Picture for Itay Itzhak

Itay Itzhak

DOVE: A Large-Scale Multi-Dimensional Predictions Dataset Towards Meaningful LLM Evaluation

Add code
Mar 04, 2025
Viaarxiv icon

Trust Me, I'm Wrong: High-Certainty Hallucinations in LLMs

Add code
Feb 18, 2025
Viaarxiv icon

Instructed to Bias: Instruction-Tuned Language Models Exhibit Emergent Cognitive Bias

Add code
Aug 01, 2023
Viaarxiv icon

Models In a Spelling Bee: Language Models Implicitly Learn the Character Composition of Tokens

Add code
Aug 25, 2021
Figure 1 for Models In a Spelling Bee: Language Models Implicitly Learn the Character Composition of Tokens
Figure 2 for Models In a Spelling Bee: Language Models Implicitly Learn the Character Composition of Tokens
Figure 3 for Models In a Spelling Bee: Language Models Implicitly Learn the Character Composition of Tokens
Figure 4 for Models In a Spelling Bee: Language Models Implicitly Learn the Character Composition of Tokens
Viaarxiv icon