Researchers · Interviewed at EACL 2026

Atoosa Chegini

University of Maryland / Apple

Reasoning Can Hurt LLM Safety?! Rethinking Accuracy in AI Systems (EACL 2026)

EACL 2026 · April 6, 2026 · 22 min

Reasoning Can Hurt LLM Safety?! Rethinking Accuracy in AI Systems (EACL 2026)

In this episode of #WiAIRpodcast, we dive into a subtle but critical question: Does adding reasoning actually make LLMs safer and more reliable?

Paper:

More from EACL 2026

All event interviews →