Modelpedia
Work in progress
About
Findings
Models
Concepts
Methods
Datasets
Sources
Light
Dark
Breaking Free from MMI: A New Frontier in Rationalization by Probing Input Utilization
2025-01-22
· ICLR 2025 Poster ·
anchor
Findings
IC-294
Llama-3.1-8B-Instruct with 2-shot prompting achieves limited rationale extraction quality (F1 15.7–48.3) across four text classification datasets