no code implementations • 17 Nov 2024 • Mohammad Kachuee, Sarthak Ahuja, Vaibhav Kumar, Puyang Xu, Xiaohu Liu
By conducting extensive experiments on a dataset covering complex and multi-tool scenarios, we show that leveraging LLMs for query generation improves the retrieval for in-domain (seen tools) and out-of-domain (unseen tools) settings.
no code implementations • 21 May 2024 • Bilgehan Sel, Priya Shanmugasundaram, Mohammad Kachuee, Kun Zhou, Ruoxi Jia, Ming Jin
Large Language Models (LLMs) have shown remarkable capabilities in tasks such as summarization, arithmetic reasoning, and question answering.
no code implementations • 14 Feb 2024 • Siwon Kim, Shuyang Dai, Mohammad Kachuee, Shayan Ray, Tara Taghavi, Sungroh Yoon
Current conversational AI systems based on large language models (LLMs) are known to generate unsafe responses, agreeing to offensive user input or including toxic content.
no code implementations • 7 Jun 2023 • Ting-Wei Wu, Fatemeh Sheikholeslami, Mohammad Kachuee, Jaeyoung Do, Sungjin Lee
Large-scale conversational systems typically rely on a skill-routing component to route a user request to an appropriate skill and interpretation to serve the request.
no code implementations • 17 May 2023 • Sarthak Ahuja, Mohammad Kachuee, Fateme Sheikholeslami, Weiqing Liu, Jaeyoung Do
Off-Policy reinforcement learning has been a driving force for the state-of-the-art conversational AIs leading to more natural humanagent interactions and improving the user satisfaction for goal-oriented agents.
no code implementations • 17 Sep 2022 • Mohammad Kachuee, Sungjin Lee
Based on the experimental results, we demonstrate that the proposed approach is capable of achieving the best balance between the policy value and constraint satisfaction rate.
no code implementations • NAACL (ACL) 2022 • Mohammad Kachuee, Jinseok Nam, Sarthak Ahuja, Jin-Myung Won, Sungjin Lee
Skill routing is an important component in large-scale conversational systems.
no code implementations • WASSA (ACL) 2022 • Zixuan Ke, Mohammad Kachuee, Sungjin Lee
In many real-world machine learning applications, samples belong to a set of domains e. g., for product reviews each review belongs to a product category.
1 code implementation • 11 Nov 2020 • Orpaz Goldstein, Mohammad Kachuee, Derek Shiell, Majid Sarrafzadeh
Transferring knowledge in a selective decentralized approach enables models to retain their local insights, allowing for local flavors of a machine learning model.
no code implementations • NAACL 2021 • Mohammad Kachuee, Hao Yuan, Young-Bum Kim, Sungjin Lee
Moreover, a powerful satisfaction model can be used as an objective function that a conversational agent continuously optimizes for.
no code implementations • 20 Dec 2019 • Mohammad Kachuee, Sajad Darabi, Shayan Fazeli, Majid Sarrafzadeh
GMLP is based on the idea of learning expressive feature combinations (groups) and exploiting them to reduce the network complexity by defining local group-wise operations.
no code implementations • 17 Dec 2019 • Kimmo Kärkkäinen, Mohammad Kachuee, Orpaz Goldstein, Majid Sarrafzadeh
The chosen features should increase the prediction accuracy for a low cost, but determining which features will do that is challenging.
no code implementations • 4 Oct 2019 • Sajad Darabi, Mohammad Kachuee, Majid Sarrafzadeh
In this work, we present a two-step unsupervised representation learning scheme to summarize the multi-modal clinical time series consisting of signals and medical codes into a patient status vector.
no code implementations • 15 Sep 2019 • Orpaz Goldstein, Mohammad Kachuee, Kimmo Karkkainen, Majid Sarrafzadeh
In many real-world scenarios where data is high dimensional, test time acquisition of features is a non-trivial task due to costs associated with feature acquisition and evaluating feature value.
2 code implementations • 11 Aug 2019 • Sajad Darabi, Mohammad Kachuee, Shayan Fazeli, Majid Sarrafzadeh
The data contained in these records are irregular and contain multiple modalities such as notes, and medical codes.
2 code implementations • 22 May 2019 • Mohammad Kachuee, Kimmo Karkkainen, Orpaz Goldstein, Sajad Darabi, Majid Sarrafzadeh
In order to make imputations, we train a simple and effective generator network to generate imputations that a discriminator network is tasked to distinguish.
2 code implementations • 19 Feb 2019 • Mohammad Kachuee, Kimmo Karkkainen, Orpaz Goldstein, Davina Zamanzadeh, Majid Sarrafzadeh
Furthermore, based on the suggested dataset, we provide a comparison of recent and state-of-the-art approaches to cost-sensitive feature acquisition and learning.
1 code implementation • ICLR 2019 • Mohammad Kachuee, Orpaz Goldstein, Kimmo Karkkainen, Sajad Darabi, Majid Sarrafzadeh
The suggested method acquires features incrementally based on a context-aware feature-value function.
1 code implementation • 3 Nov 2018 • Mohammad Kachuee, Sajad Darabi, Babak Moatamed, Majid Sarrafzadeh
In real-world scenarios, different features have different acquisition costs at test-time which necessitates cost-aware methods to optimize the cost and performance trade-off.
13 code implementations • 19 Apr 2018 • Mohammad Kachuee, Shayan Fazeli, Majid Sarrafzadeh
Electrocardiogram (ECG) can be reliably used as a measure to monitor the functionality of the cardiovascular system.