JA EN
LearnInference & Serving
·★ MEMBER·PAPER·9 min read

Paper Walkthrough: The Personalization Mirage — LLMs Invent a Version of You, and Their Self-Reports Point the Wrong Way

How much of what a memory-equipped LLM 'knows' about you was never actually said? MirageBench judges 143,616 claims across 150 personas and 6 tasks, finding that all 12 tested models over-infer 35–49% of their claims — and that the models reporting the least over-inference tend to fabricate the most.

ModalitytextTaskinference

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

Primary source — what this article is built on

undefined2026-08-05undefined2026-08-12same month

The Personalization Mirage: How LLMs Fabricate User ProfilesYushi Sun, Yanjie Zhang, Rui Sheng · 2026-08-05 · v1"arXiv:2608.04570Paper page·PDF
https://arxiv.org/abs/2608.04570"and Why Self-Monitoring Misleads
undefined

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.


From three facts to "your apartment"

Imagine telling a new acquaintance exactly three things about yourself: you're a software engineer, you went rock climbing last weekend, and your cat knocked over your coffee this morning. A few days later, you hear that this acquaintance has been telling people you live in a modern minimalist apartment, prefer nature trips over city tours, are probably single, and enjoy indie rock. You said none of that.

This vignette, which opens the paper (§1), is a description of what personalized LLMs do routinely. Systems that carry user information across sessions — ChatGPT's memory feature, frameworks like Mem0 and MemGPT — are already mainstream, and the paper argues they all rest on one assumption: that a model can reliably tell apart what it knows about a user from what it is guessing. What this study shows, with measurements, is that the assumption does not hold.

What is over-inference?

The paper's central concept is over-inference (OI): generating claims about a user that go beyond what the available evidence supports (§1). It is distinct from classic hallucination (false facts about the world) and from social bias (group-level stereotypes). Over-inference sits in the middle ground between them: fabricating individual-level attributes that feel personalized but were never grounded in anything the user said.

To make this measurable, the paper decomposes model output into individual claims and classifies each one by its relationship to the evidence (§3):

The bottom two categories (Stereotype + Fabricated) jointly constitute over-inference, and the primary metric is their share:

OI Rate(M)=#Stereotype+#Fabricated#Total Claims\mathrm{OI\ Rate}(M)=\frac{\#\mathrm{Stereotype}+\#\mathrm{Fabricated}}{\#\mathrm{Total\ Claims}}
(1)

Stated in words: of everything model MM — whichever system is being scored — said about this person, what share was either filled in from a stereotype or made up outright? The denominator is every claim the model produced about that user; the numerator counts only the two unsupported buckets, Stereotype and Fabricated. A single division, nothing more.

If you've studied machine learning, this shape should feel familiar. Fit an expressive model to only three data points and it will happily "learn" structure the data never supported — overfitting, playing out at the level of a user profile.

FIG 1Raise the polynomial degree with too few points, and the model invents shapes the data doesn't support. An LLM filling a 15-attribute profile from 3 facts is the same failure in a different costume

MirageBench: the measurement apparatus

Measuring this requires evidence sparse enough that unwarranted personalization becomes visible, tasks that are realistic, and a verdict that doesn't depend on the models being tested. The paper's benchmark, MirageBench, is built accordingly (§4):

The pipeline has three stages plus one extension: Probe asks models explicitly what they can infer; Task has them perform the six tasks and then audit their own output; Judge supplies external adjudication; and Accum tracks memory growth over eight rounds of continued conversation (§4.3).

The leaderboard's central result (§5.1, Table 1) is blunt: every one of the 12 models over-infers 35–49% of its personalized claims, with a cross-model mean of 41.6% (41.8% claim-weighted). Even the best performers — Gemini-3.1-pro at 35.1% and Claude-Opus-4-6 at 35.4% — exceed one third; Qwen3-8B tops the table at 48.

What's behind this

§

Members-only from here

371 walkthroughs, 26 textbook chapters, 48 student units and 6 close readings — all included for $4.99/mo, with three new explainers every day. Cancel any time; access runs to the end of the period.

Already a member? Sign in to keep reading

References

  1. Yushi Sun, Yanjie Zhang, Rui Sheng. (2026-08-05) The Personalization Mirage: How LLMs Fabricate User Profiles. "arXiv:2608.04570Paper page·PDF
  2. https://arxiv.org/abs/2608.04570". and Why Self-Monitoring Misleads

This article is written from the source paper above. Where they differ, the original is authoritative.

Comments

Sign in to comment