Research Topics

Selected papers grouped by topic. Each tag on the homepage links here.

A quick index into the selected research on the homepage — grouped by the tags that appear on each tile.

reliability

The Reliability Paradox: Shortcut Learning & Language Model Calibration — HICSS 2025
Evaluating Language Models on Grooming Risk Estimation Using Fuzzy Theory — NAFIPS 2024

shortcut learning

The Reliability Paradox: Shortcut Learning & Language Model Calibration — HICSS 2025
Learning Shortcuts: On the Misleading Promise of NLU in Language Models — AIDPS 2025

responsible AI

Hire Me or Not? Examining Language Model Behavior with Occupation Attributes — COLING 2025

evaluation

Hire Me or Not? Examining Language Model Behavior with Occupation Attributes — COLING 2025
Learning Shortcuts: On the Misleading Promise of NLU in Language Models — AIDPS 2025
Evaluating Language Models on Grooming Risk Estimation Using Fuzzy Theory — NAFIPS 2024

language understanding

Learning Shortcuts: On the Misleading Promise of NLU in Language Models — AIDPS 2025
Low Anisotropy Sense Retrofitting (LASeR) — DeeLIO 2021

digital safety

Evaluating Language Models on Grooming Risk Estimation Using Fuzzy Theory — NAFIPS 2024