Search Results for author:
Found 21 papers, 11 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).
Evaluating and Mitigating Discrimination in Language Model Decisions
We present a method for proactively evaluating the potential discriminatory impact of LMs in a wide range of use cases, including hypothetical use cases where they have not yet been deployed.
Towards Understanding Sycophancy in Language Models
Overall, our results indicate that sycophancy is a general behavior of state-of-the-art AI assistants, likely driven in part by human preference judgments favoring sycophantic responses.
Specific versus General Principles for Constitutional AI
Constitutional AI offers an alternative, replacing human feedback with feedback from AI models conditioned only on a list of written principles.
Towards Measuring the Representation of Subjective Global Opinions in Language Models
We first build a dataset, GlobalOpinionQA, comprised of questions and answers from cross-national surveys designed to capture diverse opinions on global issues across different countries.
The Capacity for Moral Self-Correction in Large Language Models
We believe that at this level of scale, language models obtain two capabilities that they can use for moral self-correction: (1) they can follow instructions and (2) they can learn complex normative concepts of harm like stereotyping, bias, and discrimination.
Discovering Language Model Behaviors with Model-Written Evaluations
We also find some of the first examples of inverse scaling in RL from Human Feedback (RLHF), where more RLHF makes LMs worse.
Constitutional AI: Harmlessness from AI Feedback
In the RL phase, we sample from the finetuned model, use a model to evaluate which of the two samples is better, and then train a preference model from this dataset of AI preferences.
Measuring Progress on Scalable Oversight for Large Language Models
Developing safe and useful general-purpose AI systems will require us to make progress on scalable oversight: the problem of supervising systems that potentially outperform us on most skills relevant to the task at hand.
In-context Learning and Induction Heads
In this work, we present preliminary and indirect evidence for a hypothesis that induction heads might constitute the mechanism for the majority of all "in-context learning" in large transformer models (i. e. decreasing loss at increasing token indices).
Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned
We provide our own analysis of the data and find a variety of harmful outputs, which range from offensive language to more subtly harmful non-violent unethical outputs.
Language Models (Mostly) Know What They Know
We study whether language models can evaluate the validity of their own claims and predict which questions they will be able to answer correctly.
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
BIG-bench focuses on tasks that are believed to be beyond the capabilities of current language models.
Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
We apply preference modeling and reinforcement learning from human feedback (RLHF) to finetune language models to act as helpful and harmless assistants.
Training language models to follow instructions with human feedback
In this paper, we show an avenue for aligning language models with user intent on a wide range of tasks by fine-tuning with human feedback.
A General Language Assistant as a Laboratory for Alignment
We find that the benefits from modest interventions increase with model size, generalize to a variety of alignment evaluations, and do not compromise the performance of large models.
Learning Transferable Visual Models From Natural Language Supervision
State-of-the-art computer vision systems are trained to predict a fixed set of predetermined object categories.
Ranked #1 on
Zero-Shot Learning
on COCO-MLT
(using extra training data)
Language Models are Few-Shot Learners
By contrast, humans can generally perform a new language task from only a few examples or from simple instructions - something which current NLP systems still largely struggle to do.
Ranked #1 on
Question Answering
on CoQA
(Overall metric)
Toward Trustworthy AI Development: Mechanisms for Supporting Verifiable Claims
With the recent wave of progress in artificial intelligence (AI) has come a growing awareness of the large-scale impacts of AI systems, and recognition that existing regulations and norms in industry and academia are insufficient to ensure responsible AI development.
Computers and Society
Release Strategies and the Social Impacts of Language Models
Large language models have a range of beneficial uses: they can assist in prose, poetry, and programming; analyze dataset biases; and more.
The Role of Cooperation in Responsible AI Development
In this paper, we argue that competitive pressures could incentivize AI companies to underinvest in ensuring their systems are safe, secure, and have a positive social impact.
