Researchers · Interviewed at EACL 2026

Maor Juliet Lavi

Tel Aviv University

Why LLMs Hallucinate, and How to Make Them Say "I Don't Know" (EACL 2026)

EACL 2026 · April 3, 2026 · 15 min

Why LLMs Hallucinate, and How to Make Them Say "I Don't Know" (EACL 2026)

LLMs are notoriously overconfident, but can we teach them to admit uncertainty?

In this episode, Maor Juliet Lavi (Tel Aviv University) presents her EACL 2026 paper on Detecting Unanswerability in Large Language Models with Linear Directions.

More from EACL 2026

All event interviews →