One of the objectives of the 2020 white paper was to formulate a proposal for an AI liability directive. The purpose of this proposal is to "to contribute to the proper functioning of the internal market by harmonising certain national non-contractual fault-based liability rules, so as to ensure that persons claiming compensation for damage caused to them by an AI system enjoy a level of protection equivalent to that enjoyed by persons claiming compensation for damage caused without the involvement of an AI system."

A central goal in the cognitive sciences is the development of numerical models for mental representations of object concepts. This paper introduces Variational Interpretable Concept Embeddings (VICE), an approximate Bayesian method for embedding object concepts in a vector space using data collected from humans in a triplet odd-one-out task. VICE uses variational inference to obtain sparse, non-negative representations of object concepts with uncertainty estimates for the embedding values. These estimates are used to automatically select the dimensions that best explain the data. We derive a PAC learning bound for VICE that can be used to estimate generalization performance or determine a sufficient sample size for experimental design. VICE rivals or outperforms its predecessor, SPoSE, at predicting human behavior in the triplet odd-one-out task. Furthermore, VICE's object representations are more reproducible and consistent across random initializations, highlighting the unique advantage of using VICE for deriving interpretable embeddings from human behavior.

The estimation of heterogeneous treatment effects (HTEs) has attracted considerable interest in many disciplines, most prominently in medicine and economics. Contemporary research has so far primarily focused on continuous and binary responses where HTEs are traditionally estimated by a linear model, which allows the estimation of constant or heterogeneous effects even under certain model misspecifications. More complex models for survival, count, or ordinal outcomes require stricter assumptions to reliably estimate the treatment effect. Most importantly, the noncollapsibility issue necessitates the joint estimation of treatment and prognostic effects. Model-based forests allow simultaneous estimation of covariate-dependent treatment and prognostic effects, but only for randomized trials. In this paper, we propose modifications to model-based forests to address the confounding issue in observational data. In particular, we evaluate an orthogonalization strategy originally proposed by Robinson (1988, Econometrica) in the context of model-based forests targeting HTE estimation in generalized linear models and transformation models. We found that this strategy reduces confounding effects in a simulated study with various outcome distributions. We demonstrate the practical aspects of HTE estimation for survival and ordinal outcomes by an assessment of the potentially heterogeneous effect of Riluzole on the progress of Amyotrophic Lateral Sclerosis.

We consider the problem of modeling heterogeneous materials where micro-scale dynamics and interactions affect global behavior. In the presence of heterogeneities in material microstructure it is often impractical, if not impossible, to provide quantitative characterization of material response. The goal of this work is to develop a Bayesian framework for uncertainty quantification (UQ) in material response prediction when using nonlocal models. Our approach combines the nonlocal operator regression (NOR) technique and Bayesian inference. Specifically, we use a Markov chain Monte Carlo (MCMC) method to sample the posterior probability distribution on parameters involved in the nonlocal constitutive law, and associated modeling discrepancies relative to higher fidelity computations. As an application, we consider the propagation of stress waves through a one-dimensional heterogeneous bar with randomly generated microstructure. Several numerical tests illustrate the construction, enabling UQ in nonlocal model predictions. Although nonlocal models have become popular means for homogenization, their statistical calibration with respect to high-fidelity models has not been presented before. This work is a first step towards statistical characterization of nonlocal model discrepancy in the context of homogenization.

Abstract-- Evaluating the safety of an autonomous vehicle (AV) depends on the behavior of surrounding agents which can be heavily influenced by factors such as environmental context and informally-defined driving etiquette. A key challenge is in determining a minimum set of assumptions on what constitutes reasonable foreseeable behaviors of other road users for the development of AV safety models and techniques. In this paper, we propose a data-driven AV safety design methodology that first learns "reasonable" behavioral assumptions from data, and then synthesizes an AV safety concept using these Figure 1: Evaluating the safety of an autonomous vehicle (AV) learned behavioral assumptions. We borrow techniques from depends on what constitutes as reasonable foreseeable behaviors of control theory, namely high order control barrier functions other road users. For example, determining whether the autonomous and Hamilton-Jacobi reachability, to provide inductive bias car (blue) is currently in a safe state depends on how the human to aid interpretability, verifiability, and tractability of our driver (red) may behave (e.g., speed up or swerve away).

We explore the idea of compressing the prompts used to condition language models, and show that compressed prompts can retain a substantive amount of information about the original prompt. For severely compressed prompts, while fine-grained information is lost, abstract information and general sentiments can be retained with surprisingly few parameters, which can be useful in the context of decode-time algorithms for controllability and toxicity reduction. We explore contrastive conditioning to steer language model generation towards desirable text and away from undesirable text, and find that some complex prompts can be effectively compressed into a single token to guide generation. We also show that compressed prompts are largely compositional, and can be constructed such that they can be used to control independent aspects of generated text.

Answering complex questions that require multi-step multi-type reasoning over raw text is challenging, especially when conducting numerical reasoning. Neural Module Networks(NMNs), follow the programmer-interpreter framework and design trainable modules to learn different reasoning skills. However, NMNs only have limited reasoning abilities, and lack numerical reasoning capability. We up-grade NMNs by: (a) bridging the gap between its interpreter and the complex questions; (b) introducing addition and subtraction modules that perform numerical reasoning over numbers. On a subset of DROP, experimental results show that our proposed methods enhance NMNs' numerical reasoning skills by 17.7% improvement of F1 score and significantly outperform previous state-of-the-art models.

Interpretable machine learning plays a key role in healthcare because it is challenging in understanding feature importance in deep learning model predictions. We propose a novel framework that uses deep learning to study feature sensitivity for model predictions. This work combines sensitivity analysis with heterogeneous time-series deep learning model prediction, which corresponds to the interpretations of spatio-temporal features. We forecast county-level COVID-19 infection using the Temporal Fusion Transformer. We then use the sensitivity analysis extending Morris Method to see how sensitive the outputs are with respect to perturbation to our static and dynamic input features. The significance of the work is grounded in a real-world COVID-19 infection prediction with highly non-stationary, finely granular, and heterogeneous data. 1) Our model can capture the detailed daily changes of temporal and spatial model behaviors and achieves high prediction performance compared to a PyTorch baseline. 2) By analyzing the Morris sensitivity indices and attention patterns, we decipher the meaning of feature importance with observational population and dynamic model changes. 3) We have collected 2.5 years of socioeconomic and health features over 3142 US counties, such as observed cases and deaths, and a number of static (age distribution, health disparity, and industry) and dynamic features (vaccination, disease spread, transmissible cases, and social distancing). Using the proposed framework, we conduct extensive experiments and show our model can learn complex interactions and perform predictions for daily infection at the county level. Being able to model the disease infection with a hybrid prediction and description accuracy measurement with Morris index at the county level is a central idea that sheds light on individual feature interpretation via sensitivity analysis.

On the other hand, these research insights are meant to intervene on platforms that are globally present, serving a global population from diverse societies, cultures and values, with their own forms of injustices. A core concern in this arrangement is that of value imposition, where local values, i.e., values that are local to the regions where the interventions are built, implicitly shape and inform global systems without any or much room for discussion or contestation from those affected by those interventions. More specifically, interventions designed to address FATE failures necessarily impart a normative value system, but the values that guide the proposed solutions are rarely recognized as sites of contestation. This is problematic because while there may be ethical principles for ML that garner a degree of consensus across different value systems, in a pluralistic world this consensus is not something that should be assumed. Instead, we need to be explicit about the values that underpin the quest for ethical and just AI, and to cultivate an active debate about those values, critically examining and evaluating claims about them[28]. Another shortcoming of not being explicit about what normative value systems shape the interventions is the vagueness it entails, making it harder to arrive at a common vocabulary and shared understanding between computer scientists and civil society. Such a shared understanding is crucial to bridge the gap between research and practice, especially in a way that effectively supports the priorities of the latter constituency.

Language features are ever-evolving in the real-world social media environment. Many trained models in natural language understanding (NLU), ineffective in semantic inference for unseen features, might consequently struggle with the deteriorating performance in dynamicity. To address this challenge, we empirically study social media NLU in a dynamic setup, where models are trained on the past data and test on the future. It better reflects the realistic practice compared to the commonly-adopted static setup of random data split. To further analyze model adaption to the dynamicity, we explore the usefulness of leveraging some unlabeled data created after a model is trained. The performance of unsupervised domain adaption baselines based on auto-encoding and pseudo-labeling and a joint framework coupling them both are examined in the experiments. Substantial results on four social media tasks imply the universally negative effects of evolving environments over classification accuracy, while auto-encoding and pseudo-labeling collaboratively show the best robustness in dynamicity.