Assessing Confidence in Large Language Models by Classifying Task Correctness using Similarity Features
- Debarun Bhattacharjya
- Balaji Ganesan
- et al.
- 2025
- ICLR 2025
Workshop paper
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
Q-function Decomposition with Intervention Semantics for Factored Action Spaces
- Junkyu Lee
- Tian Gao
- et al.
- 2025
- AAAI 2025
Workshop paperAbductive Reasoning in Logical Credal Networks
- Radu Marinescu
- Junkyu Lee
- et al.
- 2024
- NeurIPS 2024
Conference paperConsistency-based Black-box Uncertainty Quantification for Text-to-SQL
- Debarun Bhattacharjya
- Balaji Ganesan
- et al.
- 2024
- NeurIPS 2024
Workshop paperA Framework for Agents Guiding Foundation Models through Knowledge and Reasoning
- Debarun Bhattacharjya
- Junkyu Lee
- et al.
- 2024
- IJCAI 2024
Workshop paperSome Orders Are Important: Partially Preserving Orders in Top-Quality Planning
- Michael Katz
- Junkyu Lee
- et al.
- 2024
- SoCS 2024
Conference paperA Human-in-the-loop API Sequencing Tool Powered by AI Planning
- Jung koo Kang
- Tathagata Chakraborti
- et al.
- 2024
- ICAPS 2024
Demo paperLarge Language Models as Planning Domain Generators
- James Oswald
- Kavitha Srinivas
- et al.
- 2024
- ICAPS 2024
Conference paperUnifying and Certifying Top-Quality Planning
- Michael Katz
- Junkyu Lee
- et al.
- 2024
- ICAPS 2024
Conference paperLarge Language Models as Planning Domain Generators
- James Oswald
- Kavitha Srinivas
- et al.
- 2024
- AAAI 2024
Conference paper
Patents
- US
- 12675731
- US
- I919230
Projects
Top collaborators
RM
Radu Marinescu
Research Staff Member
AP
Alessandra Pascale
Senior Research Scientist and manager, Algorithms and Applications, PDEs in Partnerships
GR
Gaetano Rossiello
Staff Research Scientist
TT
Tigran Tchrakian
Research Scientist