LM Control, LM Steering, LM Alignment
2025 – Present
Hallucination, Factuality, Faithfulness
2024 – Present
Linguistic Uncertainty
2023 – Present
Uncertainty Quantification, Uncertainty Estimation
2023 – Present
Decoding algorithms, Constrained Decoding, LM Control
2023 – Present
Natural Language Processing
2021 – Present
Calibration in NLP
2021 – Present
Large Language Models
2021 – Present
Confidence, Uncertainty, LLMs
2021 – Present
Model Evaluation
2019 – Present
Machine Learning
2017 – Present
Fairness in NLP
2022 – 2024
Responsible AI
2019 – 2022
Algorithmic Fairness
2019 – 2022
Explainable AI
2019 – 2021
Multi-Objective Optimization
2017 – 2019