Publications

This work identifies 18 foundational challenges in assuring the alignment and safety of large language models (LLMs). These challenges are o… (voir plus)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 (prépublication)

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 … (voir 18 de plus)

Heidi Chenyu Zhang

Ruiqi Zhong

Sean O hEigeartaigh

Gabriel Recchia

Giulio Corsi

Alan Chan

Markus Anderljung

Lilian Edwards

Yoshua Bengio

Danqi Chen

Samuel Albanie

Tegan Maharaj

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… (voir plus)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 (prépublication)

Government Interventions to Avert Future Catastrophic AI Risks

Yoshua Bengio

2024-04-15

Special Issue 5: Grappling With the Generative AI Revolution (publié)

Improving microbial phylogeny with citizen science within a mass-market video game

Roman Sarrazin-Gendron

Parham Ghasemloo Gheidari

Alexander Butyaev

Timothy Keding

Eddie Cai

Jiayue Zheng

Renata Mutalova

Julien Mounthanyvong

Yuxue Zhu

Elena Nazarova

Chrisostomos Drogaris

Kornél Erhart

David Bélanger

Amélie Brouillette

Michael Bouffard

Gabriel Richard

Joshua Davidson

Randy Pitchford

Mathieu Falaise

Sébastien Caisse … (voir 14 de plus)

Vincent Fiset

Mathieu Blanchette

Steven Hebert

Daniel McDonald

Dan Hewitt

Rob Knight

Jonathan Huot

Attila Szantner

Seung Kim

Jérôme Waldispühl

Jonathan Moreau-Genest

David Najjab

Steve Prince

Ludger Saintélien

2024-04-15

Nature Biotechnology (publié)

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… (voir plus)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 (prépublication)

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… (voir plus)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 (prépublication)

CryCeleb: A Speaker Verification Dataset Based on Infant Cry Sounds

David Budaghyan

Arsenii Gorin

Cem Subakan

Charles Onu

Doina Precup

This paper describes the Ubenwa CryCeleb dataset - a labeled collection of infant cries - and the accompanying CryCeleb 2023 task, which is … (voir plus)a public speaker verification challenge based on cry sounds. We released more than 6 hours of manually segmented cry sounds from 786 newborns for academic use, aiming to encourage research in infant cry analysis. The inaugural public competition attracted 59 participants, 11 of whom improved the baseline performance. The top-performing system achieved a significant improvement scoring 25.8% equal error rate, which is still far from the performance of state-of-the-art adult speaker verification systems. Therefore, we believe there is room for further research on this dataset, potentially extending beyond the verification task.

2024-04-14

ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (publié)

Focal Modulation Networks for Interpretable Sound Classification

Luca Della Libera

Cem Subakan

Mirco Ravanelli

The increasing success of deep neural networks has raised concerns about their inherent black-box nature, posing challenges related to inter… (voir plus)pretability and trust. While there has been extensive exploration of interpretation techniques in vision and language, interpretability in the audio domain has received limited attention, primarily focusing on post-hoc explanations. This paper addresses the problem of interpretability by-design in the audio domain by utilizing the recently proposed attention-free focal modulation networks (FocalNets). We apply FocalNets to the task of environmental sound classification for the first time and evaluate their interpretability properties on the popular ESC-50 dataset. Our method outperforms a similarly sized vision transformer both in terms of accuracy and interpretability. Furthermore, it is competitive against PIQ, a method specifically designed for post-hoc interpretation in the audio domain.

2024-04-14

2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW) (publié)

PathOCl: Path-Based Prompt Augmentation for OCL Generation with GPT-4

Seif Abukhalaf

Mohammad Hamdaqa

Foutse Khomh

The rapid progress of AI-powered programming assistants, such as GitHub Copilot, has facilitated the development of software applications. T… (voir plus)hese assistants rely on large language models (LLMs), which are foundation models (FMs) that support a wide range of tasks related to understanding and generating language. LLMs have demonstrated their ability to express UML model specifications using formal languages like the Object Constraint Language (OCL). However, the context size of the prompt is limited by the number of tokens an LLM can process. This limitation becomes significant as the size of UML class models increases. In this study, we intro-duce PathOCL, a novel path-based prompt augmentation technique designed to facilitate OCL generation. PathOCL addresses the limi-tations of LLMs, specifically their token processing limit and the challenges posed by large UML class models. PathOCL is based on the concept of chunking, which selectively augments the prompts with a subset of UML classes relevant to the English specification. Our findings demonstrate that PathOCL, compared to augmenting the complete UML class model (UML-Augmentation), generates a higher number of valid and correct OCL constraints using the GPT-4 model. Moreover, the average prompt size crafted using PathOCL significantly decreases when scaling the size of the UML class models.

2024-04-14

ArXiv (prépublication)

Resource-Efficient Separation Transformer

Luca Della Libera

Cem Subakan

Mirco Ravanelli

Samuele Cornell

Frédéric Lepoutre

François Grondin

Transformers have recently achieved state-of-the-art performance in speech separation. These models, however, are computationally demanding … (voir plus)and require a lot of learnable parameters. This paper explores Transformer-based speech separation with a reduced computational cost. Our main contribution is the development of the Resource-Efficient Separation Transformer (RE-SepFormer), a self-attention-based architecture that reduces the computational burden in two ways. First, it uses non-overlapping blocks in the latent space. Second, it operates on compact latent summaries calculated from each chunk. The RE-SepFormer reaches a competitive performance on the popular WSJ0-2Mix and WHAM! datasets in both causal and non-causal settings. Remarkably, it scales significantly better than the previous Transformer-based architectures in terms of memory and inference time, making it more suitable for processing long mixtures.

2024-04-14

ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (publié)

SKILL: Similarity-aware Knowledge distILLation for Speech Self-Supervised Learning

Luca Zampierin

Ghouthi Boukli Hacene

Bac Nguyen

Mirco Ravanelli

2024-04-14

2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW) (publié)

Towards Practical Tool Usage for Continually Learning LLMs

Jerry Huang

Prasanna Parthasarathi

Mehdi Rezagholizadeh

Sarath Chandar

Large language models (LLMs) show an innate skill for solving language based tasks. But insights have suggested an inability to adjust for i… (voir plus)nformation or task-solving skills becoming outdated, as their knowledge, stored directly within their parameters, remains static in time. Tool use helps by offloading work to systems that the LLM can access through an interface, but LLMs that use them still must adapt to nonstationary environments for prolonged use, as new tools can emerge and existing tools can change. Nevertheless, tools require less specialized knowledge, therefore we hypothesize they are better suited for continual learning (CL) as they rely less on parametric memory for solving tasks and instead focus on learning when to apply pre-defined tools. To verify this, we develop a synthetic benchmark and follow this by aggregating existing NLP tasks to form a more realistic testing scenario. While we demonstrate scaling model size is not a solution, regardless of tool usage, continual learning techniques can enable tool LLMs to both adapt faster while forgetting less, highlighting their potential as continual learners.

2024-04-14

ArXiv (prépublication)