Joelle Pineau

2024-03-12

Proceedings of the Symposium on Computer Science and Law (publié)

On the Societal Impact of Open Foundation Models

Sayash Kapoor

Rishi Bommasani

Kevin Klyman

Shayne Longpre

Ashwin Ramaswami

Peter Cihon

Aspen Hopkins

Kevin Bankston

Stella Biderman

Miranda Bogen

Rumman Chowdhury

Alex Engler

Peter Henderson

Yacine Jernite

Seth Lazar

Stefano Maffulli

Alondra Nelson

Aviya Skowron

Dawn Song … (voir 5 de plus)

Victor Storchan

Daniel Zhang

Daniel E. Ho

Percy Liang

Arvind Narayanan

Foundation models are powerful technologies: how they are released publicly directly shapes their societal impact. In this position paper, w… (voir plus)e focus on open foundation models, defined here as those with broadly available model weights (e.g. Llama 2, Stable Diffusion XL). We identify five distinctive properties (e.g. greater customizability, poor monitoring) of open foundation models that lead to both their benefits and risks. Open foundation models present significant benefits, with some caveats, that span innovation, competition, the distribution of decision-making power, and transparency. To understand their risks of misuse, we design a risk assessment framework for analyzing their marginal risk. Across several misuse vectors (e.g. cyberattacks, bioweapons), we find that current research is insufficient to effectively characterize the marginal risk of open foundation models relative to pre-existing technologies. The framework helps explain why the marginal risk is low in some cases, clarifies disagreements about misuse risks by revealing that past work has focused on different subsets of the framework with different assumptions, and articulates a way forward for more constructive debate. Overall, our work helps support a more grounded assessment of the societal impact of open foundation models by outlining what research is needed to empirically validate their theoretical benefits and risks.

2024-02-27

ArXiv (prépublication)

On the Societal Impact of Open Foundation Models

Sayash Kapoor

Rishi Bommasani

Kevin Klyman

Shayne Longpre

Ashwin Ramaswami

Peter Cihon

Aspen Hopkins

Kevin Bankston

Stella Biderman

Miranda Bogen

Rumman Chowdhury

Alex Engler

Peter Henderson

Yacine Jernite

Seth Lazar

Stefano Maffulli

Alondra Nelson

Aviya Skowron

Dawn Song … (voir 5 de plus)

Victor Storchan

Daniel Zhang

Daniel E. Ho

Percy Liang

Arvind Narayanan

Foundation models are powerful technologies: how they are released publicly directly shapes their societal impact. In this position paper, w… (voir plus)e focus on open foundation models, defined here as those with broadly available model weights (e.g. Llama 2, Stable Diffusion XL). We identify five distinctive properties (e.g. greater customizability, poor monitoring) of open foundation models that lead to both their benefits and risks. Open foundation models present significant benefits, with some caveats, that span innovation, competition, the distribution of decision-making power, and transparency. To understand their risks of misuse, we design a risk assessment framework for analyzing their marginal risk. Across several misuse vectors (e.g. cyberattacks, bioweapons), we find that current research is insufficient to effectively characterize the marginal risk of open foundation models relative to pre-existing technologies. The framework helps explain why the marginal risk is low in some cases, clarifies disagreements about misuse risks by revealing that past work has focused on different subsets of the framework with different assumptions, and articulates a way forward for more constructive debate. Overall, our work helps support a more grounded assessment of the societal impact of open foundation models by outlining what research is needed to empirically validate their theoretical benefits and risks.

2024-02-27

ArXiv (prépublication)

On the Societal Impact of Open Foundation Models

Sayash Kapoor

Rishi Bommasani

Kevin Klyman

Shayne Longpre

Ashwin Ramaswami

Peter Cihon

Aspen Hopkins

Kevin Bankston

Stella Biderman

Miranda Bogen

Rumman Chowdhury

Alex Engler

Peter Henderson

Yacine Jernite

Seth Lazar

Stefano Maffulli

Alondra Nelson

Aviya Skowron

Dawn Song … (voir 5 de plus)

Victor Storchan

Daniel Zhang

Daniel E. Ho

Percy Liang

Arvind Narayanan

Foundation models are powerful technologies: how they are released publicly directly shapes their societal impact. In this position paper, w… (voir plus)e focus on open foundation models, defined here as those with broadly available model weights (e.g. Llama 2, Stable Diffusion XL). We identify five distinctive properties (e.g. greater customizability, poor monitoring) of open foundation models that lead to both their benefits and risks. Open foundation models present significant benefits, with some caveats, that span innovation, competition, the distribution of decision-making power, and transparency. To understand their risks of misuse, we design a risk assessment framework for analyzing their marginal risk. Across several misuse vectors (e.g. cyberattacks, bioweapons), we find that current research is insufficient to effectively characterize the marginal risk of open foundation models relative to pre-existing technologies. The framework helps explain why the marginal risk is low in some cases, clarifies disagreements about misuse risks by revealing that past work has focused on different subsets of the framework with different assumptions, and articulates a way forward for more constructive debate. Overall, our work helps support a more grounded assessment of the societal impact of open foundation models by outlining what research is needed to empirically validate their theoretical benefits and risks.

2024-02-27

ArXiv (prépublication)

A novel and efficient machine learning Mendelian randomization estimator applied to predict the safety and efficacy of sclerostin inhibition

Marc-André Legault

Jason Hartford

Benoit J. Arsenault

Y. Archer

Yang

Mendelian Randomization (MR) enables estimation of causal effects while controlling for unmeasured confounding factors. However, traditional… (voir plus) MR's reliance on strong parametric assumptions can introduce bias if these are violated. We introduce a new machine learning MR estimator named Quantile Instrumental Variable (IV) that achieves low estimation error in a wide range of plausible MR scenarios. Quantile IV is distinctive in its ability to estimate nonlinear and heterogeneous causal effects and offers a flexible approach for subgroup analysis. Applying Quantile IV, we investigate the impact of circulating sclerostin levels on heel bone mineral density, osteoporosis, and cardiovascular outcomes in the UK Biobank. Employing various MR estimators and colocalization techniques that allow multiple causal variants, our analysis reveals that a genetically predicted reduction in sclerostin levels significantly increases heel bone mineral density and reduces the risk of osteoporosis, while showing no discernible effect on ischemic cardiovascular diseases. Quantile IV contributes to the advancement of MR methodology, and the case study on the impact of circulating sclerostin modulation contributes to our understanding of the on-target effects of sclerostin inhibition.

2024-01-31

medRxiv (prépublication)

Piecewise Linear Parametrization of Policies: Towards Interpretable Deep Reinforcement Learning

Maxime Wabartha

2024-01-16

ICLR.cc/2024/Conference (poster)

Piecewise Linear Parametrization of Policies: Towards Interpretable Deep Reinforcement Learning

Maxime Wabartha

Learning inherently interpretable policies is a central challenge in the path to developing autonomous agents that humans can trust. Linear … (voir plus)policies can justify their decisions while interacting in a dynamic environment, but their reduced expressivity prevents them from solving hard tasks. Instead, we argue for the use of piecewise-linear policies. We carefully study to what extent they can retain the interpretable properties of linear policies while reaching competitive performance with neural baselines. In particular, we propose the HyperCombinator (HC), a piecewise-linear neural architecture expressing a policy with a controllably small number of sub-policies. Each sub-policy is linear with respect to interpretable features, shedding light on the decision process of the agent without requiring an additional explanation model. We evaluate HC policies in control and navigation experiments, visualize the improved interpretability of the agent and highlight its trade-off with performance. Moreover, we validate that the restricted model class that the HyperCombinator belongs to is compatible with the algorithmic constraints of various reinforcement learning algorithms.

2024-01-16

ICLR.cc/2024/Conference (poster)

Piecewise Linear Parametrization of Policies: Towards Interpretable Deep Reinforcement Learning

Maxime Wabartha

Learning inherently interpretable policies is a central challenge in the path to developing autonomous agents that humans can trust. We argu… (voir plus)e for the use of policies that are piecewise-linear. We carefully study to what extent they can retain the interpretable properties of linear policies while performing competitively with neural baselines. In particular, we propose the HyperCombinator (HC), a piecewise-linear neural architecture expressing a policy with a controllably small number of sub-policies. Each sub-policy is linear with respect to interpretable features, shedding light on the agent’s decision process without needing an additional explanation model. We evaluate HC policies in control and navigation experiments, visualize the improved interpretability of the agent and highlight its trade-off with performance.

2024-01-01

International Conference on Learning Representations (publié)

On the Societal Impact of Open Foundation Models

Sayash Kapoor

Rishi Bommasani

Kevin Klyman

Shayne Longpre

Ashwin Ramaswami

Peter Cihon

Aspen Hopkins

Kevin Bankston

Stella Biderman

Miranda Bogen

Rumman Chowdhury

Alex Engler

Peter Henderson

Yacine Jernite

Seth Lazar

Stefano Maffulli

Alondra Nelson

Aviya Skowron

Dawn Song … (voir 5 de plus)

Victor Storchan

Daniel Zhang

Daniel E. Ho

Percy Liang

Arvind Narayanan

2024-01-01

ICML (publié)

Questions Are All You Need to Train a Dense Passage Retriever

Devendra Singh Sachan

Mike Lewis

Dani Yogatama

Luke Zettlemoyer

Manzil Zaheer

We introduce ART, a new corpus-level autoencoding approach for training dense retrieval models that does not require any labeled training da… (voir plus)ta. Dense retrieval is a central challenge for open-domain tasks, such as Open QA, where state-of-the-art methods typically require large supervised datasets with custom hard-negative mining and denoising of positive examples. ART, in contrast, only requires access to unpaired inputs and outputs (e.g., questions and potential answer passages). It uses a new passage-retrieval autoencoding scheme, where (1) an input question is used to retrieve a set of evidence passages, and (2) the passages are then used to compute the probability of reconstructing the original question. Training for retrieval based on question reconstruction enables effective unsupervised learning of both passage and question encoders, which can be later incorporated into complete Open QA systems without any further finetuning. Extensive experiments demonstrate that ART obtains state-of-the-art results on multiple QA retrieval benchmarks with only generic initialization from a pre-trained language model, removing the need for labeled data and task-specific losses.1 Our code and model checkpoints are available at: https://github.com/DevSinghSachan/art.

2023-06-20

Transactions of the Association for Computational Linguistics (publié)

Group Fairness in Reinforcement Learning

Harsh Satija

Alessandro Lazaric

Matteo Pirotta

We pose and study the problem of satisfying fairness in the online Reinforcement Learning (RL) setting. We focus on the group notions of fai… (voir plus)rness, according to which agents belonging to different groups should have similar performance based on some given measure. We consider the setting of maximizing return in an unknown environment (unknown transition and reward function) and show that it is possible to have RL algorithms that learn the best fair policies without violating the fairness requirements at any point in time during the learning process. In the tabular finite-horizon episodic setting, we provide an algorithm that combines the principle of optimism and pessimism under uncertainty to achieve zero fairness violation with arbitrarily high probability while also maintaining sub-linear regret guarantees. For the high-dimensional Deep-RL setting, we present algorithms based on the performance-difference style approximate policy improvement update step and we report encouraging empirical results on various traditional RL-inspired benchmarks showing that our algorithms display the desired behavior of learning the optimal policy while performing a fair learning process.

2023-04-28

TMLR (accepté)

Estimating causal effects with optimization-based methods: A review and empirical comparison

Martin Cousineau

Vedat Verter

Susan A. Murphy

2023-01-01

European Journal of Operational Research (publié)