David Scott Krueger

Noam Kolt

Lennart Heim

Markus Anderljung

2024-06-05

The 2024 ACM Conference on Fairness, Accountability, and Transparency (published)

Stress-Testing Capability Elicitation With Password-Locked Models

Ryan Greenblatt

Fabien Roger

Dmitrii Krasheninnikov

To determine the safety of large language models (LLMs), AI developers must be able to assess their dangerous capabilities. But simple promp… (see more)ting strategies often fail to elicit an LLM's full capabilities. One way to elicit capabilities more robustly is to fine-tune the LLM to complete the task. In this paper, we investigate the conditions under which fine-tuning-based elicitation suffices to elicit capabilities. To do this, we introduce password-locked models, LLMs fine-tuned such that some of their capabilities are deliberately hidden. Specifically, these LLMs are trained to exhibit these capabilities only when a password is present in the prompt, and to imitate a much weaker LLM otherwise. Password-locked models enable a novel method of evaluating capabilities elicitation methods, by testing whether these password-locked capabilities can be elicited without using the password. We find that a few high-quality demonstrations are often sufficient to fully elicit password-locked capabilities. More surprisingly, fine-tuning can elicit other capabilities that have been locked using the same password, or even different passwords. Furthermore, when only evaluations, and not demonstrations, are available, approaches like reinforcement learning are still often able to elicit capabilities. Overall, our findings suggest that fine-tuning is an effective method of eliciting hidden capabilities of current models, but may be unreliable when high-quality demonstrations are not available, e.g. as may be the case when models' (hidden) capabilities exceed those of human demonstrators.

2024-05-29

ArXiv (preprint)

Stress-Testing Capability Elicitation With Password-Locked Models

Ryan Greenblatt

Fabien Roger

Dmitrii Krasheninnikov

2024-05-29

ArXiv (preprint)

Implicitly Bayesian Prediction Rules in Deep Learning

Bruno Mlodozeniec

Richard E. Turner

The Bayesian approach leads to coherent updates of predictions under new data, which makes adhering to Bayesian principles appealing in deci… (see more)sion-making contexts. Traditionally, integrating Bayesian principles into models like deep neural networks involves setting priors on parameters and approximating posteriors. This is done despite the fact that, typically, priors on parameters reflect any prior beliefs only insofar as they dictate function space behaviour. In this paper, we rethink this approach and consider what properties characterise a prediction rule as being Bayesian. Algorithms meeting such criteria can be deemed implicitly Bayesian — they make the same predictions as some Bayesian model, without explicitly manifesting priors and posteriors. We argue this might be a more fruitful approach towards integrating Bayesian principles into deep learning. In this paper, we propose how to measure how close a general prediction rule is to being implicitly Bayesian, and empirically evaluate multiple prediction strategies using our approach. We also show theoretically that agents relying on non-implicitly Bayesian prediction rules can be easily exploited in adversarial betting settings.

2024-05-27

approximateinference.org/AABI/2024/Symposium_Archival_Track (accepted)

proceedings.mlr.press

openreview.net

What Mechanisms Does Knowledge Distillation Distill?

Cindy Wu

Ekdeep Singh Lubana

Bruno Mlodozeniec

Robert Kirk

Knowledge distillation is a commonly-used compression method in ML due to the popularity of increasingly large-scale models, but it is uncle… (see more)ar if all the information a teacher model contains is distilled into the smaller student model. We aim to formalize the concept of ‘knowledge’ to investigate how knowledge is transferred during distillation, focusing on shared invariant outputs to counterfactual changes of dataset latent variables (we call these latents mechanisms). We define a student model to be a good stand-in model for a teacher if it shares the teacher’s learned mechanisms, and find that Jacobian matching and contrastive representation learning are viable methods by which to train such models. While these methods do not result in perfect transfer of mechanisms, we show they often improve student fidelity or mitigate simplicity bias (as measured by the teacher-to-student KL divergence and accuracy on various out-of-distribution test datasets), especially on datasets with spurious statistical correlations.

2024-05-14

Proceedings of UniReps: the First Workshop on Unifying Representations in Neural Models (published)

proceedings.mlr.press

openreview.net

Foundational Challenges in Assuring Alignment and Safety of Large Language Models

Usman Anwar

Abulhair Saparov

Javier Rando

Daniel Paleka

Miles Turpin

Peter Hase

Ekdeep Singh Lubana

Erik Jenner

Stephen Casper

Oliver Sourbut

Benjamin L. Edelman

Zhaowei Zhang

Mario Günther

Anton Korinek

Jose Hernandez-Orallo

Lewis Hammond

Eric J Bigelow

Alexander Pan

Lauro Langosco

Tomasz Korbak … (see 18 more)

Heidi Chenyu Zhang

Ruiqi Zhong

Sean O hEigeartaigh

Gabriel Recchia

Giulio Corsi

Alan Chan

Markus Anderljung

Lilian Edwards

Danqi Chen

Samuel Albanie

Jakob Nicolaus Foerster

Florian Tramèr

He He

Atoosa Kasirzadeh

Yejin Choi

This work identifies 18 foundational challenges in assuring the alignment and safety of large language models (LLMs). These challenges are o… (see more)rganized into three different categories: scientific understanding of LLMs, development and deployment methods, and sociotechnical challenges. Based on the identified challenges, we pose

2024-04-15

ArXiv (preprint)

Foundational Challenges in Assuring Alignment and Safety of Large Language Models

Usman Anwar

Abulhair Saparov

Javier Rando

Daniel Paleka

Miles Turpin

Peter Hase

Ekdeep Singh Lubana

Erik Jenner

Stephen Casper

Oliver Sourbut

Benjamin L. Edelman

Zhaowei Zhang

Mario Günther

Anton Korinek

Jose Hernandez-Orallo

Lewis Hammond

Eric J Bigelow

Alexander Pan

Lauro Langosco

Tomasz Korbak … (see 18 more)

Heidi Zhang

Ruiqi Zhong

Sean 'o H'eigeartaigh

Gabriel Recchia

Giulio Corsi

Alan Chan

Markus Anderljung

Lilian Edwards

Danqi Chen

Samuel Albanie

Jakob Nicolaus Foerster

Florian Tramèr

He He

Atoosa Kasirzadeh

Yejin Choi

This work identifies 18 foundational challenges in assuring the alignment and safety of large language models (LLMs). These challenges are o… (see more)rganized into three different categories: scientific understanding of LLMs, development and deployment methods, and sociotechnical challenges. Based on the identified challenges, we pose

2024-04-15

ArXiv (preprint)

Foundational Challenges in Assuring Alignment and Safety of Large Language Models

Usman Anwar

Abulhair Saparov

Javier Rando

Daniel Paleka

Miles Turpin

Peter Hase

Ekdeep Singh Lubana

Erik Jenner

Stephen Casper

Oliver Sourbut

Benjamin L. Edelman

Zhaowei Zhang

Mario Günther

Anton Korinek

Jose Hernandez-Orallo

Lewis Hammond

Eric J Bigelow

Alexander Pan

Lauro Langosco

Tomasz Korbak … (see 18 more)

Heidi Chenyu Zhang

Ruiqi Zhong

Sean O hEigeartaigh

Gabriel Recchia

Giulio Corsi

Alan Chan

Markus Anderljung

Lilian Edwards

Danqi Chen

Samuel Albanie

Jakob Nicolaus Foerster

Florian Tramèr

He He

Atoosa Kasirzadeh

Yejin Choi

This work identifies 18 foundational challenges in assuring the alignment and safety of large language models (LLMs). These challenges are o… (see more)rganized into three different categories: scientific understanding of LLMs, development and deployment methods, and sociotechnical challenges. Based on the identified challenges, we pose

2024-04-15

ArXiv (preprint)

Foundational Challenges in Assuring Alignment and Safety of Large Language Models

Usman Anwar

Abulhair Saparov

Javier Rando

Daniel Paleka

Miles Turpin

Peter Hase

Ekdeep Singh Lubana

Erik Jenner

Stephen Casper

Oliver Sourbut

Benjamin L. Edelman

Zhaowei Zhang

Mario Günther

Anton Korinek

Jose Hernandez-Orallo

Lewis Hammond

Eric J Bigelow

Alexander Pan

Lauro Langosco

Tomasz Korbak … (see 18 more)

Heidi Chenyu Zhang

Ruiqi Zhong

Sean O hEigeartaigh

Gabriel Recchia

Giulio Corsi

Alan Chan

Markus Anderljung

Lilian Edwards

Danqi Chen

Samuel Albanie

Jakob Nicolaus Foerster

Florian Tramèr

He He

Atoosa Kasirzadeh

Yejin Choi

This work identifies 18 foundational challenges in assuring the alignment and safety of large language models (LLMs). These challenges are o… (see more)rganized into three different categories: scientific understanding of LLMs, development and deployment methods, and sociotechnical challenges. Based on the identified challenges, we pose

2024-04-15

ArXiv (preprint)

Foundational Challenges in Assuring Alignment and Safety of Large Language Models

Usman Anwar

Abulhair Saparov

Javier Rando

Daniel Paleka

Miles Turpin

Peter Hase

Ekdeep Singh Lubana

Erik Jenner

Stephen Casper

Oliver Sourbut

Benjamin L. Edelman

Zhaowei Zhang

Mario Günther

Anton Korinek

Jose Hernandez-Orallo

Lewis Hammond

Eric J Bigelow

Alexander Pan

Lauro Langosco

Tomasz Korbak … (see 18 more)

Heidi Chenyu Zhang

Ruiqi Zhong

Sean O hEigeartaigh

Gabriel Recchia

Giulio Corsi

Alan Chan

Markus Anderljung

Lilian Edwards

Danqi Chen

Samuel Albanie

Jakob Nicolaus Foerster

Florian Tramèr

He He

Atoosa Kasirzadeh

Yejin Choi

This work identifies 18 foundational challenges in assuring the alignment and safety of large language models (LLMs). These challenges are o… (see more)rganized into three different categories: scientific understanding of LLMs, development and deployment methods, and sociotechnical challenges. Based on the identified challenges, we pose

2024-04-15

ArXiv (preprint)

Affirmative safety: An approach to risk management for high-risk AI

Akash Wasil

Joshua Clymer

Emily Dardaman

Simeon Campos

Evan Murphy

Prominent AI experts have suggested that companies developing high-risk AI systems should be required to show that such systems are safe bef… (see more)ore they can be developed or deployed. The goal of this paper is to expand on this idea and explore its implications for risk management. We argue that entities developing or deploying high-risk AI systems should be required to present evidence of affirmative safety: a proactive case that their activities keep risks below acceptable thresholds. We begin the paper by highlighting global security risks from AI that have been acknowledged by AI experts and world governments. Next, we briefly describe principles of risk management from other high-risk fields (e.g., nuclear safety). Then, we propose a risk management approach for advanced AI in which model developers must provide evidence that their activities keep certain risks below regulator-set thresholds. As a first step toward understanding what affirmative safety cases should include, we illustrate how certain kinds of technical evidence and operational evidence can support an affirmative safety case. In the technical section, we discuss behavioral evidence (evidence about model outputs), cognitive evidence (evidence about model internals), and developmental evidence (evidence about the training process). In the operational section, we offer examples of organizational practices that could contribute to affirmative safety cases: information security practices, safety culture, and emergency response capacity. Finally, we briefly compare our approach to the NIST AI Risk Management Framework. Overall, we hope our work contributes to ongoing discussions about national and global security risks posed by AI and regulatory approaches to address these risks.

2024-04-14

ArXiv (preprint)

Affirmative safety: An approach to risk management for high-risk AI

Akash Wasil

Joshua Clymer

Emily Dardaman

Simeon Campos

Evan Murphy

Prominent AI experts have suggested that companies developing high-risk AI systems should be required to show that such systems are safe bef… (see more)ore they can be developed or deployed. The goal of this paper is to expand on this idea and explore its implications for risk management. We argue that entities developing or deploying high-risk AI systems should be required to present evidence of affirmative safety: a proactive case that their activities keep risks below acceptable thresholds. We begin the paper by highlighting global security risks from AI that have been acknowledged by AI experts and world governments. Next, we briefly describe principles of risk management from other high-risk fields (e.g., nuclear safety). Then, we propose a risk management approach for advanced AI in which model developers must provide evidence that their activities keep certain risks below regulator-set thresholds. As a first step toward understanding what affirmative safety cases should include, we illustrate how certain kinds of technical evidence and operational evidence can support an affirmative safety case. In the technical section, we discuss behavioral evidence (evidence about model outputs), cognitive evidence (evidence about model internals), and developmental evidence (evidence about the training process). In the operational section, we offer examples of organizational practices that could contribute to affirmative safety cases: information security practices, safety culture, and emergency response capacity. Finally, we briefly compare our approach to the NIST AI Risk Management Framework. Overall, we hope our work contributes to ongoing discussions about national and global security risks posed by AI and regulatory approaches to address these risks.

2024-04-14

ArXiv (preprint)