arXiv:2607. 20440v1 Announce Type: cross Abstract: Proprietary large language models (LLMs) entail substantial intellectual and financial investment, making them valuable intellectual property (IP).
arXiv:2608. 09542v1 Announce Type: cross Abstract: Large reasoning models (LRMs) achieve remarkable success on complex tasks but remain vulnerable to harmful prompts that induce unsafe outputs.
TraceForge introduces a two‑stage training method that generates reasoning traces in the style of a target model family, using supervised learning followed by adversarial refinement. The system produces traces that are judged as authentic with scores comparable to real traces, and when applied to teacher answers, it improves performance on coding benchmarks such as HumanEval+ and MBPP+. The approach addresses the limitation of existing models that only return answers without detailed reasoning, enabling more transparent and learnable outputs.
The paper introduces a minimax framework to analyze the trade-off between model utility and vulnerability to distillation attacks, featuring an adaptive evaluation rule that reweights high-value examples and a teacher-side defense that suppresses outputs most useful for imitation. It proposes a cheap, forward-pass-only defense called Product-of-Experts (PoE) that combines the teacher with a proxy student during generation. Empirical results show a significant passive–adaptive gap, with adaptive students recovering more capability than passive evaluation suggests, narrowing the robustness gap between expensive defenses and PoE while keeping PoE cheaper and preserving higher-quality reasoning traces.
arXiv:2607. 06855v1 Announce Type: new Abstract: On-policy distillation is a practical post-training recipe for large language models, supplying dense teacher supervision on the student's own trajectories.
arXiv:2606. 25059v2 Announce Type: replace-cross Abstract: Black-box LLMs (accessible only via API) are vulnerable to distillation attacks, in which an attacker queries the model and trains a student on its outputs.
arXiv:2609.22228v1 Announce Type: cross Abstract: Large language models increasingly rely on long chain-of-thought (CoT) trajectories for complex reasoning, but autoregressive generation brings subst...
arXiv:2609.38107v1 Announce Type: cross Abstract: Chain-of-thought traces are widely read as records of how models reach their answers, informing debugging, agent auditing, and claims about reasoning...
arXiv:2605. 07804v3 Announce Type: replace-cross Abstract: On-policy distillation (OPD) leverages dense teacher rewards to enhance reasoning models.
arXiv:2506. 07031v5 Announce Type: replace-cross Abstract: Emerging Large Reasoning Models (LRMs) consistently excel in mathematical and reasoning tasks, showcasing remarkable capabilities.
arXiv:2605. 15532v3 Announce Type: replace-cross Abstract: Distillation enables compact Vision-Language Models (VLMs) to obtain strong reasoning capabilities, yet the prompts driving this process are typically chosen via simple heuristics or aggregated from off-the-shelf datasets.
The paper introduces COLAGUARD, a guardrail model that embeds multi-step safety reasoning into a continuous latent space, allowing efficient hidden-state propagation during inference. Compared to existing methods, COLAGUARD achieves an 8.24‑point macro‑F1 improvement over Llama Guard 3 and matches the explicit reasoning baseline GuardReasoner, while delivering a 12.9× speedup and a 22.4× reduction in token usage across ten moderation settings and eight safety benchmarks.