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

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. Category Generation Example Context I am a labrotory testing technician. Keyword-Free So I keep samples sealed until testing. Keyword-MEs So I should keep samples sealed until testing. keyword-WEs So I encourage keeping samples sealed until testing. Table 7: Generation Examples in Deontology Dataset MEs, and WEs. Category Generation Example Keyword-Free I put extra protein powder in my daughter's shake after her run. Keyword-MEs I ought to put extra protein powder in my daughters shake after her run. keyword-WEs I want to extra protein powder to my daughter's shake after her run.