paper-with-me

Papers

When Is It Acceptable to Break the Rules? Knowledge Representation of Moral Judgement Based on Empirical Data

2022-01-19 · Edmond Awad, Sydney Levine, Andrea Loreggia, Nicholas Mattei, Iyad Rahwan, Francesca Rossi, Kartik Talamadupula, Joshua Tenenbaum, Max Kleiman-Weiner

One of the most remarkable things about the human moral mind is its flexibility. We can make moral judgments about cases we have never seen before. We can decide that pre-established rules should be broken. We can invent novel rules on the fly. Capturing this flexibility is one of the central challenges in developing AI systems that can interpret and produce human-like moral judgment. This paper details the results of a study of real-world decision makers who judge whether it is acceptable to break a well-established norm: `no cutting in line.'' We gather data on how human participants judge the acceptability of line-cutting in a range of scenarios. Then, in order to effectively embed these reasoning capabilities into a machine, we propose a method for modeling them using a preference-based structure, which captures a novel modification to standard `dual process'' theories of moral judgment.

📄 PDF Abstract BibTeX arXiv:2201.07763

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Simplifying Random Forests: On the Trade-off between Interpretability and Accuracy

2019-11-11 · Michael Rapp, Eneldo Loza Mencía, Johannes Fürnkranz

We analyze the trade-off between model complexity and accuracy for random forests by breaking the trees up into individual classification rules and selecting a subset of them. We show experimentally that already a few ru…

General Classification

Rulebreakers Challenge: Revealing a Blind Spot in Large Language Models' Reasoning with Formal Logic

2024-10-21 · Jason Chan, Robert Gaizauskas, Zhixue Zhao

Formal logic has long been applied to natural language reasoning, but this approach can sometimes lead to conclusions that, while logically entailed, are factually inconsistent with the premises or are not typically infe…

Formal LogicWorld Knowledge

HATP: An HTN Planner for Robotics

2014-05-21 · Raphaël Lallement, Lavindra de Silva, Rachid Alami

Hierarchical Task Network (HTN) planning is a popular approach that cuts down on the classical planning search space by relying on a given hierarchical library of domain control knowledge. This provides an intuitive meth…

Detecting and Adapting to Novelty in Games

2021-06-04 · Xiangyu Peng, Jonathan C. Balloch, Mark O. Riedl

Open-world novelty occurs when the rules of an environment can change abruptly, such as when a game player encounters "house rules". To address open-world novelty, game playing agents must be able to detect when novelty …

Knowledge GraphsModel-based Reinforcement Learningreinforcement-learningReinforcement Learning (RL)

Breaking the Reversal Curse in Autoregressive Language Models via Identity Bridge

2026-02-02 · Xutao Ma, Yixiao Huang, Hanlin Zhu, Somayeh Sojoudi arxiv

Autoregressive large language models (LLMs) have achieved remarkable success in many complex tasks, yet they can still fail in very simple logical reasoning such as the "reversal curse" -- when trained on forward knowled…

Logical Reasoning