How to train your model organism
cs.LG
Submitted: 2026-10-07
Updated: 2026-10-07
Code: https://github.com/Rice-wxl/multi_objective_mo
Sources
- Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs
- Sparse Autoencoders Find Highly Interpretable Features in Language Models
- Eliciting Secret Knowledge from Language Models
- Safe RLHF: Safe Reinforcement Learning from Human Feedback
- KTO: Model Alignment as Prospect Theoretic Optimization
- Olmo 3
- Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models
- Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training
- Enhancing LLM Safety via Constrained Direct Preference Optimization
- Auditing language models for hidden objectives
- Automatically Interpreting Millions of Features in Large Language Models
- Direct Preference Optimization: Your Language Model is Secretly a Reward Model
- RelP: Faithful and Efficient Circuit Discovery in Language Models via Relevance Patching
- AuditBench: Evaluating Alignment Auditing Techniques on Models with Hidden Behaviors
- Believe It or Not: How Deeply do LLMs Believe Implanted Facts?
- The Model Organism Lottery: Model Organism Interpretability Strongly Depends on Training Methodology
- Investigating task-specific prompts and sparse autoencoders for activation monitoring
- Model Organisms for Emergent Misalignment
- Stepwise Alignment for Constrained Language Model Policy Optimization
- WildChat: 1M ChatGPT Interaction Logs in the Wild
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks