Don't Blame The Preferences: Examining The Emergence of Sycophancy in LLM Training
cs.AI
Submitted: 2026-11-05
Updated: 2026-11-10
Terminology
Sources
- A General Theoretical Paradigm to Understand Learning from Human Preferences
- Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
- Eliciting Latent Predictions from Transformers with the Tuned Lens
- Chameleon: Mixed-Modal Early-Fusion Foundation Models
- Training Verifiers to Solve Math Word Problems
- Towards A Rigorous Science of Interpretable Machine Learning
- Toy Models of Superposition
- SycEval: Evaluating LLM Sycophancy
- A Primer on the Inner Workings of Transformer-based Language Models
- The Llama 3 Herd of Models
- OLMo: Accelerating the Science of Language Models
- Tulu 3: Pushing Frontiers in Open Language Model Post-Training
- Tracing Persona Vectors Through LLM Pretraining
- Olmo 3
- 2 OLMo 2 Furious
- In-context Learning and Induction Heads
- Discovering Language Model Behaviors with Model-Written Evaluations
- Direct Preference Optimization: Your Language Model is Secretly a Reward Model
- Proximal Policy Optimization Algorithms
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
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