Agent Incentives: A Causal Perspective

通过战略资源分配实现激励感知的AI安全：从Stackelberg安全游戏视角出发

Incentive-Aware AI Safety via Strategic Resource Allocation: A Stackelberg Security Games Perspective

本文提出基于Stackelberg安全游戏的AI安全框架，通过战略资源分配设计激励机制，提升AI监管的主动性与鲁棒性。

GCAD：从格兰杰因果视角进行多元时间序列异常检测

GCAD: Anomaly Detection in Multivariate Time Series from the Perspective of Granger Causality

本文提出GCAD框架，利用可解释的格兰杰因果关系建模多元时间序列的空间依赖，并通过因果模式变化检测异常，在真实数据集上优于基线方法。

从因果视角重新审视少样本学习

Revisiting Few-Shot Learning from a Causal Perspective

本文从因果视角解释基于度量的少样本学习方法，将其统一为前门调整形式，并提出两种兼顾样本关系与表示多样性的因果方法，在多个基准上提升少样本分类性能。

A Topological Perspective on Causal Inference

This paper presents a topological learning-theoretic perspective on causal inference by introducing a series of topologies defined on general spaces of structural causal models (SCMs). As an illustration of the framework we prove a topological causal hierarchy theorem, showing that substantive assumption-free causal inference is possible only in a meager set of SCMs. Thanks to a known correspondence between open sets in the weak topology and statistically verifiable hypotheses, our results show that inductive assumptions sufficient to license valid causal inferences are statistically unverifia…

Reward Tampering Problems and Solutions in Reinforcement Learning: A Causal Influence Diagram Perspective

Can humans get arbitrarily capable reinforcement learning (RL) agents to do their bidding? Or will sufficiently capable RL agents always find ways to bypass their intended objectives by shortcutting their reward signal? This question impacts how far RL can be scaled, and whether alternative paradigms must be developed in order to build safe artificial general intelligence. In this paper, we study when an RL agent has an instrumental goal to tamper with its reward process, and describe design principles that prevent instrumental goals for two different types of reward tampering (reward function…

The Impossibility Theorem of Machine Fairness -- A Causal Perspective

With the increasing pervasive use of machine learning in social and economic settings, there has been an interest in the notion of machine bias in the AI community. Models trained on historic data reflect biases that exist in society and propagated them to the future through their decisions. There are three prominent metrics of machine fairness used in the community, and it has been shown statistically that it is impossible to satisfy them all at the same time. This has led to an ambiguity with regards to the definition of fairness. In this report, a causal perspective to the impossibility the…

关于因果语言建模中Transformer的元学习视角

A Meta-Learning Perspective on Transformers for Causal Language Modeling

本文从元学习视角解析了Transformer在因果语言建模中的训练过程，通过阐明其内部优化机制，发现并理论分析了学习到的token表示范数的特殊特征，且得到了多设置实验的支持。

异构图神经网络在节点分类中真的有效吗？因果视角

Are Heterogeneous Graph Neural Networks Truly Effective for Node Classification? A Causal Perspective

从模型架构和异构信息角度研究异构图神经网络用于节点分类，通过复现实验和因果中介分析框架，发现模型架构和复杂度对性能无因果效应，异构信息通过增加同质性等产生正向因果效应。

Causality Learning: A New Perspective for Interpretable Machine Learning

Recent years have witnessed the rapid growth of machine learning in a wide range of fields such as image recognition, text classification, credit scoring prediction, recommendation system, etc. In spite of their great performance in different sectors, researchers still concern about the mechanism under any machine learning (ML) techniques that are inherently black-box and becoming more complex to achieve higher accuracy. Therefore, interpreting machine learning model is currently a mainstream topic in the research community. However, the traditional interpretable machine learning focuses on th…

On Pitfalls of Identifiability in Unsupervised Learning. A Note on: "Desiderata for Representation Learning: A Causal Perspective"

Model identifiability is a desirable property in the context of unsupervised representation learning. In absence thereof, different models may be observationally indistinguishable while yielding representations that are nontrivially related to one another, thus making the recovery of a ground truth generative model fundamentally impossible, as often shown through suitably constructed counterexamples. In this note, we discuss one such construction, illustrating a potential failure case of an identifiability result presented in "Desiderata for Representation Learning: A Causal Perspective" by Wa…

域泛化中因果关系视角的转变

A Shift in Perspective on Causality in Domain Generalization

本文重新审视因果建模在域泛化中的泛化承诺，通过调和现有文献中的矛盾，提出更细致的因果作用理论，并提供交互式演示。

没有免费的午餐：医学影像机器学习中数据集偏差的因果视角

No Fair Lunch: A Causal Perspective on Dataset Bias in Machine Learning for Medical Imaging

本文从因果视角分析医学影像机器学习中的数据集偏差，提出三类因果偏差机制，并指出当前缓解方法的局限性，进而提供一个实用的三步框架以支持安全公平的AI预测模型开发。

偏好学习用于AI对齐：一种因果视角

Preference Learning for AI Alignment: a Causal Perspective

本文从因果视角出发，探讨了基于偏好数据的奖励建模在对齐大语言模型与人类价值观中的关键作用，提出因果工具箱以解决因果误识别、偏好异质性和用户特定因素的混淆问题，并提出未来研究的方向。

具有切换因果关系的系统：元因果视角

Systems with Switching Causal Relations: A Meta-Causal Perspective

针对因果关系恒定假设的局限，提出元因果状态概念，通过聚类经典因果模型分析系统定性变化，可从智能体行为推断并用于动态系统，拓展因果框架至非外部驱动场景。

The Importance of Modeling Data Missingness in Algorithmic Fairness: A Causal Perspective

Training datasets for machine learning often have some form of missingness. For example, to learn a model for deciding whom to give a loan, the available training data includes individuals who were given a loan in the past, but not those who were not. This missingness, if ignored, nullifies any fairness guarantee of the training procedure when the model is deployed. Using causal graphs, we characterize the missingness mechanisms in different real-world scenarios. We show conditions under which various distributions, used in popular fairness algorithms, can or can not be recovered from the trai…

集体代理的因果基础

Causal Foundations of Collective Agency

本文探讨了多智能体系统中集体代理形成的因果基础，提出通过因果游戏和因果抽象框架分析集体行为的理性与目标导向性，解决多智能体激励问题和投票机制的集体代理度评估。

面向 GNN 的 LLM 增强器：基于因果机制识别视角的分析

LLM Enhancers for GNNs: An Analysis from the Perspective of Causal Mechanism Identification

本文基于交换干预分析 LLM 增强 GNN 节点表示的因果机制，构建可控合成图数据集并提出即插即用优化模块，实验验证其可改善二者间的信息传递。

Adjustment Criteria in Causal Diagrams: An Algorithmic Perspective

Identifying and controlling bias is a key problem in empirical sciences. Causal diagram theory provides graphical criteria for deciding whether and how causal effects can be identified from observed (nonexperimental) data by covariate adjustment. Here we prove equivalences between existing as well as new criteria for adjustment and we provide a new simplified but still equivalent notion of d-separation. These lead to efficient algorithms for two important tasks in causal diagram analysis: (1) listing minimal covariate adjustments (with polynomial delay); and (2) identifying the subdiagram invo…

Membership Inference Attacks and Generalization: A Causal Perspective

Membership inference (MI) attacks highlight a privacy weakness in present stochastic training methods for neural networks. It is not well understood, however, why they arise. Are they a natural consequence of imperfect generalization only? Which underlying causes should we address during training to mitigate these attacks? Towards answering such questions, we propose the first approach to explain MI attacks and their connection to generalization based on principled causal reasoning. We offer causal graphs that quantitatively explain the observed MI attack performance achieved for $6$ attack va…

一种研究数据特征间关系的新方法——基于对数学、技术与因果方法论的综合考察

A novel approach to the relationships between data features -- based on comprehensive examination of mathematical, technological, and causal methodology

针对现有AI特征关系分析方法易扭曲内在作用的问题，本研究提出整合多视角的收敛融合范式（CFP）理论，结合希尔伯特空间等方法解决共因问题，提升反事实推理下的AI透明度与治理能力。

从因果视角提升对抗攻击与防御

A Causal Perspective for Enhancing Jailbreak Attack and Defense

本文提出Causal Analyst框架，通过因果分析提升大语言模型的对抗攻击与防御能力。

从因果视角重新思考图对比学习中的维度理据

Rethinking Dimensional Rationale in Graph Contrastive Learning from Causal Perspective

本文从因果视角分析图对比学习中的维度理据，构建结构因果模型，并提出结合可学习理据获取网络、双层元学习与冗余减少约束的DRGCL，显著提升判别性和迁移性。

基于离线模型强化学习的激励式广告激励分配学习

Learning to Allocate Incentives for Incentivized Advertising via Offline Model-Based Reinforcement Learning

本研究针对激励式广告的序列激励分配问题，提出离线模型强化学习框架，实验显示MB-IQL可显著提升人均净利润，验证了该框架的有效性。

Algorithmic Bias in Recidivism Prediction: A Causal Perspective

ProPublica's analysis of recidivism predictions produced by Correctional Offender Management Profiling for Alternative Sanctions (COMPAS) software tool for the task, has shown that the predictions were racially biased against African American defendants. We analyze the COMPAS data using a causal reformulation of the underlying algorithmic fairness problem. Specifically, we assess whether COMPAS exhibits racial bias against African American defendants using FACT, a recently introduced causality grounded measure of algorithmic fairness. We use the Neyman-Rubin potential outcomes framework for ca…

Invariant Policy Learning: A Causal Perspective

Contextual bandit and reinforcement learning algorithms have been successfully used in various interactive learning systems such as online advertising, recommender systems, and dynamic pricing. However, they have yet to be widely adopted in high-stakes application domains, such as healthcare. One reason may be that existing approaches assume that the underlying mechanisms are static in the sense that they do not change over different environments. In many real-world systems, however, the mechanisms are subject to shifts across environments which may invalidate the static environment assumption…

COLA：从因果推断视角进行情境化常识因果推理

COLA: Contextualized Commonsense Causal Reasoning from the Causal Inference Perspective

本文提出情境化常识因果推理任务及零样本框架COLA，利用时间性和协变量平衡消除混杂效应，实验证明其优于基线。

协作因果推断中的数据共享机制（扩展版）

Mechanisms for Data Sharing in Collaborative Causal Inference (Extended Version)

本文针对协作因果推断中数据共享的激励问题，提出基于CPDAG比较的数据估值方案，用于公平奖励或最大化各参与方的数据贡献。

大语言模型的价值是否在结构上与人类对齐？一个因果视角

Are the Values of LLMs Structurally Aligned with Humans? A Causal Perspective

本研究从因果视角揭示LLM价值结构异于人类，提出基于因果价值图的角色提示与稀疏自编码器导向方法，实现轻量且细粒度的价值对齐。

面向 AGI 发展的因果表征学习关系优先建模范式

Relation-First Modeling Paradigm for Causal Representation Learning toward the Development of AGI

针对传统 i.i.d. 范式难以建模因果关系的问题，论文提出关系优先的因果建模范式，并给出 RIRL 实现，实验验证了其有效性。

决策中因果性的重要性：推荐系统视角

The Importance of Causality in Decision Making: A Perspective on Recommender Systems

本文从因果性视角形式化推荐系统问题，利用潜在结果和结构因果模型定义待估计的因果量，并提出通用因果图以推动未来研究。

公平性与准确性的权衡：因果视角

Fairness-Accuracy Trade-Offs: A Causal Perspective

本研究首次从因果视角分析公平性与准确性的权衡，引入路径特定超额损失（PSEL）将总超额损失（TEL）分解为局部成分，并提出因果公平性/效用比指标，同时开发了一种新的因果约束公平学习神经方法。

因果世界模型的统一视角：从观测到表征再到结构

A Unifying Perspective on Causal World Models: From Observations to Representations to Structure

本文从因果视角研究不同抽象层级的世界模型，提出因果世界模型的形式定义，关联相关领域工作并阐明其组件可从数据恢复的条件，为世界模型奠定支持因果推理与决策的基础。

Towards Robust and Adaptive Motion Forecasting: A Causal Representation Perspective

Learning behavioral patterns from observational data has been a de-facto approach to motion forecasting. Yet, the current paradigm suffers from two shortcomings: brittle under distribution shifts and inefficient for knowledge transfer. In this work, we propose to address these challenges from a causal representation perspective. We first introduce a causal formalism of motion forecasting, which casts the problem as a dynamic process with three groups of latent variables, namely invariant variables, style confounders, and spurious features. We then introduce a learning framework that treats eac…

潜在因果探测：从因果数据模型视角对探测的形式化分析

Latent Causal Probing: A Formal Perspective on Probing with Causal Models of Data

本文提出用结构因果模型形式化分析语言模型探测，将核心问题界定为模型是否学会表示潜在变量，并在合成导航任务中验证了语言模型归纳潜在概念的能力。

IFAR：基于大语言模型的多视角多层次因果发现

IFAR: Multi-Perspective and Multi-Level Causal Discovery with LLMs

研究针对大语言模型溯因推理中多视角多层次原因这一挑战，提出IFAR框架，结合广义反向推理与正向验证，构建专门数据集，实验表明该框架能提升大语言模型溯因推理性能，在F1分数等方面有显著改进。

The Causal Frame Problem: An Algorithmic Perspective

The Frame Problem (FP) is a puzzle in philosophy of mind and epistemology, articulated by the Stanford Encyclopedia of Philosophy as follows: "How do we account for our apparent ability to make decisions on the basis only of what is relevant to an ongoing situation without having explicitly to consider all that is not relevant?" In this work, we focus on the causal variant of the FP, the Causal Frame Problem (CFP). Assuming that a reasoner's mental causal model can be (implicitly) represented by a causal Bayes net, we first introduce a notion called Potential Level (PL). PL, in essence, encode…

因果性在可解释人工智能中的作用

The role of causality in explainable artificial intelligence

本文综述了因果性与可解释人工智能之间的关系，识别出三种主要视角，并提供了相关软件工具，旨在为两个领域提供统一视角并揭示潜在联系与局限。

向内看，为何大语言模型会产生幻觉：一种因果视角

Look Within, Why LLMs Hallucinate: A Causal Perspective

本文从因果视角干预大语言模型的自注意力层，发现禁用前端或尾部特定层可缓解幻觉问题，为理解与缓解幻觉开辟新途径。

因果框架比较：潜在结果、结构模型、图与抽象

Comparing Causal Frameworks: Potential Outcomes, Structural Models, Graphs, and Abstractions

该研究从中立逻辑视角比较RCM与SCM因果框架，明确RCM可被SCM表示的条件，证明所有RCM都是可表示RCM的抽象，还阐释了SCM原则的应用价值与图的代数约束，推动两类框架的对比研究。

决策理论的因果建模视角

A causal modeling perspective on decision theory

基于非参数结构方程模型（NPSEM）为决策理论提供统一形式框架，提出个人决策理论并证明其在特定假设下的最优性。