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

arXiv: https://arxiv.org/abs/2606.05890 · HTML: https://mlsanity.com/paper/2606.05890/

## 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 (most cited first, 19 of 19)

- [gpt-oss-120b & gpt-oss-20b Model Card](https://mlsanity.com/paper/2508.10925/) (2025)
- [Towards Understanding Sycophancy in Language Models](https://mlsanity.com/paper/2310.13548/) (2023)
- [Scaling Synthetic Data Creation with 1,000,000,000 Personas](https://mlsanity.com/paper/2406.20094/) (2024)
- [Quantifying the Persona Effect in LLM Simulations](https://mlsanity.com/paper/2402.10811/) (2024)
- [Modular Pluralism: Pluralistic Alignment via Multi-LLM Collaboration](https://mlsanity.com/paper/2406.15951/) (2024)
- [ProsocialDialog: A Prosocial Backbone for Conversational Agents](https://mlsanity.com/paper/2205.12688/) (2022)
- [Scruples: A Corpus of Community Ethical Judgments on 32,000 Real-Life Anecdotes](https://mlsanity.com/paper/2008.09094/) (2020)
- [The Moral Integrity Corpus: A Benchmark for Ethical Dialogue Systems](https://mlsanity.com/paper/2204.03021/) (2022)
- [When to Make Exceptions: Exploring Language Models as Accounts of Human Moral Judgment](https://mlsanity.com/paper/2210.01478/) (2022)
- [Aligning Language Models to Explicitly Handle Ambiguity](https://mlsanity.com/paper/2404.11972/) (2024)
- [Beyond Demographics: Aligning Role-playing LLM-based Agents Using Human Belief Networks](https://mlsanity.com/paper/2406.17232/) (2024)
- [Synthetic Socratic Debates: Examining Persona Effects on Moral Decision and Persuasion Dynamics](https://mlsanity.com/paper/2506.12657/) (2025)
- [The Staircase of Ethics: Probing LLM Value Priorities through Multi-Step Induction to Complex Moral Dilemmas](https://mlsanity.com/paper/2505.18154/) (2025)
- [The Greatest Good Benchmark: Measuring LLMs' Alignment with Utilitarian Moral Dilemmas](https://mlsanity.com/paper/2503.19598/) (2025)
- [Are Language Models Consequentialist or Deontological Moral Reasoners?](https://mlsanity.com/paper/2505.21479/) (2025)
- [Moral Persuasion in Large Language Models: Evaluating Susceptibility and Ethical Alignment](https://mlsanity.com/paper/2411.11731/) (2024)
- [Discerning What Matters: A Multi-Dimensional Assessment of Moral Competence in LLMs](https://mlsanity.com/paper/2506.13082/) (2025)
- [Many LLMs Are More Utilitarian Than One](https://mlsanity.com/paper/2507.00814/) (2025)
- [Beyond Quantification: Navigating Uncertainty in Professional AI Systems](https://mlsanity.com/paper/2509.03271/) (2025)

## 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.