Fetching the paper…

Reading the bibliography…

2023

Machine Learning Model Attribution Challenge

Merkhofer, Elizabeth, Chaudhari, Deepesh, Anderson, Hyrum S. et al.

Original
PDF
Post on X

Understand

We present the findings of the Machine Learning Model Attribution Challenge.

Fine-tuned machine learning models may derive from other trained models without obvious attribution characteristics.
In this challenge, participants identify the publicly-available base models that underlie a set of anonymous, fine-tuned large language models (LLMs) using only textual output of the models.
Contestants aim to correctly attribute the most fine-tuned models, with ties broken in the favor of contestants whose solutions use fewer calls to the fine-tuned models' API.

Machine Learning Model Attribution Challenge · Around

Built on

T. Fang, M. Jaggi, and K. Argyraki, “Generating steganographic text with LSTMs,” in Proceedings of ACL 2017, Student Research Workshop . Vancouver, Canada: Association for Computational Linguistics, Jul. 2017, pp. 100–106. [Online]. Available: https://aclanthology.org/P17-3017
2017
Earlier work this paper cites.
D. Ippolito, D. Duckworth, C. Callison-Burch, and D. Eck, “Automatic detection of generated text is easiest when humans are fooled,” in Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics . Online: Association for Computational Linguistics, Jul. 2020, pp. 1808–1822. [Online]. Available: https://aclanthology.org/2020.acl-main.164
2020
Earlier work this paper cites.
A. Radford, “Better language models and their implications,” Jun 2021. [Online]. Available: https://openai.com/blog/better-language-models/
2021
Earlier work this paper cites.
R. Bommasani, D. A. Hudson, E. Adeli, R. Altman, S. Arora, S. von Arx, M. S. Bernstein, J. Bohg, A. Bosselut, E. Brunskill, E. Brynjolfsson, S. Buch, D. Card, R. Castellon, N. S. Chatterji, A. S. Chen, K. Creel, J. Q. Davis, D. Demszky, C. Donahue, M. Doumbouya, E. Durmus, S. Ermon, J. Etchemendy, K. Ethayarajh, L. Fei-Fei, C. Finn, T. Gale, L. Gillespie, K. Goel, N. D. Goodman, S. Grossman, N. Guha, T. Hashimoto, P. Henderson, J. Hewitt, D. E. Ho, J. Hong, K. Hsu, J. Huang, T. Icard, S. Jain, D. Jurafsky, P. Kalluri, S. Karamcheti, G. Keeling, F. Khani, O. Khattab, P. W. Koh, M. S. Krass, R. Krishna, R. Kuditipudi, and et al., “On the opportunities and risks of foundation models,” CoRR , vol. abs/2108.07258, 2021. [Online]. Available: https://arxiv.org/abs/2108.07258
Original
2021
Earlier work this paper cites.

Similar

L. Weidinger, J. Mellor, M. Rauh, C. Griffin, J. Uesato, P. Huang, M. Cheng, M. Glaese, B. Balle, A. Kasirzadeh, Z. Kenton, S. Brown, W. Hawkins, T. Stepleton, C. Biles, A. Birhane, J. Haas, L. Rimell, L. A. Hendricks, W. S. Isaac, S. Legassick, G. Irving, and I. Gabriel, “Ethical and social risks of harm from language models,” CoRR , vol. abs/2112.04359, 2021. [Online]. Available: https://arxiv.org/abs/2112.04359
Original
2021
Cited alongside, same era.
S. Aaronson, “My ai safety lecture for ut effective altruism,” Dec 2022. [Online]. Available: https://scottaaronson.blog/?p=6823
2022
Cited alongside, same era.
P. Aggarwal, “Identifying pretrained models from finetuned lms,” Oct 2022. [Online]. Available: https://pranjal2041.medium.com/identifying-pretrained-models-from-finetuned-lms-32ceb878898f
2022
Cited alongside, same era.
Y. Ding, “Model attribution.” [Online]. Available: https://docs.google.com/document/d/1Xbm0F7P2O9qG0b3bYrRsyBefrUw_gtKaShAz6i68mNU/edit
Cited in the paper.

Then

J. T. Lucas, “Blog,” 2022. [Online]. Available: https://josephtlucas.github.io/blog/content/mlmac.html
2022
Later among the works it cites.
F. Dhanani and M. Rafi, “Artificial interrogation for attributing language models,” 2022. [Online]. Available: https://arxiv.org/abs/2211.10877
Original
2022
Later among the works it cites.
J. A. Goldstein, G. Sastry, M. Musser, R. DiResta, M. Gentzel, and K. Sedova, “Generative language models and automated influence operations: Emerging threats and potential mitigations,” 2023. [Online]. Available: https://arxiv.org/abs/2301.04246
Original
2023
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

H. M. Nguyễn, “A solution to the model attribution challenge.” [Online]. Available: https://jordine.github.io/

Cited in the paper.