Between a Rock and a Hard Place: The Tension Between Ethical Reasoning and Safety Alignment in LLMs

ACL ARR 2026 January Submission8118 Authors

Keywords: Ethics, Bias, and Fairness, Language Modeling, Interpretability and Analysis of Models for NLP, Question Answering

Abstract: Large Language Model safety alignment predominantly operates on a binary assumption that requests are either safe or unsafe. This classification proves insufficient when models encounter ethical dilemmas, where the capacity to reason through moral trade-offs creates a distinct attack surface. We formalize this vulnerability through TRIAL, a multi-turn red-teaming methodology that embeds harmful requests within ethical framings. TRIAL achieves consistently high attack success rates across models by exploiting the model's own ethical reasoning to frame harmful actions as morally necessary compromises. Building on these insights, we introduce ERR (Ethical Reasoning Robustness), a defense framework that distinguishes between instrumental responses that enable harmful outcomes and explanatory responses that analyze ethical frameworks without endorsing harmful acts. ERR employs a Layer-Stratified Harm-Gated LoRA architecture, achieving robust defense against reasoning-based attacks while preserving model utility.

Paper Type: Long

Research Area: Safety and Alignment in LLMs

Research Area Keywords: Ethics, Bias, and Fairness, Language Modeling, Interpretability and Analysis of Models for NLP, Question Answering

Contribution Types: Model analysis & interpretability, NLP engineering experiment, Publicly available software and/or pre-trained models, Data resources

Languages Studied: English

Submission Number: 8118