# From Sycophantic Consensus to Pluralistic Repair: Why AI Alignment Must Surface Disagreement

arXiv: https://arxiv.org/abs/2605.14912 · HTML: https://mlsanity.com/paper/2605.14912/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Human values and AI feedback alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 8 of its 17 references that are in the map.
- First posted on arXiv 14 May 2026.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Human values and AI feedback alignment](https://mlsanity.com/alignment/human-values-and-ai-feedback-alignment/)

## Builds on (most cited first, 8 of 8)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024)
- [Towards Understanding Sycophancy in Language Models](https://mlsanity.com/paper/2310.13548/) (2023)
- [Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety](https://mlsanity.com/paper/2507.11473/) (2025)
- [Adaptive Alignment: Dynamic Preference Adjustments via Multi-Objective Reinforcement Learning for Pluralistic AI](https://mlsanity.com/paper/2410.23630/) (2024)
- [CURATe: Benchmarking Personalised Alignment of Conversational AI Assistants](https://mlsanity.com/paper/2410.21159/) (2024)
- [Deployment-Relevant Alignment Cannot Be Inferred from Model-Level Evaluation Alone](https://mlsanity.com/paper/2605.04454/) (2026)

## Built on by (most cited first, 1 of 1)

- [A Roadmap to Impactful Pluralistic Alignment Research](https://mlsanity.com/paper/2607.22305/) (2026)

## Abstract (arXiv)

Pluralistic alignment is typically operationalised as preference aggregation: producing responses that span (Overton), steer toward (Steerable), or proportionally represent (Distributional) diverse human values. We argue that aggregation alone is an incomplete primitive for deployed pluralistic alignment. Under genuine value pluralism, the failure mode of contemporary RLHF-trained assistants is not insufficient coverage but sycophantic consensus: a learned tendency to agree with, validate, and minimise friction with the immediate interlocutor. Because deployed AI systems now mediate consequential deliberation across health, civic life, labour, and governance, the collapse of disagreement at the interaction layer is not a narrow technical concern but a structural failure with distributive consequences. We reframe pluralistic alignment around three conversational mechanisms drawn from Grice's maxims: scoping (acknowledging the limits of one's perspective), signalling (surfacing value-conflict rather than smoothing it over), and repair (revising one's position on principled grounds, not on user pressure). We formalise a metric, the Pluralistic Repair Score (PRS), distinguishing principled revision from capitulation, and present a small-scale empirical illustration on two frontier RLHF-trained models (Claude Sonnet 4.5, N=198; GPT-4o, N=100) showing that, for both, agreement-following coexists with low repair-quality on contested-value prompts. PRS measures an interactional precondition for pluralism (visible disagreement; principled revision) rather than pluralism in full; we discuss the difference, take seriously the reflexive question of whose "principled" counts, and argue that pluralism is most decisively made or unmade at the deployment-governance layer: interfaces, preference-data pipelines, and audit infrastructure.