My name is Amir Saffari and this is my website and blog. I’ve a PhD in Computer Vision and Machine Learning and work at Alexa AI, Amazon as a Principal ML Scientist. Currently, I focus on generative AI, training large language models (LLMs), teaching LLMs to use thousands of tools and APIs to accomplish personalised and complex tasks in real-time, reasoning using weak supervision, and reinforcement learning based program synthesis.
- Priyanka Sen, Sandeep Mavadia, Amir Saffari, Knowledge Graph-Augmented Language Models for Complex Question Answering ACL Natural Language Reasoning and Structured Explanations Workshop 2023.
- Jinheon Baek, Alham Fikri Aji, Amir Saffari, Knowledge-Augmented Language Model Prompting or Zero-Shot Knowledge Graph Question Answering ACL Matching Workshop 2023.
- Andy Rosenbaum, Saleh Soltan, Wael Hamza, Amir Saffari, Macro Damonte, Isabel Groves, CLASP: Few-Shot Cross-Lingual Data Augmentation for Semantic Parsing, arXiv, AACL 2022
- Priyanka Sen, Alham Fikri Aji, Amir Saffari, Mintaka: A Complex, Natural, and Multilingual Dataset for End-to-End Question Answering, arXiv, COLING 2022. Dataset
- Priyanka Sen, Amir Saffari, Armin Oliya, Expanding End-to-End Question Answering on Differentiable Knowledge Graphs with Intersection, EMNLP 2021.
- Armin Oliya, Amir Saffari, Priyanka Sen, Tom Ayoola, End-to-End Entity Resolution and Question Answering Using Differentiable Knowledge Graphs, EMNLP 2021.
- 2023: We have two papers accepted at ACL workshops exploring augmenting LLMs with knowledge graphs for zero-shot question answering: KAPING and Rigel-KAPING.
- 2022: Mintaka dataset is now available, see our paper for more information.
- 2021: Our two new papers at EMNLP extend differentiable knowledge graphs for complex QA, E2EQA and Rigel.