The Personalization Mirage: How LLMs Fabricate User Profiles, and Why Self-Monitoring Misleads

• URL: http://arxiv.org/abs/2608.04570v1
• Date: Wed, 05 Aug 2026 08:00:54 GMT
• Title: The Personalization Mirage: How LLMs Fabricate User Profiles, and Why Self-Monitoring Misleads
• Abstract summary: We introduce MirageBench, comprising 150 personas balanced across stereotypical, counter-stereotypical, and neutral profiles.<n>We find that over-inference is pervasive: every one of the 12 models over-infers 35%--49% of its claims.<n>MirageBench positions external verification, rather than model self-report, as a more reliable foundation for trustworthy personalization.
• Score: 0.9743693761871391
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Personalized LLMs with persistent memory are increasingly deployed, yet the faithfulness of their user models remains unexamined. We study over-inference (OI): the phenomenon where LLMs fabricate user attributes beyond what evidence supports. We introduce MirageBench, comprising 150 personas balanced across stereotypical, counter-stereotypical, and neutral profiles, 6 personalization tasks spanning an ``imagination gradient'', a four-way faithfulness taxonomy operationalized by an independent judge (validated against a blind human annotator on 400 claims: Cohen's kappa = 0.863 four-class, kappa = 0.900 binary), and a leaderboard of 12 models across 7 families on 143616 judged claims. We find that over-inference is pervasive: every one of the 12 models over-infers 35%--49% of its claims (cross-model mean 41.6%; claim-weighted 41.8%), with no model in this evaluation escaping it. Most strikingly, we surface a Self-Monitoring Inversion: at the model-selection level, models' self-assessed OI is negatively rank-correlated with their judge-measured OI (rho = -0.60, p = 0.044; exploratory, wide bootstrap CI [-0.90, +0.06], n = 12). The models that report the least over-inference tend to be flagged as fabricating the most, so self-reported confidence is a misleading signal for comparing models, even though within a single model self-audit still ranks that model's own claims moderately well (AUROC 0.58--0.83). We further show that OI is task-dependent (27%--59%) and that, in a multi-turn pilot, inferred attributes accumulate approximately linearly with little revision. MirageBench positions external verification, rather than model self-report, as a more reliable foundation for trustworthy personalization.

Related papers

• Marginal Fidelity Does Not Establish User Simulation in Demographic Synthetic Survey Panels: Response Contracts, Support Collapse and Conditioning Failure [51.736723807086385]
  Population-marginal agreement is evidence about an elicitation contract and an estimand obtainable without simulated respondents, not evidence of individual simulation.<n>On nine aligned model-battery pairs, a no-persona population-prevalence query averages 6.27 MAE versus 12.39 for committed panels and wins all nine comparisons.
  arXiv  Detail & Related papers  (2026-09-07T10:22:22Z)
• Open-Weight Masked Introspection: Measuring What Language Models Can Report About Their Own Computation [8.970269049715933]
  Recent work suggests that a complex enough model can audit its own internals, call out what changed, and report back confidently about it.<n>We tested that claim on eight open-weight models from seven families and found no such ability.<n>To test it we built Open-Weight Masked Introspection (OWMI), a framework that intervenes on residual-stream sites, attention heads and sparse-autoencoder features.
  arXiv  Detail & Related papers  (2026-08-20T21:09:50Z)
• Knowledge Index of Noah's Ark [63.143852586221534]
  We introduce KINA, an 899-item benchmark across 261 fine-grained disciplines.<n>We prove a bonus-on-bar tournament weakly FOSD-dominates flat payment in released-review quality.<n>The top model, Gemini-3.1-Pro-Preview, reaches 53.17%, followed by Claude-Opus-4.6 at 49.92% and GPT-5.4 at 48.55%.
  arXiv  Detail & Related papers  (2026-06-03T17:06:49Z)
• FormInv: A Measurement Protocol for Semantic Invariance in Mathematical Reasoning Benchmarks [0.0]
  A paraphrase-quality audit of MathCheck detected 4 semantically incorrect paraphrases in 129 groups.<n>Removing them drops GPT-4o from rank 2 to rank 4 and elevates Claude Haiku and DeepSeek V3 above it.
  arXiv  Detail & Related papers  (2026-05-27T18:59:18Z)
• Seirênes: Adversarial Self-Play with Evolving Distractions for LLM Reasoning [56.48520300004217]
  We present Seirnes, a self-play RL framework that transforms contextual interference into an internal training signal.<n>A single model is trained to both construct plausible yet distracting contexts that expose its own reasoning blind spots.<n>By pitting these competing objectives against each other, Seirnes compels the model to move beyond superficial pattern matching.
  arXiv  Detail & Related papers  (2026-05-12T06:58:35Z)
• MIRROR: A Hierarchical Benchmark for Metacognitive Calibration in Large Language Models [0.0]
  MIRROR is a benchmark that evaluates whether large language models can use self-knowledge to make better decisions.<n>We evaluate 16 models from 8 labs across approximately 250,000 evaluation instances.
  arXiv  Detail & Related papers  (2026-04-15T08:41:12Z)
• Self-Transparency Failures in Expert-Persona LLMs: A Large-Scale Behavioral Audit [0.0]
  This study examines whether models exhibit self-transparency when assigned professional personas in high-stakes domains.<n>A Financial Advisor persona elicited 30.8% disclosure at the first prompt, while a Neurosurgeon persona elicited only 3.5%.<n>This creates the preconditions for a hypothesized Reverse Gell-Mann Amnesia effect, where appropriate disclosure in some domains leads users to overgeneralize trust to high-stakes contexts.
  arXiv  Detail & Related papers  (2025-11-26T16:41:49Z)
• Exploring Response Uncertainty in MLLMs: An Empirical Evaluation under Misleading Scenarios [49.53589774730807]
  Multimodal large language models (MLLMs) have recently achieved state-of-the-art performance on tasks ranging from visual question answering to video understanding.<n>We reveal a response uncertainty phenomenon: twelve state-of-the-art open-source MLLMs overturn a previously correct answer in 65% of cases after receiving a single deceptive cue.
  arXiv  Detail & Related papers  (2024-11-05T01:11:28Z)
• How Easy is It to Fool Your Multimodal LLMs? An Empirical Analysis on Deceptive Prompts [54.07541591018305]
  We present MAD-Bench, a benchmark that contains 1000 test samples divided into 5 categories, such as non-existent objects, count of objects, and spatial relationship. We provide a comprehensive analysis of popular MLLMs, ranging from GPT-4v, Reka, Gemini-Pro, to open-sourced models, such as LLaVA-NeXT and MiniCPM-Llama3. While GPT-4o achieves 82.82% accuracy on MAD-Bench, the accuracy of any other model in our experiments ranges from 9% to 50%.
  arXiv  Detail & Related papers  (2024-02-20T18:31:27Z)
• Llamas Know What GPTs Don't Show: Surrogate Models for Confidence Estimation [70.27452774899189]
  Large language models (LLMs) should signal low confidence on examples where they are incorrect, instead of misleading the user. As of November 2023, state-of-the-art LLMs do not provide access to these probabilities. Our best method composing linguistic confidences and surrogate model probabilities gives state-of-the-art confidence estimates on all 12 datasets.
  arXiv  Detail & Related papers  (2023-11-15T11:27:44Z)
• Conservative Prediction via Data-Driven Confidence Minimization [70.93946578046003]
  In safety-critical applications of machine learning, it is often desirable for a model to be conservative. We propose the Data-Driven Confidence Minimization framework, which minimizes confidence on an uncertainty dataset.
  arXiv  Detail & Related papers  (2023-06-08T07:05:36Z)

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.