Ed H.

Modeling Task Relationships in Multi-task Learning with Multi-gate Mixture-of-Experts

2018

Neural-based multi-task learning has been successfully used in many real-world large-scale applications such as recommendation systems. For example, in movie recommendations, beyond providing users movies which they tend to purchase and watch, the system might …

Beyond Point Estimate: Inferring Ensemble Prediction Variation from Neuron Activation Strength in Recommender Systems

2021

Despite deep neural network (DNN)'s impressive prediction performance in various domains, it is well known now that a set of DNN models trained with the same model specification and the exact same training data could …

Emergent Abilities of Large Language Models

2022 · arXiv (Cornell University)

Scaling up language models has been shown to predictably improve performance and sample efficiency on a wide range of downstream tasks. This paper instead discusses an unpredictable phenomenon that we refer to as emergent abilities …

Improving Classifier Robustness through Active Generation of Pairwise Counterfactuals

2023 · arXiv (Cornell University)

Counterfactual Data Augmentation (CDA) is a commonly used technique for improving robustness in natural language classifiers. However, one fundamental challenge is how to discover meaningful counterfactuals and efficiently label them, with minimal human labeling cost. …

Cluster Anchor Regularization to Alleviate Popularity Bias in Recommender Systems

2024

Recommender systems are essential for finding personalized content for users on online platforms. These systems are often trained on historical user interaction data, which collects user feedback on system recommendations. This creates a feedback loop …

Aligning Large Language Models with Recommendation Knowledge

2024

Yuwei Cao, Nikhil Mehta, Xinyang Yi, Raghunandan Hulikal Keshavan, Lukasz Heldt, Lichan Hong, Ed Chi, Maheswaran Sathiamoorthy. Findings of the Association for Computational Linguistics: NAACL 2024. 2024.

Bridging the Gap: Unpacking the Hidden Challenges in Knowledge Distillation for Online Ranking Systems

2024

Knowledge Distillation (KD) is a powerful approach for compressing a large model into a smaller, more efficient model, particularly beneficial for latency-sensitive applications like recommender systems. However, current KD research predominantly focuses on Computer Vision …

Latent Cross

2018

The success of recommender systems often depends on their ability to understand and make use of the context of the recommendation request. Significant research has focused on how time, location, interfaces, and a plethora of …

Recommending what video to watch next

2019

In this paper, we introduce a large scale multi-objective ranking system for recommending what video to watch next on an industrial video sharing platform. The system faces many real-world challenges, including the presence of multiple …

BNAI, NO-TOKEN, and MIND-UNITY: Pillars of a Systemic Revolution in Artificial Intelligence

2022 · arXiv (Cornell University)

AbstractThere is a failure mode in large language models that we do not have a good name for, and thatwe therefore tend not to treat seriously enough. It is not hallucination — the model is …

Self-Consistency Improves Chain of Thought Reasoning in Language Models

2022 · arXiv (Cornell University)

Chain-of-thought prompting combined with pre-trained large language models has achieved encouraging results on complex reasoning tasks. In this paper, we propose a new decoding strategy, self-consistency, to replace the naive greedy decoding used in chain-of-thought …

LaMDA: Language Models for Dialog Applications

2022 · arXiv (Cornell University)

We present LaMDA: Language Models for Dialog Applications. LaMDA is a family of Transformer-based neural language models specialized for dialog, which have up to 137B parameters and are pre-trained on 1.56T words of public dialog …

Least-to-Most Prompting Enables Complex Reasoning in Large Language Models

2022 · arXiv (Cornell University)

Chain-of-thought prompting has demonstrated remarkable performance on various natural language reasoning tasks. However, it tends to perform poorly on tasks which requires solving problems harder than the exemplars shown in the prompts. To overcome this …

Scaling Instruction-Finetuned Language Models

2022 · arXiv (Cornell University)

Finetuning language models on a collection of datasets phrased as instructions has been shown to improve model performance and generalization to unseen tasks. In this paper we explore instruction finetuning with a particular focus on …

Gemini: A Family of Highly Capable Multimodal Models

2023 · arXiv (Cornell University)

This report introduces a new family of multimodal models, Gemini, that exhibit remarkable capabilities across image, audio, video, and text understanding. The Gemini family consists of Ultra, Pro, and Nano sizes, suitable for applications ranging …