Search Results for author:
Found 9 papers, 4 papers with code
Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training
We find that such backdoor behavior can be made persistent, so that it is not removed by standard safety training techniques, including supervised fine-tuning, reinforcement learning, and adversarial training (eliciting unsafe behavior and then training to remove it).
Thousands of AI Authors on the Future of AI
Between 38% and 51% of respondents gave at least a 10% chance to advanced AI leading to outcomes as bad as human extinction.
Managing AI Risks in an Era of Rapid Progress
In this short consensus paper, we outline risks from upcoming, advanced AI systems.
How to Catch an AI Liar: Lie Detection in Black-Box LLMs by Asking Unrelated Questions
Large language models (LLMs) can "lie", which we define as outputting false statements despite "knowing" the truth in a demonstrable sense.
Question Decomposition Improves the Faithfulness of Model-Generated Reasoning
As large language models (LLMs) perform more difficult tasks, it becomes harder to verify the correctness and safety of their behavior.
Measuring Faithfulness in Chain-of-Thought Reasoning
Large language models (LLMs) perform better when they produce step-by-step, "Chain-of-Thought" (CoT) reasoning before answering a question, but it is unclear if the stated reasoning is a faithful explanation of the model's actual reasoning (i. e., its process for answering the question).
Prioritized Training on Points that are Learnable, Worth Learning, and Not Yet Learnt
But most computation and time is wasted on redundant and noisy points that are already learnt or not learnable.
Mapping global dynamics of benchmark creation and saturation in artificial intelligence
Benchmarks are crucial to measuring and steering progress in artificial intelligence (AI).
Prioritized training on points that are learnable, worth learning, and not yet learned (workshop version)
We introduce Goldilocks Selection, a technique for faster model training which selects a sequence of training points that are "just right".
