Mona Diab

According to our database, Mona Diab authored at least 6 papers in 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

2024

Decoding Dark Matter: Specialized Sparse Autoencoders for Interpreting Rare Concepts in Foundation Models.

Aashiq Muhamed, Mona Diab, Virginia Smith

CoRR, 2024

BIG5-CHAT: Shaping LLM Personalities Through Training on Human-Grounded Data.

Wenkai Li, Jiarui Liu, Andy Liu, Xuhui Zhou, Mona Diab, Maarten Sap

CoRR, 2024

A Note on Bias to Complete.

Jia Xu, Mona Diab

CoRR, 2024

GRASS: Compute Efficient Low-Memory LLM Training with Structured Sparse Gradients.

Aashiq Muhamed, Oscar Li, David P. Woodruff, Mona Diab, Virginia Smith

Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024

Towards a Responsible Thinking in the New Era of Gen AI: Walking the Walk.

Mona Diab

Proceedings of the 13th International Conference on Data Science, 2024

Evaluating Large Language Model Biases in Persona-Steered Generation.

Andy Liu, Mona Diab, Daniel Fried

Proceedings of the Findings of the Association for Computational Linguistics, 2024