arXiv:2609.36956v1 Announce Type: cross Abstract: Manipulating next-token probabilities during generation can bypass the safety alignment of large language models. Existing approaches, however, rely...
arXiv:2606. 09135v1 Announce Type: cross Abstract: We demonstrate that widely deployed Large Language Model (LLM) inference stacks harbor a steganographic channel that requires no modification to model weights, sampling code, or output distributions.
arXiv:2608.23375v1 Announce Type: cross Abstract: Gumbel-based inference verification bounds LLM weight exfiltration by only forgiving token choices that plausibly arise from honest GPU nondeterminis...
arXiv:2607. 20791v1 Announce Type: new Abstract: High-temperature sampling is one of the primary mechanisms for increasing diversity in LLMs.
arXiv:2606. 04778v1 Announce Type: new Abstract: Safety-aligned Large Language Models (LLMs) remain vulnerable to interventions during inference that redirect generation toward harmful outputs.
arXiv:2608. 10621v1 Announce Type: new Abstract: Recent research on Large Language Model (LLM) safety has widely adopted guardrails to identify unsafe LLM outputs.
The paper introduces a lightweight single‑layer sampler that allows masked diffusion language models to approximate joint sampling of multiple tokens in a single full‑model forward pass. By training the sampler to mimic exact joint sampling from a frozen diffusion model, the authors enable parallel unmasking of tokens while maintaining a close match to the true joint distribution. Experiments on Dream‑7B and Llada‑7B models show that unmasking four tokens per denoising step yields a MAUVE score of 0.87, a substantial improvement over the marginal baseline of 0.31.
The paper introduces Fork-dLLM, a hybrid sampling strategy for diffusion language models that combines parallel token generation with autoregressive ordering only at uncertain fallback steps, thereby avoiding the flexibility trap that reduces generation diversity. It also presents ForkGRPO, an extension that applies the GRPO objective selectively during post‑training rollouts, preserving policy‑likelihood ratios while cutting rollout and optimization costs. Experiments show Fork-dLLM achieves pass@k scaling comparable to autoregressive sampling but 2–3× more efficient, and ForkGRPO matches or surpasses AR‑based GRPO baselines at significantly lower training expense.
SpecCTMC is a training‑free speculative sampler for masked diffusion language models that reduces the sequential bottleneck of exact continuous‑time sampling. It updates tokens successively using previously computed predictions, evaluates intermediate states in parallel, and applies an exact acceptance‑and‑correction step, thereby preserving the joint distribution of event times, generation order, and token values. Experiments on LLaDA‑8B‑Instruct and Dream‑v0‑Instruct‑7B show 1.73‑4.38× fewer sequential model evaluations while maintaining the reference sampling distribution.
arXiv:2606. 10487v1 Announce Type: cross Abstract: Deploying large language models in user-facing systems requires efficient output safety filtering.
arXiv:2606.04483v2 Announce Type: replace Abstract: Existing jailbreaks against aligned LLMs are discrete artifacts whose surface forms are easy to fingerprint and patch. We argue that the broader fa...
arXiv:2608. 02995v1 Announce Type: cross Abstract: Modern large language models (LLMs) exhibit activation sparsity, wherein only a subset of their neurons is activated for given input tokens.