In an era of increasingly capable foundation models, job seekers are turning to generative AI tools to enhance their application materials. However, unequal access to and knowledge about generative AI tools can harm both employers and candidates by reducing the accuracy of hiring decisions and giving some candidates an unfair advantage. To address these challenges, we introduce a new variant of the strategic classification framework tailored to manipulations performed using large language models, accommodating varying levels of manipulations and stochastic outcomes. We propose a "two-ticket" scheme, where the hiring algorithm applies an additional manipulation to each submitted resume and considers this manipulated version together with the original submitted resume. We establish theoretical guarantees for this scheme, showing improvements for both the fairness and accuracy of hiring decisions when the true positive rate is maximized subject to a no false positives constraint. We further generalize this approach to an $n$-ticket scheme and prove that hiring outcomes converge to a fixed, group-independent decision, eliminating disparities arising from differential LLM access. Finally, we empirically validate our framework and the performance of our two-ticket scheme on real resumes using an open-source resume screening tool.

The field of algorithms with predictions incorporates machine learning advice in the design of online algorithms to improve real-world performance. A central consideration is the extent to which predictions can be trusted—while existing approaches often require users to specify an aggregate trust level, modern machine learning models can provide estimates of prediction-level uncertainty. In this paper, we propose calibration as a principled and practical tool to bridge this gap, demonstrating the benefits of calibrated advice through two case studies: the ski rental and online job scheduling problems. For ski rental, we design an algorithm that achieves near-optimal prediction-dependent performance and prove that, in high-variance settings, calibrated advice offers more effective guidance than alternative methods for uncertainty quantification. For job scheduling, we demonstrate that using a calibrated predictor leads to significant performance improvements over existing methods. Evaluations on real-world data validate our theoretical findings, highlighting the practical impact of calibration for algorithms with predictions.

While modern explanation methods have been shown to be inconsistent and contradictory, the explainability of black-box models nevertheless remains desirable. When the role of explanations extends from understanding models to aiding decision making, the semantics of explanations is not always fully understood – to what extent do explanations ``explain” a decision and to what extent do they merely advocate for a decision? Can we help humans gain insights from explanations accompanying correct predictions and not over-rely on incorrect predictions advocated for by explanations? With this perspective in mind, we introduce the notion of dissenting explanations: conflicting predictions with accompanying explanations. We first explore the advantage of dissenting explanations in the setting of model multiplicity, where multiple models with similar performance may have different predictions. Through a human study on the task of identifying deceptive reviews, we demonstrate that dissenting explanations reduce overreliance on model predictions, without reducing overall accuracy. Motivated by the utility of dissenting explanations we present both global and local methods for their generation.

To address the shortcomings of real-world datasets, robust learning algorithms have been designed to overcome arbitrary and indiscriminate data corruption. However, practical processes of gathering data may lead to patterns of data corruption that are localized to specific partitions of the training dataset. Motivated by critical applications where the learned model is deployed to make predictions about people from a rich collection of overlapping subpopulations, we initiate the study of multigroup robust algorithms whose robustness guarantees for each subpopulation only degrade with the amount of data corruption inside that subpopulation. When the data corruption is not distributed uniformly over subpopulations, our algorithms provide more meaningful robustness guarantees than standard guarantees that are oblivious to how the data corruption and the affected subpopulations are related. Our techniques establish a new connection between multigroup fairness and robustness.

We show that adding differential privacy to Explainable Boosting Machines (EBMs), a recent method for training interpretable ML models, yields state-of-the-art accuracy while protecting privacy. Our experiments on multiple classification and regression datasets show that DP-EBM models suffer surprisingly little accuracy loss even with strong differential privacy guarantees. In addition to high accuracy, two other benefits of applying DP to EBMs are: a) trained models provide exact global and local interpretability, which is often important in settings where differential privacy is needed; and b) the models can be edited after training without loss of privacy to correct errors which DP noise may have introduced.

Differentially Private-SGD (DP-SGD) of Abadi et al. and its variations are the only known algorithms for private training of large scale neural networks. This algorithm requires computation of per-sample gradients norms which is extremely slow and memory intensive in practice. In this paper, we present a new framework to design differentially private optimizers called DP-SGD-JL and DP-Adam-JL. Our approach uses Johnson–Lindenstrauss (JL) projections to quickly approximate the per-sample gradient norms without exactly computing them, thus making the training time and memory requirements of our optimizers closer to that of their non-DP versions. Unlike previous attempts to make DP-SGD faster which work only on a subset of network architectures or use compiler techniques, we propose an algorithmic solution which works for any network in a black-box manner which is the main contribution of this paper. To illustrate this, on IMDb dataset, we train a Recurrent Neural Network (RNN) to achieve good privacy-vs-accuracy tradeoff, while being significantly faster than DP-SGD and with a similar memory footprint as non-private SGD.

Open-domain dialog generation is a challenging problem; maximum likelihood training can lead to repetitive outputs, models have difficulty tracking long-term conversational goals, and training on standard movie or online datasets may lead to the generation of inappropriate, biased, or offensive text. Reinforcement Learning (RL) is a powerful framework that could potentially address these issues, for example by allowing a dialog model to optimize for reducing toxicity and repetitiveness. However, previous approaches which apply RL to open-domain dialog generation do so at the word level, making it difficult for the model to learn proper credit assignment for long-term conversational rewards. In this paper, we propose a novel approach to hierarchical reinforcement learning (HRL), VHRL, which uses policy gradients to tune the utterance-level embedding of a variational sequence model. This hierarchical approach provides greater flexibility for learning long-term, conversational rewards. We use self-play and RL to optimize for a set of human-centered conversation metrics, and show that our approach provides significant improvements – in terms of both human evaluation and automatic metrics – over state-of-the-art dialog models, including Transformers.

Natasha Jaques, Judy Hanwen Shen, Asma Ghandeharioun, Craig Ferguson, Agata Lapedriza, Noah Jones, Shixiang Gu, Rosalind Picard. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). 2020.

We study the basic operation of set union in the global model of differential privacy. In this problem, we are given a universe $U$ of items, possibly of infinite size, and a database $D$ of users. Each user $i$ contributes a subset $W_i \subseteq U$ of items. We want an ($\epsilon$,$\delta$)-differentially private Algorithm which outputs a subset $S \subset \cup_i W_i$ such that the size of $S$ is as large as possible. The problem arises in countless real world applications, and is particularly ubiquitous in natural language processing (NLP) applications. For example, discovering words, sentences, $n$-grams etc., from private text data belonging to users is an instance of the set union problem. In this paper we design new algorithms for this problem that significantly outperform the best known algorithms.

Online platforms displaying long streams of examples are often employed to gather labels from both experts and crowd workers. While previous work in crowdsourcing focused on objective tasks and estimating error parameters of annotators, collecting labels in a subjective setting (e.g. emotion recognition) is more complicated due to different interpretations of examples. These interpretations could be influenced by many factors such as annotator mood and previously seen examples. In this work, we examine two hypotheses of order-dependent biases in sequential labeling tasks: negatively auto-correlated sequential decision making and positively auto-correlated affective priming. Using controlled generation of facial expressions, we find that i) annotators achieve higher agreement when presented examples in the same sequential order, ii) the valence label of the current image positively correlates with the previous labels given. While we also observe a positive correlation between labels and the number of preceding positive and negative images seen, this correlation is highly dependent on example ordering. Our findings demonstrate that randomized examples given to annotators may produce systematic bias in labels. Future data collection should present examples in orderings which mitigate such bias.

Building an open-domain conversational agent is a challenging problem. Current evaluation methods, mostly post-hoc judgments of static conversation, do not capture conversation quality in a realistic interactive context. In this paper, we investigate interactive human evaluation and provide evidence for its necessity; we then introduce a novel, model-agnostic, and dataset-agnostic method to approximate it. In particular, we propose a self-play scenario where the dialog system talks to itself and we calculate a combination of proxies such as sentiment and semantic coherence on the conversation trajectory. We show that this metric is capable of capturing the human-rated quality of a dialog model better than any automated metric known to-date, achieving a significant Pearson correlation (r>.7, p<.05). To investigate the strengths of this novel metric and interactive evaluation in comparison to state-of-the-art metrics and human evaluation of static conversations, we perform extended experiments with a set of models, including several that make novel improvements to recent hierarchical dialog generation architectures through sentiment and semantic knowledge distillation on the utterance level. Finally, we open-source the interactive evaluation platform we built and the dataset we collected to allow researchers to efficiently deploy and evaluate dialog models.

Simple reference games (Wittgenstein, 1953) are of central theoretical and empirical importance in the study of situated language use.Although language provides rich, compositional truth-conditional semantics to facilitate reference, speakers and listeners may sometimes lack the overall lexical and cognitive resources to guarantee successful reference through these means alone.However, language also has rich associational structures that can serve as a further resource for achieving successful reference.Here we investigate this use of associational information in a setting where only associational information is available: a simplified version of the popular game Codenames.Using optimal experiment design techniques, we compare a range of models varying in the type of associative information deployed and in level of pragmatic sophistication against human behavior.In this setting we find that listeners' behavior reflects direct bigram collocational associations more strongly than word-embedding or semantic knowledge graph-based associations and that there is little evidence for pragmatically sophisticated behavior by either speakers or listeners of the type that might be predicted by recursive-reasoning models such as the Rational Speech Acts theory.These results shed light on the nature of the lexical resources that speakers and listeners can bring to bear in achieving reference through associative meaning alone.

We introduce TuringBox, a platform to democratize the study of AI. On one side of the platform, AI contributors upload existing and novel algorithms to be studied scientifically by others. On the other side, AI examiners develop and post machine intelligence tasks to evaluate and characterize the outputs of algorithms. We outline the architecture of such a platform, and describe two interactive case studies of algorithmic auditing on the platform.