Recon: Reconstruction-Guided Reasoning Synthesis for User Modeling
cs.CL, cs.AI
Submitted: 2026-05-26
Updated: 2026-11-03
Code: https://github.com/walkerdb/supreme_court_transcripts
Project page: https://recon-user-modeling.com
Terminology
Sources
- How to Train Your Advisor: Steering Black-Box LLMs with Advisor Models
- Aligning Language Models from User Interactions
- Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging
- Personalized Language Modeling from Personalized Human Feedback
- Can LLM Agents Simulate Multi-Turn Human Behavior? Evidence from Real Online Customer Behavior Data
- ParaStudent: Closing the Sim2Real Gap in User Simulators for AI Tutor Evaluation
- Flipping the Dialogue: Training and Evaluating User Language Models
- AI Simulations Grounded in Rich Self-Reports Increase Accuracy and Reduce Distortion
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- OpenAI GPT-5 System Card
- FSPO: Few-Shot Optimization of Synthetic Preferences Personalizes to Real Users
- CollabLLM: From Passive Responders to Active Collaborators
- HumanLM: Simulating Users with State Alignment Beats Response Imitation
- Qwen3 Technical Report
- How to Steal Reasoning Without Reasoning Traces
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data