用互信息架起多目标探索与偏好优化的桥梁，ECML/PKDD 2026 最新研究，值得深度研读。
arXiv:2607.01392v1 Announce Type: new Abstract: Aligning large language models with diverse and heterogeneous human values requires multi-objective al…
用神经网络端到端监督训练直接学习互信息估计函数，开辟数据驱动估计新范式
arXiv:2511.18945v4 Announce Type: replace Abstract: We propose a fully data-driven approach to designing mutual information (MI) estimators. Since any…
新研究揭示LLM推理过程不对称性，提出跨架构分析避免单探针偏见
arXiv:2605.28006v1 Announce Type: cross Abstract: Understanding how LLMs reason is hindered by a practical asymmetry: while their generated outputs ar…
仅用LLM和对比估计提示就能预测点互信息，PromptNCE方法简洁高效，值得关注。
arXiv:2605.21776v1 Announce Type: new Abstract: Estimating mutual information from text usually requires training a task-specific critic, which limits…