Humans and Machines Lab
Popular repositories Loading
-
Illusion-of-Reasoning
Illusion-of-Reasoning PublicForked from liv-daliberti/Illusion-of-Reasoning
Do reasoning models have "Aha!" moments? Prior work suggests that models like DeepSeek-R1-Zero undergo sudden realizations that lead to accurate outputs. Yet it remains unclear whether such shifts …
Python 3
-
-
LLM-TA-Companion
LLM-TA-Companion PublicLanguage Models as Teaching Assistant Companions in Proof-Based Courses
-
ai-feedback-provision
ai-feedback-provision PublicAI Assistance for Discretionary Work: Increasing Feedback Provision in Higher Education
Jupyter Notebook
Repositories
- ai-feedback-provision Public
AI Assistance for Discretionary Work: Increasing Feedback Provision in Higher Education
- Illusion-of-Reasoning Public Forked from liv-daliberti/Illusion-of-Reasoning
Do reasoning models have "Aha!" moments? Prior work suggests that models like DeepSeek-R1-Zero undergo sudden realizations that lead to accurate outputs. Yet it remains unclear whether such shifts in reasoning strategy actually improve performance. In this repo, we attempt to operationalize "Aha!" event occurence and detection.
Top languages
Loading…
Most used topics
Loading…