Suzan Verberne
Papers
3
Total Citations
47
H-Index
3
About
Suzan Verberne is a leading researcher in natural language processing (NLP), with a focus on the reasoning and affective capabilities of large language models (LLMs). Her work explores how LLMs, particularly generative pre-trained transformers like ChatGPT, can perform complex cognitive tasks. In her highly cited 2023 paper, "Fine-grained Affective Processing Capabilities Emerging from Large Language Models" (21 citations), she demonstrated that ChatGPT can execute affective computing tasks—such as emotion detection and sentiment analysis—through zero-shot prompting alone, revealing emergent emotional intelligence in these models. Verberne also made significant contributions to understanding LLM reasoning with her 2024 and 2025 surveys on "Multi-Step Reasoning with Large Language Models" (13 citations each), which systematically analyzed how models with billions of parameters handle logical inference and problem-solving. Her work has been instrumental in bridging the gap between traditional NLP benchmarks and the advanced in-context learning abilities of modern LLMs, highlighting both their strengths and limitations. Verberne's research is widely cited for its insights into the intersection of language, reasoning, and emotion, making her a key voice in the ongoing evolution of AI language systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2Multi-Step Reasoning with Large Language Models, a Survey13 citations · 2025
- 3Multi-Step Reasoning with Large Language Models, a Survey13 citations · 2024