STaD: Scaffolded Task Design for Identifying Compositional Skill Gaps in LLMs

Documenti analoghi

• Split, Unlearn, Merge: Leveraging Data Attributes for More Effective Unlearning in LLMs
  di: Kadhe, Swanand Ravindra, et al.
  Pubblicazione: (2024)
• Runtime-Structured Task Decomposition for Agentic Coding Systems
  di: Asthana, Shubhi, et al.
  Pubblicazione: (2026)
• SafeMERGE: Preserving Safety Alignment in Fine-Tuned Large Language Models via Selective Layer-Wise Model Merging
  di: Djuhera, Aladin, et al.
  Pubblicazione: (2025)
• Fixing It in Post: A Comparative Study of LLM Post-Training Data Quality and Model Performance
  di: Djuhera, Aladin, et al.
  Pubblicazione: (2025)
• When Data is the Algorithm: A Systematic Study and Curation of Preference Optimization Datasets
  di: Djuhera, Aladin, et al.
  Pubblicazione: (2025)