Publications

The Singapore Consensus on Global AI Safety Research Priorities
Yoshua Bengio
Tegan Maharaj
Luke Ong
Stuart Russell
Dawn Song
Max Tegmark
Lan Xue
Ya-Qin Zhang
Stephen Casper
Wan Sie Lee
Sören Mindermann
Vanessa Wilfred
Vidhisha Balachandran
Fazl Barez
Michael Belinsky
Ima Bello
Malo Bourgon
Mark Brakel
Simeon Campos
Duncan Cass-Beggs … (voir 67 de plus)
Jiahao Chen
Rumman Chowdhury
Chua Kuan Seah
Jeff Clune
Juntao Dai
Agnes Delaborde
Nouha Dziri
Francisco Eiras
Joshua Engels
Jinyu Fan
Adam Gleave
Noah Goodman
Fynn Heide
Johannes Heidecke
Dan Hendrycks
Cyrus Hodes
Bryan Low
Minlie Huang
Sami Jawhar
Jingyu Wang
Adam Kalai
Meindert Kamphuis
Mohan Kankanhalli
Subhash Kantamneni
Mathias Kirk Bonde
Thomas Kwa
Jeffrey Ladish
Kwok Yan Lam
Wan Sie Lee
Taewhi Lee
Xiaojian Li
Jiajun Liu
Chaochao Lu
Yifan Mai
Richard Mallah
Julian Michael
Nicolas Moës
Simon Moeller
Kihyuk Nam
Kwan Yee Ng
Mark Nitzberg
Besmira Nushi
Seán Ó hÉigeartaigh
Alejandro Ortega
Pierre Peigné
James Petrie
Benjamin Prud'homme
Reihaneh Rabbany
Nayat Sanchez-Pi
Sarah Schwettmann
Buck Shlegeris
SAAD SIDDIQUI
Anu Sinha
Martin Soto
Cheston Tan
Anthony Tung
William Tjhi
Robert Trager
Brian Tse
Anthony Tung
John Willes
Denise Wong
Wei Xu
Rongwu Xu
Yi Zeng
Hongjiang Zhang
Djordje Zikelic
Rapidly improving AI capabilities and autonomy hold significant promise of transformation, but are also driving vigorous debate on how to en… (voir plus)sure that AI is safe, i.e., trustworthy, reliable, and secure. Building a trusted ecosystem is therefore essential – it helps people embrace AI with confidence and gives maximal space for innovation while avoiding backlash. This requires policymakers, industry, researchers and the broader public to collectively work toward securing positive outcomes from AI’s development. AI safety research is a key dimension. Given that the state of science today for building trustworthy AI does not fully cover all risks, accelerated investment in research is required to keep pace with commercially driven growth in system capabilities. Goals: The 2025 Singapore Conference on AI (SCAI): International Scientific Exchange on AI Safety aims to support research in this important space by bringing together AI scientists across geographies to identify and synthesise research priorities in AI safety. The result, The Singapore Consensus on Global AI Safety Research Priorities, builds on the International AI Safety Report-A (IAISR) chaired by Yoshua Bengio and backed by 33 governments. By adopting a defence-in-depth model, this document organises AI safety research domains into three types: challenges with creating trustworthy AI systems (Development), challenges with evaluating their risks (Assessment), and challenges with monitoring and intervening after deployment (Control). Through the Singapore Consensus, we hope to globally facilitate meaningful conversations between AI scientists and AI policymakers for maximally beneficial outcomes. Our goal is to enable more impactful R&D efforts to rapidly develop safety and evaluation mechanisms and foster a trusted ecosystem where AI is harnessed for the public good.
2024-12-31
arXiv.org (prépublication)
doi.org
arxiv.org
The Size of Teachers as a Measure of Data Complexity: PAC-Bayes Excess Risk Bounds and Scaling Laws
Gintare Karolina Dziugaite
Daniel M. Roy
We study the generalization properties of randomly initialized neural networks, under the assumption that the network is larger than some un… (voir plus)known "teacher" network that achieves low risk. We extend the analysis of Buzaglo et al. (2024) to allow for student networks of arbitrary width and depth, and to the setting where no (small) teacher network perfectly interpolates the data. We obtain an oracle inequality, relating the risk of Gibbs posterior sampling to that of narrow teacher networks. As a result, the sample complexity is once again bounded in terms of the size of narrow teacher networks that themselves achieve small risk. We then introduce a new notion of data complexity, based on the minimal size of a teacher network required to achieve a certain level of excess risk. By comparing the scaling laws resulting from our bounds to those observed in empirical studies, we are able to estimate the data complexity of standard benchmarks according to our measure.
2024-12-31
AISTATS (publié)
proceedings.mlr.press
proceedings.mlr.press
Towards contrast-agnostic soft segmentation of the spinal cord
Sandrine Bédard
Enamundram Naga Karthik
Charidimos Tsagkas
Emanuele Pravatà
Cristina Granziera
Andrew Smith
Kenneth Arnold Weber II
Julien Cohen-Adad
Spinal cord segmentation is clinically relevant and is notably used to compute spinal cord cross-sectional area (CSA) for the diagnosis and … (voir plus)monitoring of cord compression or neurodegenerative diseases such as multiple sclerosis. While several semi and automatic methods exist, one key limitation remains: the segmentation depends on the MRI contrast, resulting in different CSA across contrasts. This is partly due to the varying appearance of the boundary between the spinal cord and the cerebrospinal fluid that depends on the sequence and acquisition parameters. This contrast-sensitive CSA adds variability in multi-center studies where protocols can vary, reducing the sensitivity to detect subtle atrophies. Moreover, existing methods enhance the CSA variability by training one model per contrast, while also producing binary masks that do not account for partial volume effects. In this work, we present a deep learning-based method that produces soft segmentations of the spinal cord. Using the Spine Generic Public Database of healthy participants (
2024-12-31
Medical Image Anal. (publié)
doi.org
arxiv.org
Towards More Realistic Extraction Attacks: An Adversarial Perspective
Yash More
Prakhar Ganesh
Golnoosh Farnadi
Language models are prone to memorizing their training data, making them vulnerable to extraction attacks. While existing research often exa… (voir plus)mines isolated setups, such as a single model or a fixed prompt, real-world adversaries have a considerably larger attack surface due to access to models across various sizes and checkpoints, and repeated prompting. In this paper, we revisit extraction attacks from an adversarial perspective -- with multi-faceted access to the underlying data. We find significant churn in extraction trends, i.e., even unintuitive changes to the prompt, or targeting smaller models and earlier checkpoints, can extract distinct information. By combining multiple attacks, our adversary doubles (
2024-12-31
Trans. Assoc. Comput. Linguistics (publié)
doi.org
arxiv.org
Trained Without My Consent: Detecting Code Inclusion In Language Models Trained on Code
Vahid Majdinasab
Amin Nikanjam
Foutse Khomh
Code auditing ensures that the developed code adheres to standards, regulations, and copyright protection by verifying that it does not cont… (voir plus)ain code from protected sources. The recent advent of Large Language Models (LLMs) as coding assistants in the software development process poses new challenges for code auditing. The dataset for training these models is mainly collected from publicly available sources. This raises the issue of intellectual property infringement as developers' codes are already included in the dataset. Therefore, auditing code developed using LLMs is challenging, as it is difficult to reliably assert if an LLM used during development has been trained on specific copyrighted codes, given that we do not have access to the training datasets of these models. Given the non-disclosure of the training datasets, traditional approaches such as code clone detection are insufficient for asserting copyright infringement. To address this challenge, we propose a new approach, TraWiC; a model-agnostic and interpretable method based on membership inference for detecting code inclusion in an LLM's training dataset. We extract syntactic and semantic identifiers unique to each program to train a classifier for detecting code inclusion. In our experiments, we observe that TraWiC is capable of detecting 83.87% of codes that were used to train an LLM. In comparison, the prevalent clone detection tool NiCad is only capable of detecting 47.64%. In addition to its remarkable performance, TraWiC has low resource overhead in contrast to pair-wise clone detection that is conducted during the auditing process of tools like CodeWhisperer reference tracker, across thousands of code snippets.
2024-12-31
ACM Trans. Softw. Eng. Methodol. (publié)
doi.org
arxiv.org
Training Dynamics Underlying Language Model Scaling Laws: Loss Deceleration and Zero-Sum Learning
Andrei Mircea
Supriyo Chakraborty
Nima Chitsazan
Irina Rish
Ekaterina Lobacheva
This work aims to understand how scaling improves language models, specifically in terms of training dynamics. We find that language models … (voir plus)undergo loss deceleration early in training; an abrupt slowdown in the rate of loss improvement, resulting in piecewise linear behaviour of the loss curve in log-log space. Scaling up the model mitigates this transition by (1) decreasing the loss at which deceleration occurs, and (2) improving the log-log rate of loss improvement after deceleration. We attribute loss deceleration to a type of degenerate training dynamics we term zero-sum learning (ZSL). In ZSL, per-example gradients become systematically opposed, leading to destructive interference in per-example changes in loss. As a result, improving loss on one subset of examples degrades it on another, bottlenecking overall progress. Loss deceleration and ZSL provide new insights into the training dynamics underlying language model scaling laws, and could potentially be targeted directly to improve language models independent of scale. We make our code and artefacts available at: https://github.com/mirandrom/zsl
2024-12-31
ACL (1) (publié)
doi.org
arxiv.org
Training Language Models to Self-Correct via Reinforcement Learning
Aviral Kumar
Vincent Zhuang
Rishabh Agarwal
Yi Su
John D Co-Reyes
Avi Singh
Kate Baumli
Shariq Iqbal
Colton Bishop
Rebecca Roelofs
Lei M Zhang
Kay McKinney
Disha Shrivastava
Cosmin Paduraru
George Tucker
Doina Precup
Feryal Behbahani
Aleksandra Faust
Self-correction is a highly desirable capability of large language models (LLMs), yet it has consistently been found to be largely ineffecti… (voir plus)ve in modern LLMs. Existing approaches for training self-correction either require multiple models or rely on a more capable model or other forms of supervision. To this end, we develop a multi-turn online reinforcement learning (RL) approach, SCoRe, that significantly improves an LLM's self-correction ability using entirely self-generated data. To build SCoRe, we first show that variants of supervised fine-tuning (SFT) on offline model-generated correction traces are insufficient for instilling self-correction behavior. In particular, we observe that training via SFT either suffers from a distribution mismatch between the training data and the model's own responses or implicitly prefers only a certain mode of correction behavior that is often not effective at test time. SCoRe addresses these challenges by training under the model's own distribution of self-generated correction traces and using appropriate regularization to steer the learning process into learning a self-correction strategy that is effective at test time as opposed to simply fitting high-reward responses for a given prompt. This regularization prescribes running a first phase of RL on a base model to generate a policy initialization that is less susceptible to collapse and then using a reward bonus to amplify self-correction during training. When applied to Gemini 1.0 Pro and 1.5 Flash models, we find that SCoRe achieves state-of-the-art self-correction performance, improving the base models' self-correction by 15.6% and 9.1% respectively on the MATH and HumanEval benchmarks.
2024-12-31
ICLR (publié)
doi.org
openreview.net
Training of LLM-Based List-Wise Multilingual Reranker
Hao Yu
David Ifeoluwa Adelani
2024-12-31
Proceedings of the 5th Workshop on Multilingual Representation Learning (MRL 2025) (publié)
doi.org
TrajGPT: Irregular Time-Series Representation Learning of Health Trajectory
Ziyang Song
Qincheng Lu
He Zhu
David Buckeridge
Yue Li
In the healthcare domain, time-series data are often irregularly sampled with varying intervals through outpatient visits, posing challenges… (voir plus) for existing models designed for equally spaced sequential data. To address this, we propose Trajectory Generative Pre-trained Transformer (TrajGPT) for representation learning on irregularly-sampled healthcare time series. TrajGPT introduces a novel Selective Recurrent Attention (SRA) module that leverages a data-dependent decay to adaptively filter irrelevant past information. As a discretized ordinary differential equation (ODE) framework, TrajGPT captures underlying continuous dynamics and enables a time-specific inference for forecasting arbitrary target timesteps without auto-regressive prediction. Experimental results based on the longitudinal EHR data PopHR from Montreal health system and eICU from PhysioNet showcase TrajGPT's superior zero-shot performance in disease forecasting, drug usage prediction, and sepsis detection. The inferred trajectories of diabetic and cardiac patients reveal meaningful comorbidity conditions, underscoring TrajGPT as a useful tool for forecasting patient health evolution.
2024-12-31
IEEE Journal of Biomedical and Health Informatics (inconnu)
doi.org
TransCeption: Enhancing medical image segmentation with an inception-like transformer design for efficient feature fusion
Reza Azad
Yiwei Jia
Ehsan Khodapanah Aghdam
Julien Cohen-Adad
Dorit Merhof
2024-12-31
Comput. Vis. Media (publié)
doi.org
Tree semantic segmentation from aerial image time series
Venkatesh Ramesh
Arthur Ouaknine
David Rolnick
Earth's forests play an important role in the fight against climate change, and are in turn negatively affected by it. Effective monitoring … (voir plus)of different tree species is essential to understanding and improving the health and biodiversity of forests. In this work, we address the challenge of tree species identification by performing semantic segmentation of trees using an aerial image dataset spanning over a year. We compare models trained on single images versus those trained on time series to assess the impact of tree phenology on segmentation performances. We also introduce a simple convolutional block for extracting spatio-temporal features from image time series, enabling the use of popular pretrained backbones and methods. We leverage the hierarchical structure of tree species taxonomy by incorporating a custom loss function that refines predictions at three levels: species, genus, and higher-level taxa. Our findings demonstrate the superiority of our methodology in exploiting the time series modality and confirm that enriching labels using taxonomic information improves the semantic segmentation performance.
2024-12-31
Environmental Data Science (publié)
doi.org
arxiv.org
Understanding and Meeting Practitioner Needs When Measuring Representational Harms Caused by LLM-Based Systems
Emma Harvey
Emily Sheng
Su Lin Blodgett
Alexandra Chouldechova
Jean Garcia-Gathright
A.R. Olteanu
Hanna Wallach
The NLP research community has made publicly available numerous instruments for measuring representational harms caused by large language mo… (voir plus)del (LLM)-based systems. These instruments have taken the form of datasets, metrics, tools, and more. In this paper, we examine the extent to which such instruments meet the needs of practitioners tasked with evaluating LLM-based systems. Via semi-structured interviews with 12 such practitioners, we find that practitioners are often unable to use publicly available instruments for measuring representational harms. We identify two types of challenges. In some cases, instruments are not useful because they do not meaningfully measure what practitioners seek to measure or are otherwise misaligned with practitioner needs. In other cases, instruments - even useful instruments - are not used by practitioners due to practical and institutional barriers impeding their uptake. Drawing on measurement theory and pragmatic measurement, we provide recommendations for addressing these challenges to better meet practitioner needs.
2024-12-31
ACL (Findings) (publié)
doi.org
arxiv.org