Jad Kabbara

LLM Targeted Underperformance Disproportionately Impacts Vulnerable Users
Elinor Poole-Dayan, Deb Roy, Jad Kabbara  
Pre-print
[PAPER]    

AI-assisted sensemaking: Human-AI collaboration for the analysis and interpretation of recorded facilitated conversations
Jad Kabbara, Thanh-Mai Phan, Marina Rakhilin, Maya Detwiller, Dimitra Dimitrakopoulou and Deb Roy  
CHI 2025, Yokohama, Japan, April 2025
[PAPER]    

Bridging the Data Provenance Gap Across Text, Speech and Video
Shayne Longpre, Nikhil Singh, Manuel Cherep, Kushagra Tiwary, Joanna Materzynska, William Brannon, Robert Mahari, Naana Obeng-Marnu, ... , Caiming Xiong, Luis Villa, Stella Biderman, Alex Pentland, Sara Hooker, Jad Kabbara  
ICLR 2025, Vancouver, BC, Canada, April 2025
[PAPER]    

Bridging Context Gaps: Enhancing Comprehension in Long-Form Social Conversations Through Contextualized Excerpts
Shrestha Mohanty, Sarah Xuan, Jacob Jobraeel, Anurag Kumar, Deb Roy and Jad Kabbara  
COLING 2025, Abu Dhabi, UAE, January 2025
[PAPER]    

Consent in Crisis: The Rapid Decline of the AI Data Commons
Shayne Longpre, Robert Mahari, Ariel Lee, Campbell Lund, ..., Caiming Xiong, Luis Villa, Stella Biderman, Hanlin Li, Daphne Ippolito, Sara Hooker, Jad Kabbara, Alex ‘Sandy’ Pentland  
NeurIPS 2024, Vancouver, BC, Canada, December 2024
[PAPER]    

On the Relationship between Truth and Political Bias in Language Models
Suyash Fulay, William Brannon, Shrestha Mohanty, Cassandra Overney, Elinor Poole-Dayan, Deb Roy, Jad Kabbara  
EMNLP 2024, Miami, Florida, USA, December 2024
[PAPER]    

Fora: A corpus and framework for the study of facilitated dialogue
Hope Schroeder, Deb Roy and Jad Kabbara  
ACL 2024, Bangkok, Thailand, August 2024
[PAPER]     [DATA]    

Leveraging Large Language Models for Learning Complex Legal Concepts through Storytelling
Hang Jiang, Xiajie Zhang, Robert Mahari, Daniel Kessler, Eric Ma, Tal August, Irene Li, Sandy Pentland, Yoon Kim, Deb Roy and Jad Kabbara  
ACL 2024, Bangkok, Thailand, August 2024
[PAPER]    

Confidence Under the Hood: An Investigation into the Confidence-Probability Alignment in Large Language Models
Abhishek Kumar, Robert Morabito, Sanzhar Umbet, Jad Kabbara and Ali Emami  
ACL 2024, Bangkok, Thailand, August 2024
[PAPER]    

ConGraT: Self-Supervised Contrastive Pretraining for Joint Graph and Text Embeddings
William Brannon, Wonjune Kang, Suyash Fulay, Hang Jiang, Brandon Roy, Deb Roy and Jad Kabbara  
TextGraphs-17 @ACL 2024, Bangkok, Thailand, August 2024
[PAPER]    

Data Authenticity, Consent, & Provenance for AI are all broken: what will it take to fix them?
Shayne Longpre, Robert Mahari, Naana Obeng-Marnu, William Brannon, Tobin South, Katy Gero, Sandy Pentland and Jad Kabbara  
ICML 2024, Vienna, Austria, July 2024
[PAPER]    
Spotlight Paper [3.5% acceptance rate]

The Data Provenance Initiative: A Large Scale Audit of Dataset Licensing & Attribution in AI
Shayne Longpre, Robert Mahari, Anthony Chen, Naana Obeng-Marnu, Damien Sileo, William Brannon, Niklas Muennighoff, Nathan Khazam, Jad Kabbara, Kartik Perisetla, Xinyi Wu, Enrico Shippole, Kurt Bollacker, Tongshuang Wu, Luis Villa, Sandy Pentland, Sara Hooker  
Natural Machine Intelligence, July 2024
[PAPER]     [WEBSITE]    

PersonaLLM: Investigating the Ability of Large Language Models to Express Personality Traits
Hang Jiang, Xiajie Zhang, Xubo Cao, Cynthia Breazeal, Deb Roy and Jad Kabbara  
Findings of NAACL 2024, Mexico City, Mexico, June 2024
[PAPER]    
Preliminary version appeared as extended abstract at IC2S2 2023, Copenhagen, Denmark, July 2023.

Investigating the Effect of Pre-finetuning BERT Models on NLI Involving Presuppositions
Jad Kabbara and Jackie C.K. Cheung  
Findings of EMNLP 2023, Singapore, Singapore, December 2023
[PAPER]    

Debiasing should be Good and Bad: Measuring the Consistency of Debiasing Techniques in Language Models
Robert Morabito, Jad Kabbara and Ali Emami  
Findings of ACL 2023, Toronto, Canada, July 2023
[PAPER]    

Investigating the Performance of Transformer-Based NLI Models on Presuppositional Inferences
Jad Kabbara and Jackie C.K. Cheung  
COLING 2022, Gyeongju, Republic of Korea, October 2022
[PAPER]    
Best Short Paper Award

Post-Editing Extractive Summaries by Definiteness Prediction
Jad Kabbara and Jackie C.K. Cheung  
Findings of EMNLP 2021, Punta Cana, Dominican Republic, November 2021
[PAPER]    

Computational Investigations of Pragmatic Effects in Natural Language
Jad Kabbara  
NAACL Student Reseserch Workshop 2019, Minneapolis, Minnesota, USA, June 2019

Let's do it "again": A First Computational Approach to Detecting Adverbial Presupposition Triggers
Andre Cianflone*, Yulan Feng*, Jad Kabbara* and Jackie C.K. Cheung (* denotes equal contribution) 
ACL 2018, Melbourne, Australia, July 2018
[PAPER]     [DATA]    
Best Paper Award

Relevance Effect: Exploiting Bayesian Networks to Improve Supervised Learning
Ardavan S. Nobandegani*, Jad Kabbara* and Ioannis N. Psaromiligkos (* denotes equal contribution)  
IJCNN 2017, Anchorage, Alaska, USA, May 2017
[PAPER]    

Capturing Pragmatic Knowledge in Article Usage Prediction using LSTMs
Jad Kabbara, Yulan Feng and Jackie C.K. Cheung  
COLING 2016, Osaka, Japan, December 2016
[PAPER]    

Stylistic Transfer in Natural Language Generation Systems Using Recurrent Neural Networks
Jad Kabbara and Jackie C.K. Cheung  
Workshop on Uphill Battles in Language Processing 2016 (@ EMNLP 2016), Austin, Texas, USA, November 2016
[PAPER]    

Kernel Subspace Pursuit for Sparse Regression
Jad Kabbara and Ioannis N. Psaromiligkos  
Pattern Recognition Letters, January 2016
[PAPER]    

Improving the tracking ability of KRLS using kernel subspace pursuit
Jad Kabbara and Ioannis N. Psaromiligkos  
IEEE ICASSP 2014, Florence, Italy, May 2014
[PAPER]