Min-K% Prob detects pretraining data in LLMs by flagging outlier low-probability words in text, achieving 7.4% better performance than prior methods on the new WIKIMIA benchmark.
Data contamination: From memorization to exploitation
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
support 1representative citing papers
SSA harness matches frontier model pass@1 scores on agent benchmarks and 138k trajectory analysis in code state-spaces shows model-specific differences in edit frequency, testing activity, and phase transitions.
DualEval jointly calibrates LLM abilities and item difficulties/sharpness in a shared latent space using static labels and reward-model scores to unify benchmark and arena-style evaluation.
citing papers explorer
-
Detecting Pretraining Data from Large Language Models
Min-K% Prob detects pretraining data in LLMs by flagging outlier low-probability words in text, achieving 7.4% better performance than prior methods on the new WIKIMIA benchmark.
-
Dissecting model behavior through agent trajectories
SSA harness matches frontier model pass@1 scores on agent benchmarks and 138k trajectory analysis in code state-spaces shows model-specific differences in edit frequency, testing activity, and phase transitions.
-
DualEval: Joint Model-Item Calibration for Unified LLM Evaluation
DualEval jointly calibrates LLM abilities and item difficulties/sharpness in a shared latent space using static labels and reward-model scores to unify benchmark and arena-style evaluation.