Is Bigger Edit Batch Size Always Better? -- An Empirical Study on Model Editing with Llama-3

Built on

Causal mediation analysis for interpreting neural nlp: The case of gender bias
Original
Jesse Vig, Sebastian Gehrmann, Yonatan Belinkov, Sharon Qian, Daniel Nevo, Simas Sakenis, Jason Huang, Yaron Singer, and Stuart Shieber. 2020 · 2004
Earlier work this paper cites.
A brief review of hypernetworks in deep learning
Original
Vinod Kumar Chauhan, Jiandong Zhou, Ping Lu, Soheila Molaei, and David A Clifton. 2023 · 2023
Earlier work this paper cites.
Massive editing for large language models via meta learning
Original
Chenmien Tan, Ge Zhang, and Jie Fu. 2023 · 2023
Earlier work this paper cites.

Llama 2: Open foundation and fine-tuned chat models, 2023
Original
Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, et al. 2023 · 2023
Cited alongside, same era.
Editing large language models: Problems, methods, and opportunities
Original
Yunzhi Yao, Peng Wang, Bozhong Tian, Siyuan Cheng, Zhoubo Li, Shumin Deng, Huajun Chen, and Ningyu Zhang. 2023 · 2023
Cited alongside, same era.
Model editing can hurt general abilities of large language models
Original
Jia-Chen Gu, Hao-Xiang Xu, Jun-Yu Ma, Pan Lu, Zhen-Hua Ling, Kai-Wei Chang, and Nanyun Peng. 2024 · 2024
Cited alongside, same era.
Model editing at scale leads to gradual and catastrophic forgetting
Original
Akshat Gupta, Anurag Rao, and Gopala Anumanchipalli. 2024a
Cited in the paper.
A unified framework for model editing
Original
Akshat Gupta, Dev Sajnani, and Gopala Anumanchipalli. 2024b
Cited in the paper.
Locating and editing factual associations in gpt
Kevin Meng, David Bau, Alex Andonian, and Yonatan Belinkov. 2022a
Cited in the paper.
Mass-editing memory in a transformer
Original
Kevin Meng, Arnab Sen Sharma, Alex Andonian, Yonatan Belinkov, and David Bau. 2022b
Cited in the paper.

Does localization inform editing? surprising differences in causality-based localization vs. knowledge editing in language models
Peter Hase, Mohit Bansal, Been Kim, and Asma Ghandeharioun. 2024 · 2024
Closest in time.
Introducing meta llama 3: The most capable openly available llm to date
Meta. 2024 · 2024
Closest in time.