无需训练即可在token级别精准引导大模型，让AI协作写作更贴合个人风格。
arXiv:2608.06069v1 Announce Type: new Abstract: While Large Language Models (LLMs) show great promise for personalization, they often lack specialized…
逐Token定位大模型谄媚行为，用归因引导精准纠偏，提升模型可靠性。
arXiv:2607.28906v1 Announce Type: new Abstract: Sycophancy refers to the tendency for large language models (LLMs) to match user beliefs at the cost o…
针对多模态大语言模型压缩难题，提出Token级响应-视觉注意力引导，提升蒸馏效果
arXiv:2607.02593v1 Announce Type: cross Abstract: While knowledge distillation (KD) is widely adopted for training lightweight models by leveraging su…
从Token级视角洞察代码任务中的LLM行为，让模型决策过程更透明可解析。
arXiv:2607.01235v1 Announce Type: cross Abstract: Understanding how Large Language Models (LLMs) make token-level decisions during code generation rem…
在token生成前用位掩码策略拦截越狱攻击，reskSecure实现LLM安全防火墙新思路。
Links: PyPI: https://pypi.org/project/resksecure GitHub: https://github.com/Resk-Security/reskSecure Web: https://resk.fr Most prompt injection and ja…
提出平衡token级策略优化方法，精准缓解大模型幻觉问题
arXiv:2606.15893v1 Announce Type: new Abstract: Hallucinations remain a major obstacle to deploying large language models (LLMs) in knowledge-intensiv…
通过学习token级重要性优化大模型遗忘机制，比传统方法更精准高效。
arXiv:2606.06320v1 Announce Type: cross Abstract: Machine unlearning aims to remove targeted knowledge from a trained model while preserving its gener…
提出基于锚定token级logits的LLM越狱检测方法SelfGrader，高效识别对抗性攻击。
arXiv:2604.01473v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are powerful tools for answering user queries, yet they remain …
用特权信息生成密集token级监督，提升LLM推理能力的新蒸馏方法。
arXiv:2605.28791v1 Announce Type: cross Abstract: On-policy self-distillation (SD) improves LLM reasoning by using teacher-side privileged information…
利用视觉信号增强视觉-语言模型令牌级不确定性估计，提升生成稳健性，前沿研究值得关注。
arXiv:2605.27136v1 Announce Type: new Abstract: Uncertainty quantification (UQ) remains a critical challenge in Large Vision Language Models (LVLMs) f…
提出Token级LLM协作新方法FusionRoute，突破领域模型融合粒度，让小模型协同超越大模型。
arXiv:2601.05106v4 Announce Type: replace-cross Abstract: Large language models (LLMs) exhibit strengths across diverse domains. However, achieving st…
提出TokenRatio方法，通过比值匹配实现原则性token级偏好优化，突破DPO的序列级局限，更精准对齐语言模型
arXiv:2605.12288v2 Announce Type: replace-cross Abstract: Direct Preference Optimization (DPO) is a widely used RL-free method for aligning language m…