首页/论文/cs/0312038

arXiv cs/03120382003-12-17cs.AIcs.LO

责任和责备：结构模型方法

Responsibility and blame: a structural-model approach

Hana Chockler, Joseph Y. Halpern

摘要：

因果关系通常被视为全有或全无的概念;要么A是B的原因，要么不是。我们扩展了Halpern和Pearl [2001]引入的因果关系的定义，以考虑A对B的责任程度。例如，如果某人以11比0赢得选举，那么每个投票给他的人对胜利的责任要比他以6比5获胜的责任小。然后，我们定义了一个概念的程度的责任，它考虑到代理人的认知状态。粗略地说，A对B的责备程度是A对B的预期责任程度，接管了一个代理人的认知状态。

英文摘要：

Causality is typically treated an all-or-nothing concept; either A is a cause of B or it is not. We extend the definition of causality introduced by Halpern and Pearl [2001] to take into account the degree of responsibility of A for B. For example, if someone wins an election 11--0, then each person who votes for him is less responsible for the victory than if he had won 6--5. We then define a notion of degree of blame, which takes into account an agent's epistemic state. Roughly speaking, the degree of blame of A for B is the expected degree of responsibility of A for B, taken over the epistemic state of an agent.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

摘要英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

Learning Tractable Probabilistic Models for Moral Responsibility and Blame

University of Oxford（牛津大学）；University of Edinburgh（爱丁堡大学）；Alan Turing Institute（艾伦·图灵研究所）

Moral responsibility is a major concern in autonomous systems, with applications ranging from self-driving cars to kidney exchanges. Although there have been recent attempts to formalise responsibility and blame, among similar notions, the problem of learning within these formalisms has been unaddressed. From the viewpoint of such systems, the urgent questions are: (a) How can models of moral scenarios and blameworthiness be extracted and learnt automatically from data? (b) How can judgements be computed effectively and efficiently, given the split-second decision points faced by some systems?…

2021-01-30cs.AIcs.LGcs.LO

Towards Formal Definitions of Blameworthiness, Intention, and Moral Responsibility

Cornell University（康奈尔大学）；Massachusetts Institute of Technology（麻省理工学院）

We provide formal definitions of degree of blameworthiness and intention relative to an epistemic state (a probability over causal models and a utility function on outcomes). These, together with a definition of actual causality, provide the key ingredients for moral responsibility judgments. We show that these definitions give insight into commonsense intuitions in a variety of puzzling cases from the literature.

2018-10-13cs.AIcs.CY

Causality, Responsibility and Blame in Team Plans

University of Nottingham（诺丁汉大学）；Cornell University（康奈尔大学）

Many objectives can be achieved (or may be achieved more effectively) only by a group of agents executing a team plan. If a team plan fails, it is often of interest to determine what caused the failure, the degree of responsibility of each agent for the failure, and the degree of blame attached to each agent. We show how team plans can be represented in terms of structural equations, and then apply the definitions of causality introduced by Halpern [2015] and degree of responsibility and blame introduced by Chockler and Halpern [2004] to determine the agent(s) who caused the failure and what t…

2020-05-20cs.AIcs.MA

Cause, Responsibility, and Blame: oA Structural-Model Approach

Cornell University（康奈尔大学）

A definition of causality introduced by Halpern and Pearl, which uses structural equations, is reviewed. A more refined definition is then considered, which takes into account issues of normality and typicality, which are well known to affect causal ascriptions. Causality is typically an all-or-nothing notion: either A is a cause of B or it is not. An extension of the definition of causality to capture notions of degree of responsibility and degree of blame, due to Chockler and Halpern, is reviewed. For example, if someone wins an election 11-0, then each person who votes for him is less respo…

2014-12-09cs.AI

人机协作中的因果责任归因

Causal Responsibility Attribution for Human-AI Collaboration

ETH Zürich（苏黎世联邦理工学院）；MPI Tübingen（马克斯·普朗克智能系统研究所（蒂宾根））；University of Toronto（多伦多大学）

本文提出基于结构因果模型和反事实推理的因果框架，用于在人机协作中系统归因责任，并通过案例研究展示其适应性。

2024-11-05cs.AIcs.HCstat.AP

Blaming humans in autonomous vehicle accidents: Shared responsibility across levels of automation

Massachusetts Institute of Technology（麻省理工学院）；Harvard University（哈佛大学）；University of California, Irvine（加利福尼亚大学尔湾分校）；Toulouse School of Economics (TSM-R), CNRS, University of Toulouse（图卢兹经济学院（TSM-R）、法国国家科学研究中心、图卢兹大学）；Institute for Data, Systems and Society（数据、系统与社会研究所）

When a semi-autonomous car crashes and harms someone, how are blame and causal responsibility distributed across the human and machine drivers? In this article, we consider cases in which a pedestrian was hit and killed by a car being operated under shared control of a primary and a secondary driver. We find that when only one driver makes an error, that driver receives the blame and is considered causally responsible for the harm, regardless of whether that driver is a machine or a human. However, when both drivers make errors in cases of shared control between a human and a machine, the blam…

2018-03-21cs.AIcs.CY

更多相关论文收起更多论文

On Blame Attribution for Accountable Multi-Agent Sequential Decision Making

MPI-SWS（马克斯·普朗克软件系统研究所）

Blame attribution is one of the key aspects of accountable decision making, as it provides means to quantify the responsibility of an agent for a decision making outcome. In this paper, we study blame attribution in the context of cooperative multi-agent sequential decision making. As a particular setting of interest, we focus on cooperative decision making formalized by Multi-Agent Markov Decision Processes (MMDPs), and we analyze different blame attribution methods derived from or inspired by existing concepts in cooperative game theory. We formalize desirable properties of blame attribution…

2022-01-25cs.AI

AUDITA：自主多智能体系统中不良结果的可验证审计与因果归因

AUDITA: certified auditing and causal attribution of adverse outcomes in autonomous multi-agent systems

Duke University（杜克大学）

AUDITA是自主多智能体系统的审计层，结合防篡改智能体命令记录与可验证因果归因引擎，可减少责任错误、处理多重决定等场景，将责任判定从争论转为证据计算。

2026-09-01cs.AI

探究大语言模型推理中的社会归因：一种理论引导的探测方法

Examining Social Attribution in LLM Reasoning: A Theory-Guided Probing Methodology

Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）

本文首次系统探究LLM的社会归因，构建含7639个问题的基准，评估32个LLM和5个基线，发现LLM与人类判断部分一致且一致性随模型规模提升，部分归因维度可从隐藏状态解码。

2026-10-09cs.AIcs.CLcs.LG

Human Perceptions on Moral Responsibility of AI: A Case Study in AI-Assisted Bail Decision-Making

KAIST（韩国科学技术院）；IBS（韩国基础科学研究院）；Max Planck Institute for Software Systems（马克斯·普朗克软件系统研究所）；Max Planck Institute for Research on Collective Goods（马克斯·普朗克集体利益研究所）

How to attribute responsibility for autonomous artificial intelligence (AI) systems' actions has been widely debated across the humanities and social science disciplines. This work presents two experiments ($N$=200 each) that measure people's perceptions of eight different notions of moral responsibility concerning AI and human agents in the context of bail decision-making. Using real-life adapted vignettes, our experiments show that AI agents are held causally responsible and blamed similarly to human agents for an identical task. However, there was a meaningful difference in how people perce…

2021-02-01cs.AIcs.CYcs.HC

Quantified Degrees of Group Responsibility (Extended Abstract)

Utrecht University（乌得勒支大学）

This paper builds on an existing notion of group responsibility and proposes two ways to define the degree of group responsibility: structural and functional degrees of responsibility. These notions measure the potential responsibilities of (agent) groups for avoiding a state of affairs. According to these notions, a degree of responsibility for a state of affairs can be assigned to a group of agents if, and to the extent that, the group has the potential to preclude the state of affairs.

2018-01-23cs.AIcs.MA

责任真空：规模化智能体系统中的组织失效

The Responsibility Vacuum: Organizational Failure in Scaled Agent Systems

研究揭示规模化智能体系统中因决策生成吞吐量超出人类验证能力导致的责任归属问题，指出自动化加剧而非缓解责任真空现象，呼吁重新设计决策边界以缓解系统失效。

2026-01-21cs.AIcs.SYeess.SY

Towards Computationally Efficient Responsibility Attribution in Decentralized Partially Observable MDPs

Max Planck Institute for Software Systems（马克斯·普朗克软件系统研究所）

Responsibility attribution is a key concept of accountable multi-agent decision making. Given a sequence of actions, responsibility attribution mechanisms quantify the impact of each participating agent to the final outcome. One such popular mechanism is based on actual causality, and it assigns (causal) responsibility based on the actions that were found to be pivotal for the considered outcome. However, the inherent problem of pinpointing actual causes and consequently determining the exact responsibility assignment has shown to be computationally intractable. In this paper, we aim to provid…

2023-02-24cs.AI

模块化说话者架构：在多智能体AI通信中维持责任与语境完整性的框架

Modular Speaker Architecture: A Framework for Sustaining Responsibility and Contextual Integrity in Multi-Agent AI Communication

AI Department（人工智能部门）；GTM Department（GTM部门）

本文提出模块化说话者架构（MSA），通过角色跟踪、责任链和语境完整性验证三个模块，在多智能体通信中维持角色意识与语境连贯性，并验证其结构稳定性。

2025-06-01cs.AI

Actual Causality and Responsibility Attribution in Decentralized Partially Observable Markov Decision Processes

Max Planck Institute for Software Systems（马克斯·普朗克软件系统研究所）

Actual causality and a closely related concept of responsibility attribution are central to accountable decision making. Actual causality focuses on specific outcomes and aims to identify decisions (actions) that were critical in realizing an outcome of interest. Responsibility attribution is complementary and aims to identify the extent to which decision makers (agents) are responsible for this outcome. In this paper, we study these concepts under a widely used framework for multi-agent sequential decision making under uncertainty: decentralized partially observable Markov decision processes …

2022-08-09cs.AI

人类对AI在代理、滥用和偏差中的因果归因

Human Attribution of Causality to AI Across Agency, Misuse, and Misalignment

Università degli Studi di Genova（热那亚大学）；FAIR IALAB；University of Buenos Aires（布宜诺斯艾利斯大学）；University College London（伦敦大学学院）

研究探讨了人类在AI导致有害结果时对因果责任的归因，发现AI代理程度越高，责任归于AI；开发者虽远离事件但被归责高，用户责任降低；分解AI为大语言模型和代理组件时，代理部分更易被归责。

2026-02-17cs.AIcs.CY

问责地平线：人类-智能体集体治理的不可能性定理

The Accountability Horizon: An Impossibility Theorem for Governing Human-Agent Collectives

University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Responsible Intelligence Institute（负责任智能研究所）

本文通过引入人类-智能体集体形式化模型和问责不完全性定理，证明当自主性超过可计算阈值时，现有AI问责框架必然失效，并基于合成实验验证了该相变边界。

2026-06-02cs.AI

自演化多智能体系统的拓扑一致性

Topological Coherence for Self-evolving Multi-agent Systems

Towngas（港华燃气）

针对复杂任务中智能体职责、交接与内存边界需与任务依赖保持一致的问题，提出拓扑一致多智能体系统TOCOMAS，通过结构约束与奖励评估的自演化，在多个基准上提升任务成功率。

2026-09-30cs.AI

激励还是本体？对OpenAI“幻觉假说”的结构反驳

Incentives or Ontology? A Structural Rebuttal to OpenAI's Hallucination Thesis

RA Software（RA软件公司）；Sofia University “St. Kliment Ohridski”（索非亚大学“圣克里门特·奥里兹斯基”）

本文反驳OpenAI关于幻觉源于激励不匹配的观点，指出幻觉是Transformer架构的必然结果，需通过外部验证模块消除，而非改变激励或微调。

2025-12-16cs.AIcs.CLcs.LG