no code implementations • Findings (ACL) 2022 • Navita Goyal, Roodram Paneri, Ayush Agarwal, Udit Kalani, Abhilasha Sancheti, Niyati Chhaya
We leverage causal inference techniques to identify causally significant aspects of a text that lead to the target metric and then explicitly guide generative models towards these by a feedback mechanism.
no code implementations • NAACL 2022 • Himanshu Maheshwari, Nethraa Sivakumar, Shelly Jain, Tanvi Karandikar, Vinay Aggarwal, Navita Goyal, Sumit Shekhar
Linearly consuming (via scrolling or navigation through default table of content) these documents is time-consuming and challenging.
1 code implementation • 4 Dec 2023 • Eleftheria Briakou, Navita Goyal, Marine Carpuat
Explainable NLP techniques primarily explain by answering "Which tokens in the input are responsible for this prediction?''.
no code implementations • 19 Oct 2023 • Chenglei Si, Navita Goyal, Sherry Tongshuang Wu, Chen Zhao, Shi Feng, Hal Daumé III, Jordan Boyd-Graber
To reduce over-reliance on LLMs, we ask LLMs to provide contrastive information - explain both why the claim is true and false, and then we present both sides of the explanation to users.
no code implementations • 12 Oct 2023 • Navita Goyal, Connor Baumler, Tin Nguyen, Hal Daumé III
In this work, we study the effect of the presence of protected and proxy features on participants' perception of model fairness and their ability to improve demographic parity over an AI alone.
no code implementations • 23 May 2023 • Navita Goyal, Eleftheria Briakou, Amanda Liu, Connor Baumler, Claire Bonial, Jeffrey Micher, Clare R. Voss, Marine Carpuat, Hal Daumé III
In this work, we study how users interact with QA systems in the absence of sufficient information to assess their predictions.
no code implementations • 30 Jun 2022 • Atanu R Sinha, Navita Goyal, Sunny Dhamnani, Tanay Asija, Raja K Dubey, M V Kaarthik Raja, Georgios Theocharous
The recognition of cognitive bias in computer science is largely in the domain of information retrieval, and bias is identified at an aggregate level with the help of annotated data.
no code implementations • 24 Oct 2020 • Navita Goyal, Roodram Paneri, Ayush Agarwal, Udit Kalani, Abhilasha Sancheti, Niyati Chhaya
We leverage causal inference techniques to identify causally significant aspects of a text that lead to the target metric and then explicitly guide generative models towards these by a feedback mechanism.
no code implementations • NAACL 2021 • Navita Goyal, Balaji Vasan Srinivasan, Anandhavelu Natarajan, Abhilasha Sancheti
Style transfer has been widely explored in natural language generation with non-parallel corpus by directly or indirectly extracting a notion of style from source and target domain corpus.