# Agreement Is Not Alignment: Divergent Moral Grounds in Human and LLM Ethical Judgments

arXiv: https://arxiv.org/abs/2608.12368 · HTML: https://mlsanity.com/paper/2608.12368/

## Key facts

- No citing papers in the map yet (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 13 of its 30 references that are in the map.
- First posted on arXiv 14 Jul 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, 13 of 13)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [A General Language Assistant as a Laboratory for Alignment](https://mlsanity.com/paper/2112.00861/) (2021)
- [Whose Opinions Do Language Models Reflect?](https://mlsanity.com/paper/2303.17548/) (2023)
- [Aligning AI With Shared Human Values](https://mlsanity.com/paper/2008.02275/) (2020)
- [Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?](https://mlsanity.com/paper/2004.03685/) (2020)
- [e-SNLI: Natural Language Inference with Natural Language Explanations](https://mlsanity.com/paper/1812.01193/) (2018)
- [Artificial Intelligence, Values and Alignment](https://mlsanity.com/paper/2001.09768/) (2020)
- [Explain Yourself! Leveraging Language Models for Commonsense Reasoning](https://mlsanity.com/paper/1906.02361/) (2019)
- [Social Chemistry 101: Learning to Reason about Social and Moral Norms](https://mlsanity.com/paper/2011.00620/) (2020)
- [Can Machines Learn Morality? The Delphi Experiment](https://mlsanity.com/paper/2110.07574/) (2021)
- [Moral Stories: Situated Reasoning about Norms, Intents, Actions, and their Consequences](https://mlsanity.com/paper/2012.15738/) (2020)
- [Moral Foundations of Large Language Models](https://mlsanity.com/paper/2310.15337/) (2023)
- [Strong and weak alignment of large language models with human values](https://mlsanity.com/paper/2408.04655/) (2024)

## Abstract (arXiv)

Agreement with human judgments is a common proxy for evaluating the alignment of large language models (LLMs). Yet agreement in final labels does not show that human annotators and models rely on the same moral grounds. Two agents may reach the same judgment while appealing to different principles, contextual assumptions, or interpretations of the situation. We test this distinction using a curated 500-item ETHICS-derived benchmark spanning five domains of moral judgment, with new human annotator and LLM annotations of both final labels and supporting rationales. Across frontier and open model families, agreement with human annotator majority labels is often high. However, rationale-level analysis reveals systematic divergence in the moral grounds expressed by human annotators and models. In particular, models redistribute attention across categories such as harm, respect, promise-keeping, justice, desert, and excuse relevance, even when their final labels match the human annotator majority. Our results show that agreement should not be treated as equivalent to alignment. Label-based evaluation can therefore be misleadingly reassuring unless complemented by analysis of the reasons, principles, and moral priorities expressed in model judgments.