Modelpedia
Work in progress
About
Findings
Models
Concepts
Methods
Datasets
Sources
Light
Dark
Physics of Language Models: Part 3.2, Knowledge Manipulation
2025-01-22
· ICLR 2025 Poster ·
anchor
Findings
IC-474
GPT-4, GPT-4o, and Llama-3.1-405B fail at knowledge classification and comparison without chain-of-thought
IC-475
GPT-4, GPT-3.5, GPT-4o, and Llama-3.1-405B fail at inverse knowledge search regardless of prompting
IC-476
GPT-4 and GPT-3.5 show strong positional bias in Chinese idiom character completion