TextReg mitigates prompt distributional overfitting via regularized text-space optimization, reporting up to +16.5% OOD accuracy gains over prior methods on reasoning benchmarks.
Large language models are human-level prompt engineers
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
Generative video models exhibit emergent zero-shot capabilities across perception, manipulation, and basic reasoning tasks.
A systematic review that categorizes prompting strategies for LLM-based code summarization, assesses their effectiveness, and identifies gaps in research and evaluation practices.
citing papers explorer
-
TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization
TextReg mitigates prompt distributional overfitting via regularized text-space optimization, reporting up to +16.5% OOD accuracy gains over prior methods on reasoning benchmarks.
-
Video models are zero-shot learners and reasoners
Generative video models exhibit emergent zero-shot capabilities across perception, manipulation, and basic reasoning tasks.
-
Prompt-Driven Code Summarization: A Systematic Literature Review
A systematic review that categorizes prompting strategies for LLM-based code summarization, assesses their effectiveness, and identifies gaps in research and evaluation practices.