RealityTest: How People Probe AI Identity and Whether Models Disclose It

• URL: http://arxiv.org/abs/2606.00168v1
• Date: Fri, 29 May 2026 12:40:16 GMT
• Title: RealityTest: How People Probe AI Identity and Whether Models Disclose It
• Abstract summary: We present RealityTest to test whether AI systems disclose their identity when asked.<n>We release the underlying dataset of 3,152 identity-probing queries collected from 750 participants across 49 countries and five languages.<n>We find that only 31% of people ask about identity directly in ambiguous scenarios, and that the questions people ask are far more diverse than machine-generated queries.
• Score: 5.4667629504496285
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: AI systems are increasingly deployed in conversational settings where users may be uncertain whether they are speaking with a human or an AI. Despite mounting regulatory attention to this known safety risk, existing evaluations of AI disclosure are typically English-only, based on machine-generated questions, and restricted to text. We present RealityTest to comprehensively test whether AI systems disclose their identity when asked. The benchmark is the first large-scale multimodal and multilingual evaluation, grounded in human data on how people actually encounter and question AI identity in the real-world. Alongside the benchmark, we release the underlying dataset of 3,152 identity-probing queries collected from ~750 participants across 49 countries and five languages, in text and speech scenarios. We find that only 31% of people ask about identity directly in ambiguous scenarios, and that the questions people ask are far more diverse than machine-generated queries. We test 17 text and 6 speech models, and find substantial variation in disclosure behaviour. However, a single suppression instruction reduces disclosure rates to below 30%, even in the best-performing models. Validating our investment in diverse, human-grounded evaluation data, we find that how the question is phrased and the context of the conversation matter more for disclosure than which model is being tested. Safety evaluations built on narrow or synthetic query sets risk mischaracterising how models behave in realistic deployment settings.

Related papers

• Inverse Turing Bench: Evaluating Language Models as Judges of Human vs. AI Dialogue [1.1305136905804842]
  We present Inverse Turing Bench, a benchmark that evaluates models on their ability to differentiate humans and AI in multi-turn text.<n>The benchmark provides a collection of paired dialogue transcripts, wherein one dialogue is between two humans and the other is between a human and an AI.<n>We evaluated a preliminary set of models against this benchmark, and found that GPTZero, Claude Opus-4.6, and GPT-5.5 achieve the highest accuracy.
  arXiv  Detail & Related papers  (2026-06-20T02:47:56Z)
• RogueAI: A Reverse Turing Test for Detecting Licensed AI Deception in Dialogue [2.7606655162305476]
  We present RogueAI, an interactive webapp that operationalizes this test as a one-on-two interrogation game.<n>The player's task is to identify the deceptive agent and "shut it off" before a turn budget is exhausted.<n>We introduce AutoRogueAI, a procedural extension in which players co-design a custom scenario with a narrator agent that secretly chooses its own deception strategy.
  arXiv  Detail & Related papers  (2026-06-11T13:07:02Z)
• 'Your AI Text is not Mine': Redefining and Evaluating AI-generated Text Detection under Realistic Assumptions [50.1119556361129]
  We systematically define various notions of AI-generated text and their characteristics.<n>AITDNA is a new benchmark of human-machine co-constructed texts.<n>We benchmark various machine-generated text detectors and find that they often only perform well for specific notions but not as broad detectors.
  arXiv  Detail & Related papers  (2026-06-03T14:05:14Z)
• Implicit Intelligence -- Evaluating Agents on What Users Don't Say [0.3580891736370874]
  Implicit Intelligence is an evaluation framework testing whether AI agents can move beyond prompt-following to become genuine goal-fulfillers.<n>Our scenarios feature apparent simplicity in user requests, hidden complexity in correct solutions, and discoverability of constraints through environmental exploration.
  arXiv  Detail & Related papers  (2026-02-23T23:46:55Z)
• Disclosure By Design: Identity Transparency as a Behavioural Property of Conversational AI Models [10.35358368112024]
  When AI identity is unclear, users may unwittingly share sensitive information, place unwarranted trust in AI-generated advice, or fall victim to AI-enabled fraud.<n>We advocate for disclosure by design, where AI systems explicitly disclose their artificial identity when directly asked.<n>We find that baseline disclosure rates are often high but drop substantially in role-play and can be suppressed under adversarial prompting.
  arXiv  Detail & Related papers  (2026-01-27T17:31:37Z)
• AHELM: A Holistic Evaluation of Audio-Language Models [78.20477815156484]
  multimodal audio-language models (ALMs) take interleaved audio and text as input and output text.<n>AHELM is a benchmark that aggregates various datasets -- including 2 new synthetic audio-text datasets called PARADE and CoRe-Bench.<n>We also standardize the prompts, inference parameters, and evaluation metrics to ensure equitable comparisons across models.
  arXiv  Detail & Related papers  (2025-08-29T07:40:39Z)
• Could AI Trace and Explain the Origins of AI-Generated Images and Text? [53.11173194293537]
  AI-generated content is increasingly prevalent in the real world.<n> adversaries might exploit large multimodal models to create images that violate ethical or legal standards.<n>Paper reviewers may misuse large language models to generate reviews without genuine intellectual effort.
  arXiv  Detail & Related papers  (2025-04-05T20:51:54Z)
• Almost AI, Almost Human: The Challenge of Detecting AI-Polished Writing [55.2480439325792]
  This study systematically evaluations twelve state-of-the-art AI-text detectors using our AI-Polished-Text Evaluation dataset.<n>Our findings reveal that detectors frequently flag even minimally polished text as AI-generated, struggle to differentiate between degrees of AI involvement, and exhibit biases against older and smaller models.
  arXiv  Detail & Related papers  (2025-02-21T18:45:37Z)
• Testing AI on language comprehension tasks reveals insensitivity to underlying meaning [3.335047764053173]
  Large Language Models (LLMs) are recruited in applications that span from clinical assistance and legal support to question answering and education. Yet, reverse-engineering is bound by Moravec's Paradox, according to which easy skills are hard. We systematically assess 7 state-of-the-art models on a novel benchmark.
  arXiv  Detail & Related papers  (2023-02-23T20:18:52Z)
• Can Machines Imitate Humans? Integrative Turing-like tests for Language and Vision Demonstrate a Narrowing Gap [56.611702960809644]
  We benchmark AI's ability to imitate humans in three language tasks and three vision tasks.<n>Next, we conducted 72,191 Turing-like tests with 1,916 human judges and 10 AI judges.<n>Imitation ability showed minimal correlation with conventional AI performance metrics.
  arXiv  Detail & Related papers  (2022-11-23T16:16:52Z)
• AES Systems Are Both Overstable And Oversensitive: Explaining Why And Proposing Defenses [66.49753193098356]
  We investigate the reason behind the surprising adversarial brittleness of scoring models. Our results indicate that autoscoring models, despite getting trained as "end-to-end" models, behave like bag-of-words models. We propose detection-based protection models that can detect oversensitivity and overstability causing samples with high accuracies.
  arXiv  Detail & Related papers  (2021-09-24T03:49:38Z)

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.