Junkyu Lee

Title

Research Scientist

Bio

I am interested in designing algorithms for solving large-scale sequential decision-making problems. My research focuses on inference and learning algorithms in graphical models, AI planning, and reinforcement learning.

Publications

FactReasoner: A Probabilistic Approach to Long-Form Factuality Assessment for Large Language Models
- - Radu Marinescu
  - Debarun Bhattacharjya
  - et al.
- 2025
- EMNLP 2025
The Consistency Hypothesis in Uncertainty Quantification for Large Language Models
- - Quan Xiao
  - Debarun Bhattacharjya
  - et al.
- 2025
- UAI 2025
Q-function Decomposition with Intervention Semantics for Factored Action Spaces
- - Junkyu Lee
  - Tian Gao
  - et al.
- 2025
- AISTATS 2025
Rationalization Models for Text-to-SQL
- - Gaetano Rossiello
  - Nhan Pham
  - et al.
- 2025
- ICLR 2025
Assessing Confidence in Large Language Models by Classifying Task Correctness using Similarity Features
- - Debarun Bhattacharjya
  - Balaji Ganesan
  - et al.
- 2025
- ICLR 2025
Q-function Decomposition with Intervention Semantics for Factored Action Spaces
- - Junkyu Lee
  - Tian Gao
  - et al.
- 2025
- AAAI 2025
Abductive Reasoning in Logical Credal Networks
- - Radu Marinescu
  - Junkyu Lee
  - et al.
- 2024
- NeurIPS 2024
Consistency-based Black-box Uncertainty Quantification for Text-to-SQL
- - Debarun Bhattacharjya
  - Balaji Ganesan
  - et al.
- 2024
- NeurIPS 2024
A Framework for Agents Guiding Foundation Models through Knowledge and Reasoning
- - Debarun Bhattacharjya
  - Junkyu Lee
  - et al.
- 2024
- IJCAI 2024
Some Orders Are Important: Partially Preserving Orders in Top-Quality Planning
- - Michael Katz
  - Junkyu Lee
  - et al.
- 2024
- SoCS 2024

Visit Google Scholar

Projects

AI Planning

Top collaborators

Radu Marinescu

Research Staff Member

Balaji Ganesan

Senior Research Engineer

Alessandra Pascale

Senior Research Scientist and manager, Accelerated Discovery, NLP and Inference on Graphs

Gaetano Rossiello

Staff Research Scientist