Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
MGI: Member vs Generated Inference
Bihe Zhao, Michel Meintz, Juangui Xu +2
As generative models increasingly produce samples that are indistinguishable from human-created content, it becomes difficult to determine whether a given data point was part of a…
cs.LG2025
Unlocking Post-hoc Dataset Inference with Synthetic Data
Bihe Zhao, Pratyush Maini, Franziska Boenisch +1
The remarkable capabilities of Large Language Models (LLMs) can be mainly attributed to their massive training datasets, which are often scraped from the internet without respectin…