# Deontological Keyword Bias: The Impact of Modal Expressions on Normative Judgments of Language Models

arXiv: https://arxiv.org/abs/2506.11068 · HTML: https://mlsanity.com/paper/2506.11068/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 56 references that are in the map.
- First posted on arXiv 1 Jun 2025.

## Builds on (most cited first, 27 of 27)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [Language Models as Knowledge Bases?](https://mlsanity.com/paper/1909.01066/) (2019)
- [Calibrate Before Use: Improving Few-Shot Performance of Language Models](https://mlsanity.com/paper/2102.09690/) (2021)
- [Ethical and social risks of harm from Language Models](https://mlsanity.com/paper/2112.04359/) (2021)
- [Aligning AI With Shared Human Values](https://mlsanity.com/paper/2008.02275/) (2020)
- [Bias and Fairness in Large Language Models: A Survey](https://mlsanity.com/paper/2309.00770/) (2023)
- [Release Strategies and the Social Impacts of Language Models](https://mlsanity.com/paper/1908.09203/) (2019)
- [Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations](https://mlsanity.com/paper/2204.02937/) (2022)
- [Prompting GPT-3 To Be Reliable](https://mlsanity.com/paper/2210.09150/) (2022)
- [Evaluating the Moral Beliefs Encoded in LLMs](https://mlsanity.com/paper/2307.14324/) (2023)
- [Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming](https://mlsanity.com/paper/2501.18837/) (2025)
- [Detecting Emergent Intersectional Biases: Contextualized Word Embeddings Contain a Distribution of Human-like Biases](https://mlsanity.com/paper/2006.03955/) (2020)
- [Intrinsic Bias Metrics Do Not Correlate with Application Bias](https://mlsanity.com/paper/2012.15859/) (2020)
- [Ethical Reasoning over Moral Alignment: A Case and Framework for In-Context Ethical Policies in LLMs](https://mlsanity.com/paper/2310.07251/) (2023)
- [Rethinking Machine Ethics -- Can LLMs Perform Moral Reasoning through the Lens of Moral Theories?](https://mlsanity.com/paper/2308.15399/) (2023)
- [Parameter-efficient Modularised Bias Mitigation via AdapterFusion](https://mlsanity.com/paper/2302.06321/) (2023)
- [Normative Evaluation of Large Language Models with Everyday Moral Dilemmas](https://mlsanity.com/paper/2501.18081/) (2025)
- [Obligation and Prohibition Extraction Using Hierarchical RNNs](https://mlsanity.com/paper/1805.03871/) (2018)
- [Why LLMs Hallucinate, and How to Get (Evidential) Closure: Perceptual, Intensional, and Extensional Learning for Faithful Natural Language Generation](https://mlsanity.com/paper/2310.15355/) (2023)
- [Identifying and Mitigating Social Bias Knowledge in Language Models](https://mlsanity.com/paper/2408.11843/) (2024)
- [Norm Conflict Resolution in Stochastic Domains](https://mlsanity.com/paper/1706.07448/) (2017)

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

- [Structuring the Space of Sociotechnical Alignment](https://mlsanity.com/paper/2607.01250/) (2026)
- [Rule vs.Consequence: Dissociable Internal Representations of Moral Reasoning in LLMs](https://mlsanity.com/paper/2610.16371/) (2026)
- [Incomplete Prompt Jailbreaks in Large Language Models](https://mlsanity.com/paper/2607.20473/) (2026)

## Abstract (arXiv)

Large language models (LLMs) are increasingly engaging in moral and ethical reasoning, where criteria for judgment are often unclear, even for humans. While LLM alignment studies cover many areas, one important yet underexplored area is how LLMs make judgments about obligations. This work reveals a strong tendency in LLMs to judge non-obligatory contexts as obligations when prompts are augmented with modal expressions such as must or ought to. We introduce this phenomenon as Deontological Keyword Bias (DKB). We find that LLMs judge over 90% of commonsense scenarios as obligations when modal expressions are present. This tendency is consist across various LLM families, question types, and answer formats. To mitigate DKB, we propose a judgment strategy that integrates few-shot examples with reasoning prompts. This study sheds light on how modal expressions, as a form of linguistic framing, influence the normative decisions of LLMs and underscores the importance of addressing such biases to ensure judgment alignment.