Loyalty Capture: Reporting Relationships and Structural Sycophancy in Frontier AI Models
cs.AI
Submitted: 2026-11-11
Updated: 2026-11-11
Terminology
Sources
- Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training
- Breaking Bad Financial Habits: How LLM Conversations Correct Financial Misconceptions
- Why Better Models Can Create Riskier Systems: Evidence from LLM Agents in Financial Markets
- Simple synthetic data reduces sycophancy in large language models
- BloombergGPT: A Large Language Model for Finance
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- 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
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents