Rethinking Psychometric Evaluation of LLMs: When and Why Self-Reports Predict Behavior
Paper • 2606.12730 • Published • 6
Peiyang Song
p-song1
AI & ML interests
Formal Reasoning, Natural Language Reasoning, Neuro-Symbolic AI, AI4MATH, LLMs
Recent Activity
upvoted a paper 18 days ago
Rethinking Psychometric Evaluation of LLMs: When and Why Self-Reports Predict Behavior upvoted a paper about 1 month ago
Interactive Evaluation Requires a Design Science authored a paper 5 months ago
Steer2Adapt: Dynamically Composing Steering Vectors Elicits Efficient Adaptation of LLMsOrganizations
upvoted a paper 18 days ago
upvoted a paper about 1 month ago
authored a
paper 5 months ago
upvoted a paper 5 months ago
submitted a
paper to Daily Papers 5 months ago
authored a
paper 5 months ago
upvoted a paper 5 months ago
submitted a
paper to Daily Papers 5 months ago
commented a
paper 5 months ago
upvoted a paper 5 months ago
commented a
paper 5 months ago
upvoted a paper 5 months ago
authored a
paper 6 months ago
upvoted a paper 6 months ago
authored 6
papers 7 months ago
LeanAgent: Lifelong Learning for Formal Theorem Proving
Paper • 2410.06209 • Published • 2
The Personality Illusion: Revealing Dissociation Between Self-Reports & Behavior in LLMs
Paper • 2509.03730 • Published • 3
Lean Copilot: Large Language Models as Copilots for Theorem Proving in Lean
Paper • 2404.12534 • Published • 1
In-Context Learning May Not Elicit Trustworthy Reasoning: A-Not-B Errors in Pretrained Language Models
Paper • 2409.15454 • Published • 2
Creative and Context-Aware Translation of East Asian Idioms with GPT-4
Paper • 2410.00988 • Published • 4
LeanProgress: Guiding Search for Neural Theorem Proving via Proof Progress Prediction
Paper • 2502.17925 • Published • 1