Correct Labels Are Not Enough: Reliable Metadata Can Silently Control Model Behavior
cs.AI
Submitted: 2026-11-03
Updated: 2026-11-03
Comments: NeurIPS 2026 AI4GOOD
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
- Training Verifiers to Solve Math Word Problems
- Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models
- BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain
- Risks from Learned Optimization in Advanced Machine Learning Systems
- Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training
- From Decorative to Load-Bearing: Task Difficulty Shapes the Causal Role of Chain-of-Thought
- CTRL: A Conditional Transformer Language Model for Controllable Generation
- Natural Emergent Misalignment from Reward Hacking in Production RL
- Auditing language models for hidden objectives
- Goal Misgeneralization: Why Correct Specifications Aren't Enough For Correct Goals
- Poisoning Attacks on LLMs Require a Near-constant Number of Poison Samples
- Label-Consistent Backdoor Attacks
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