What Happened in LLMs Layers when Trained for Fast vs. Slow Thinking: A Gradient Perspective
Paper
•
2410.23743
•
Published
•
59
Joanna Liang
joliang17
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 1 month ago
What Happened in LLMs Layers when Trained for Fast vs. Slow Thinking: A
Gradient Perspective
authored
a paper
about 1 month ago
CFMatch: Aligning Automated Answer Equivalence Evaluation with Expert
Judgments For Open-Domain Question Answering
authored
a paper
about 1 month ago
PANDA (Pedantic ANswer-correctness Determination and
Adjudication):Improving Automatic Evaluation for Question Answering and Text
Generation
Organizations
joliang17's activity
upvoted
2
papers
about 1 month ago