author = {Teufel, Simone and Moens, Marc},118 title = {Summarizing Scientific Articles: Experiments with Relevance and Rhetorical Status},119 journal = {Computational Linguistics},120 year = {2002},121 volume = {28},122 number = {4},123 pages = {409--445},124 doi = {10.1162/089120102762671936},125 note = {verified Crossref 2026-11-03}126}127128@inproceedings{cohan2019sequential,129 author = {Cohan, Arman and Beltagy, Iz and King, Daniel and Dalvi, Bhavana and Weld, Dan},130 title = {Pretrained Language Models for Sequential Sentence Classification},131 booktitle = {Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)},132 publisher = {Association for Computational Linguistics},133 year = {2019},134 pages = {3691--3697},135 doi = {10.18653/v1/D19-1383},136 note = {verified Crossref 2026-11-03}137}138139@inproceedings{lo2020s2orc,140 author = {Lo, Kyle and Wang, Lucy Lu and Neumann, Mark and Kinney, Rodney and Weld, Daniel},141 title = {{S2ORC}: The {Semantic Scholar} Open Research Corpus},142 booktitle = {Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics},143 publisher = {Association for Computational Linguistics},144 year = {2020},145 pages = {4969--4983},146 doi = {10.18653/v1/2020.acl-main.447},147 note = {verified Crossref 2026-11-03}148}149150@incollection{lopez2009grobid,151 author = {Lopez, Patrice},152 title = {{GROBID}: Combining Automatic Bibliographic Data Recognition and Term Extraction for Scholarship Publications},153 booktitle = {Research and Advanced Technology for Digital Libraries (ECDL 2009)},154 series = {Lecture Notes in Computer Science},155 publisher = {Springer},156 address = {Berlin, Heidelberg},157 year = {2009},158 pages = {473--474},159 doi = {10.1007/978-3-642-04346-8_62},160 note = {verified Crossref 2026-11-03}161}162163% --- Economics writing guidance (peer-reviewed journals) ---164165@article{mccloskey1985economical,166 author = {McCloskey, Donald N.},167 title = {Economical Writing},168 journal = {Economic Inquiry},169 year = {1985},170 volume = {23},171 number = {2},172 pages = {187--222},173 doi = {10.1111/j.1465-7295.1985.tb01761.x},174 note = {verified Crossref 2026-11-03}175}176177@article{thomson1999guide,178 author = {Thomson, William},179 title = {The Young Person's Guide to Writing Economic Theory},180 journal = {Journal of Economic Literature},181 year = {1999},182 volume = {37},183 number = {1},184 pages = {157--183},185 doi = {10.1257/jel.37.1.157},186 note = {verified Crossref 2026-11-03}187}188189% ---------------------------------------------------------------------------190% (b) Writing conventions, readability and publishing in economics/finance191% ---------------------------------------------------------------------------192193@article{li2008readability,194 author = {Li, Feng},195 title = {Annual Report Readability, Current Earnings, and Earnings Persistence},196 journal = {Journal of Accounting and Economics},197 year = {2008},198 volume = {45},199 number = {2--3},200 pages = {221--247},201 doi = {10.1016/j.jacceco.2008.02.003},202 note = {verified Crossref 2026-11-03}203}204205@article{loughran2011liability,206 author = {Loughran, Tim and McDonald, Bill},207 title = {When Is a Liability Not a Liability? {Textual} Analysis, Dictionaries, and 10-{K}s},208 journal = {The Journal of Finance},209 year = {2011},210 volume = {66},211 number = {1},212 pages = {35--65},213 doi = {10.1111/j.1540-6261.2010.01625.x},214 note = {verified Crossref 2026-11-03}215}216217@article{loughran2014readability,218 author = {Loughran, Tim and McDonald, Bill},219 title = {Measuring Readability in Financial Disclosures},220 journal = {The Journal of Finance},221 year = {2014},222 volume = {69},223 number = {4},224 pages = {1643--1671},225 doi = {10.1111/jofi.12162},226 note = {verified Crossref 2026-11-03}227}228229@article{loughran2016textual,230 author = {Loughran, Tim and McDonald, Bill},231 title = {Textual Analysis in Accounting and Finance: A Survey},232 journal = {Journal of Accounting Research},233 year = {2016},234 volume = {54},235 number = {4},236 pages = {1187--1230},237 doi = {10.1111/1475-679X.12123},238 note = {verified Crossref 2026-11-03}239}240241@article{gentzkow2019text,242 author = {Gentzkow, Matthew and Kelly, Bryan and Taddy, Matt},243 title = {Text as Data},244 journal = {Journal of Economic Literature},245 year = {2019},246 volume = {57},247 number = {3},248 pages = {535--574},249 doi = {10.1257/jel.20181020},250 note = {verified Crossref 2026-11-03}251}252253@article{dowling2018easy,254 author = {Dowling, Michael and Hammami, Helmi and Zreik, Ousayna},255 title = {Easy to Read, Easy to Cite?},256 journal = {Economics Letters},257 year = {2018},258 volume = {173},259 pages = {100--103},260 doi = {10.1016/j.econlet.2018.09.023},261 note = {verified Crossref 2026-11-03}262}263264@article{hengel2022publishing,265 author = {Hengel, Erin},266 title = {Publishing While Female: Are Women Held to Higher Standards? {Evidence} from Peer Review},267 journal = {The Economic Journal},268 year = {2022},269 volume = {132},270 number = {648},271 pages = {2951--2991},272 doi = {10.1093/ej/ueac032},273 note = {verified Crossref 2026-11-03}274}275276@article{card2013nine,277 author = {Card, David and DellaVigna, Stefano},278 title = {Nine Facts about Top Journals in Economics},279 journal = {Journal of Economic Literature},280 year = {2013},281 volume = {51},282 number = {1},283 pages = {144--161},284 doi = {10.1257/jel.51.1.144},285 note = {verified Crossref 2026-11-03}286}287288@article{card2014pagelimits,289 author = {Card, David and DellaVigna, Stefano},290 title = {Page Limits on Economics Articles: Evidence from Two Journals},291 journal = {Journal of Economic Perspectives},292 year = {2014},293 volume = {28},294 number = {3},295 pages = {149--168},296 doi = {10.1257/jep.28.3.149},297 note = {verified Crossref 2026-11-03}298}299300@article{plaven2017readability,301 author = {Plav{\'e}n-Sigray, Pontus and Matheson, Granville James and Schiffler, Bj{\"o}rn Christian and Thompson, William Hedley},302 title = {The Readability of Scientific Texts Is Decreasing over Time},303 journal = {eLife},304 year = {2017},305 volume = {6},306 pages = {e27725},307 doi = {10.7554/eLife.27725},308 note = {verified Crossref 2026-11-03}309}310311@article{hartley2014structured,312 author = {Hartley, James},313 title = {Current Findings from Research on Structured Abstracts: An Update},314 journal = {Journal of the Medical Library Association},315 year = {2014},316 volume = {102},317 number = {3},318 pages = {146--148},319 doi = {10.3163/1536-5050.102.3.002},320 note = {verified Crossref 2026-11-03}321}322323@article{korinek2023generative,324 author = {Korinek, Anton},325 title = {Generative {AI} for Economic Research: Use Cases and Implications for Economists},326 journal = {Journal of Economic Literature},327 year = {2023},328 volume = {61},329 number = {4},330 pages = {1281--1317},331 doi = {10.1257/jel.20231736},332 note = {verified Crossref 2026-11-03}333}334335% ---------------------------------------------------------------------------336% (c) Retrieval-augmented generation and LLM-assisted academic writing/review337% ---------------------------------------------------------------------------338339@misc{lewis2020rag,340 author = {Lewis, Patrick and Perez, Ethan and Piktus, Aleksandra and Petroni, Fabio and Karpukhin, Vladimir and Goyal, Naman and K{\"u}ttler, Heinrich and Lewis, Mike and Yih, Wen-tau and Rockt{\"a}schel, Tim and Riedel, Sebastian and Kiela, Douwe},341 title = {Retrieval-Augmented Generation for Knowledge-Intensive {NLP} Tasks},342 year = {2020},343 howpublished = {arXiv preprint arXiv:2005.11401},344 eprint = {2005.11401},345 archivePrefix = {arXiv},346 url = {https://arxiv.org/abs/2005.11401},347 note = {verified arXiv 2026-11-03}348}349350@misc{guu2020realm,351 author = {Guu, Kelvin and Lee, Kenton and Tung, Zora and Pasupat, Panupong and Chang, Ming-Wei},352 title = {{REALM}: Retrieval-Augmented Language Model Pre-Training},353 year = {2020},354 howpublished = {arXiv preprint arXiv:2002.08909},355 eprint = {2002.08909},356 archivePrefix = {arXiv},357 url = {https://arxiv.org/abs/2002.08909},358 note = {verified arXiv 2026-11-03}359}360361@inproceedings{karpukhin2020dpr,362 author = {Karpukhin, Vladimir and O{\u{g}}uz, Barlas and Min, Sewon and Lewis, Patrick and Wu, Ledell and Edunov, Sergey and Chen, Danqi and Yih, Wen-tau},363 title = {Dense Passage Retrieval for Open-Domain Question Answering},364 booktitle = {Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)},365 publisher = {Association for Computational Linguistics},366 year = {2020},367 pages = {6769--6781},368 doi = {10.18653/v1/2020.emnlp-main.550},369 note = {verified Crossref 2026-11-03}370}371372@misc{gao2023ragsurvey,373 author = {Gao, Yunfan and Xiong, Yun and Gao, Xinyu and Jia, Kangxiang and Pan, Jinliu and Bi, Yuxi and Dai, Yi and Sun, Jiawei and Wang, Meng and Wang, Haofen},374 title = {Retrieval-Augmented Generation for Large Language Models: A Survey},375 year = {2023},376 howpublished = {arXiv preprint arXiv:2312.10997},377 eprint = {2312.10997},378 archivePrefix = {arXiv},379 url = {https://arxiv.org/abs/2312.10997},380 note = {verified arXiv 2026-11-03}381}382383@article{liang2024feedback,384 author = {Liang, Weixin and Zhang, Yuhui and Cao, Hancheng and Wang, Binglu and Ding, Daisy Yi and Yang, Xinyu and Vodrahalli, Kailas and He, Siyu and Smith, Daniel Scott and Yin, Yian and McFarland, Daniel A. and Zou, James},385 title = {Can Large Language Models Provide Useful Feedback on Research Papers? {A} Large-Scale Empirical Analysis},386 journal = {NEJM AI},387 year = {2024},388 volume = {1},389 number = {8},390 doi = {10.1056/AIoa2400196},391 note = {verified Crossref 2026-11-03}392}393394@misc{liang2024mapping,395 author = {Liang, Weixin and Zhang, Yaohui and Wu, Zhengxuan and Lepp, Haley and Ji, Wenlong and Zhao, Xuandong and Cao, Hancheng and Liu, Sheng and He, Siyu and Huang, Zhi and Yang, Diyi and Potts, Christopher and Manning, Christopher D. and Zou, James Y.},396 title = {Mapping the Increasing Use of {LLMs} in Scientific Papers},397 year = {2024},398 howpublished = {arXiv preprint arXiv:2404.01268},399 eprint = {2404.01268},400 archivePrefix = {arXiv},401 url = {https://arxiv.org/abs/2404.01268},402 note = {verified arXiv 2026-11-03}403}404405@misc{liang2024monitoring,406 author = {Liang, Weixin and Izzo, Zachary and Zhang, Yaohui and Lepp, Haley and Cao, Hancheng and Zhao, Xuandong and Chen, Lingjiao and Ye, Haotian and Liu, Sheng and Huang, Zhi and McFarland, Daniel A. and Zou, James Y.},407 title = {Monitoring {AI}-Modified Content at Scale: A Case Study on the Impact of {ChatGPT} on {AI} Conference Peer Reviews},408 year = {2024},409 howpublished = {arXiv preprint arXiv:2403.07183},410 eprint = {2403.07183},411 archivePrefix = {arXiv},412 url = {https://arxiv.org/abs/2403.07183},413 note = {verified arXiv 2026-11-03}414}415416@article{kobak2025delving,417 author = {Kobak, Dmitry and Gonz{\'a}lez-M{\'a}rquez, Rita and Horv{\'a}t, Em{\H{o}}ke-{\'A}gnes and Lause, Jan},418 title = {Delving into {LLM}-Assisted Writing in Biomedical Publications through Excess Vocabulary},419 journal = {Science Advances},420 year = {2025},421 volume = {11},422 number = {27},423 pages = {eadt3813},424 doi = {10.1126/sciadv.adt3813},425 note = {verified Crossref 2026-11-03}426}427428@article{else2023abstracts,429 author = {Else, Holly},430 title = {Abstracts Written by {ChatGPT} Fool Scientists},431 journal = {Nature},432 year = {2023},433 volume = {613},434 number = {7944},435 pages = {423},436 doi = {10.1038/d41586-023-00056-7},437 note = {verified Crossref 2026-11-03}438}439440@article{gao2023comparing,441 author = {Gao, Catherine A. and Howard, Frederick M. and Markov, Nikolay S. and Dyer, Emma C. and Ramesh, Siddhi and Luo, Yuan and Pearson, Alexander T.},442 title = {Comparing Scientific Abstracts Generated by {ChatGPT} to Real Abstracts with Detectors and Blinded Human Reviewers},443 journal = {npj Digital Medicine},444 year = {2023},445 volume = {6},446 number = {1},447 doi = {10.1038/s41746-023-00819-6},448 note = {verified Crossref 2026-11-03}449}450451@article{vannoorden2023survey,452 author = {Van Noorden, Richard and Perkel, Jeffrey M.},453 title = {{AI} and Science: What 1,600 Researchers Think},454 journal = {Nature},455 year = {2023},456 volume = {621},457 number = {7980},458 pages = {672--675},459 doi = {10.1038/d41586-023-02980-0},460 note = {verified Crossref 2026-11-03}461}462463@misc{zheng2023judge,464 author = {Zheng, Lianmin and Chiang, Wei-Lin and Sheng, Ying and Zhuang, Siyuan and Wu, Zhanghao and Zhuang, Yonghao and Lin, Zi and Li, Zhuohan and Li, Dacheng and Xing, Eric P. and Zhang, Hao and Gonzalez, Joseph E. and Stoica, Ion},465 title = {Judging {LLM}-as-a-Judge with {MT-Bench} and {Chatbot Arena}},466 year = {2023},467 howpublished = {arXiv preprint arXiv:2306.05685},468 eprint = {2306.05685},469 archivePrefix = {arXiv},470 url = {https://arxiv.org/abs/2306.05685},471 note = {verified arXiv 2026-11-03}472}473474@inproceedings{wang2024notfair,475 author = {Wang, Peiyi and Li, Lei and Chen, Liang and Cai, Zefan and Zhu, Dawei and Lin, Binghuai and Cao, Yunbo and Kong, Lingpeng and Liu, Qi and Liu, Tianyu and Sui, Zhifang},476 title = {Large Language Models Are Not Fair Evaluators},477 booktitle = {Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},478 publisher = {Association for Computational Linguistics},479 year = {2024},480 pages = {9440--9450},481 doi = {10.18653/v1/2024.acl-long.511},482 note = {verified Crossref 2026-11-03}483}484485@misc{panickssery2024self,486 author = {Panickssery, Arjun and Bowman, Samuel R. and Feng, Shi},487 title = {{LLM} Evaluators Recognize and Favor Their Own Generations},488 year = {2024},489 howpublished = {arXiv preprint arXiv:2404.13076},490 eprint = {2404.13076},491 archivePrefix = {arXiv},492 url = {https://arxiv.org/abs/2404.13076},493 note = {verified arXiv 2026-11-03}494}495496@article{thelwall2024chatgpt,497 author = {Thelwall, Mike},498 title = {Can {ChatGPT} Evaluate Research Quality?},499 journal = {Journal of Data and Information Science},500 year = {2024},501 volume = {9},502 number = {2},503 pages = {1--21},504 doi = {10.2478/jdis-2024-0013},505 note = {verified Crossref 2026-11-03}506}507508@article{hosseini2023fighting,509 author = {Hosseini, Mohammad and Horbach, Serge P. J. M.},510 title = {Fighting Reviewer Fatigue or Amplifying Bias? {Considerations} and Recommendations for Use of {ChatGPT} and Other Large Language Models in Scholarly Peer Review},511 journal = {Research Integrity and Peer Review},512 year = {2023},513 volume = {8},514 number = {1},515 doi = {10.1186/s41073-023-00133-5},516 note = {verified Crossref 2026-11-03}517}518519@misc{du2024critique,520 author = {Du, Jiangshu and Wang, Yibo and Zhao, Wenting and Deng, Zhongfen and Liu, Shuaiqi and Lou, Renze and Zou, Henry Peng and Venkit, Pranav Narayanan and Zhang, Nan and Srinath, Mukund and Zhang, Haoran Ranran and Gupta, Vipul and Li, Yinghui and Li, Tao and Wang, Fei and Liu, Qin and Liu, Tianlin and Gao, Pengzhi and Xia, Congying and Xing, Chen and Cheng, Jiayang and Wang, Zhaowei and Su, Ying and Shah, Raj Sanjay and Guo, Ruohao and Gu, Jing and Li, Haoran and Wei, Kangda and Wang, Zihao and Cheng, Lu and Ranathunga, Surangika and Fang, Meng and Fu, Jie and Liu, Fei and Huang, Ruihong and Blanco, Eduardo and Cao, Yixin and Zhang, Rui and Yu, Philip S. and Yin, Wenpeng},521 title = {{LLMs} Assist {NLP} Researchers: Critique Paper (Meta-)Reviewing},522 year = {2024},523 howpublished = {arXiv preprint arXiv:2406.16253},524 eprint = {2406.16253},525 archivePrefix = {arXiv},526 url = {https://arxiv.org/abs/2406.16253},527 note = {verified arXiv 2026-11-03}528}529530@misc{latona2024lottery,531 author = {Latona, Giuseppe Russo and Horta Ribeiro, Manoel and Davidson, Tim R. and Veselovsky, Veniamin and West, Robert},532 title = {The {AI} Review Lottery: Widespread {AI}-Assisted Peer Reviews Boost Paper Scores and Acceptance Rates},533 year = {2024},534 howpublished = {arXiv preprint arXiv:2405.02150},535 eprint = {2405.02150},536 archivePrefix = {arXiv},537 url = {https://arxiv.org/abs/2405.02150},538 note = {verified arXiv 2026-11-03}539}540541@misc{si2024ideas,542 author = {Si, Chenglei and Yang, Diyi and Hashimoto, Tatsunori},543 title = {Can {LLMs} Generate Novel Research Ideas? {A} Large-Scale Human Study with 100+ {NLP} Researchers},544 year = {2024},545 howpublished = {arXiv preprint arXiv:2409.04109},546 eprint = {2409.04109},547 archivePrefix = {arXiv},548 url = {https://arxiv.org/abs/2409.04109},549 note = {verified arXiv 2026-11-03}550}551552@article{shumailov2024collapse,553 author = {Shumailov, Ilia and Shumaylov, Zakhar and Zhao, Yiren and Papernot, Nicolas and Anderson, Ross and Gal, Yarin},554 title = {{AI} Models Collapse When Trained on Recursively Generated Data},555 journal = {Nature},556 year = {2024},557 volume = {631},558 number = {8022},559 pages = {755--759},560 doi = {10.1038/s41586-024-07566-y},561 note = {verified Crossref 2026-11-03}562}563564% ---------------------------------------------------------------------------565% (d) Evaluation, contamination, memorization and reproducibility566% ---------------------------------------------------------------------------567568@inproceedings{sainz2023contamination,569 author = {Sainz, Oscar and Campos, Jon and Garc{\'i}a-Ferrero, Iker and Etxaniz, Julen and L{\'o}pez de Lacalle, Oier and Agirre, Eneko},570 title = {{NLP} Evaluation in Trouble: On the Need to Measure {LLM} Data Contamination for Each Benchmark},571 booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2023},572 publisher = {Association for Computational Linguistics},573 year = {2023},574 pages = {10776--10787},575 doi = {10.18653/v1/2023.findings-emnlp.722},576 note = {verified Crossref 2026-11-03}577}578579@inproceedings{magar2022contamination,580 author = {Magar, Inbal and Schwartz, Roy},581 title = {Data Contamination: From Memorization to Exploitation},582 booktitle = {Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)},583 publisher = {Association for Computational Linguistics},584 year = {2022},585 pages = {157--165},586 doi = {10.18653/v1/2022.acl-short.18},587 note = {verified Crossref 2026-11-03}588}589590@inproceedings{deng2024investigating,591 author = {Deng, Chunyuan and Zhao, Yilun and Tang, Xiangru and Gerstein, Mark and Cohan, Arman},592 title = {Investigating Data Contamination in Modern Benchmarks for Large Language Models},593 booktitle = {Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)},594 publisher = {Association for Computational Linguistics},595 year = {2024},596 pages = {8706--8719},597 doi = {10.18653/v1/2024.naacl-long.482},598 note = {verified Crossref 2026-11-03}599}600601@misc{golchin2024timetravel,602 author = {Golchin, Shahriar and Surdeanu, Mihai},603 title = {Time Travel in {LLMs}: Tracing Data Contamination in Large Language Models},604 year = {2024},605 howpublished = {arXiv preprint arXiv:2308.08493},606 eprint = {2308.08493},607 archivePrefix = {arXiv},608 url = {https://arxiv.org/abs/2308.08493},609 note = {verified arXiv 2026-11-03}610}611612@misc{carlini2023memorization,613 author = {Carlini, Nicholas and Ippolito, Daphne and Jagielski, Matthew and Lee, Katherine and Tramer, Florian and Zhang, Chiyuan},614 title = {Quantifying Memorization Across Neural Language Models},615 year = {2023},616 howpublished = {arXiv preprint arXiv:2202.07646},617 eprint = {2202.07646},618 archivePrefix = {arXiv},619 url = {https://arxiv.org/abs/2202.07646},620 note = {verified arXiv 2026-11-03}621}622623@inproceedings{lee2022dedup,624 author = {Lee, Katherine and Ippolito, Daphne and Nystrom, Andrew and Zhang, Chiyuan and Eck, Douglas and Callison-Burch, Chris and Carlini, Nicholas},625 title = {Deduplicating Training Data Makes Language Models Better},626 booktitle = {Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},627 publisher = {Association for Computational Linguistics},628 year = {2022},629 pages = {8424--8445},630 doi = {10.18653/v1/2022.acl-long.577},631 note = {verified Crossref 2026-11-03}632}633634@article{kapoor2023leakage,635 author = {Kapoor, Sayash and Narayanan, Arvind},636 title = {Leakage and the Reproducibility Crisis in Machine-Learning-Based Science},637 journal = {Patterns},638 year = {2023},639 volume = {4},640 number = {9},641 pages = {100804},642 doi = {10.1016/j.patter.2023.100804},643 note = {verified Crossref 2026-11-03}644}645646@article{nosek2018preregistration,647 author = {Nosek, Brian A. and Ebersole, Charles R. and DeHaven, Alexander C. and Mellor, David T.},648 title = {The Preregistration Revolution},649 journal = {Proceedings of the National Academy of Sciences},650 year = {2018},651 volume = {115},652 number = {11},653 pages = {2600--2606},654 doi = {10.1073/pnas.1708274114},655 note = {verified Crossref 2026-11-03}656}657658@inproceedings{bowman2021benchmarking,659 author = {Bowman, Samuel R. and Dahl, George},660 title = {What Will It Take to Fix Benchmarking in Natural Language Understanding?},661 booktitle = {Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies},662 publisher = {Association for Computational Linguistics},663 year = {2021},664 pages = {4843--4855},665 doi = {10.18653/v1/2021.naacl-main.385},666 note = {verified Crossref 2026-11-03}667}668669@inproceedings{dodge2019showyourwork,670 author = {Dodge, Jesse and Gururangan, Suchin and Card, Dallas and Schwartz, Roy and Smith, Noah A.},671 title = {Show Your Work: Improved Reporting of Experimental Results},672 booktitle = {Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)},673 publisher = {Association for Computational Linguistics},674 year = {2019},675 pages = {2185--2194},676 doi = {10.18653/v1/D19-1224},677 note = {verified Crossref 2026-11-03}678}679680@misc{pineau2021reproducibility,681 author = {Pineau, Joelle and Vincent-Lamarre, Philippe and Sinha, Koustuv and Larivi{\`e}re, Vincent and Beygelzimer, Alina and d'Alch{\'e}-Buc, Florence and Fox, Emily and Larochelle, Hugo},682 title = {Improving Reproducibility in Machine Learning Research (A Report from the {NeurIPS} 2019 Reproducibility Program)},683 year = {2021},684 howpublished = {arXiv preprint arXiv:2003.12206},685 eprint = {2003.12206},686 archivePrefix = {arXiv},687 url = {https://arxiv.org/abs/2003.12206},688 note = {verified arXiv 2026-11-03}689}690691@article{robertson2009bm25,692 title = {The Probabilistic Relevance Framework: {BM25} and Beyond},693 author = {Robertson, Stephen and Zaragoza, Hugo},694 journal = {Foundations and Trends in Information Retrieval},695 volume = {3}, number = {4}, pages = {333--389}, year = {2009},696 doi = {10.1561/1500000019},697 note = {verified Crossref 2026-11-03}698}699@misc{reimers2019sbert,700 title = {Sentence-{BERT}: Sentence Embeddings using Siamese {BERT}-Networks},701 author = {Reimers, Nils and Gurevych, Iryna},702 year = {2019}, eprint = {1908.10084}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/1908.10084},703 note = {verified arXiv 2026-11-03}704}705@misc{wang2020minilm,706 title = {{MiniLM}: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers},707 author = {Wang, Wenhui and Wei, Furu and Dong, Li and Bao, Hangbo and Yang, Nan and Zhou, Ming},708 year = {2020}, eprint = {2002.10957}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2002.10957},709 note = {verified arXiv 2026-11-03}710}711@article{holm1979simple,712 title = {A Simple Sequentially Rejective Multiple Test Procedure},713 author = {Holm, Sture},714 journal = {Scandinavian Journal of Statistics},715 volume = {6}, number = {2}, pages = {65--70}, year = {1979},716 url = {https://www.jstor.org/stable/4615733},717 note = {verified JSTOR stable URL 2026-11-03 (no DOI registered)}718}719@article{cliff1993dominance,720 title = {Dominance Statistics: Ordinal Analyses to Answer Ordinal Questions},721 author = {Cliff, Norman},722 journal = {Psychological Bulletin},723 volume = {114}, number = {3}, pages = {494--509}, year = {1993},724 doi = {10.1037/0033-2909.114.3.494},725 note = {verified Crossref 2026-11-03}726}727@book{krippendorff2019content,728 title = {Content Analysis: An Introduction to Its Methodology},729 author = {Krippendorff, Klaus},730 edition = {4}, publisher = {SAGE Publications}, address = {Thousand Oaks, CA}, year = {2019},731 doi = {10.4135/9781071878781}, isbn = {9781506395661},732 note = {verified Crossref 2026-11-03}733}734