Events2Join

chrisliu298/awesome|llm|unlearning


chrisliu298/awesome-llm-unlearning - GitHub

A resource repository for machine unlearning in large language models - chrisliu298/awesome-llm-unlearning.

Actions · chrisliu298/awesome-llm-unlearning · GitHub

A resource repository for machine unlearning in large language models - Actions · chrisliu298/awesome-llm-unlearning.

awesome-llm-unlearning | Ecosyste.ms

A resource repository for machine unlearning in large language models. https://github.com/chrisliu298/awesome-llm-unlearning

LLM Unlearning Benchmarks are Weak Measures of Progress - arXiv

Liu, “Awesome llm unlearning,” https://github.com/chrisliu298/awesome-llm-unlearning, 2024, accessed: 2024-09-22. Huang et al. [2024] J ...

Projects - Chris Yuhao Liu

Awesome Sparse Autoencoders GitHub. Awesome Representation Engineering GitHub. Awesome Large Language Model Unlearning GitHub. 2022. Toward Disentangling Double ...

Large Language Model Unlearning via Embedding-Corrupted ...

We have made our code publicly available at https://github.com/chrisliu298/llm-unlearn-eco. ... LLM unlearning method that enforces an unlearned state over an ...

Large Language Model Unlearning via Embedding-Corrupted ...

PDF Abstract. Code. Edit. Add Remove Mark official. chrisliu298/llm-unlearn-eco. 9. chrisliu298/llm-unlearn-eco. 9. Tasks. Edit. Add Remove ...

News | Chris Liu

Our paper Large Language Model Unlearning via Embedding-Corrupted Prompts has been accepted to NeurIPS 2024! [2024-09] We released Skywork-Reward-Gemma-2 ...

Projects in Awesome Lists tagged with llm-unlearning | Ecosyste.ms ...

A curated list of projects in awesome lists tagged with llm-unlearning . Sort. Recently synced · Stars · https://github.com/chrisliu298/llm-unlearn-eco. Code ...

chrisliu298 (Chris (Yuhao) Liu) - Hugging Face

chrisliu298's activity · Skywork-Reward: Bag of Tricks for Reward Modeling in LLMs · Large Language Model Unlearning via Embedding-Corrupted Prompts · Rethinking ...

Position: LLM Unlearning Benchmarks are Weak Measures of ...

Request PDF | Position: LLM Unlearning Benchmarks are Weak Measures of Progress | Unlearning ... Liu, "Awesome llm unlearning," https: //github.com/chrisliu298/ ...

Large Language Model Unlearning via Embedding-Corrupted ...

... no additional cost as the number of parameters increases. We have made our code publicly available at \url{https://github.com/chrisliu298/llm-unlearn-eco}.

Soft Prompting for Unlearning in Large Language Models

We have made our code publicly available at url{https://github.com/chrisliu298/llm-unlearn-eco}. ... LLM unlearning. This initiative aims ...

An Efficient LLM Unlearning Framework from Logit Difference

In this work, we propose eliminating the need to retain data or the reference LLM for response calibration in LLM unlearning. ... chrisliu298/llm-unlearn-eco}.

Large Language Model Unlearning via Embedding-Corrupted ...

... chrisliu298/llm-unlearn ... We have made our code publicly available at url{https://github.com/chrisliu298/llm-unlearn-eco}.

Are there any groupchats for people working on Representation ...

... chrisliu298/awesome-representation-engineering. Perhaps you could create such a group if you wanted to because such a thing seems interesting ...

emily.fan - LessWrong

... chrisliu298/awesome-representation-engineering. Perhaps you could create such a group if you wanted to because such a thing seems interesting? Happy to share ...

From Zero to Hero in AI: My Serverless LLM Adventure! - YouTube

In this Civo Navigate 2024 session, Engin Diri shares his unexpected journey into managing Open-Source Large Language Models (LLMs) in a ...

TOFU: A Task of Fictitious Unlearning for LLMs

Unlearning, or tuning models to forget things present in their training data, provides us with a way to protect private data after training. Although many ...

A video tutorial | Sebastian Raschka, PhD posted on the topic

You're doing an important good job for learning how LLM are working for those who AI is something strange. I hope that, for those who really ...