Find a story
Search Spins
Search titles, summaries, and missing voices across published articles — press releases, announcements, and media coverage.
2 results for “instruction tuning”
SPIN Processed News Frame: The Fog
Task Competence Is Not Instruction Following: Evaluating Instruction-Conflicting Behavior in Small Language Models
A research paper on arXiv demonstrates that small instruction-tuned language models often ignore conflicting instructions while maintaining high task accuracy, revealing a fundamental decoupling between task competence and instruction following.
Spin 35% Claim Present in Source AI Risk Moderate
arXiv Computation and Language
Jul 23, 2026
SPIN Processed News Frame: The Hype
Learning from Synthetic Data without Model Collapse in Iterative Instruction Tuning
Researchers propose KITE, a two-stage framework for iterative instruction tuning using synthetic data that aims to prevent model collapse by diagnosing and mitigating competence polarization—where strong skills are reinforced while weak ones degrade—across multiple open-source LLMs.
Spin 45% Claim Present in Source AI Risk Moderate
arXiv Computation and Language
Jul 21, 2026