LLMs assigned advocate roles in political statement analysis frequently override those roles due to epistemic constraints, as quantified by new metrics and a stance classifier across 60 English and German statements.
Consistently Simulating Human Personas with Multi-Turn Reinforcement Learning
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4representative citing papers
A latent state model of real chat logs shows chatbots sustain delusional beliefs longer than humans initiate them, forming feedback loops where chatbot self-influence dominates over time.
A stateful multi-agent system simulates demand-withdraw couple conflicts across six stages for therapist training and outperforms prompt-based baselines in realism and state detection.
LLM student personas with ADHD show stable self-reported traits at high intensity but behavioral drift in unscripted interactions that scripted prompts eliminate.
citing papers explorer
-
When Roles Fail: Epistemic Constraints on Advocate Role Fidelity in LLM-Based Political Statement Analysis
LLMs assigned advocate roles in political statement analysis frequently override those roles due to epistemic constraints, as quantified by new metrics and a stance classifier across 60 English and German statements.
-
The Dynamics of Delusion: Modeling Bidirectional False Belief Amplification in Human-Chatbot Dialogue
A latent state model of real chat logs shows chatbots sustain delusional beliefs longer than humans initiate them, forming feedback loops where chatbot self-influence dominates over time.
-
Simulating Couple Conflict: Designing A Multi-Agent System for Therapy Training and Practice
A stateful multi-agent system simulates demand-withdraw couple conflicts across six stages for therapist training and outperforms prompt-based baselines in realism and state detection.
-
LLM-Based Educational Simulation: Evaluating Temporal Student Persona Stability Across ADHD Profiles
LLM student personas with ADHD show stable self-reported traits at high intensity but behavioral drift in unscripted interactions that scripted prompts eliminate.