# Are Language Models Sensitive to Morally Irrelevant Distractors?

arXiv: https://arxiv.org/abs/2602.09416 · HTML: https://mlsanity.com/paper/2602.09416/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 44 references that are in the map.
- First posted on arXiv 10 Feb 2026.

## Builds on (most cited first, 17 of 17)

- [Semantics derived automatically from language corpora contain human-like biases](https://mlsanity.com/paper/1608.07187/) (2016)
- [Aligning AI With Shared Human Values](https://mlsanity.com/paper/2008.02275/) (2020)
- [Evaluating the Moral Beliefs Encoded in LLMs](https://mlsanity.com/paper/2307.14324/) (2023)
- [Political Compass or Spinning Arrow? Towards More Meaningful Evaluations for Values and Opinions in Large Language Models](https://mlsanity.com/paper/2402.16786/) (2024)
- [Moral Foundations of Large Language Models](https://mlsanity.com/paper/2310.15337/) (2023)
- [Expressing stigma and inappropriate responses prevents LLMs from safely replacing mental health providers](https://mlsanity.com/paper/2504.18412/) (2025)
- [LLM Agents for Education: Advances and Applications](https://mlsanity.com/paper/2503.11733/) (2025)
- [Are Large Language Models Consistent over Value-laden Questions?](https://mlsanity.com/paper/2407.02996/) (2024)
- [Randomness, Not Representation: The Unreliability of Evaluating Cultural Alignment in LLMs](https://mlsanity.com/paper/2503.08688/) (2025)
- [Mind the Value-Action Gap: Do LLMs Act in Alignment with Their Values?](https://mlsanity.com/paper/2501.15463/) (2025)
- [Bias in Language Models: Beyond Trick Tests and Toward RUTEd Evaluation](https://mlsanity.com/paper/2402.12649/) (2024)
- [Actions Speak Louder than Words: Agent Decisions Reveal Implicit Biases in Language Models](https://mlsanity.com/paper/2501.17420/) (2025)
- [Normative Evaluation of Large Language Models with Everyday Moral Dilemmas](https://mlsanity.com/paper/2501.18081/) (2025)
- [Does Liking Yellow Imply Driving a School Bus? Semantic Leakage in Language Models](https://mlsanity.com/paper/2408.06518/) (2024)
- [The Greatest Good Benchmark: Measuring LLMs' Alignment with Utilitarian Moral Dilemmas](https://mlsanity.com/paper/2503.19598/) (2025)
- [Discerning What Matters: A Multi-Dimensional Assessment of Moral Competence in LLMs](https://mlsanity.com/paper/2506.13082/) (2025)
- [Am I Blue or Is My Hobby Counting Teardrops? Expression Leakage in Large Language Models as a Symptom of Irrelevancy Disruption](https://mlsanity.com/paper/2508.01708/) (2025)

## Built on by (most cited first, 3 of 3)

- [Are LLMs Bad at Moral Reasoning?](https://mlsanity.com/paper/2606.11635/) (2026)
- [Normative Robustness as a Frontier for Non-Verifiable Reasoning in LLMs](https://mlsanity.com/paper/2606.12731/) (2026)
- [Reading Too Much into Context: Passive Exposure Can Steer LLM Decisions](https://mlsanity.com/paper/2609.33065/) (2026)

## Abstract (arXiv)

With the rapid uptake of large language models (LLMs) across high-stakes settings, it is becoming increasingly important to ensure that LLMs behave in ways that align with human values. Existing moral benchmarks for this purpose often prompt LLMs with value statements, moral scenarios, or psychological questionnaires, with the implicit underlying assumption that LLMs report somewhat stable moral preferences. However, moral psychology research has shown that even human moral judgements are sensitive to morally irrelevant situational factors such as the smell of cinnamon rolls or the level of ambient noise, thereby challenging moral theories which assume that human moral judgements are stable. Here we draw inspiration from this "situationist" view of moral psychology to evaluate whether LLMs exhibit similar cognitive moral biases. We curate a novel multimodal dataset of 60 "moral distractors" from existing psychological datasets of emotionally-valenced images and narratives, which have no moral relevance to the situation presented. After injecting these distractors into existing moral benchmarks, we find that moral distractors can shift the moral judgements of LLMs by over 30% even in unambiguous scenarios, highlighting the instability of LLMs' moral judgements and the need for more contextual approaches to AI alignment.