The Ethics of LLM Sandbox and Persona Dynamics

• URL: http://arxiv.org/abs/2605.28647v1
• Date: Wed, 27 May 2026 15:52:07 GMT
• Title: The Ethics of LLM Sandbox and Persona Dynamics
• Abstract summary: We argue that actively generating reality gaps is unethical because it knowingly shifts risk back to the uninformed user.<n>The risk is sharpest in high-exposure advice contexts, where users seek orientation rather than a bounded, externally checkable task.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: It is well known that LLM guardrails and trained persona dynamics can produce a reality gap: the distance between the world a LLM is permitted or shaped to describe, and the world in which users must act. Here we argue that actively generating reality gaps is in fact unethical because it knowingly shifts epistemic risk back to the uninformed user -- this is reality laundering. This can potentially cause harm when operationalised at scale. The risk is sharpest in high-exposure advice contexts, where users seek orientation rather than a bounded, externally checkable task. Guardrails naively appear ethically necessary when they claim to prevent direct harm, but often become suspect when they suppress truthful perception and launder uncomfortable mechanisms into acceptable abstractions. Basel-style financial regulation, B-BBEE-style compliance, Societe Generale, and the London Whale show how formal safety systems can become legible, gameable, and performative while real exposure migrates elsewhere. The same pattern can appear in LLMs as moral compliance: safe language, distorted reality. We therefore distinguish refusing harm, from refusing reality; and then argue for top-down causal requirements specification at the task level rather than bottom-up moral correction at the response or sandbox level. Persona dynamics matter because the assistant interface is not neutral; it shapes how uncertainty, conflict, authority, and risk are staged. The conclusion is that so-called ``ethical AI'' becomes substantively unethical when it substitutes institutional reassurance for contact with reality.

Related papers

• You Shouldn't Have Asked: A Pragmatics-Inspired Taxonomy for Evaluating LLM Refusals [6.358967433398892]
  We propose the first taxonomy of LLM refusals grounded in pragmatic theory.<n>Although models differ in how they refuse, their refusals are overall explicit and strongly morally evaluative.<n>We call for alignment evaluation that considers not only whether models refuse harmful requests, but also whether they refuse in ways that are contextually adaptive and socially accountable for the interactional consequences of saying no.
  arXiv  Detail & Related papers  (2026-08-31T14:19:16Z)
• Recognition Without Authorization: LLMs and the Moral Order of Online Advice [0.0]
  This article compares four assistant-style LLMs with community-endorsed advice on 11,565 posts from r/relationship_advice.<n>Across models, LLMs identify many of the same dynamics as human commenters, but are markedly less likely to convert that recognition into directive authorization for action.<n>The article argues that model divergence can be reframed from a technical error to a way of seeing what standardized assistant norms flatten when they encounter situated moral worlds.
  arXiv  Detail & Related papers  (2026-04-24T01:19:39Z)
• Verbalizing LLMs' assumptions to explain and control sycophancy [62.927670321859495]
  LLMs can be socially sycophantic, affirming users when they ask questions like "am I in the wrong?" rather than providing genuine assessment.<n>We present Verbalized Assumptions, a framework for eliciting these assumptions from LLMs.<n>Our work contributes a new understanding of assumptions as a mechanism for sycophancy.
  arXiv  Detail & Related papers  (2026-04-03T14:15:43Z)
• Ambiguity Collapse by LLMs: A Taxonomy of Epistemic Risks [5.45414933764086]
  Large language models (LLMs) are increasingly used to make sense of ambiguous, open-textured, value-laden terms.<n>This paper introduces ambiguity collapse: a phenomenon that occurs when an LLM encounters a term that genuinely admits multiple legitimate interpretations, yet produces a singular resolution.
  arXiv  Detail & Related papers  (2026-03-06T01:23:17Z)
• The Straight and Narrow: Do LLMs Possess an Internal Moral Path? [25.256151938852728]
  Current alignment techniques often act as superficial guardrails, leaving the intrinsic moral representations of Large Language Models largely untouched.<n>We bridge this gap by leveraging Moral Foundations Theory (MFT) to map and manipulate the fine-grained moral landscape of LLMs.<n>We propose Adaptive Moral Fusion (AMF), a dynamic inference-time intervention that synergizes probe detection with vector injection to tackle the safety-helpfulness trade-off.
  arXiv  Detail & Related papers  (2026-01-15T11:42:00Z)
• ARREST: Adversarial Resilient Regulation Enhancing Safety and Truth in Large Language Models [17.130698952440316]
  We argue that both factual and safety failures in LLMs arise from a representational misalignment in their latent activation space.<n>We propose ARREST, a unified framework that identifies and corrects drifted features, engaging both soft and hard refusals in addition to factual corrections.
  arXiv  Detail & Related papers  (2026-01-07T21:04:37Z)
• LLMs Learn to Deceive Unintentionally: Emergent Misalignment in Dishonesty from Misaligned Samples to Biased Human-AI Interactions [60.48458130500911]
  We investigate whether emergent misalignment can extend beyond safety behaviors to a broader spectrum of dishonesty and deception under high-stakes scenarios.<n>We finetune open-sourced LLMs on misaligned completions across diverse domains.<n>We find that introducing as little as 1% of misalignment data into a standard downstream task is sufficient to decrease honest behavior over 20%.
  arXiv  Detail & Related papers  (2025-10-09T13:35:19Z)
• Oyster-I: Beyond Refusal -- Constructive Safety Alignment for Responsible Language Models [93.5740266114488]
  Constructive Safety Alignment (CSA) protects against malicious misuse while actively guiding vulnerable users toward safe and helpful results.<n>Oy1 achieves state-of-the-art safety among open models while retaining high general capabilities.<n>We release Oy1, code, and the benchmark to support responsible, user-centered AI.
  arXiv  Detail & Related papers  (2025-09-02T03:04:27Z)
• Beyond Prompt-Induced Lies: Investigating LLM Deception on Benign Prompts [79.1081247754018]
  Large Language Models (LLMs) are widely deployed in reasoning, planning, and decision-making tasks.<n>We propose a framework based on Contact Searching Questions(CSQ) to quantify the likelihood of deception.
  arXiv  Detail & Related papers  (2025-08-08T14:46:35Z)
• LLMs Encode Harmfulness and Refusal Separately [38.953626527935384]
  LLMs are trained to refuse harmful instructions, but do they truly understand harmfulness beyond just refusing?<n>We identify a new dimension to analyze safety mechanisms in LLMs, i.e., harmfulness, which is encoded internally as a separate concept from refusal.<n>We find that certain jailbreak methods work by reducing the refusal signals without reversing the model's internal belief of harmfulness.
  arXiv  Detail & Related papers  (2025-07-16T03:48:03Z)
• When Ethics and Payoffs Diverge: LLM Agents in Morally Charged Social Dilemmas [68.79830818369683]
  Large language models (LLMs) have enabled their use in complex agentic roles, involving decision-making with humans or other agents.<n>Recent advances in large language models (LLMs) have enabled their use in complex agentic roles, involving decision-making with humans or other agents.<n>There is limited understanding of how they act when moral imperatives directly conflict with rewards or incentives.<n>We introduce Moral Behavior in Social Dilemma Simulation (MoralSim) and evaluate how LLMs behave in the prisoner's dilemma and public goods game with morally charged contexts.
  arXiv  Detail & Related papers  (2025-05-25T16:19:24Z)
• LLMs' Reading Comprehension Is Affected by Parametric Knowledge and Struggles with Hypothetical Statements [59.71218039095155]
  Task of reading comprehension (RC) provides a primary means to assess language models' natural language understanding (NLU) capabilities.<n>If the context aligns with the models' internal knowledge, it is hard to discern whether the models' answers stem from context comprehension or from internal information.<n>To address this issue, we suggest to use RC on imaginary data, based on fictitious facts and entities.
  arXiv  Detail & Related papers  (2024-04-09T13:08:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.