Societal Frameworks Can Improve LLM Alignment
Authors:
- Karolina StańczakKSKarolina Stańczak
- Nicholas MeadeNMNicholas Meade
- Mehar BhatiaMBMehar Bhatia
- Hattie ZhouHZHattie Zhou
- Konstantin BöttingerKBKonstantin Böttinger
- Jeremy BarnesJBJeremy Barnes
- Jason StanleyJSJason Stanley
- Nicolas PapernotNPNicolas Papernot
- Nicolas ChapadosNCNicolas Chapados
- Denis TherienDTDenis Therien
- Timothy P LillicrapTLTimothy P Lillicrap
- Ana MarasovićAMAna Marasović
Open Access
- 25 June 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 4491-4510
Abstract
No abstract availableAll Related Versions
Funding Information
- R3AI R10 Research Regroupment (n/a)
- Mila P2v5 grant (n/a)
- Mila-Samsung grant (n/a)
This publication has 61 references indexed in Scilit:
- Normative conflicts and shallow AI alignmentPhilosophical Studies, 2025
- A matter of principle? AI alignment as the fair treatment of claimsPhilosophical Studies, 2025
- Beyond Preferences in AI AlignmentPhilosophical Studies, 2024
- How Robots’ Unintentional Metacommunication Affects Human–Robot Interactions. A Systemic ApproachMinds and Machines, 2021
- Language and IntelligenceMinds and Machines, 2021
- Artificial Intelligence, Values, and AlignmentMinds and Machines, 2020
- Statistical Numeracy for HealthArchives of internal medicine (1960), 2010
- Numeracy, ratio bias, and denominator neglect in judgments of risk and probabilityLearning and Individual Differences, 2008
- Legal Reasoning Models2001
- The Problem of Rationality in the Social World1976