Taiwei Shi's picture

4 9 1

Taiwei Shi

MaksimSTW

·

https://maksimstw.github.io/

AI & ML interests

alignment, human-AI collaboration, and computational social science

Recent Activity

updated a collection 9 days ago

updated a collection 10 days ago

updated a collection 10 days ago

View all activity

Organizations

MaksimSTW's activity

updated a collection 9 days ago

Papers

5 items • Updated 9 days ago

updated a collection 10 days ago

Papers

5 items • Updated 9 days ago

authored 2 papers 10 days ago

Detecting and Filtering Unsafe Training Data via Data Attribution

Paper • 2502.11411 • Published 14 days ago • 1

On the Trustworthiness of Generative Foundation Models: Guideline, Assessment, and Perspective

Paper • 2502.14296 • Published 11 days ago • 45

upvoted 2 papers 10 days ago

On the Trustworthiness of Generative Foundation Models: Guideline, Assessment, and Perspective

Paper • 2502.14296 • Published 11 days ago • 45

Detecting and Filtering Unsafe Training Data via Data Attribution

Paper • 2502.11411 • Published 14 days ago • 1

upvoted a paper about 1 month ago

WildFeedback: Aligning LLMs With In-situ User Interactions And Feedback

Paper • 2408.15549 • Published Aug 28, 2024 • 1

authored 5 papers 4 months ago

WildFeedback: Aligning LLMs With In-situ User Interactions And Feedback

Paper • 2408.15549 • Published Aug 28, 2024 • 1

CoAnnotating: Uncertainty-Guided Work Allocation between Human and Large Language Models for Data Annotation

Paper • 2310.15638 • Published Oct 24, 2023 • 1

Neural Story Planning

Paper • 2212.08718 • Published Dec 16, 2022

Can Language Model Moderators Improve the Health of Online Discourse?

Paper • 2311.10781 • Published Nov 16, 2023 • 1

How Susceptible are Large Language Models to Ideological Manipulation?

Paper • 2402.11725 • Published Feb 18, 2024 • 1

updated a collection 4 months ago

Papers

5 items • Updated 9 days ago

upvoted a paper 4 months ago

How Susceptible are Large Language Models to Ideological Manipulation?

Paper • 2402.11725 • Published Feb 18, 2024 • 1

updated a collection 4 months ago

Papers

5 items • Updated 9 days ago

upvoted a paper 4 months ago

Can Language Model Moderators Improve the Health of Online Discourse?

Paper • 2311.10781 • Published Nov 16, 2023 • 1

updated a collection 4 months ago

Papers

5 items • Updated 9 days ago

upvoted a paper 4 months ago

CoAnnotating: Uncertainty-Guided Work Allocation between Human and Large Language Models for Data Annotation

Paper • 2310.15638 • Published Oct 24, 2023 • 1