The Assistant's Ideal Self

arXiv:2609.00304 · cs.AI · Submitted 2026-08-31 · Read on arXiv

cs.AI

Submitted: 2026-08-31

Updated: 2026-08-31

Code: https://github.com/myazann/LLM-Self-Concept

Project page: https://myazann.github.io/LLM-Self-Concept

Terminology

• Alignment — 4× in this paper · explained in 1 episode
• Transformer — 2× in this paper · explained in 2 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Meeting of the Association for Computational Linguistics — 1× in this paper
• Pairwise Comparisons — 1× in this paper · explained in 2 episodes
• Robustness — 1× in this paper · explained in 5 episodes

Sources

• A General Language Assistant as a Laboratory for Alignment
• The Personality Illusion: Revealing Dissociation Between Self-Reports & Behavior in LLMs
• Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs
• Large Language Models Sensitivity to The Order of Options in Multiple-Choice Questions
• Alignment Pretraining: AI Discourse Causes Self-Fulfilling (Mis)alignment
• Large Language Models are not Fair Evaluators
• Large Language Models Are Not Robust Multiple Choice Selectors

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection