{"total":13,"rows":[{"id":"2402.01761","title":"Rethinking Interpretability in the Era of Large Language Models","created":"2024-01-30","cited_by_count":111,"area":"lr"},{"id":"2308.01264","title":"Exploring the psychology of LLMs' Moral and Legal Reasoning","created":"2023-08-02","cited_by_count":44,"area":"lr"},{"id":"2311.10934","title":"Case Repositories: Towards Case-Based Reasoning for AI Alignment","created":"2023-11-18","cited_by_count":11,"area":"lr"},{"id":"2405.12933","title":"Skin-in-the-Game: Decision Making via Multi-Stakeholder Alignment in LLMs","created":"2024-05-21","cited_by_count":8,"area":"lr"},{"id":"2502.13329","title":"Language Models Can Predict Their Own Behavior","created":"2025-02-18","cited_by_count":8,"area":"lr"},{"id":"2408.11879","title":"Beyond Labels: Aligning Large Language Models with Human-like Reasoning","created":"2024-08-20","cited_by_count":6,"area":"lr"},{"id":"2510.18184","title":"ActivationReasoning: Logical Reasoning in Latent Activation Spaces","created":"2025-10-21","cited_by_count":5,"area":"lr"},{"id":"2601.10520","title":"Breaking Up with Normatively Monolithic Agency with GRACE: A Reason-Based Neuro-Symbolic Architecture for Safe and Ethical AI Alignment","created":"2026-01-15","cited_by_count":5,"area":"lr"},{"id":"2508.07284","title":"\"Pull or Not to Pull?'': Investigating Moral Biases in Leading Large Language Models Across Ethical Dilemmas","created":"2025-08-10","cited_by_count":3,"area":"lr"},{"id":"2601.18730","title":"Reflect: Transparent Principle-Guided Reasoning for Constitutional Alignment at Scale","created":"2026-01-26","cited_by_count":2,"area":"lr"},{"id":"2604.21043","title":"Strategic Polysemy in AI Discourse: A Philosophical Analysis of Language, Hype, and Power","created":"2026-04-22","cited_by_count":1,"area":"lr"},{"id":"2601.20604","title":"Dialogical Reasoning Across AI Architectures: A Multi-Model Framework for Testing AI Alignment Strategies","created":"2026-01-28","cited_by_count":0,"area":"lr"},{"id":"2604.11065","title":"AI Integrity: A New Paradigm for Verifiable AI Governance","created":"2026-04-13","cited_by_count":0,"area":"lr"}],"next_cursor":null}