# Unsupervised Elicitation of Moral Values from Language Models

arXiv: https://arxiv.org/abs/2601.17728 · HTML: https://mlsanity.com/paper/2601.17728/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 46 references that are in the map.
- First posted on arXiv 25 Jan 2026.

## Builds on (most cited first, 28 of 28)

- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?](https://mlsanity.com/paper/2504.13837/) (2025)
- [Discovering Latent Knowledge in Language Models Without Supervision](https://mlsanity.com/paper/2212.03827/) (2022)
- [Aligning AI With Shared Human Values](https://mlsanity.com/paper/2008.02275/) (2020)
- [Social Bias Frames: Reasoning about Social and Power Implications of Language](https://mlsanity.com/paper/1911.03891/) (2019)
- [The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning](https://mlsanity.com/paper/2312.01552/) (2023)
- [Social Chemistry 101: Learning to Reason about Social and Moral Norms](https://mlsanity.com/paper/2011.00620/) (2020)
- [Chain-of-Thought Reasoning Without Prompting](https://mlsanity.com/paper/2402.10200/) (2024)
- [Learning to Reason without External Rewards](https://mlsanity.com/paper/2505.19590/) (2025)
- [The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning](https://mlsanity.com/paper/2505.15134/) (2025)
- [Reasoning Models Know When They're Right: Probing Hidden States for Self-Verification](https://mlsanity.com/paper/2504.05419/) (2025)
- [Moral Stories: Situated Reasoning about Norms, Intents, Actions, and their Consequences](https://mlsanity.com/paper/2012.15738/) (2020)
- [Do I Know This Entity? Knowledge Awareness and Hallucinations in Language Models](https://mlsanity.com/paper/2411.14257/) (2024)
- [Which Economic Tasks are Performed with AI? Evidence from Millions of Claude Conversations](https://mlsanity.com/paper/2503.04761/) (2025)
- [Red-Teaming for Generative AI: Silver Bullet or Security Theater?](https://mlsanity.com/paper/2401.15897/) (2024)
- [ALI-Agent: Assessing LLMs' Alignment with Human Values via Agent-based Evaluation](https://mlsanity.com/paper/2405.14125/) (2024)
- [The Unreasonable Effectiveness of Easy Training Data for Hard Tasks](https://mlsanity.com/paper/2401.06751/) (2024)
- [Moral Alignment for LLM Agents](https://mlsanity.com/paper/2410.01639/) (2024)
- [Challenges with unsupervised LLM knowledge discovery](https://mlsanity.com/paper/2312.10029/) (2023)
- [Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution](https://mlsanity.com/paper/2506.01055/) (2025)
- [CIVICS: Building a Dataset for Examining Culturally-Informed Values in Large Language Models](https://mlsanity.com/paper/2405.13974/) (2024)
- [Unsupervised Elicitation of Language Models](https://mlsanity.com/paper/2506.10139/) (2025)
- [Reward Model Interpretability via Optimal and Pessimal Tokens](https://mlsanity.com/paper/2506.07326/) (2025)
- [Resource Rational Contractualism Should Guide AI Alignment](https://mlsanity.com/paper/2506.17434/) (2025)
- [Moral Change or Noise? On Problems of Aligning AI With Temporally Unstable Human Feedback](https://mlsanity.com/paper/2511.10032/) (2025)
- [Web-Browsing LLMs Can Access Social Media Profiles and Infer User Demographics](https://mlsanity.com/paper/2507.12372/) (2025)

## Abstract (arXiv)

As AI systems become pervasive, grounding their behavior in human values is critical. Prior work suggests that language models (LMs) exhibit limited inherent moral reasoning, leading to calls for explicit moral teaching. However, constructing ground truth data for moral evaluation is difficult given plural frameworks and pervasive biases. We investigate unsupervised elicitation as an alternative, asking whether pretrained (base) LMs possess intrinsic moral reasoning capability that can be surfaced without human supervision. Using the Internal Coherence Maximization (ICM) algorithm across three benchmark datasets and four LMs, we test whether ICM can reliably label moral judgments, generalize across moral frameworks, and mitigate social bias. Results show that ICM outperforms all pre-trained and chatbot baselines on the Norm Bank and ETHICS benchmarks, while fine-tuning on ICM labels performs on par with or surpasses those of human labels. Across theoretically motivated moral frameworks, ICM yields its largest relative gains on Justice and Commonsense morality. Furthermore, although chatbot LMs exhibit social bias failure rates comparable to their pretrained ones, ICM reduces such errors by more than half, with the largest improvements in race, socioeconomic status, and politics. These findings suggest that pretrained LMs possess latent moral reasoning capacities that can be elicited through unsupervised methods like ICM, providing a scalable path for AI alignment.