Semantic Regexes: Auto-Interpreting LLM Features with a Structured Language

Documenti analoghi

• Compress and Compare: Interactively Evaluating Efficiency and Behavior Across ML Model Compression Experiments
  di: Boggust, Angie, et al.
  Pubblicazione: (2024)
• Exploring Empty Spaces: Human-in-the-Loop Data Augmentation
  di: Yeh, Catherine, et al.
  Pubblicazione: (2024)
• Constructive Circuit Amplification: Improving Math Reasoning in LLMs via Targeted Sub-Network Updates
  di: Prakash, Nikhil, et al.
  Pubblicazione: (2025)
• Abstraction Alignment: Comparing Model-Learned and Human-Encoded Conceptual Relationships
  di: Boggust, Angie, et al.
  Pubblicazione: (2024)
• Evaluating Long Range Dependency Handling in Code Generation LLMs
  di: Assogba, Yannick, et al.
  Pubblicazione: (2024)