Search Results for author:
Found 51 papers, 13 papers with code
Making Reasoning Matter: Measuring and Improving Faithfulness of Chain-of-Thought Reasoning
In this paper, we perform a causal mediation analysis on twelve LLMs to examine how intermediate reasoning steps generated by the LLM influence the final outcome and find that LLMs do not reliably use their intermediate reasoning steps when generating an answer.
δ-CAUSAL: Exploring Defeasibility in Causal Reasoning
CESAR achieves a significant 69. 7% relative improvement over existing metrics, increasing from 47. 2% to 80. 1% in capturing the causal strength change brought by supporters and defeaters.
REFINER: Reasoning Feedback on Intermediate Representations
Language models (LMs) have recently shown remarkable performance on reasoning tasks by explicitly generating intermediate inferences, e. g., chain-of-thought prompting.
Language Model Decoding as Likelihood-Utility Alignment
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.
A Practical Influence Approximation for Privacy-Preserving Data Filtering in Federated Learning
Federated Learning by nature is susceptible to low-quality, corrupted, or even malicious data that can severely degrade the quality of the learned model.
Interlock-Free Multi-Aspect Rationalization for Text Classification
Explanation is important for text classification tasks.
Assistive Recipe Editing through Critiquing
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).
Positive and Negative Critiquing for VAE-based Recommenders
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.
Self-training Improves Pre-training for Few-shot Learning in Task-oriented Dialog Systems
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.
Representation Memorization for Fast Learning New Knowledge without Forgetting
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.
SLIM: Explicit Slot-Intent Mapping with BERT for Joint Multi-Intent Detection and Slot Filling
Utterance-level intent detection and token-level slot filling are two key tasks for natural language understanding (NLU) in task-oriented systems.
Multi-Step Critiquing User Interface for Recommender Systems
Recommendations with personalized explanations have been shown to increase user trust and perceived quality and help users make better decisions.
AI-driven Prices for Externalities and Sustainability in Production Markets
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).
Rationalization through Concepts
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.
Improving Multi-agent Coordination by Learning to Estimate Contention
We present a multi-agent learning algorithm, ALMA-Learning, for efficient and fair allocations in large-scale systems.
Fast Multi-Step Critiquing for VAE-based Recommender 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.
Improved Cooperation by Exploiting a Common Signal
Inspired by human behavior, we investigate the learning dynamics and emergence of temporal conventions, focusing on common-pool resources.
A Distributed Differentially Private Algorithm for Resource Allocation in Unboundedly Large Settings
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.
Continual Learning for Natural Language Generation in Task-oriented Dialog Systems
Natural language generation (NLG) is an essential component of task-oriented dialog systems.
Modeling Online Behavior in Recommender Systems: The Importance of Temporal Context
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.
Momentum-based Gradient Methods in Multi-Objective Recommendation
We evaluate the benefits of Multi-objective Adamize on two multi-objective recommender systems and for three different objective combinations, both correlated or conflicting.
Addressing Fairness in Classification with a Model-Agnostic Multi-Objective Algorithm
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.
ADER: Adaptively Distilled Exemplar Replay Towards Continual Learning for Session-based Recommendation
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.
Interacting with Explanations through Critiquing
Using personalized explanations to support recommendations has been shown to increase trust and perceived quality.
Memory Augmented Neural Model for Incremental Session-based Recommendation
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.
Generating Higher-Fidelity Synthetic Datasets with Privacy Guarantees
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.
HotelRec: a Novel Very Large-Scale Hotel Recommendation Dataset
In this paper, we propose HotelRec, a very large-scale hotel recommendation dataset, based on TripAdvisor, containing 50 million reviews.
GameWikiSum: a Novel Large Multi-Document Summarization Dataset
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.
Putting Ridesharing to the Test: Efficient and Scalable Solutions and the Power of Dynamic Vehicle Relocation
We study the optimization of large-scale, real-time ridesharing systems and propose a modular design methodology, Component Algorithms for Ridesharing (CAR).
Multi-Gradient Descent for Multi-Objective Recommender Systems
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)
Federated Learning with Bayesian Differential Privacy
We consider the problem of reinforcing federated learning with formal privacy guarantees.
Federated Generative Privacy
In this paper, we propose FedGP, a framework for privacy-preserving data release in the federated learning setting.
Multi-Dimensional Explanation of Target Variables from Documents
Past work used attention and rationale mechanisms to find words that predict the target variable of a document.
Multi-Dimensional Explanation of Reviews
Neural models achieved considerable improvement for many natural language processing tasks, but they offer little transparency, and interpretability comes at a cost.
Learning to Create Sentence Semantic Relation Graphs for Multi-Document Summarization
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.
An Effective Upperbound on Treewidth Using Partial Fill-in of Separators
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.
Rewarding High-Quality Data via Influence Functions
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.
Infochain: A Decentralized, Trustless and Transparent Oracle on Blockchain
For the first time, we show how to implement a trustless and transparent oracle in Ethereum.
Meta-Learning for Low-resource Natural Language Generation in Task-oriented Dialogue Systems
Natural language generation (NLG) is an essential component of task-oriented dialogue systems.
Anytime Heuristic for Weighted Matching Through Altruism-Inspired Behavior
We present a novel anytime heuristic (ALMA), inspired by the human principle of altruism, for solving the assignment problem.
Bayesian Differential Privacy for Machine Learning
Traditional differential privacy is independent of the data distribution.
Crowdsourcing with Fairness, Diversity and Budget Constraints
Recent studies have shown that the labels collected from crowdworkers can be discriminatory with respect to sensitive attributes such as gender and race.
Context Tree for Adaptive Session-based Recommendation
Therefore, recommendations need to be adaptive to such frequent changes.
Information Retrieval
CompNet: Neural networks growing via the compact network morphism
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.
Deep Bayesian Trust : A Dominant and Fair Incentive Mechanism for Crowd
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.
Generating Artificial Data for Private Deep Learning
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.
BIG-bench Machine Learning
Generative Adversarial Network
+1
Generating Differentially Private Datasets Using GANs
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.
BIG-bench Machine Learning
Generative Adversarial Network
+1
Personalization in Goal-Oriented Dialog
The main goal of modeling human conversation is to create agents which can interact with people in both open-ended and goal-oriented scenarios.
Protecting Privacy through Distributed Computation in Multi-agent Decision Making
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.
Personalized News Recommendation with Context Trees
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.
