no code implementations • 13 Jan 2024 • Yujun Mao, Yoon Kim, Yilun Zhou
And while self-generated verbalizations of intermediate reasoning steps (i. e., chain-of-thought prompting) have been shown to be helpful, whether LLMs can make use of helpful side information such as problem-specific hints has not been investigated before.
no code implementations • 10 Dec 2023 • Shawn Im, Jacob Andreas, Yilun Zhou
One of the motivations for explainable AI is to allow humans to make better and more informed decisions regarding the use and deployment of AI models.
no code implementations • 17 Oct 2023 • Shiyuan Huang, Siddarth Mamidanna, Shreedhar Jangam, Yilun Zhou, Leilani H. Gilpin
Through an extensive set of experiments, we find that ChatGPT's self-explanations perform on par with traditional ones, but are quite different from them according to various agreement metrics, meanwhile being much cheaper to produce (as they are generated along with the prediction).
1 code implementation • 27 May 2023 • Daking Rai, Bailin Wang, Yilun Zhou, Ziyu Yao
Compositional and domain generalization present significant challenges in semantic parsing, even for state-of-the-art semantic parsers based on pre-trained language models (LMs).
Ranked #6 on Text-To-SQL on spider
no code implementations • 17 Mar 2023 • Yilun Zhou
For a subject that receives a negative model prediction (e. g., mortgage application denial), the CF explanations are similar instances but with positive predictions, which informs the subject of ways to improve.
no code implementations • 25 Jan 2023 • Daking Rai, Yilun Zhou, Bailin Wang, Ziyu Yao
While large language models (LLMs) have demonstrated strong capability in structured prediction tasks such as semantic parsing, few amounts of research have explored the underlying mechanisms of their success.
1 code implementation • 18 May 2022 • Yilun Zhou, Julie Shah
Feature attribution methods are popular for explaining neural network predictions, and they are often evaluated on metrics such as comprehensiveness and sufficiency.
1 code implementation • NAACL 2022 • Yilun Zhou, Marco Tulio Ribeiro, Julie Shah
Interpretability methods are developed to understand the working mechanisms of black-box models, which is crucial to their responsible deployment.
1 code implementation • NAACL (TrustNLP) 2022 • Yiming Zheng, Serena Booth, Julie Shah, Yilun Zhou
We call for more rigorous and comprehensive evaluations of these models to ensure desired properties of interpretability are indeed achieved.
1 code implementation • 27 Apr 2021 • Yilun Zhou, Serena Booth, Marco Tulio Ribeiro, Julie Shah
Feature attribution methods are exceedingly popular in interpretable machine learning.
no code implementations • 14 Feb 2021 • Ganesh Ghalme, Vineet Nair, Vishakha Patil, Yilun Zhou
Fairness has emerged as an important concern in automated decision-making in recent years, especially when these decisions affect human welfare.
1 code implementation • 29 Dec 2020 • Yilun Zhou, Adithya Renduchintala, Xian Li, Sida Wang, Yashar Mehdad, Asish Ghoshal
Active learning (AL) algorithms may achieve better performance with fewer data because the model guides the data selection process.
1 code implementation • 19 Feb 2020 • Serena Booth, Yilun Zhou, Ankit Shah, Julie Shah
To address these challenges, we introduce a flexible model inspection framework: Bayes-TrEx.
no code implementations • 16 Jan 2020 • Mycal Tucker, Yilun Zhou, Julie Shah
Robotic agents must adopt existing social conventions in order to be effective teammates.
no code implementations • 9 Jan 2020 • Serena Booth, Ankit Shah, Yilun Zhou, Julie Shah
In this paper, we consider the problem of exploring the prediction level sets of a classifier using probabilistic programming.
1 code implementation • WS 2019 • Yilun Zhou, Julie A. Shah, Steven Schockaert
Commonsense procedural knowledge is important for AI agents and robots that operate in a human environment.
no code implementations • 11 Sep 2019 • Yilun Zhou, Derrik E. Asher, Nicholas R. Waytowich, Julie A. Shah
Multi-agent reinforcement learning (MARL) extends (single-agent) reinforcement learning (RL) by introducing additional agents and (potentially) partial observability of the environment.
Multi-agent Reinforcement Learning reinforcement-learning +1
1 code implementation • 21 Feb 2019 • Yilun Zhou, Steven Schockaert, Julie A. Shah
In this paper we instead propose to learn to predict path quality from crowdsourced human assessments.