May 2024 Invited Talk “What it can create, it may not understand” Studying the Limits of Transformers” at the University of Cambridge.
Feb 2024 Featured in TechCrunch talking about why LMs perform better when we “motivate” them or ask them “nicely”?
Jan 2024 3 papers accepted at ICLR 2024. 1 Oral and 2 posters. See you in Vienna :musical_score: :musical_note: :musical_note:
Dec 2023 Guest Lecture: “Limits of Generative AI Models and their Societal Implications” for the “Generative AI” course taught by Prof. Adji Bousso at the Princeton University.
Nov 2023 Invited Talk: Presented “Faith and Fate” & “Generative AI Paradox” at LLM evaluation workshop at The Alan Turing Institute.
Nov 2023 Invited Talk: Presented “Faith and Fate” in ILCC CDT/NLP seminar, University of Edinburgh.
Nov 2023 Invited Talk: Presented “Faith and Fate” at SAIL workshop on fundamental limits of LLMs.
Nov 2023 New paper :mega: “The Generative AI Paradox: What It Can Create, It May Not Understand” is out. [Paper]
Oct 2023 New paper :mega: “Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinement” is out. (ICLR Oral 2024) [Paper][Code]
Oct 2023 Invited Talk: Presented “Faith and Fate” at the University of Pittisburgh
Oct 2023 2 papers accepted at EMNLP.
Sep 2023 Invited Talk: Presented “Faith and Fate” at the Formal Languages and Neural Networks Seminar [Video]
Sep 2023 3 papers accepted at NeurIPS. See you in New Orleans :airplane:
Jun 2023 New paper :mega: “Fine-Grained Human Feedback Gives Better Rewards for Language Model Training” is out. [Paper] [Code/Data] (NeurIPS Spotlight 2023)
May 2023 New paper :mega: :sparkles: “Faith and Fate: Limits of Transformers in Compositionality” :sparkles: is out. [Paper][Code][Blog] (NeurIPS Spotlight 2023)
Mar 2023 New paper :mega: “Self-Refine: Iterative Refinement with Self-Feedback” :speech_balloon: is out. [Paper][Website][Demo] (NeurIPS 2023)
Dec 2022 Defended my PhD successfully :mortar_board: and was nominated for the best thesis award :trophy:
Nov 2022 Joined AI2 (Mosaic) as a postdoc.
Jun 2022 Invited Talk: Stanford NLP Seminar.
May 2022 Our work “Evaluating Attribution in Dialogue Systems: The BEGIN Benchmark” got accepted at TACL 2022 [Paper] .
Apr 2022 New Benchmark FaithDial for building faithful information-seeking dialogue systems got accepted at TACL 2022. [Preprint] [Data] [Code] [Project Page]
Apr 2022 Our work “On the Origin of Hallucination in Conversational Models: Is it the Datasets or the Models?” got accepted at NAACL 2022. [Paper] [Data]
Jan 2022 Joined Google Research as a student researcher.
Aug 2021 Our work “Neural Path Hunter: Reducing Hallucination in Dialogue Systems via Path Grounding” got accepted at EMNLP 2021. [Paper] [Code]
May 2021 Joined Mila as a visiting researcher to work with Siva Reddy.
May 2021 Our work “Decomposed Mutual Information Estimation for Contrastive Representation Learning” got accepted at ICML 2021 [Paper].
Apr 2021 Passed my PhD candidacy successfully!
Apr 2021 New Benchmark BEGIN about evaluating groundedness in dialogue systems. [Preprint] [Data]
Mar 2021 Invited Talk: DSC Women in Tech Conference about inspiring females to pursue a career in STEM. [Video]
Sep 2020 Invited Talk: Montreal NLP Meetups about conversational AI.
Jun 2020 Interned at Google Research Language team NYC under Tal Linzen and David Reitter.
Dec 2019 Invited Talk: DeepMind Montreal about evaluating consistency in dialogue systems.
Sep 2019 Interned at Microsoft Research Montreal.
Sep 2019 Invited talk at Rasa Developer Summit. [Slides] [Video]
May 2019 Interned at Google Research Language team NYC.
May 2019 Our work “Augmenting Neural Response Generation with Context-Aware Topical Attention” got accepted at ACL workshop NLP4ConvAI. [Paper] [Code]
Mar 2019 Invited to the Amazon Graduate Research Symposium among top student researchers across North America to present my work in Seattle.
Feb 2019 Our paper “Evaluating Coherence in Dialogue Systems using Entailment” got accepted at NAACL 2019. [Paper][Code]
Dec 2018 Presented a poster “Response Generation For Open-Ended Conversational Agent” at NeurIPS Workshop on Women in Machine Learning (WiML), Montreal, Canada.
Oct 2018 Check out my interview with l’Express about my studies at the University of Alberta.
Sep 2018 Attended the Grace Hopper Celebration 2018 at Houston, Texas.
Jan 2018 Our work “Automatic Dialogue Generation with Expressed Emotions” got accepted at NAACL 2018. [Paper] [Code]