NAACL 2024, June 20
Program
Session 1 (9:00 – 10:30 am):
09:00 – 09:10 am Workshop Introduction and Brief Program Overview
09:10 – 10:00 am Keynote Talk 1
Show It or Tell It? Text, Visualization, and Their Combination
Marti Hearst, UC Berkeley
10:00 – 10:30 am Invited Talk 1
Training Social Skills via Human-AI Collaboration
Diyi Yang, Stanford
AM Workshop Break (10:30 – 11:00 am)
Session 2 (11:00 am – 12:30 pm):
Regular Papers (15 min each)
APE: Active Learning-based Tooling for Finding Informative Few-shot Examples for LLM-based Entity Matching
Kun Qian, Yisi Sang, Farima Bayat†, Anton Belyi, Xianqi Chu, Yash Govind, Samira Khorshidi, Rahul Khot, Katherine Luna, Azadeh Nikfarjam, Xiaoguang Qi, Fei Wu, Xianhan Zhang and Yunyao Li
Towards Optimizing and Evaluating a Retrieval Augmented QA Chatbot using LLMs with Human-in-the-Loop
Anum Afzal, Alexander Kowsik, Rajna Fani and Florian Matthes
Evaluation and Continual Improvement for an Enterprise AI Assistant
Akash Maharaj, Kun Qian, Uttaran Bhattacharya, Sally Fang, Horia Galatanu, Manas Garg, Rachel Hanessian, Nishant Kapoor, Ken Russell, Shivakumar Vaithyanathan and Yunyao Li
Mini-DA: Improving Your Model Performance through Minimal Data Augmentation Using LLM
Shuangtao Yang, Xiaoyi Liu, Xiaozheng Dong and Bo Fu
CURATRON: Complete and Robust Preference Data for Rigorous Alignment of Large Language Models
Son The Nguyen, Niranjan Uma Naresh and Theja Tulabandhula
Invited Paper from Findings of NAACL’24 (15 min)
Asking More Informative Questions for Grounded Retrieval
Sedrick Keh, Justin T. Chiu, Daniel Fried
Lunch Break (12:30 – 2:00 pm)
Session 3 (2:00 – 3:20 pm):
2:00 – 2:50 pm Keynote Talk 2
Show Reasoning Myths about Language Models: What is Next?
Dan Roth, University of Pennsylvania
2:50 – 3:20 Invited Papers from Findings of NAACL’24 (15 min each):
Human-in-the-Loop Synthetic Text Data Inspection with Provenance Tracking
Hong Jin Kang, Fabrice Harel-Canada, Muhammad Ali Gulzar, Violet Peng, Miryung Kim
LETI: Learning to Generate from Textual Interactions
Xingyao Wang, Hao Peng, Reyhaneh Jabbarv. and Heng Ji
PM Workshop Break (3:20 – 4:00 pm)
Session 4 (4:00 – 5:30 pm):
4:00 – 4:30 pm Invited Talk 2
Model-Aided Human Annotation at Scale
Hadas Kotek, Apple
4:30 – 5:15 pm Panel: Opportunities and Challenges of Data Science with Human-in-the-Loop in the Age of Large Language Models
Panelists: Dan Roth, Diyi Yang, Hadas Kotek
Moderator: Yunyao Li