A new stratified per-question probability-gap metric shows that existing contamination mitigation strategies overstate restoration, and a step-wise decoding cap (RailCap) achieves the lowest measured gap.
Unveiling the spectrum of data contamination in language model: A survey from detection to remediation
4 Pith papers cite this work, alongside 5 external citations. Polarity classification is still indexing.
4
Pith papers citing it
5
external citations · Crossref
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
A new paired-prompt protocol reveals alignment-pipeline-specific heterogeneity in how open-weight LLMs respond to evaluation versus deployment framings.
MISS-QA, a new benchmark for information-seeking QA over schematic diagrams, shows the best open-source multimodal model at 61.6% accuracy versus 89.0% for human experts.
Introduces a parameter-driven framework for data attribution in LLMs that enables negotiation among creators, users, and intermediaries to meet stakeholder goals within the data economy.
citing papers explorer
-
Zero Gap Is Not Restoration: Stratified Per-Question Probability Evaluation and Step-wise Mitigation of Benchmark Contamination
A new stratified per-question probability-gap metric shows that existing contamination mitigation strategies overstate restoration, and a step-wise decoding cap (RailCap) achieves the lowest measured gap.
-
Measuring Evaluation-Context Divergence in Open-Weight LLMs: A Paired-Prompt Protocol with Pilot Evidence of Alignment-Pipeline-Specific Heterogeneity
A new paired-prompt protocol reveals alignment-pipeline-specific heterogeneity in how open-weight LLMs respond to evaluation versus deployment framings.
-
Can Multimodal Foundation Models Understand Schematic Diagrams? An Empirical Study on Information-Seeking QA over Scientific Papers
MISS-QA, a new benchmark for information-seeking QA over schematic diagrams, shows the best open-source multimodal model at 61.6% accuracy versus 89.0% for human experts.
-
A Human-Centric Framework for Data Attribution in Large Language Models
Introduces a parameter-driven framework for data attribution in LLMs that enables negotiation among creators, users, and intermediaries to meet stakeholder goals within the data economy.