Search Results for author:
Found 5 papers, 3 papers with code
Adaptive Deployment of Untrusted LLMs Reduces Distributed Threats
As large language models (LLMs) become increasingly capable, it is prudent to assess whether safety measures remain effective even if LLMs intentionally try to bypass them.
Debating with More Persuasive LLMs Leads to More Truthful Answers
In anticipation of this, we ask: can weaker models assess the correctness of stronger models?
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).
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).
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.
