Elamur Research⌕
☰
home / papers / 2024 / Benchmarking Benchmark Leakage in Large Language Models

Benchmarking Benchmark Leakage in Large Language Models

Paper · 2024 · Ruijie Xu, Zengzhi Wang, Run-Ze Fan et al.

Summary

Large language models are often trained on undisclosed corpora that may include public benchmark data, sometimes on purpose. This inflates scores and makes comparisons between models unfair. Xu et al. propose a lightweight way to estimate such leakage without seeing the training data. Their testbed is mathematical reasoning: GSM8K and MATH, which both have train and test splits. The pipeline uses two basic language-modeling signals: Perplexity (a continuous view) and N-gram Accuracy (a discrete view). It checks how well a model predicts the original benchmark items compared with paraphrased reference versions of the same items. An unusually large advantage on the originals suggests the model saw them before. Meta-experiments support the method, and the n-gram signal works even for individual examples. Across 31 open-source LLMs, about half show signs of exposure to benchmark training data, and some show signs of test-set exposure. The authors call for explicit documentation of benchmark use through a proposed "Benchmark Transparency Card". This matters for anyone who relies on published leaderboard numbers when choosing or comparing models.

Key points

  • The study audits 31 open-source LLMs on GSM8K and MATH, including the Qwen, InternLM2, Aquila2, Yi, Baichuan, LLaMA, Gemma and Phi families. It compares train-versus-test gaps (δ train-test) in Perplexity and N-gram Accuracy.
  • The instance-level example: Qwen-1.8B correctly predicts every 5-gram in 223 GSM8K training items and 67 MATH training items. It does the same for 25 MATH test items.
  • A near-zero train-test gap is ambiguous. It can mean the model saw neither split, or that it saw both. This is a stated limitation, along with the difficulty of catching augmented or reformatted benchmark data.
  • The authors' recommendations:
    • Build benchmarks from recent text and refresh them dynamically.
    • Avoid posting raw question-answer pairs online; encrypt test sets or keep them private behind leaderboards.
    • Be cautious when sending benchmark data to proprietary model APIs.
  • Released resources: the code (GAIR-NLP/benben on GitHub), a leaderboard, model predictions, and a Hugging Face demo (GAIR/benbench).

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓Shanghai Jiao Tong UniversityShanghai · China212 works · 19,544 citations

 Fields, topics and concepts

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 18,614 worksArtificial Intelligence · 17,965 worksArts and Humanities · 17,450 worksLanguage and Linguistics · 17,296 works

🧭 Topics 1Research subjects and languages the work is about.Evaluation & benchmarks · 1,341 works

Cite

Cite as Ruijie Xu, Zengzhi Wang, Run-Ze Fan and Pengfei Liu. 2024. Benchmarking Benchmark Leakage in Large Language Models. arXiv:2404.18824.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.48550/arxiv.2404.18824 · arXiv 2404.18824

@misc{xu2024benchmarking,
  title = {{Benchmarking Benchmark Leakage in Large Language Models}},
  author = {Ruijie Xu, Zengzhi Wang, Run-Ze Fan and Pengfei Liu},
  year = {2024},
  doi = {10.48550/arxiv.2404.18824},
  eprint = {2404.18824},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2404.18824}
}

References

76 references, 44 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. 01. AI, :, Alex Young, Bei Chen, Chao Li, Chengen Huang, Ge Zhang, Guanwei Zhang, Heng Li, Jiangcheng Zhu, Jianqun Chen, Jing Chang, Kaidong Yu, Peng Liu, Qiang Liu, Shawn Yue, Senbin Yang, Shiming Yang, Tao Yu, Wen Xie, Wenhao Huang, Xiaohui Hu, Xiaoyi Ren, Xinyao Niu, Pengcheng Nie, Yuchi Xu, Yudo… — Yi: Open Foundation Models by 01.AI
  2. Anthropic. Introducing the next generation of claude \\ anthropic. https://www.anthropic.com/news/claude-3-family, Mar 2024. ↗
  3. BAAI. Aquila2. https://github.com/FlagAI-Open/Aquila2, 2023. ↗
  4. Jinze Bai, Shuai Bai, Yunfei Chu, Zeyu Cui, Kai Dang, Xiaodong Deng, Yang Fan, Wenbin Ge, Yu Han, Fei Huang, Binyuan Hui, Luo Ji, Mei Li, Junyang Lin, Runji Lin, Dayiheng Liu, Gao Liu, Chengqiang Lu, Keming Lu, Jianxin Ma, Rui Men, Xingzhang Ren, Xuancheng Ren, Chuanqi Tan, Sinan Tan, Jianhong Tu, P… — Qwen Technical Report
  5. Baichuan. Baichuan 2: Open large-scale language models. arXiv preprint arXiv:2309.10305, 2023. URL https://arxiv.org/abs/2309.10305. ↗
  6. Rishi Bommasani, Kevin Klyman, Shayne Longpre, Sayash Kapoor, Nestor Maslej, Betty Xiong, Daniel Zhang, and Percy Liang. The foundation model transparency index. CoRR, abs/2310.12941, 2023. doi: 10.48550/ARXIV.2310.12941. URL https://doi.org/10.48550/arXiv.2310.12941. ↗
  7. Tom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel M. Ziegler, Jeffrey Wu, Clemens Winter,… — Language Models are Few-Shot Learners
  8. Zheng Cai, Maosong Cao, Haojiong Chen, Kai Chen, Keyu Chen, Xin Chen, Xun Chen, Zehui Chen, Zhi Chen, Pei Chu, Xiaoyi Dong, Haodong Duan, Qi Fan, Zhaoye Fei, Yang Gao, Jiaye Ge, Chenya Gu, Yuzhe Gu, Tao Gui, Aijia Guo, Qipeng Guo, Conghui He, Yingfan Hu, Ting Huang, Tao Jiang, Penglong Jiao, Zhenjia… — InternLM2 Technical Report
  9. Nicholas Carlini, Florian Tramèr, Eric Wallace, Matthew Jagielski, Ariel Herbert-Voss, Katherine Lee, Adam Roberts, Tom B. Brown, Dawn Song, Úlfar Erlingsson, Alina Oprea, and Colin Raffel. Extracting training data from large language models. In Michael D. Bailey and Rachel Greenstadt (eds.), 30th…
  10. USENIX Association, 2021. URL https://www.usenix.org/conference/usenixsecurity21/presentation/carlini-extracting. ↗
  11. Yupeng Chang, Xu Wang, Jindong Wang, Yuan Wu, Linyi Yang, Kaijie Zhu, Hao Chen, Xiaoyuan Yi, Cunxiang Wang, Yidong Wang, Wei Ye, Yue Zhang, Yi Chang, Philip S. Yu, Qiang Yang, and Xing Xie. A survey on evaluation of large language models. ACM Trans. Intell. Syst. Technol., 15(3), mar 2024. ISSN 2157…
  12. Karl Cobbe, Vineet Kosaraju, Mohammad Bavarian, Mark Chen, Heewoo Jun, Lukasz Kaiser, Matthias Plappert, Jerry Tworek, Jacob Hilton, Reiichiro Nakano, Christopher Hesse, and John Schulman. Training verifiers to solve math word problems. CoRR, abs/2110.14168, 2021. URL https://arxiv.org/abs/2110.1416… ↗
  13. Chunyuan Deng, Yilun Zhao, Xiangru Tang, Mark Gerstein, and Arman Cohan. Investigating data contamination in modern benchmarks for large language models. CoRR, abs/2311.09783, 2023. doi: 10.48550/ARXIV.2311.09783. URL https://doi.org/10.48550/arXiv.2311.09783. ↗
  14. Jesse Dodge, Maarten Sap, Ana Marasović, William Agnew, Gabriel Ilharco, Dirk Groeneveld, Margaret Mitchell, and Matt Gardner. Documenting large webtext corpora: A case study on the colossal clean crawled corpus. In Marie-Francine Moens, Xuanjing Huang, Lucia Specia, and Scott Wen-tau Yih (eds.), P… find
  15. Run-Ze Fan, Xuefeng Li, Haoyang Zou, Junlong Li, Shwai He, Ethan Chern, Jiewen Hu, and Pengfei Liu. Reformatted alignment. arXiv preprint arXiv:2402.12219, 2024. URL https://arxiv.org/abs/2402.12219. ↗
  16. Leo Gao, Jonathan Tow, Stella Biderman, Sid Black, Anthony DiPofi, Charles Foster, Laurence Golding, Jeffrey Hsu, Kyle McDonell, Niklas Muennighoff, Jason Phang, Laria Reynolds, Eric Tang, Anish Thite, Ben Wang, Kevin Wang, and Andy Zou. A framework for few-shot language model evaluation, September… — [doi:10.5281/zenodo.5371628](https://doi.org/10.5281/zenodo.5371628) find
  17. Timnit Gebru, Jamie Morgenstern, Briana Vecchione, Jennifer Wortman Vaughan, Hanna Wallach, Hal Daumé III, and Kate Crawford. Datasheets for datasets. Commun. ACM, 64 (12):86–92, nov 2021. ISSN 0001-0782. doi: 10.1145/3458723. URL https://doi.org/10.1145/3458723. — [doi:10.1145/3458723](https://doi.org/10.1145/3458723) ↗
  18. Sebastian Gehrmann, Tosin Adewumi, Karmanya Aggarwal, Pawan Sasanka Ammanamanchi, Anuoluwapo Aremu, Antoine Bosselut, Khyathi Raghavi Chandu, Miruna-Adriana Clinciu, Dipanjan Das, Kaustubh Dhole, Wanyu Du, Esin Durmus, Ondřej Dušek, Chris Chinenye Emezue, Varun Gangal, Cristina Garbacea, Tatsunori… — The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics
  19. Shahriar Golchin and Mihai Surdeanu. Data contamination quiz: A tool to detect and estimate contamination in large language models. CoRR, abs/2311.06233, 2023. doi: 10.48550/ARXIV.2311.06233. URL https://doi.org/10.48550/arXiv.2311.06233. ↗
  20. Diego Granziol, Stefan Zohren, and Stephen Roberts. Learning rates as a function of batch size: A random matrix theory approach to neural network training. J. Mach. Learn. Res., 23:173:1–173:65, 2022. URL http://jmlr.org/papers/v23/20-1258.html. ↗
  21. Dan Hendrycks, Collin Burns, Steven Basart, Andy Zou, Mantas Mazeika, Dawn Song, and Jacob Steinhardt. Measuring massive multitask language understanding. In 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021.
  22. OpenReview.net, 2021a. URL https://openreview.net/forum?id=d7KBjmI3GmQ. ↗
  23. Dan Hendrycks, Collin Burns, Saurav Kadavath, Akul Arora, Steven Basart, Eric Tang, Dawn Song, and Jacob Steinhardt. Measuring mathematical problem solving with the MATH dataset. In Joaquin Vanschoren and Sai-Kit Yeung (eds.), Proceedings of the Neural Information Processing Systems Track on Dataset…
  24. Shengding Hu, Yuge Tu, Xu Han, Chaoqun He, Ganqu Cui, Xiang Long, Zhi Zheng, Yewei Fang, Yuxiang Huang, Weilin Zhao, Xinrong Zhang, Zhen Leng Thai, Kaihuo Zhang, Chongyi Wang, Yuan Yao, Chenyang Zhao, Jie Zhou, Jie Cai, Zhongwu Zhai, Ning Ding, Chaochao Jia, Guoyang Zeng, Dahai Li, Zhiyuan Liu, and… — MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies
  25. Yuzhen Huang, Yuzhuo Bai, Zhihao Zhu, Junlei Zhang, Jinghan Zhang, Tangjun Su, Junteng Liu, Chuancheng Lv, Yikai Zhang, Jiayi Lei, Yao Fu, Maosong Sun, and Junxian He. C-eval: A multi-level multi-discipline chinese evaluation suite for foundation models. In Advances in Neural Information Processing…
  26. Alon Jacovi, Avi Caciularu, Omer Goldman, and Yoav Goldberg. Stop uploading test data in plain text: Practical strategies for mitigating data contamination by evaluation benchmarks. In Conference on Empirical Methods in Natural Language Processing, 2023. URL https://api.semanticscholar.org/CorpusID:… ↗
  27. Naman Jain, King Han, Alex Gu, Wen-Ding Li, Fanjia Yan, Tianjun Zhang, Sida Wang, Armando Solar-Lezama, Koushik Sen, and Ion Stoica. Livecodebench: Holistic and contamination free evaluation of large language models for code. arXiv preprint arXiv:2403.07974, 2024.
  28. Fred Jelinek, Robert L Mercer, Lalit R Bahl, and James K Baker. Perplexity—a measure of the difficulty of speech recognition tasks. The Journal of the Acoustical Society of America, 62 (S1):S63–S63, 1977. find
  29. Albert Q. Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, Lélio Renard Lavaud, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Thibaut Lavril, Thomas Wang, Timothée Lacroi… find
  30. Minhao Jiang, Ken Ziyu Liu, Ming Zhong, Rylan Schaeffer, Siru Ouyang, Jiawei Han, and Sanmi Koyejo. Investigating data contamination for pre-training language models. CoRR, abs/2401.06059, 2024. doi: 10.48550/ARXIV.2401.06059. URL https://doi.org/10.48550/arXiv.2401.06059. — [doi:10.48550/arxiv.2401.06059](https://doi.org/10.48550/arxiv.2401.06059) ↗
  31. Haonan Li, Yixuan Zhang, Fajri Koto, Yifei Yang, Hai Zhao, Yeyun Gong, Nan Duan, and Timothy Baldwin. CMMLU: measuring massive multitask language understanding in chinese. CoRR, abs/2306.09212, 2023a. doi: 10.48550/ARXIV.2306.09212. URL https://doi.org/10.48550/arXiv.2306.09212. ↗
  32. Yuan-Fang Li, Sébastien Bubeck, Ronen Eldan, Allison Del Giorno, Suriya Gunasekar, and Yin Tat Lee. Textbooks are all you need ii: phi-1.5 technical report. ArXiv, abs/2309.05463, 2023b. URL https://api.semanticscholar.org/CorpusID:261696657. ↗
  33. Yucheng Li. Estimating contamination via perplexity: Quantifying memorisation in language model evaluation. CoRR, abs/2309.10677, 2023a. doi: 10.48550/ARXIV.2309.10677. URL https://doi.org/10.48550/arXiv.2309.10677. — [doi:10.48550/arxiv.2309.10677](https://doi.org/10.48550/arxiv.2309.10677) ↗
  34. Yucheng Li. An open source data contamination report for llama series models. CoRR, abs/2310.17589, 2023b. URL https://doi.org/10.48550/arXiv.2310.17589. ↗
  35. Percy Liang, Rishi Bommasani, Tony Lee, Dimitris Tsipras, Dilara Soylu, Michihiro Yasunaga, Yian Zhang, Deepak Narayanan, Yuhuai Wu, Ananya Kumar, Benjamin Newman, Binhang Yuan, Bobby Yan, Ce Zhang, Christian Alexander Cosgrove, Christopher D Manning, Christopher Re, Diana Acosta-Navas, Drew Arad Hu… find
  36. Chin-Yew Lin. ROUGE: A package for automatic evaluation of summaries. In Text Summarization Branches Out, pp. 74–81, Barcelona, Spain, July 2004. Association for Computational Linguistics. URL https://aclanthology.org/W04-1013. ↗
  37. Inbal Magar and Roy Schwartz. Data contamination: From memorization to exploitation. In Smaranda Muresan, Preslav Nakov, and Aline Villavicencio (eds.), Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), ACL 2022, Dublin, Ireland, May 22… find
  38. Mitch Marcus, Beatrice Santorini, and Mary Ann Marcinkiewicz. Building a large annotated corpus of english: The penn treebank. Computational Linguistics, 19(2):313–330, 1993.
  39. Gemma Team Thomas Mesnard, Cassidy Hardin, Robert Dadashi, Surya Bhupatiraju, Shreya Pathak, L. Sifre, Morgane Riviere, Mihir Kale, J Christopher Love, Pouya Dehghani Tafti, L’eonard Hussenot, Aakanksha Chowdhery, Adam Roberts, Aditya Barua, Alex Botev, Alex Castro-Ros, Ambrose Slone, Am’elie H’elio… find
  40. Meta. Introducing meta llama 3: The most capable openly available llm to date. https://ai.meta.com/blog/meta-llama-3/, April 2024. ↗
  41. Microsoft. Phi-2: The surprising power of small language models - microsoft research. https://www.microsoft.com/en-us/research/blog/phi-2-the-surprising-power-of-small-language-models/, Dec 2023. ↗
  42. Margaret Mitchell, Simone Wu, Andrew Zaldivar, Parker Barnes, Lucy Vasserman, Ben Hutchinson, Elena Spitzer, Inioluwa Deborah Raji, and Timnit Gebru. Model cards for model reporting. In Proceedings of the Conference on Fairness, Accountability, and Transparency, FAT* ’19, pp. 220–229, New York, NY,… find
  43. Arindam Mitra, Luciano Del Corro, Shweti Mahajan, Andrés Codas, Clarisse Simões, Sahaj Agrawal, Xuxi Chen, Anastasia Razdaibiedina, Erik Jones, Kriti Aggarwal, Hamid Palangi, Guoqing Zheng, Corby Rosset, Hamed Khanpour, and Ahmed Awadallah. Orca 2: Teaching small language models how to reason. CoR…
  44. OpenAI. GPT-4 technical report. CoRR, abs/2303.08774, 2023. doi: 10.48550/ARXIV.2303.08774. URL https://doi.org/10.48550/arXiv.2303.08774. ↗
  45. Yonatan Oren, Nicole Meister, Niladri S. Chatterji, Faisal Ladhak, and Tatsunori B. Hashimoto. Proving test set contamination in black box language models. CoRR, abs/2310.17623, 2023. doi: 10.48550/ARXIV.2310.17623. URL https://doi.org/10.48550/arXiv.2310.17623. ↗
  46. Jupinder Parmar, Shrimai Prabhumoye, Joseph Jennings, Mostofa Patwary, Sandeep Subramanian, Dan Su, Chen Zhu, Deepak Narayanan, Aastha Jhunjhunwala, Ayush Dattagupta, Vibhu Jawa, Jiwei Liu, Ameya Mahabaleshwarkar, Osvald Nitski, Annika Brundyn, James Maki, Miguel Martinez, Jiaxuan You, John Kamalu,… — Nemotron-4 15B Technical Report
  47. Keiran Paster. Testing language models on a held-out high school national finals exam. https://huggingface.co/datasets/keirp/hungarian national hs finals exam, 2023. ↗
  48. Mahima Pushkarna, Andrew Zaldivar, and Oddur Kjartansson. Data cards: Purposeful and transparent dataset documentation for responsible ai. In Proceedings of the 2022 ACM Conference on Fairness, Accountability, and Transparency, FAccT ’22, pp. 1776–1826, New York, NY, USA, 2022. Association for Compu… — [doi:10.1145/3531146.3533231](https://doi.org/10.1145/3531146.3533231) find
  49. Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, Ilya Sutskever, et al. Language models are unsupervised multitask learners. OpenAI blog, 1(8):9, 2019. find
  50. Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J. Liu. Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res., 21(1), jan 2020. ISSN 1532-4435.
  51. Pranav Rajpurkar, Jian Zhang, Konstantin Lopyrev, and Percy Liang. SQuAD: 100,000+ questions for machine comprehension of text. In Jian Su, Kevin Duh, and Xavier Carreras (eds.), Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pp. 2383–2392, Austin, Texas, Nov…
  52. Zhihong Shao, Peiyi Wang, Qihao Zhu, Runxin Xu, Junxiao Song, Mingchuan Zhang, Y. K. Li, Y. Wu, and Daya Guo. Deepseekmath: Pushing the limits of mathematical reasoning in open language models. CoRR, abs/2402.03300, 2024. doi: 10.48550/ARXIV.2402.03300. URL https://doi.org/10.48550/arXiv.2402.03300. ↗
  53. Weijia Shi, Anirudh Ajith, Mengzhou Xia, Yangsibo Huang, Daogao Liu, Terra Blevins, Danqi Chen, and Luke Zettlemoyer. Detecting pretraining data from large language models. In The Twelfth International Conference on Learning Representations, 2024. URL https://openreview.net/forum?id=zWqr3MQuNs. ↗
  54. Richard Socher, Alex Perelygin, Jean Wu, Jason Chuang, Christopher D. Manning, Andrew Ng, and Christopher Potts. Recursive deep models for semantic compositionality over a sentiment treebank. In David Yarowsky, Timothy Baldwin, Anna Korhonen, Karen Livescu, and Steven Bethard (eds.), Proceedings of…
  55. Aarohi Srivastava, Abhinav Rastogi, Abhishek Rao, Abu Awal Md Shoeb, Abubakar Abid, Adam Fisch, Adam R. Brown, Adam Santoro, Aditya Gupta, Adrià Garriga-Alonso, Agnieszka Kluska, Aitor Lewkowycz, Akshat Agarwal, Alethea Power, Alex Ray, Alex Warstadt, Alexander W. Kocurek, Ali Safaya, Ali Tazarv, A… — Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
  56. InternLM Team. Internlm: A multilingual language model with progressively enhanced capabilities. https://github.com/InternLM/InternLM-techreport, 2023. ↗
  57. Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timothée Lacroix, Baptiste Rozière, Naman Goyal, Eric Hambro, Faisal Azhar, Aurelien Rodriguez, Armand Joulin, Edouard Grave, and Guillaume Lample. Llama: Open and efficient foundation language models. ArXiv, abs/2…
  58. Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, Dan Bikel, Lukas Blecher, Cristian Canton-Ferrer, Moya Chen, Guillem Cucurull, David Esiobu, Jude Fernandes, Jeremy Fu, Wenyin Fu, Brian Fuller,… — Llama 2: Open Foundation and Fine-Tuned Chat Models
  59. Hugo Touvron, Louis Martin, Kevin R. Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, Daniel M. Bikel, Lukas Blecher, Cristian Cantón Ferrer, Moya Chen, Guillem Cucurull, David Esiobu, Jude Fernandes, Jeremy Fu, Wenyin Fu, Bri… — Llama 2: Open Foundation and Fine-Tuned Chat Models
  60. Alex Wang, Amanpreet Singh, Julian Michael, Felix Hill, Omer Levy, and Samuel Bowman. GLUE: A multi-task benchmark and analysis platform for natural language understanding. In Tal Linzen, Grzegorz Chrupała, and Afra Alishahi (eds.), Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and I…
  61. Alex Wang, Yada Pruksachatkun, Nikita Nangia, Amanpreet Singh, Julian Michael, Felix Hill, Omer Levy, and Samuel R. Bowman. Superglue: A stickier benchmark for general-purpose language understanding systems. In Hanna M. Wallach, Hugo Larochelle, Alina Beygelzimer, Florence d’Alché-Buc, Emily B. Fox…
  62. Guan Wang, Sijie Cheng, Xianyuan Zhan, Xiangang Li, Sen Song, and Yang Liu. Openchat: Advancing open-source language models with mixed-quality data. arXiv preprint arXiv:2309.11235, 2023. URL https://arxiv.org/abs/2309.11235. ↗
  63. Jason Wei, Maarten Bosma, Vincent Y. Zhao, Kelvin Guu, Adams Wei Yu, Brian Lester, Nan Du, Andrew M. Dai, and Quoc V. Le. Finetuned language models are zero-shot learners. In The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25-29, 2022.
  64. OpenReview.net, 2022. URL https://openreview.net/forum?id=gEZrGCozdqR. ↗
  65. Tianwen Wei, Liang Zhao, Lichang Zhang, Bo Zhu, Lijie Wang, Haihua Yang, Biye Li, Cheng Cheng, Weiwei Lü, Rui Hu, Chenxia Li, Liu Yang, Xilin Luo, Xuejie Wu, Lunan Liu, Wenjun Cheng, Peng Cheng, Jianhao Zhang, Xiaoyu Zhang, Lei Lin, Xiaokun Wang, Yutuan Ma, Chuanhai Dong, Yanqi Sun, Yifu Chen, Yong… — Skywork: A More Open Bilingual Foundation Model
  66. Shuo Yang, Wei-Lin Chiang, Lianmin Zheng, Joseph E. Gonzalez, and Ion Stoica. Rethinking benchmark and contamination for language models with rephrased samples, 2023.
  67. Longhui Yu, Weisen Jiang, Han Shi, Jincheng YU, Zhengying Liu, Yu Zhang, James Kwok, Zhenguo Li, Adrian Weller, and Weiyang Liu. Metamath: Bootstrap your own mathematical questions for large language models. In The Twelfth International Conference on Learning Representations, 2024. URL https://openr…
  68. Aohan Zeng, Xiao Liu, Zhengxiao Du, Zihan Wang, Hanyu Lai, Ming Ding, Zhuoyi Yang, Yifan Xu, Wendi Zheng, Xiao Xia, Weng Lam Tam, Zixuan Ma, Yufei Xue, Jidong Zhai, Wenguang Chen, Zhiyuan Liu, Peng Zhang, Yuxiao Dong, and Jie Tang. GLM-130B: an open bilingual pre-trained model. In The Eleventh Inter…
  69. OpenReview.net, 2023. URL https://openreview.net/pdf?id=-Aw0rrrPUF. ↗
  70. Lianmin Zheng, Wei-Lin Chiang, Ying Sheng, Siyuan Zhuang, Zhanghao Wu, Yonghao Zhuang, Zi Lin, Zhuohan Li, Dacheng Li, Eric P. Xing, Hao Zhang, Joseph E. Gonzalez, and Ion Stoica. Judging llm-as-a-judge with mt-bench and chatbot arena. CoRR, abs/2306.05685, 2023. doi: 10.48550/ARXIV.2306.05685. URL…
  71. ZhipuAI. Chatglm-6b: An open bilingual dialogue language model. https://github.com/THUDM/ChatGLM-6B, 2023. ↗
  72. Wanjun Zhong, Ruixiang Cui, Yiduo Guo, Yaobo Liang, Shuai Lu, Yanlin Wang, Amin Saied, Weizhu Chen, and Nan Duan. Agieval: A human-centric benchmark for evaluating foundation models. CoRR, abs/2304.06364, 2023. doi: 10.48550/ARXIV.2304.06364. URL https://doi.org/10.48550/arXiv.2304.06364. ↗
  73. Kun Zhou, Yutao Zhu, Zhipeng Chen, Wentong Chen, Wayne Xin Zhao, Xu Chen, Yankai Lin, Ji-Rong Wen, and Jiawei Han. Don’t make your LLM an evaluation benchmark cheater. CoRR, abs/2311.01964, 2023. doi: 10.48550/ARXIV.2311.01964. URL https://doi.org/10.48550/arXiv.2311.01964. ↗
  74. Kaijie Zhu, Jiaao Chen, Jindong Wang, Neil Zhenqiang Gong, Diyi Yang, and Xing Xie. Dyval: Dynamic evaluation of large language models for reasoning tasks. arXiv preprint arXiv:2309.17167, 2023a. URL https://arxiv.org/abs/2309.17167. ↗
  75. Kaijie Zhu, Jindong Wang, Qinlin Zhao, Ruochen Xu, and Xing Xie. Dyval 2: Dynamic evaluation of large language models by meta probing agents. arXiv preprint arXiv:2402.14865, 2024. URL https://arxiv.org/abs/2402.14865. ↗
  76. Wenhong Zhu, Hongkun Hao, Zhiwei He, Yunze Song, Yumeng Zhang, Hanxu Hu, Yiran Wei, Rui Wang, and Hongyuan Lu. CLEAN-EVAL: clean evaluation on contaminated large language models. CoRR, abs/2311.09154, 2023b. doi: 10.48550/ARXIV.2311.09154. URL https://doi.org/10.48550/arXiv.2311.09154. ↗

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/xu-2024-benchmarking-benchmark-leakage-large-language/