EMNLP Findings2022
Contextualizing Language Models for Norms Diverging from Social Majority
Abstract
To comprehensibly contextualize decisions, artificial systems in social situations need a high degree of awareness of the rules of conduct of human behavior. Especially transformer-based language models have recently been shown to exhibit some such awareness. But what if norms in some social setting do not adhere to or even blatantly deviate from the mainstream? In this paper, we introduce a novel mechanism based on deontic logic to allow for a flexible adaptation of individual norms by de-biasing training data sets and a task-reduction to textual entailment. Building on the popular 'Moral Stories' dataset we on the one hand highlight the intrinsic bias of current language models, on the other hand characterize the adaptability of pre-trained models to deviating norms in fine-tuning settings. 1
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
Builds on9
- ALBERT: A Lite BERT for Self-supervised Learning of Language RepresentationsZhenzhong Lan, Mingda Chen, Sebastian Goodman, Kevin Gimpel et al.ICLR 2020 · 7,418 citations
- BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and ComprehensionMike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad et al.ACL 2020 · 1,224 citations
- Plug and Play Language Models: A Simple Approach to Controlled Text GenerationSumanth Dathathri, Andrea Madotto, Janice Lan, Jane Hung et al.ICLR 2020 · 1,166 citations
- Adversarial NLI: A New Benchmark for Natural Language UnderstandingYixin Nie, Adina Williams, Emily Dinan, Mohit Bansal et al.ACL 2020 · 602 citations
- SCRUPLES: A Corpus of Community Ethical Judgments on 32, 000 Real-Life AnecdotesNicholas Lourie, Ronan Le Bras, Yejin ChoiAAAI 2021 · 147 citations
Related papers
- Moral Stories: Situated Reasoning about Norms, Intents, Actions, and their ConsequencesDenis Emelin, Ronan Le Bras, Jena D. Hwang, Maxwell Forbes et al.EMNLP 2021 · 83 citations
- Mitigating Adversarial Norm Training with Moral AxiomsTaylor Olson, Kenneth D. ForbusAAAI 2023 · 7 citations
- Agent-Specific Deontic Modality Detection in Legal LanguageAbhilasha Sancheti, Aparna Garimella, Balaji Vasan Srinivasan, Rachel RudingerEMNLP 2022 · 3 citations
- The Moral Integrity Corpus: A Benchmark for Ethical Dialogue SystemsCaleb Ziems, Jane A. Yu, Yi-Chia Wang, Alon Y. Halevy et al.ACL 2022 · 127 citations
- Machine Behavior in Relational Moral Dilemmas: Moral Rightness, Predicted Human Behavior, and Model DecisionsJiseon Kim, Jea Kwon, Luiz Felipe Vecchietti, Wenchao Dong et al.ACL Findings 2026
