HumanLM

HumanLM: Simulating Users with State Alignment Beats Response Imitation

We build user simulators that accurately reflect real users by generating natural-language latent states aligned with ground-truth responses. Fig 1. HumanLM generates responses by first producing latent states (stance, emotion, communication style) that align with ground-truth user behavior, then synthesizing responses from these aligned states. Abstract Large Language Models are increasingly used to simulate how specific users respond to any context, enabling more user-centric applications. However, existing user simulators mostly imitate surface-level patterns and language styles, which…

saved by

• Laerdon Kim

related reading

• Quantifying the Utility of User Simulators for Building Collaborative LLM Assistantsarxiv.org
• Lost in Simulation: LLM-Simulated Users are Unreliable Proxies for Human Users in Agentic Evaluationsarxiv.org
• HumanLM: Simulating Users with State Alignment Beats Response Imitationarxiv.org
• user_interactions.pdfself-distillation.github.io
• [2508.19227] Generative Interfaces for Language Modelsarxiv.org
• Today's AI Talks Like “Nobody.” New Research Gives It Real Personality. | Stanford HAIhai.stanford.edu
• The Persona Selection Model: Why AI Assistants might Behave like Humansalignment.anthropic.com
• Training and Evaluating User Language Modelsarxiv.org
• Today, we are releasing a research preview of our user model, along with a set of evaluations designed to measure how faithfully user models capture human behavior.persimmon.humansand.ai
• [2304.03442] Generative Agents: Interactive Simulacra of Human Behaviorarxiv.org
• [2304.03442] Generative Agents: Interactive Simulacra of Human Behaviorarxiv.org
• The Waluigi Effect (mega-post) — LessWronglesswrong.com