I am a Research Scientist at FAIR @ Meta. I recently completed my PhD at ETH Zürich, where I was advised by Prof. Mrinmaya Sachan and Prof. Thomas Hofmann.

Before that, I spent two years as a Research Engineer at Microsoft Research Montréal. Earlier, I completed my Master’s degree at UMass Amherst, where I was advised by Prof. Andrew McCallum.

My research focuses on building reasoning systems that are factual, well-calibrated, and trustworthy.

I was a recipient of the IBM PhD Fellowship Award (2021).

During my PhD, I interned at FAIR @ Meta in the summers of 2023 and 2024, working with Jason Weston.

Our work on Chain-of-Verification was featured in The Wall Street Journal and Forbes.

Publications

Google Scholar

2024

• Adaptive Decoding via Latent Preference Optimization
  Shehzaad Dhuliawala, Ilia Kulikov, Ping Yu, Asli Celikyilmaz, Jason Weston, Sainbayar Sukhbaatar, Jack Lanchantin
  Preprint 2024
• Towards Aligning Language Models with Textual Feedback
  Saüc Abadal Lloret*, Shehzaad Dhuliawala*, Keerthiram Murugesan, Mrinmaya Sachan
  EMNLP 2024
• Implicit Personalization in Language Models: A Systematic Study
  Zhijing Jin, Nils Heil, Jiarui Liu, Shehzaad Dhuliawala, Yahang Qi, Bernhard Schölkopf, Rada Mihalcea, Mrinmaya Sachan
  EMNLP 2024 Findings
• Chain-of-Verification Reduces Hallucinations in Large Language Models
  Shehzaad Dhuliawala, Mojtaba Komeili, Jing Xu, Roberta Raileanu, Xian Li, Asli Celikyilmaz, Jason Weston
  ACL 2024 Findings

2023

• A Diachronic Perspective on User Trust in AI under Uncertainty
  Shehzaad Dhuliawala*, Vilém Zouhar*, Mennatallah El-Assady, Mrinmaya Sachan
  EMNLP 2023 (Oral)
• Variational Classification
  Shehzaad Dhuliawala, Mrinmaya Sachan, Carl Allen
  TMLR 2023

2022

• Calibration of Machine Reading Systems at Scale
  Shehzaad Dhuliawala, Leonard Adolphs, Rajarshi Das, Mrinmaya Sachan
  ACL 2022 Findings
• Case-based Reasoning for Better Generalization in Text-Adventure Games
  Mattia Atzeni, Shehzaad Dhuliawala, Keerthiram Murugesan, Mrinmaya Sachan
  ICLR 2022

2021

• TopiOCQA: Open-domain Conversational Question Answering with Topic Switching
  Vaibhav Adlakha, Shehzaad Dhuliawala, Kaheer Suleman, Harm de Vries, Siva Reddy
  TACL 2021
• How to Query Language Models?
  Leonard Adolphs, Shehzaad Dhuliawala, Thomas Hofmann
  Preprint 2021

2020

• A Simple Approach to Case-Based Reasoning in Knowledge Bases
  Rajarshi Das, Ameya Godbole, Shehzaad Dhuliawala, Manzil Zaheer, Andrew McCallum
  AKBC 2020

2019

• Multi-step Retriever-Reader Interaction for Scalable Open-domain Question Answering
  Rajarshi Das, Shehzaad Dhuliawala, Manzil Zaheer, Andrew McCallum
  ICLR 2019

2018

• Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learning
  Shehzaad Dhuliawala*, Rajarshi Das*, Manzil Zaheer, Luke Vilnis, Ishan Durugkar, Alex Smola, Andrew McCallum
  ICLR 2018. Best Paper at AKBC @ NeurIPS 2017 [code]