追踪大模型后训练中价值对齐的动态变化，揭秘AI价值观漂移的关键时刻
arXiv:2510.26707v2 Announce Type: replace-cross Abstract: As LLMs occupy an increasingly important role in society, they are more and more confronted …
利用LLM实现电商定价中长期价值对齐，KDD 2026 oral论文，AI赋能商业决策新范式。
arXiv:2606.26787v1 Announce Type: cross Abstract: Traditional dynamic pricing models in large-scale e-commerce suffer from limited interpretability, p…
即使对齐训练完美，大模型推理仍会偏离目标价值，文中用数学形式化定义了这一风险缺口。
arXiv:2606.20624v1 Announce Type: new Abstract: Significant progress has been made in aligning LLMs with target value functions. We argue that, even w…
心理学理论赋能大模型，诱导LLM展现类人价值行为，探索AI对齐新路径
arXiv:2605.30036v1 Announce Type: new Abstract: Large Language Models (LLMs) demonstrate a remarkable capacity to adopt different personas and roles; …
用潜在激活引导破解大模型文化同质化，让AI价值观更贴合人类多样文明
arXiv:2605.26365v1 Announce Type: new Abstract: Large Language Models (LLMs) often exhibit homogenized cultural perspectives. While the World Values S…
提出PICACO方法，利用总相关优化实现大模型的多元上下文价值对齐，减少有害输出同时适配多元偏好。
arXiv:2507.16679v3 Announce Type: replace-cross Abstract: In-Context Learning has shown great potential for aligning Large Language Models (LLMs) with…
通过缝合价值函数实现扩散模型高效对齐，显著提升生成图像质量与一致性，为AI生成提供新范式
arXiv:2605.19804v1 Announce Type: cross Abstract: For practical use, diffusion- or flow-based generative models must be aligned with task-specific rew…
提出GraphRAG框架将原则转为价值指令，解决LLM智能体在自认知、困境决策及情绪上的对齐缺陷。
arXiv:2605.14034v1 Announce Type: new Abstract: Wide applications of LLM-based agents require strong alignment with human social values. However, curr…