Elamur Research⌕
☰
home / papers / 2024 / Observational Scaling Laws and the Predictability of Language Model Performance

Observational Scaling Laws and the Predictability of Language Model Performance

Summary

Classical scaling laws relate the training compute budget to the quality of a language model. Building them requires training a series of models of different sizes oneself, which few can afford. The authors propose an "observational" approach: instead of training, they take about a hundred open models and their results on standard benchmarks, notably the Open LLM Leaderboard. Different model families convert FLOPs into capabilities with differing efficiency. The researchers therefore use a low-rank decomposition (principal components) to extract a few generalized capability measures. Within a single family, these measures depend linearly on the logarithm of compute, and more complex metrics are well expressed in terms of them. This makes it possible to predict "emergent" phenomena (which turn out to be a smooth sigmoid), the performance of models as agents, and the benefit of Chain-of-Thought and Self-Consistency, even when only weaker models are available for fitting. The result is an inexpensive tool for checking whether the advantage of a new method or benchmark will persist as models scale up.

Key points

  • Data: about 100 public language models from various families (LLaMA, OPT, StarCoder, Phi, DeepSeek-Coder, etc.). A few principal components (PCs) explain the results on standard benchmarks, and within a family they align with log-FLOPs with R² > 0.9.
  • Some "emergent" capabilities change smoothly and are predictable from models smaller than Llama-2 7B.
  • The agentic performance of GPT-4 on AgentBench and AgentBoard was accurately predicted using only models weaker than GPT-3.5. Programming skills turned out to be the main factor in agentic results.
  • For such an analysis, it suffices to evaluate 10–20 models from a few representative families. The authors preregistered their predictions and update them on new models.
  • Phi deviates substantially from the general pattern in compute efficiency and benefits from CoT earlier than other models, but then improves more slowly. This underscores the role of pretraining data. Limitations of the method: it is not suitable for optimizing pretraining and does not account for benchmark contamination. The paper was presented at NeurIPS 2024.

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

Fields: AI & machine learning

Topics Language models & pretraining Evaluation & benchmarks

Cite

Cite as Yangjun Ruan, Chris J. Maddison and Tatsunori Hashimoto. 2024. Observational Scaling Laws and the Predictability of Language Model Performance. arXiv:2405.10938.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.48550/arxiv.2405.10938 · arXiv 2405.10938

@misc{ruan2024observational,
  title = {{Observational Scaling Laws and the Predictability of Language Model Performance}},
  author = {Yangjun Ruan, Chris J. Maddison and Tatsunori Hashimoto},
  year = {2024},
  doi = {10.48550/arxiv.2405.10938},
  eprint = {2405.10938},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2405.10938}
}

References

109 references, 43 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Samira Abnar, Mostafa Dehghani, Behnam Neyshabur, and Hanie Sedghi. Exploring the limits of large scale pre-training. arXiv preprint arXiv:2110.02095, 2021. — [arXiv:2110.02095](https://arxiv.org/abs/2110.02095) find
  2. Ebtesam Almazrouei, Hamza Alobeidli, Abdulaziz Alshamsi, Alessandro Cappelli, Ruxandra Cojocaru, Mérouane Debbah, Étienne Goffinet, Daniel Hesslow, Julien Launay, Quentin Malartic, et al. The falcon series of open language models. arXiv preprint arXiv:2311.16867, 2023. our card
  3. Anthropic. Claude 2, July 2023. URL https://www.anthropic.com/index/claude-2. Accessed: 2023-08-31. ↗
  4. Usman Anwar, Abulhair Saparov, Javier Rando, Daniel Paleka, Miles Turpin, Peter Hase, Ekdeep Singh Lubana, Erik Jenner, Stephen Casper, Oliver Sourbut, et al. Foundational challenges in assuring alignment and safety of large language models. arXiv preprint arXiv:2404.09932, 2024. find
  5. Sanjeev Arora and Anirudh Goyal. A theory for emergence of complex skills in language models. arXiv preprint arXiv:2307.15936, 2023. — [arXiv:2307.15936](https://arxiv.org/abs/2307.15936) find
  6. Yasaman Bahri, Ethan Dyer, Jared Kaplan, Jaehoon Lee, and Utkarsh Sharma. Explaining neural scaling laws. arXiv preprint arXiv:2102.06701, 2021. — [arXiv:2102.06701](https://arxiv.org/abs/2102.06701) find
  7. Jinze Bai, Shuai Bai, Yunfei Chu, Zeyu Cui, Kai Dang, Xiaodong Deng, Yang Fan, Wenbin Ge, Yu Han, Fei Huang, et al. Qwen technical report. arXiv preprint arXiv:2309.16609, 2023. our card
  8. Edward Beeching, Clémentine Fourrier, Nathan Habib, Sheon Han, Nathan Lambert, Nazneen Rajani, Omar Sanseviero, Lewis Tunstall, and Thomas Wolf. Open llm leaderboard. https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard, 2023. ↗
  9. Xiao Bi, Deli Chen, Guanting Chen, Shanhuang Chen, Damai Dai, Chengqi Deng, Honghui Ding, Kai Dong, Qiushi Du, Zhe Fu, et al. Deepseek llm: Scaling open-source language models with longtermism. arXiv preprint arXiv:2401.02954, 2024. find
  10. Stella Biderman, Hailey Schoelkopf, Quentin Gregory Anthony, Herbie Bradley, Kyle O’Brien, Eric Hallahan, Mohammad Aflah Khan, Shivanshu Purohit, USVSN Sai Prashanth, Edward Raff, et al. Pythia: A suite for analyzing large language models across training and scaling. In International Conference on M… find
  11. Sid Black, Stella Biderman, Eric Hallahan, Quentin Anthony, Leo Gao, Laurence Golding, Horace He, Connor Leahy, Kyle McDonell, Jason Phang, et al. Gpt-neox-20b: An open-source autoregressive language model. arXiv preprint arXiv:2204.06745, 2022. our card
  12. Bradley Brown, Jordan Juravsky, Ryan Ehrlich, Ronald Clark, Quoc V Le, Christopher Ré, and Azalia Mirhoseini. Large language monkeys: Scaling inference compute with repeated sampling. arXiv preprint arXiv:2407.21787, 2024. our card
  13. Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al. Language models are few-shot learners. Advances in neural information processing systems, 33:1877– 1901, 2020. our card
  14. Ryan Burnell, Han Hao, Andrew RA Conway, and Jose Hernandez Orallo. Revealing the structure of language model capabilities. arXiv preprint arXiv:2306.10062, 2023. find
  15. Ethan Caballero, Kshitij Gupta, Irina Rish, and David Krueger. Broken neural scaling laws. arXiv preprint arXiv:2210.14891, 2022. — [arXiv:2210.14891](https://arxiv.org/abs/2210.14891) find
  16. Mark Chen, Jerry Tworek, Heewoo Jun, Qiming Yuan, Henrique Ponde de Oliveira Pinto, Jared Kaplan, Harri Edwards, Yuri Burda, Nicholas Joseph, Greg Brockman, et al. Evaluating large language models trained on code. arXiv preprint arXiv:2107.03374, 2021. our card
  17. Wei-Lin Chiang, Zhuohan Li, Zi Lin, Ying Sheng, Zhanghao Wu, Hao Zhang, Lianmin Zheng, Siyuan Zhuang, Yonghao Zhuang, Joseph E. Gonzalez, Ion Stoica, and Eric P. Xing. Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality. https://lmsys.org/ blog/2023-03-30-vicuna/, March 2023. A… ↗
  18. Wei-Lin Chiang, Lianmin Zheng, Ying Sheng, Anastasios Nikolas Angelopoulos, Tianle Li, Dacheng Li, Hao Zhang, Banghua Zhu, Michael Jordan, Joseph E. Gonzalez, and Ion Stoica. Chatbot arena: An open platform for evaluating llms by human preference, 2024. find
  19. Peter Clark, Isaac Cowhey, Oren Etzioni, Tushar Khot, Ashish Sabharwal, Carissa Schoenick, and Oyvind Tafjord. Think you have solved question answering? try arc, the ai2 reasoning challenge. arXiv preprint arXiv:1803.05457, 2018. find
  20. Karl Cobbe, Vineet Kosaraju, Mohammad Bavarian, Mark Chen, Heewoo Jun, Lukasz Kaiser, Matthias Plappert, Jerry Tworek, Jacob Hilton, Reiichiro Nakano, et al. Training verifiers to solve math word problems. arXiv preprint arXiv:2110.14168, 2021. Dolly: The first open commercially viable instruction-[… our card
  21. Tim Dettmers, Artidoro Pagnoni, Ari Holtzman, and Luke Zettlemoyer. Qlora: Efficient finetuning of quantized llms. Advances in Neural Information Processing Systems, 36, 2023. find
  22. Zhengxiao Du, Aohan Zeng, Yuxiao Dong, and Jie Tang. Understanding emergent abilities of language models from the loss perspective. arXiv preprint arXiv:2403.15796, 2024. — [arXiv:2403.15796](https://arxiv.org/abs/2403.15796) find
  23. Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Amy Yang, Angela Fan, et al. The llama 3 herd of models. arXiv preprint arXiv:2407.21783, 2024. find
  24. Lukas Finnveden. Extrapolating gpt-n performance. https://www.lesswrong.com/posts/ k2SNji3jXaLGhBeYP/extrapolating-gpt-n-performance, 2020. Accessed: 2024-05-07. ↗
  25. Samir Yitzhak Gadre, Georgios Smyrnis, Vaishaal Shankar, Suchin Gururangan, Mitchell Wortsman, Rulin Shao, Jean Mercat, Alex Fang, Jeffrey Li, Sedrick Keh, et al. Language models scale reliably with over-training and on downstream tasks. arXiv preprint arXiv:2403.08540, 2024. find
  26. Deep Ganguli, Danny Hernandez, Liane Lovitt, Amanda Askell, Yuntao Bai, Anna Chen, Tom Conerly, Nova Dassarma, Dawn Drain, Nelson Elhage, et al. Predictability and surprise in large generative models. In Proceedings of the 2022 ACM Conference on Fairness, Accountability, and Transparency, pages 1747… find
  27. Leo Gao, Jonathan Tow, Baber Abbasi, Stella Biderman, Sid Black, Anthony DiPofi, Charles Foster, Laurence Golding, Jeffrey Hsu, Alain Le Noac’h, Haonan Li, Kyle McDonell, Niklas Muennighoff, Chris Ociepa, Jason Phang, Laria Reynolds, Hailey Schoelkopf, Aviya Skowron, Lintang Sutawika, Eric Tang, Ani… find
  28. Xinyang Geng, Arnav Gudibande, Hao Liu, Eric Wallace, Pieter Abbeel, Sergey Levine, and Dawn Song. Koala: A dialogue model for academic research. Blog post, April 2023. URL https://bair.berkeley.edu/blog/2023/04/03/koala/. ↗
  29. Behrooz Ghorbani, Orhan Firat, Markus Freitag, Ankur Bapna, Maxim Krikun, Xavier Garcia, Ciprian Chelba, and Colin Cherry. Scaling laws for neural machine translation. arXiv preprint arXiv:2109.07740, 2021. — [arXiv:2109.07740](https://arxiv.org/abs/2109.07740) find
  30. Daya Guo, Qihao Zhu, Dejian Yang, Zhenda Xie, Kai Dong, Wentao Zhang, Guanting Chen, Xiao Bi, Y Wu, YK Li, et al. Deepseek-coder: When the large language model meets programming–the rise of code intelligence. arXiv preprint arXiv:2401.14196, 2024. find
  31. Dan Hendrycks, Collin Burns, Steven Basart, Andy Zou, Mantas Mazeika, Dawn Song, and Jacob Steinhardt. Measuring massive multitask language understanding. arXiv preprint arXiv:2009.03300, 2020. our card
  32. 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. arXiv preprint arXiv:2103.03874, 2021. our card
  33. Tom Henighan, Jared Kaplan, Mor Katz, Mark Chen, Christopher Hesse, Jacob Jackson, Heewoo Jun, Tom B Brown, Prafulla Dhariwal, Scott Gray, et al. Scaling laws for autoregressive generative modeling. arXiv preprint arXiv:2010.14701, 2020. our card
  34. Danny Hernandez, Jared Kaplan, Tom Henighan, and Sam McCandlish. Scaling laws for transfer. arXiv preprint arXiv:2102.01293, 2021. our card
  35. Joel Hestness, Sharan Narang, Newsha Ardalani, Gregory Diamos, Heewoo Jun, Hassan Kianinejad, Md Mostofa Ali Patwary, Yang Yang, and Yanqi Zhou. Deep learning scaling is predictable, empirically. arXiv preprint arXiv:1712.00409, 2017. our card
  36. Jordan Hoffmann, Sebastian Borgeaud, Arthur Mensch, Elena Buchatskaya, Trevor Cai, Eliza Rutherford, Diego de Las Casas, Lisa Anne Hendricks, Johannes Welbl, Aidan Clark, et al. Training compute-optimal large language models. arXiv preprint arXiv:2203.15556, 2022. our card
  37. Shengding Hu, Xin Liu, Xu Han, Xinrong Zhang, Chaoqun He, Weilin Zhao, Yankai Lin, Ning Ding, Zebin Ou, Guoyang Zeng, Zhiyuan Liu, and Maosong Sun. Predicting emergent abilities with infinite resolution evaluation. In The Twelfth International Conference on Learning Representations, 2024. URL https:… find
  38. Yuzhen Huang, Jinghan Zhang, Zifei Shan, and Junxian He. Compression represents intelligence linearly. arXiv preprint arXiv:2404.09937, 2024. — [arXiv:2404.09937](https://arxiv.org/abs/2404.09937) find
  39. David Ilić. Unveiling the general intelligence factor in language models: A psychometric approach. arXiv preprint arXiv:2310.11616, 2023. — [arXiv:2310.11616](https://arxiv.org/abs/2310.11616) find
  40. Albert Q Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, et al. Mistral 7b. arXiv preprint arXiv:2310.06825, 2023. find
  41. Albert Q Jiang, Alexandre Sablayrolles, Antoine Roux, Arthur Mensch, Blanche Savary, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Emma Bou Hanna, Florian Bressand, et al. Mixtral of experts. arXiv preprint arXiv:2401.04088, 2024. find
  42. Carlos E Jimenez, John Yang, Alexander Wettig, Shunyu Yao, Kexin Pei, Ofir Press, and Karthik R Narasimhan. Swe-bench: Can language models resolve real-world github issues? In The Twelfth International Conference on Learning Representations, 2023. our card
  43. Jared Kaplan, Sam McCandlish, Tom Henighan, Tom B Brown, Benjamin Chess, Rewon Child, Scott Gray, Alec Radford, Jeffrey Wu, and Dario Amodei. Scaling laws for neural language models. arXiv preprint arXiv:2001.08361, 2020. our card
  44. Woosuk Kwon, Zhuohan Li, Siyuan Zhuang, Ying Sheng, Lianmin Zheng, Cody Hao Yu, Joseph E. Gonzalez, Hao Zhang, and Ion Stoica. Efficient memory management for large language model serving with pagedattention. In Proceedings of the ACM SIGOPS 29th Symposium on Operating Systems Principles, 2023. our card
  45. Cognition Labs. Introducing devin, the first ai software engineer, March 2024. URL https://www.cognition-labs.com/introducing-devin. Accessed: 2023-05-03. ↗
  46. LAION. Open assistant. https://projects.laion.ai/Open-Assistant/, 2023. Accessed: 2024-05-13. ↗
  47. Raymond Li, Loubna Ben Allal, Yangtian Zi, Niklas Muennighoff, Denis Kocetkov, Chenghao Mou, Marc Marone, Christopher Akiki, Jia Li, Jenny Chim, et al. Starcoder: may the source be with you! arXiv preprint arXiv:2305.06161, 2023. find
  48. Xuechen Li, Tianyi Zhang, Yann Dubois, Rohan Taori, Ishaan Gulrajani, Carlos Guestrin, Percy Liang, and Tatsunori B. Hashimoto. Alpacaeval: An automatic evaluator of instruction-following models. https://github.com/tatsu-lab/alpaca_eval, 2023. ↗
  49. Yuanzhi Li, Sébastien Bubeck, Ronen Eldan, Allie Del Giorno, Suriya Gunasekar, and Yin Tat Lee. Textbooks are all you need ii: phi-1.5 technical report. arXiv preprint arXiv:2309.05463, 2023. our card
  50. Percy Liang, Rishi Bommasani, Tony Lee, Dimitris Tsipras, Dilara Soylu, Michihiro Yasunaga, Yian Zhang, Deepak Narayanan, Yuhuai Wu, Ananya Kumar, et al. Holistic evaluation of language models. arXiv preprint arXiv:2211.09110, 2022. find
  51. Opher Lieber, Barak Lenz, Hofit Bata, Gal Cohen, Jhonathan Osin, Itay Dalmedigos, Erez Safahi, Shaked Meirom, Yonatan Belinkov, Shai Shalev-Shwartz, et al. Jamba: A hybrid transformer-mamba language model. arXiv preprint arXiv:2403.19887, 2024. find
  52. Stephanie Lin, Jacob Hilton, and Owain Evans. Truthfulqa: Measuring how models mimic human falsehoods. arXiv preprint arXiv:2109.07958, 2021. our card
  53. Xi Victoria Lin, Todor Mihaylov, Mikel Artetxe, Tianlu Wang, Shuohui Chen, Daniel Simig, Myle Ott, Naman Goyal, Shruti Bhosale, Jingfei Du, et al. Few-shot learning with multilingual language models. arXiv preprint arXiv:2112.10668, 2021. our card
  54. Jiawei Liu, Chunqiu Steven Xia, Yuyao Wang, and Lingming Zhang. Is your code generated by chatGPT really correct? rigorous evaluation of large language models for code generation. In Thirty-seventh Conference on Neural Information Processing Systems, 2023. URL https://openreview.net/forum?id=1qvx61… ↗ our card
  55. Nelson F Liu, Tony Lee, Robin Jia, and Percy Liang. Do question answering modeling improvements hold across benchmarks? arXiv preprint arXiv:2102.01065, 2021. find
  56. Xiao Liu, Hao Yu, Hanchen Zhang, Yifan Xu, Xuanyu Lei, Hanyu Lai, Yu Gu, Hangliang Ding, Kaiwen Men, Kejuan Yang, et al. Agentbench: Evaluating llms as agents. In The Twelfth International Conference on Learning Representations, 2023. our card
  57. Frederic M Lord. Applications of item response theory to practical testing problems. Routledge, 2012. find
  58. Anton Lozhkov, Raymond Li, Loubna Ben Allal, Federico Cassano, Joel Lamy-Poirier, Nouamane Tazi, Ao Tang, Dmytro Pykhtar, Jiawei Liu, Yuxiang Wei, et al. Starcoder 2 and the stack v2: The next generation. arXiv preprint arXiv:2402.19173, 2024. find
  59. Sheng Lu, Irina Bigoulaeva, Rachneet Sachdeva, Harish Tayyar Madabushi, and Iryna Gurevych. Are emergent abilities in large language models just in-context learning? arXiv preprint arXiv:2309.01809, 2023. find
  60. Chang Ma, Junlei Zhang, Zhihao Zhu, Cheng Yang, Yujiu Yang, Yaohui Jin, Zhenzhong Lan, Lingpeng Kong, and Junxian He. Agentboard: An analytical evaluation board of multi-turn llm agents. arXiv preprint arXiv:2401.13178, 2024. find
  61. Grégoire Mialon, Clémentine Fourrier, Craig Swift, Thomas Wolf, Yann LeCun, and Thomas Scialom. Gaia: a benchmark for general ai assistants. arXiv preprint arXiv:2311.12983, 2023. our card
  62. John P Miller, Rohan Taori, Aditi Raghunathan, Shiori Sagawa, Pang Wei Koh, Vaishaal Shankar, Percy Liang, Yair Carmon, and Ludwig Schmidt. Accuracy on the line: on the strong correlation between out-of-distribution and in-distribution generalization. In International conference on machine learning,… find
  63. Niklas Muennighoff, Thomas Wang, Lintang Sutawika, Adam Roberts, Stella Biderman, Teven Le Scao, M Saiful Bari, Sheng Shen, Zheng-Xin Yong, Hailey Schoelkopf, et al. Crosslingual generalization through multitask finetuning. arXiv preprint arXiv:2211.01786, 2022. our card
  64. Niklas Muennighoff, Alexander Rush, Boaz Barak, Teven Le Scao, Nouamane Tazi, Aleksandra Piktus, Sampo Pyysalo, Thomas Wolf, and Colin A Raffel. Scaling data-constrained language models. Advances in Neural Information Processing Systems, 36, 2024. find
  65. OpenAI. Gpt-4 technical report, 2023. our card
  66. David Owen. How predictable is language model benchmark performance? arXiv preprint arXiv:2401.04757, 2024. find
  67. Yotam Perlitz, Elron Bandel, Ariel Gera, Ofir Arviv, Liat Ein-Dor, Eyal Shnarch, Noam Slonim, Michal Shmueli-Scheuer, and Leshem Choshen. Efficient benchmarking (of language models). arXiv preprint arXiv:2308.11696, 2023. find
  68. Felipe Maia Polo, Lucas Weber, Leshem Choshen, Yuekai Sun, Gongjun Xu, and Mikhail Yurochkin. tinybenchmarks: evaluating llms with fewer examples. arXiv preprint arXiv:2402.14992, 2024. find
  69. Friedrich Pukelsheim. Optimal design of experiments. SIAM, 2006. find
  70. Yuanyuan Qiu, Hongzheng Li, Shen Li, Yingdi Jiang, Renfen Hu, and Lijiao Yang. Revisiting correlations between intrinsic and extrinsic evaluations of word embeddings. In Chinese Computational Linguistics and Natural Language Processing Based on Naturally Annotated Big Data: 17th China National Confe… find
  71. Benjamin Recht, Rebecca Roelofs, Ludwig Schmidt, and Vaishaal Shankar. Do cifar-10 classifiers generalize to cifar-10? arXiv preprint arXiv:1806.00451, 2018. — [arXiv:1806.00451](https://arxiv.org/abs/1806.00451) find
  72. Benjamin Recht, Rebecca Roelofs, Ludwig Schmidt, and Vaishaal Shankar. Do imagenet classifiers generalize to imagenet? In International conference on machine learning, pages 5389–5400. PMLR, 2019. find
  73. David Rein, Betty Li Hou, Asa Cooper Stickland, Jackson Petty, Richard Yuanzhe Pang, Julien Dirani, Julian Michael, and Samuel R Bowman. Gpqa: A graduate-level google-proof q&a benchmark. arXiv preprint arXiv:2311.12022, 2023. our card
  74. Toran Bruce Richards. Auto-gpt: Autonomous artificial intelligence software agent. https://github.com/Significant-Gravitas/Auto-GPT, 2023. URL https://github.com/ Significant-Gravitas/Auto-GPT. Initial release: March 30, 2023. ↗
  75. Baptiste Roziere, Jonas Gehring, Fabian Gloeckle, Sten Sootla, Itai Gat, Xiaoqing Ellen Tan, Yossi Adi, Jingyu Liu, Tal Remez, Jérémy Rapin, et al. Code llama: Open foundation models for code. arXiv preprint arXiv:2308.12950, 2023. our card
  76. Keisuke Sakaguchi, Ronan Le Bras, Chandra Bhagavatula, and Yejin Choi. Winogrande: An adversarial winograd schema challenge at scale. Communications of the ACM, 64(9):99–106, 2021. find
  77. Rylan Schaeffer, Brando Miranda, and Sanmi Koyejo. Are emergent abilities of large language models a mirage? Advances in Neural Information Processing Systems, 36, 2023. our card
  78. Rylan Schaeffer, Brando Miranda, and Sanmi Koyejo. Are emergent abilities of large language models a mirage? In Thirty-seventh Conference on Neural Information Processing Systems, 2023. our card
  79. Zhihong Shao, Damai Dai, Daya Guo, Bo Liu (Benjamin Liu), and Zihan Wang. Deepseek-v2: A strong, economical, and efficient mixture-of-experts language model. ArXiv, abs/2405.04434, 2024. URL https://api.semanticscholar.org/CorpusID:269613809. ↗
  80. Charlie Snell, Jaehoon Lee, Kelvin Xu, and Aviral Kumar. Scaling llm test-time compute optimally can be more effective than scaling model parameters. arXiv preprint arXiv:2408.03314, 2024. our card
  81. Aarohi Srivastava, Abhinav Rastogi, Abhishek Rao, Abu Awal Md Shoeb, Abubakar Abid, Adam Fisch, Adam R Brown, Adam Santoro, Aditya Gupta, Adrià Garriga-Alonso, et al. Beyond the imitation game: Quantifying and extrapolating the capabilities of language models. arXiv preprint arXiv:2206.04615, 2022. our card
  82. Mirac Suzgun, Nathan Scales, Nathanael Schärli, Sebastian Gehrmann, Yi Tay, Hyung Won Chung, Aakanksha Chowdhery, Quoc V Le, Ed H Chi, Denny Zhou, et al. Challenging big-bench tasks and whether chain-of-thought can solve them. arXiv preprint arXiv:2210.09261, 2022. our card
  83. Rohan Taori, Achal Dave, Vaishaal Shankar, Nicholas Carlini, Benjamin Recht, and Ludwig Schmidt. Measuring robustness to natural distribution shifts in image classification. Advances in Neural Information Processing Systems, 33:18583–18599, 2020. find
  84. Yi Tay, Mostafa Dehghani, Samira Abnar, Hyung Won Chung, William Fedus, Jinfeng Rao, Sharan Narang, Vinh Q Tran, Dani Yogatama, and Donald Metzler. Scaling laws vs model architectures: How does inductive bias influence scaling? In The 2023 Conference on Empirical Methods in Natural Language Processi… our card
  85. Gemma Team, Thomas Mesnard, Cassidy Hardin, Robert Dadashi, Surya Bhupatiraju, Shreya Pathak, Laurent Sifre, Morgane Rivière, Mihir Sanjay Kale, Juliette Love, et al. Gemma: Open models based on gemini research and technology. arXiv preprint arXiv:2403.08295, 2024. find
  86. Gemma Team, Morgane Riviere, Shreya Pathak, Pier Giuseppe Sessa, Cassidy Hardin, Surya Bhupatiraju, Léonard Hussenot, Thomas Mesnard, Bobak Shahriari, Alexandre Ramé, et al. Gemma 2: Improving open language models at a practical size. arXiv preprint arXiv:2408.00118, 2024. find
  87. Qwen Team. Introducing qwen1.5. https://qwenlm.github.io/blog/qwen1.5/, 2024. Accessed: 2024-05-13. ↗
  88. The MosaicML NLP Team. Introducing mpt-7b: A new standard for open-source, commercially usable llms. https://www.databricks.com/blog/mpt-7b, 2023. Accessed: 2024-05-13. ↗
  89. François Torregrossa, Vincent Claveau, Nihel Kooli, Guillaume Gravier, and Robin Allesiardo. On the correlation of word embedding evaluation metrics. In Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020), pages 4789–4797, 2020. find
  90. Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timothée Lacroix, Baptiste Rozière, Naman Goyal, Eric Hambro, Faisal Azhar, et al. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971, 2023. our card
  91. Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, et al. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288, 2023. find
  92. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. Attention is all you need. Advances in neural information processing systems, 30, 2017. our card
  93. Pablo Villalobos. Scaling laws literature review, 2023. URL https://epochai.org/blog/ scaling-laws-literature-review. Accessed: 2024-05-12. ↗
  94. Alex Wang, Amanpreet Singh, Julian Michael, Felix Hill, Omer Levy, and Samuel R Bowman. Glue: A multi-task benchmark and analysis platform for natural language understanding. In International Conference on Learning Representations, 2018. our card
  95. Guan Wang, Sijie Cheng, Xianyuan Zhan, Xiangang Li, Sen Song, and Yang Liu. Openchat: Advancing open-source language models with mixed-quality data. In The Twelfth International Conference on Learning Representations, 2023. our card
  96. Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc V Le, Ed H Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou. Self-consistency improves chain of thought reasoning in language models. In The Eleventh International Conference on Learning Representations, 2023. our card
  97. Jason Wei, Yi Tay, Rishi Bommasani, Colin Raffel, Barret Zoph, Sebastian Borgeaud, Dani Yogatama, Maarten Bosma, Denny Zhou, Donald Metzler, et al. Emergent abilities of large language models. Transactions on Machine Learning Research, 2022. our card
  98. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, et al. Chain-of-thought prompting elicits reasoning in large language models. Advances in neural information processing systems, 35:24824–24837, 2022. our card
  99. BigScience Workshop, Teven Le Scao, Angela Fan, Christopher Akiki, Ellie Pavlick, Suzana Ilić, Daniel Hesslow, Roman Castagné, Alexandra Sasha Luccioni, François Yvon, et al. Bloom: A 176b-parameter open-access multilingual language model. arXiv preprint arXiv:2211.05100, 2022. find
  100. Mengzhou Xia, Mikel Artetxe, Chunting Zhou, Xi Victoria Lin, Ramakanth Pasunuru, Danqi Chen, Luke Zettlemoyer, and Ves Stoyanov. Training trajectories of language models across scales. arXiv preprint arXiv:2212.09803, 2022. find
  101. Can Xu, Qingfeng Sun, Kai Zheng, Xiubo Geng, Pu Zhao, Jiazhan Feng, Chongyang Tao, and Daxin Jiang. Wizardlm: Empowering large language models to follow complex instructions. arXiv preprint arXiv:2304.12244, 2023. our card
  102. Yiheng Xu, SU Hongjin, Chen Xing, Boyu Mi, Qian Liu, Weijia Shi, Binyuan Hui, Fan Zhou, Yitao Liu, Tianbao Xie, et al. Lemur: Harmonizing natural language and code for language agents. In The Twelfth International Conference on Learning Representations, 2024. find
  103. Chhavi Yadav and Léon Bottou. Cold case: The lost mnist digits. Advances in neural information processing systems, 32, 2019. find
  104. An Yang, Baosong Yang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Zhou, Chengpeng Li, Chengyuan Li, Dayiheng Liu, Fei Huang, et al. Qwen2 technical report. arXiv preprint arXiv:2407.10671, 2024. find
  105. John Yang, Carlos E. Jimenez, Alexander Wettig, Kilian Lieret, Shunyu Yao, Karthik Narasimhan, and Ofir Press. Swe-agent: Agent computer interfaces enable software engineering language models, 2024. find
  106. Alex Young, Bei Chen, Chao Li, Chengen Huang, Ge Zhang, Guanwei Zhang, Heng Li, Jiangcheng Zhu, Jianqun Chen, Jing Chang, et al. Yi: Open foundation models by 01. ai. arXiv preprint arXiv:2403.04652, 2024. our card
  107. Rowan Zellers, Ari Holtzman, Yonatan Bisk, Ali Farhadi, and Yejin Choi. Hellaswag: Can a machine really finish your sentence? arXiv preprint arXiv:1905.07830, 2019. find
  108. Susan Zhang, Stephen Roller, Naman Goyal, Mikel Artetxe, Moya Chen, Shuohui Chen, Christopher Dewan, Mona Diab, Xian Li, Xi Victoria Lin, et al. Opt: Open pre-trained transformer language models. arXiv preprint arXiv:2205.01068, 2022. our card
  109. Shuyan Zhou, Frank F Xu, Hao Zhu, Xuhui Zhou, Robert Lo, Abishek Sridhar, Xianyi Cheng, Tianyue Ou, Yonatan Bisk, Daniel Fried, et al. Webarena: A realistic web environment for building autonomous agents. In The Twelfth International Conference on Learning Representations, 2023. our card

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/ruan-2024-observational-scaling-laws-predictability-language/