Language models (LMs) have recently shown remarkable performance on reasoning tasks by explicitly generating intermediate inferences, e. g., chain-of-thought prompting.
1 code implementation • 13 Oct 2022 • Martin Josifoski, Maxime Peyrard, Frano Rajic, Jiheng Wei, Debjit Paul, Valentin Hartmann, Barun Patra, Vishrav Chaudhary, Emre Kiciman, Boi Faltings, Robert West
Specifically, by analyzing the correlation between the likelihood and the utility of predictions across a diverse set of tasks, we provide empirical evidence supporting the proposed taxonomy and a set of principles to structure reasoning when choosing a decoding algorithm.
Federated Learning by nature is susceptible to low-quality, corrupted, or even malicious data that can severely degrade the quality of the learned model.
Prior studies have used pre-trained language models, or relied on small paired recipe data (e. g., a recipe paired with a similar one that satisfies a dietary constraint).
As a result of revisiting critiquing from the perspective of multimodal generative models, recent work has proposed M&Ms-VAE, which achieves state-of-the-art performance in terms of recommendation, explanation, and critiquing.
In this paper, we consider scenarios that require learning new classes or data distributions quickly and incrementally over time, as it often occurs in real-world dynamic environments.
In this paper, we devise a self-training approach to utilize the abundant unlabeled dialog data to further improve state-of-the-art pre-trained models in few-shot learning scenarios for ToD systems.
Utterance-level intent detection and token-level slot filling are two key tasks for natural language understanding (NLU) in task-oriented systems.
Recommendations with personalized explanations have been shown to increase user trust and perceived quality and help users make better decisions.
Traditional competitive markets do not account for negative externalities; indirect costs that some participants impose on others, such as the cost of over-appropriating a common-pool resource (which diminishes future stock, and thus harvest, for everyone).
One type of explanation is a rationale, i. e., a selection of input features such as relevant text snippets from which the model computes the outcome.
We present a multi-agent learning algorithm, ALMA-Learning, for efficient and fair allocations in large-scale systems.
Experiments on four real-world datasets demonstrate that among state-of-the-art models, our system is the first to dominate or match the performance in terms of recommendation, explanation, and multi-step critiquing.
We introduce a practical and scalable algorithm (PALMA) for solving one of the fundamental problems of multi-agent systems -- finding matches and allocations -- in unboundedly large settings (e. g., resource allocation in urban environments, mobility-on-demand systems, etc.
Natural language generation (NLG) is an essential component of task-oriented dialog systems.
Finally, we validate that the Pareto Fronts obtained with the added objective dominate those produced by state-of-the-art models that are only optimized for accuracy on three real-world publicly available datasets.
We evaluate the benefits of Multi-objective Adamize on two multi-objective recommender systems and for three different objective combinations, both correlated or conflicting.
The goal of fairness in classification is to learn a classifier that does not discriminate against groups of individuals based on sensitive attributes, such as race and gender.
In this case, the recommender is updated continually and periodically with new data that arrives in each update cycle, and the updated model needs to provide recommendations for user activities before the next model update.
We empirically show that MAN is well-suited for the incremental SR task, and it consistently outperforms state-of-the-art neural and nonparametric methods.
This paper considers the problem of enhancing user privacy in common machine learning development tasks, such as data annotation and inspection, by substituting the real data with samples form a generative adversarial network.
In this paper, we propose GameWikiSum, a new domain-specific dataset for multi-document summarization, which is one hundred times larger than commonly used datasets, and in another domain than news.
In this paper, we propose HotelRec, a very large-scale hotel recommendation dataset, based on TripAdvisor, containing 50 million reviews.
We study the optimization of large-scale, real-time ridesharing systems and propose a modular design methodology, Component Algorithms for Ridesharing (CAR).
Recommender systems need to mirror the complexity of the environment they are applied in.
Ranked #1 on Recommendation Systems on MovieLens 20M (Recall@20 metric)
Past work used attention and rationale mechanisms to find words that predict the target variable of a document.
Neural models achieved considerable improvement for many natural language processing tasks, but they offer little transparency, and interpretability comes at a cost.
To overcome these limitations, we present a novel method, which makes use of two types of sentence embeddings: universal embeddings, which are trained on a large unrelated corpus, and domain-specific embeddings, which are learned during training.
Partitioning a graph using graph separators, and particularly clique separators, are well-known techniques to decompose a graph into smaller units which can be treated independently.
We consider a crowdsourcing data acquisition scenario, such as federated learning, where a Center collects data points from a set of rational Agents, with the aim of training a model.
Natural language generation (NLG) is an essential component of task-oriented dialogue systems.
We present a novel anytime heuristic (ALMA), inspired by the human principle of altruism, for solving the assignment problem.
Recent studies have shown that the labels collected from crowdworkers can be discriminatory with respect to sensitive attributes such as gender and race.
We explored $CompNet$, in which case we morph a well-trained neural network to a deeper one where network function can be preserved and the added layer is compact.
We propose a novel mechanism that assigns gold tasks to only a few workers and exploits transitivity to derive accuracy of the rest of the workers from their peers' accuracy.
In this paper, we propose generating artificial data that retain statistical properties of real data as the means of providing privacy with respect to the original dataset.
In this paper, we present a technique for generating artificial datasets that retain statistical properties of the real data while providing differential privacy guarantees with respect to this data.
The main goal of modeling human conversation is to create agents which can interact with people in both open-ended and goal-oriented scenarios.
As large-scale theft of data from corporate servers is becoming increasingly common, it becomes interesting to examine alternatives to the paradigm of centralizing sensitive data into large databases.
The profusion of online news articles makes it difficult to find interesting articles, a problem that can be assuaged by using a recommender system to bring the most relevant news stories to readers.