no code implementations • 26 Feb 2024 • Mikayel Samvelyan, Sharath Chandra Raparthy, Andrei Lupu, Eric Hambro, Aram H. Markosyan, Manish Bhatt, Yuning Mao, Minqi Jiang, Jack Parker-Holder, Jakob Foerster, Tim Rocktäschel, Roberta Raileanu
As large language models (LLMs) become increasingly prevalent across many real-world applications, understanding and enhancing their robustness to user inputs is of paramount importance.
no code implementations • 9 Dec 2023 • Vivek Miglani, Aobo Yang, Aram H. Markosyan, Diego Garcia-Olano, Narine Kokhlikyan
Captum is a comprehensive library for model explainability in PyTorch, offering a range of methods from the interpretability literature to enhance users' understanding of PyTorch models.
no code implementations • 22 Jun 2023 • Rafayel Darbinyan, Hrayr Harutyunyan, Aram H. Markosyan, Hrant Khachatrian
Neural networks employ spurious correlations in their predictions, resulting in decreased performance when these correlations do not hold.
no code implementations • 8 Nov 2022 • Satwik Kottur, Seungwhan Moon, Aram H. Markosyan, Hardik Shah, Babak Damavandi, Alborz Geramifard
We collect a new dataset C3 (Conversational Content Creation), comprising 10k dialogs conditioned on media montages simulated from a large media collection.
no code implementations • 22 May 2022 • Kushal Tirumala, Aram H. Markosyan, Luke Zettlemoyer, Armen Aghajanyan
Despite their wide adoption, the underlying training and memorization dynamics of very large language models is not well understood.