mlsanityData to 14 Oct 2026

Staying with the Uncertainty: Uncertainty-Scaffolding Strategies for Artificial Moral Advisors in LLM-to-LLM Simulated Conversations

arXiv 2606.05890 ↗First posted 4 Jun 2026cs.CL cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

LLMs are increasingly deployed as Artificial Moral Advisors (AMA) in a variety of contexts: what kind of conversational patterns should they display? In this paper, we study how AMA can help their interlocutors "stay with the uncertainty". We propose three modes of uncertainty (Perspective-Multiplying, Tension-Preserving, Process-Reflecting) and compare them against three control conditions (Baseline, Persuasive, Sycophantic). A user-agent LLM engages in a dialogue on an ethical dilemma with an AMA following a specific uncertainty strategy, and completes pre- and post-conversation questionnaires. We further examine the effect of two persona prompt formats (Declarative and Narrative). We found that (1) no single model dominates as a simulated user agent, with open models aligning with human ambiguity through between-persona divergence and closed models through within-persona hedging; (2) declarative personas better capture initial stance diversity while narrative personas show more realistic belief revision; (3) all six AMA strategies produce distinguishable conversational patterns; and (4) uncertainty strategies differ not in how much stance revision they produce, but in the quality of engagement they sustain.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 19 of its 86 references that are in the map. First posted on arXiv 4 Jun 2026.

Builds on

19 of 86 references.

References · 19

  1. 2025gpt-oss-120b & gpt-oss-20b Model Cardcited by 1,386
  2. 2023Towards Understanding Sycophancy in Language Modelscited by 1,040
  3. 2024Scaling Synthetic Data Creation with 1,000,000,000 Personascited by 417
  4. 2024Quantifying the Persona Effect in LLM Simulationscited by 169
  5. 2024Modular Pluralism: Pluralistic Alignment via Multi-LLM Collaborationcited by 113
  6. 2022ProsocialDialog: A Prosocial Backbone for Conversational Agentscited by 109
  7. 2020Scruples: A Corpus of Community Ethical Judgments on 32,000 Real-Life Anecdotescited by 101
  8. 2022The Moral Integrity Corpus: A Benchmark for Ethical Dialogue Systemscited by 93
  9. 2022When to Make Exceptions: Exploring Language Models as Accounts of Human Moral Judgmentcited by 93
  10. 2024Aligning Language Models to Explicitly Handle Ambiguitycited by 56
  11. 2024Beyond Demographics: Aligning Role-playing LLM-based Agents Using Human Belief Networkscited by 39
  12. 2025Synthetic Socratic Debates: Examining Persona Effects on Moral Decision and Persuasion Dynamicscited by 19
7 more
  1. 2025The Staircase of Ethics: Probing LLM Value Priorities through Multi-Step Induction to Complex Moral Dilemmascited by 13
  2. 2025The Greatest Good Benchmark: Measuring LLMs' Alignment with Utilitarian Moral Dilemmascited by 12
  3. 2025Are Language Models Consequentialist or Deontological Moral Reasoners?cited by 12
  4. 2024Moral Persuasion in Large Language Models: Evaluating Susceptibility and Ethical Alignmentcited by 10
  5. 2025Discerning What Matters: A Multi-Dimensional Assessment of Moral Competence in LLMscited by 10
  6. 2025Many LLMs Are More Utilitarian Than Onecited by 8
  7. 2025Beyond Quantification: Navigating Uncertainty in Professional AI Systemscited by 4

Built on by

Not cited yet.