papers

Publications (26)

cs.CL2021

A General Language Assistant as a Laboratory for Alignment

Amanda Askell, Yuntao Bai, Anna Chen +19

Given the broad capabilities of large language models, it should be possible to work towards a general-purpose, text-based assistant that is aligned with human values, meaning that…

cs.CL2022

Constitutional AI: Harmlessness from AI Feedback

Yuntao Bai, Saurav Kadavath, Sandipan Kundu +48

As AI systems become more capable, we would like to enlist their help to supervise other AIs. We experiment with methods for training a harmless AI assistant through self-improveme…

cs.CL2022

Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned

Deep Ganguli, Liane Lovitt, Jackson Kernion +33

We describe our early efforts to red team language models in order to simultaneously discover, measure, and attempt to reduce their potentially harmful outputs. We make three main…

q-bio.NC2016

Neural and perceptual signatures of efficient sensory coding

Deep Ganguli, Eero P. Simoncelli

The mammalian brain is a metabolically expensive device, and evolutionary pressures have presumably driven it to make productive use of its resources. For sensory areas, this conce…

cs.LG2022

In-context Learning and Induction Heads

Catherine Olsson, Nelson Elhage, Neel Nanda +23

"Induction heads" are attention heads that implement a simple algorithm to complete token sequences like [A][B] ... [A] -> [B]. In this work, we present preliminary and indirect ev…

cs.SI2023

Opportunities and Risks of LLMs for Scalable Deliberation with Polis

Christopher T. Small, Ivan Vendrov, Esin Durmus +6

Polis is a platform that leverages machine intelligence to scale up deliberative processes. In this paper, we explore the opportunities and risks associated with applying Large Lan…

cs.CL2025

Values in the Wild: Discovering and Analyzing Values in Real-World Language Model Interactions

Saffron Huang, Esin Durmus, Miles McCain +7

AI assistants can impart value judgments that shape people's decisions and worldviews, yet little is known empirically about what values these systems rely on in practice. To addre…

cs.AI2021

The AI Index 2021 Annual Report

Daniel Zhang, Saurabh Mishra, Erik Brynjolfsson +10

Welcome to the fourth edition of the AI Index Report. This year we significantly expanded the amount of data available in the report, worked with a broader set of external organiza…

cs.CR2024

Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training

Evan Hubinger, Carson Denison, Jesse Mu +36

Humans are capable of strategically deceptive behavior: behaving helpfully in most situations, but then behaving very differently in order to pursue alternative objectives when giv…

cs.LG2024

Sabotage Evaluations for Frontier Models

Joe Benton, Misha Wagner, Eric Christiansen +13

Sufficiently capable models could subvert human oversight and decision-making in important contexts. For example, in the context of AI development, models could covertly sabotage e…

cs.CL2023

Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models

Aarohi Srivastava, Abhinav Rastogi, Abhishek Rao +448

Language models demonstrate both quantitative improvement and new qualitative capabilities with increasing scale. Despite their potentially transformative impact, these new capabil…

cs.CY2024

How will advanced AI systems impact democracy?

Christopher Summerfield, Lisa Argyle, Michiel Bakker +20

Advanced AI systems capable of generating humanlike text and multimodal content are now widely available. In this paper, we discuss the impacts that generative artificial intellige…

cs.AI2025

Toward an Evaluation Science for Generative AI Systems

Laura Weidinger, Inioluwa Deborah Raji, Hanna Wallach +7

There is an increasing imperative to anticipate and understand the performance and safety of generative AI systems in real-world deployment contexts. However, the current evaluatio…

cs.CL2022

Discovering Language Model Behaviors with Model-Written Evaluations

Ethan Perez, Sam Ringer, Kamilė Lukošiūtė +60

As language models (LMs) scale, they develop many novel behaviors, good and bad, exacerbating the need to evaluate how they behave. Prior work creates evaluations with crowdwork (w…

cs.CL2023

The Capacity for Moral Self-Correction in Large Language Models

Deep Ganguli, Amanda Askell, Nicholas Schiefer +46

We test the hypothesis that language models trained with reinforcement learning from human feedback (RLHF) have the capability to "morally self-correct" -- to avoid producing harmf…

cs.AI2024

Collective Constitutional AI: Aligning a Language Model with Public Input

Saffron Huang, Divya Siddarth, Liane Lovitt +4

There is growing consensus that language model (LM) developers should not be the sole deciders of LM behavior, creating a need for methods that enable the broader public to collect…

cs.CY2022

Predictability and Surprise in Large Generative Models

Deep Ganguli, Danny Hernandez, Liane Lovitt +27

Large-scale pre-training has recently emerged as a technique for creating capable, general purpose, generative models such as GPT-3, Megatron-Turing NLG, Gopher, and many others. I…

q-bio.NC2012

Implicit embedding of prior probabilities in optimally efficient neural populations

Deep Ganguli, Eero Simoncelli

We examine how the prior probability distribution of a sensory variable in the environment influences the optimal allocation of neurons and spikes in a population that represents t…

cs.CL2024

Towards Measuring the Representation of Subjective Global Opinions in Language Models

Esin Durmus, Karina Nguyen, Thomas I. Liao +15

Large language models (LLMs) may not equitably represent diverse global perspectives on societal issues. In this paper, we develop a quantitative framework to evaluate whose opinio…

cs.CY2025

Which Economic Tasks are Performed with AI? Evidence from Millions of Claude Conversations

Kunal Handa, Alex Tamkin, Miles McCain +12

Despite widespread speculation about artificial intelligence's impact on the future of work, we lack systematic empirical evidence about how these systems are actually being used f…

cs.CY2023

Report of the 1st Workshop on Generative AI and Law

A. Feder Cooper, Katherine Lee, James Grimmelmann +32

This report presents the takeaways of the inaugural Workshop on Generative AI and Law (GenLaw), held in July 2023. A cross-disciplinary group of practitioners and scholars from com…

cs.CL2022

Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Yuntao Bai, Andy Jones, Kamal Ndousse +28

We apply preference modeling and reinforcement learning from human feedback (RLHF) to finetune language models to act as helpful and harmless assistants. We find this alignment tra…

cs.CY2024

Clio: Privacy-Preserving Insights into Real-World AI Use

Alex Tamkin, Miles McCain, Kunal Handa +18

How are AI assistants being used in the real world? While model providers in theory have a window into this impact via their users' data, both privacy concerns and practical challe…

cs.CL2023

Evaluating and Mitigating Discrimination in Language Model Decisions

Alex Tamkin, Amanda Askell, Liane Lovitt +6

As language models (LMs) advance, interest is growing in applying them to high-stakes societal decisions, such as determining financing or housing eligibility. However, their poten…

cs.CL2022

Language Models (Mostly) Know What They Know

Saurav Kadavath, Tom Conerly, Amanda Askell +33

We study whether language models can evaluate the validity of their own claims and predict which questions they will be able to answer correctly. We first show that larger models a…

cs.CL2021

Understanding the Capabilities, Limitations, and Societal Impact of Large Language Models

Alex Tamkin, Miles Brundage, Jack Clark +1

On October 14th, 2020, researchers from OpenAI, the Stanford Institute for Human-Centered Artificial Intelligence, and other universities convened to discuss open research question…