# EvalMORAAL: Interpretable Chain-of-Thought and LLM-as-Judge Evaluation for Moral Alignment in Large Language Models

arXiv: https://arxiv.org/abs/2510.05942 · HTML: https://mlsanity.com/paper/2510.05942/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 15 of its 52 references that are in the map.
- First posted on arXiv 7 Oct 2025.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 15 of 15)

- [The Ghost in the Machine has an American accent: value conflict in GPT-3](https://mlsanity.com/paper/2203.07785/) (2022)
- [A Survey on Gender Bias in Natural Language Processing](https://mlsanity.com/paper/2112.14168/) (2021)
- [DailyDilemmas: Revealing Value Preferences of LLMs with Quandaries of Daily Life](https://mlsanity.com/paper/2410.02683/) (2024)
- [How Well Do LLMs Represent Values Across Cultures? Empirical Analysis of LLM Responses Based on Hofstede Cultural Dimensions](https://mlsanity.com/paper/2406.14805/) (2024)
- [Assessing LLMs for Moral Value Pluralism](https://mlsanity.com/paper/2312.10075/) (2023)
- [Chinese Tiny LLM: Pretraining a Chinese-Centric Large Language Model](https://mlsanity.com/paper/2404.04167/) (2024)
- [Normative Evaluation of Large Language Models with Everyday Moral Dilemmas](https://mlsanity.com/paper/2501.18081/) (2025)
- [LLM Ethics Benchmark: A Three-Dimensional Assessment System for Evaluating Moral Reasoning in Large Language Models](https://mlsanity.com/paper/2505.00853/) (2025)
- [Beyond Human Norms: Unveiling Unique Values of Large Language Models through Interdisciplinary Approaches](https://mlsanity.com/paper/2404.12744/) (2024)
- [Explainability in Practice: A Survey of Explainable NLP Across Various Domains](https://mlsanity.com/paper/2502.00837/) (2025)
- [Contextual Moral Value Alignment Through Context-Based Aggregation](https://mlsanity.com/paper/2403.12805/) (2024)
- [Do Large Language Models Understand Morality Across Cultures?](https://mlsanity.com/paper/2507.21319/) (2025)
- [Cultural Bias in Large Language Models: Evaluating AI Agents through Moral Questionnaires](https://mlsanity.com/paper/2507.10073/) (2025)
- [One Model, Many Morals: Uncovering Cross-Linguistic Misalignments in Computational Moral Reasoning](https://mlsanity.com/paper/2509.21443/) (2025)
- [Exploring Cultural Variations in Moral Judgments with Large Language Models](https://mlsanity.com/paper/2506.12433/) (2025)

## Built on by (most cited first, 6 of 6)

- [Rubric-Conditioned LLM Grading: Alignment, Uncertainty, and Robustness](https://mlsanity.com/paper/2601.08843/) (2025)
- [trajectory-judge: What Outcome-Only LLM Judges Miss on Agent Trajectories](https://mlsanity.com/paper/2609.00038/) (2026)
- [Untangling Input Language from Reasoning Language: A Diagnostic Framework for Cross-Lingual Moral Alignment in LLMs](https://mlsanity.com/paper/2601.10257/) (2026)
- [Do LLMs Hold Their Values? MANTA: A Multi-Turn Adversarial Benchmark for Animal Welfare Reasoning](https://mlsanity.com/paper/2605.16301/) (2026)
- [Crisis-Bench: Benchmarking Strategic Ambiguity and Reputation Management in Large Language Models](https://mlsanity.com/paper/2601.05570/) (2026)
- [How do LLMs Evaluate Perceived Moral Agency? Investigating Moral Decision-Making in Human-Artificial Agents Interactions](https://mlsanity.com/paper/2609.05037/) (2026)

## Abstract (arXiv)

We present EvalMORAAL, a transparent chain-of-thought (CoT) framework that uses two scoring methods (log-probabilities and direct ratings) plus a model-as-judge peer review to evaluate moral alignment in 20 large language models. We assess models on the World Values Survey (55 countries, 19 topics) and the PEW Global Attitudes Survey (39 countries, 8 topics). With EvalMORAAL, top models align closely with survey responses (Pearson's r ≈ 0.90 on WVS). Yet we find a clear regional difference: Western regions average r=0.82 while non-Western regions average r=0.61 (a 0.21 absolute gap), indicating a persistent regional alignment gap. Our framework adds three parts: (1) two scoring methods for all models to enable fair comparison, (2) a structured CoT protocol with self-consistency checks, and (3) a model-as-judge peer review that flags 348 conflicts using a data-driven threshold. Peer agreement relates to WVS survey alignment (r=0.74, p<.001; PEW r=0.39, n.s.), supporting automated quality checks. These results show real progress toward culture-aware AI while highlighting open challenges for use across regions.