用反事实基准和训练方法破解大模型事实一致性与异质知识推理的排序难题
arXiv:2608.07838v1 Announce Type: new Abstract: Large language models (LLMs) have increasingly supported response generation grounded in user-provided…
多模态大模型里到底谁说了算？反事实归因方法精准定位决策关键模态，AI可解释性必读。
arXiv:2608.00076v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) increasingly support high-stakes decision making by combini…
解读实际因果的最新定义，辨析差异制造概念，为因果推理研究提供哲学依据。
arXiv:2606.24832v1 Announce Type: new Abstract: Over a series of seven papers, Andreas & G\"unther have introduced seven definitions of actual causati…
反事实推理优化LLM Agent记忆管理，创新性地解决工具使用中的上下文选择与压缩难题。
arXiv:2606.08151v1 Announce Type: new Abstract: Tool-using LLM agents often fail not because relevant text is absent, but because decisive evidence is…
在固定LLM预算下，提出智能体搜索方法实现高效反事实解释，平衡推理成本与可解释性。
arXiv:2606.08696v1 Announce Type: new Abstract: Counterfactual recourse aims to provide actionable feature changes that would alter an unfavorable dec…
6G智能新范式：摒弃预测式AI，通过反事实世界模型实现近实时状态空间推理与自主决策
arXiv:2511.02748v2 Announce Type: replace-cross Abstract: We argue that sixth-generation (6G) intelligence is not fluent token prediction but the capa…
KDD 2026论文提出针对纵向数据中罕见事件的可扩展反事实风险估计方法，解决因果推断与高维数据挑战。
arXiv:2606.01539v1 Announce Type: cross Abstract: Estimating the causal effect of time-varying treatments on survival outcomes in large observational …
反事实追踪审计方法，可揭示LLM智能体技能的可解释性与可靠性缺陷，提升AI安全。
arXiv:2605.11946v2 Announce Type: replace Abstract: Large Language Model agents are increasingly augmented with agent skills. Current evaluation metho…
LLM在政策评估中的反事实推理受直觉影响，40个实证案例揭示可靠性短板
arXiv:2604.10511v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used for causal and counterfactual reasoning, yet th…
用反事实推理构建1型糖尿病数字孪生，通过患者行为优化实现精准血糖控制。
arXiv:2504.09846v2 Announce Type: replace-cross Abstract: Frequent and long-term exposure to hyperglycemia increases the risk of chronic complications…
提出反事实推理路径方法降低信用分配方差，强化学习领域新思路。
arXiv:2605.16302v1 Announce Type: new Abstract: Reinforcement learning for multi-step reasoning with large language models (LLMs) often relies on spar…