arXiv:2607. 16207v1 Announce Type: new Abstract: Membership inference attacks (MIAs) test whether a candidate example appeared in a model's training data.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.
arXiv:2607.16207v3 Announce Type: replace Abstract: Membership inference attacks (MIAs) test whether a candidate example was used to train a language model. Existing attacks on fine-tuned discrete di...
arXiv:2606. 02544v1 Announce Type: cross Abstract: Diffusion large language models (dLLMs) have recently emerged as a promising alternative to autoregressive (AR) LLMs, offering faster inference through parallel or blockwise decoding.
The paper introduces Independent Token Sampling (ITS), a query‑efficient method for detecting memorized training data in diffusion large language models (dLLMs). ITS selects token sets with weak internal dependency by approximating cumulative conditional mutual information using an attention‑derived pairwise dependency proxy and promotes diversity across sampling rounds. Experiments show ITS outperforms existing baselines, improving AUC by 0.18 on the ArXiv dataset while remaining effective under limited query budgets.
arXiv:2607. 20467v1 Announce Type: new Abstract: While parallel decoding is central to the efficiency of Diffusion Large Language Models (dLLMs), current strategies are often hindered by overly conservative confidence thresholds.
arXiv:2609.39859v1 Announce Type: new Abstract: Masked diffusion language models (dLLMs) have shown strong potential for faster inference through parallel token generation when combined with confiden...
arXiv:2606. 10829v1 Announce Type: cross Abstract: Masked diffusion language models can reduce inference steps by revealing multiple tokens per denoising iteration, but this parallelism is fragile: positions that are individually confident may be unsafe to commit together when their predictions are coupled.