The paper introduces a pragmatics-inspired taxonomy for evaluating how large language models (LLMs) refuse unsafe or inappropriate requests. By applying this framework to 16 modern LLMs across 14 harm categories, the authors find that while refusals are generally explicit and morally charged, they often lack interpersonal facework and instead offer safer alternatives, which can be problematic in sensitive contexts. The study argues for alignment evaluations that assess not just whether LLMs refuse, but how they do so in a contextually adaptive and socially responsible manner.
arXiv:2608.23264v1 Announce Type: new Abstract: Although Large Language Models (LLMs) are aligned to optimize for both helpfulness and harmlessness, these dual objectives may conflict, inevitably lea...
arXiv:2601. 21433v2 Announce Type: replace Abstract: Language models are increasingly consulted on ethically consequential questions, yet the stance a model expresses may not survive a change in framing.
arXiv:2606. 26106v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used in emotionally charged situations involving interpersonal conflict, frustration, and distress.
DeflectBench is a new benchmark that evaluates how large language models (LLMs) generate rhetorical fallacies when prompted. The study tests 23,990 generations from four leading models using three deflection strategies (whataboutism, ad hominem, red herring), seven prompt framings, and 80 claims across four controversy levels. Results show that refusal to produce fallacies depends mainly on request structure, with prompt framing and fallacy type dramatically affecting compliance rates.
arXiv:2607. 24758v1 Announce Type: new Abstract: Large language models are capable of recognizing evaluation contexts and altering their behavior to reflect evaluator expectations rather than typical deployment behaviors, a phenomenon known as alignment faking.
arXiv:2606. 02423v1 Announce Type: cross Abstract: Large language models (LLMs) can serve as helpful assistants, yet they can equally function as harm amplifiers that enable malicious users to achieve harmful outcomes beyond their capabilities through extended interactions.
arXiv:2608. 12368v1 Announce Type: new Abstract: Agreement with human judgments is a common proxy for evaluating the alignment of large language models (LLMs).
arXiv:2607. 19629v1 Announce Type: cross Abstract: Large language models operating in emotionally sensitive contexts face a structural trilemma: when users in vulnerable states request information that may reinforce maladaptive attribution, current response architectures resolve the tension through protective restriction, uninflected facilitation, or unintegrated co-presence of both imperatives -- each preserving one objective at the cost of the other.
arXiv:2509. 05367v5 Announce Type: replace-cross Abstract: Large Language Model safety alignment predominantly operates on a binary assumption that requests are either safe or unsafe.
arXiv:2606. 08076v1 Announce Type: cross Abstract: Large Language Models (LLMs) can generate high-quality arguments, yet their ability to engage in nuanced and persuasive communicative actions remains largely unexplored.
The paper investigates how annotator-style rebuttals can manipulate large language model (LLM) moderation systems, either by whitewashing hateful content as normal or smearing normal content as hateful. Using a rejudge protocol that adds decision‑boundary perturbations and adversarial rationales, the authors show that such rebuttals significantly degrade moderation performance, especially in multi‑turn settings. The study finds consistent, model‑specific asymmetries between the two manipulation directions and demonstrates that explicit reasoning prompts and defensive instructions mitigate but do not eliminate the vulnerability.
arXiv:2606. 08076v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) can generate high-quality arguments, yet their ability to engage in nuanced and persuasive communicative actions remains largely unexplored.