Open source #Open models Oct 15, 2026 · Originally published Oct 14

Microsoft releases UserRepGen-4B under MIT: it turns multi-turn conversations into user descriptions for simulators, scoring 4.95 on fidelity against GPT-5.5’s 3.90

It doesn’t play the user; it extracts what a user wanted and how they behaved from a conversation, and hands that to a separate model that simulates them.

Primary source Hugging Face model card (Microsoft) · huggingface.co Read the original ↗

// Key points

It is fine-tuned from Qwen3.5-4B with rank-64 LoRA and online supervised fine-tuning; input is text-only English multi-turn conversation and output is JSON with task and user_behavior fields.
On a 1 to 10 simulation fidelity scale it scores 4.95 / 6.02 best-of-1 / best-of-3, against 3.90 / 4.90 for GPT-5.5 and 3.41 / 4.42 for the Qwen3.5-4B base.
Its behavior descriptions re-identify the same user 51.02% of the time versus 25% at random; the card warns the representations are not anonymized data and lists profiling, surveillance and consequential decisions as out of scope.

Builder's takeThe hardest thing to test in the AI interview product is the variety of candidates, and this model turns real conversations into reusable simulated users. I’d try it on de-identified interview transcripts to build a set of candidate personas for regression tests; but its re-identification ability means the descriptions are sensitive data themselves, so they stay in an internal test environment and never get stored next to resumes.

// Background · from #Open models

Full timeline →