推理时对齐新思路：用上下文学习先构造高质量候选，突破Best-of-N依赖生成质量的局限。
arXiv:2607.03453v1 Announce Type: cross Abstract: Inference-time alignment methods, such as Best-of-$N$, offer a flexible alternative to training-base…
提出推理时对齐迁移新方法，跨词汇混合logit无需额外训练即可转移对齐能力，为大模型高效部署提供新思路。
arXiv:2606.12342v1 Announce Type: cross Abstract: Domain fine-tuning degrades the safety of large language models: fine-tuned specialists readily comp…
无需微调，推理阶段通过约束优化实现黑盒大模型安全对齐，兼顾性能与安全性。
arXiv:2510.09330v3 Announce Type: replace Abstract: Ensuring that large language models (LLMs) comply with safety requirements is a central challenge …
探索推理时对齐与执行轨迹的新方法，为AI系统行为优化提供理论框架。
arXiv:2605.21516v1 Announce Type: cross Abstract: Harness engineering has emerged as an important inference-time technique for large language model (L…