3 papers
cs.CL2025
Synthetic Dataset for Evaluating Complex Compositional Knowledge for Natural Language Inference
Sushma Anand Akoju, Robert Vacareanu, Haris Riaz +2
We introduce a synthetic dataset called Sentences Involving Complex Compositional Knowledge (SICCK) and a novel analysis that investigates the performance of Natural Language Infer…
cs.CL2025
Data Contamination Quiz: A Tool to Detect and Estimate Contamination in Large Language Models
Shahriar Golchin, Mihai Surdeanu
We propose the Data Contamination Quiz (DCQ), a simple and effective approach to detect data contamination in large language models (LLMs) and estimate the amount of it. Specifical…
cs.CL2025
Memorization in In-Context Learning
Shahriar Golchin, Mihai Surdeanu, Steven Bethard +2
In-context learning (ICL) has proven to be an effective strategy for improving the performance of large language models (LLMs) with no additional training. However, the exact mecha…