research
∙
06/13/2023
Better Generalization with Semantic IDs: A case study in Ranking for Recommendations
Training good representations for items is critical in recommender model...
share
research
∙
05/10/2023
Do LLMs Understand User Preferences? Evaluating LLMs On User Rating Prediction
Large Language Models (LLMs) have demonstrated exceptional capabilities ...
research
∙
01/31/2023
Large Language Models Can Be Easily Distracted by Irrelevant Context
Large language models have achieved impressive performance on various na...
research
∙
07/02/2022
Rationale-Augmented Ensembles in Language Models
Recent research has shown that rationales, or step-by-step chains of tho...
research
∙
05/21/2022
Least-to-Most Prompting Enables Complex Reasoning in Large Language Models
We propose a novel prompting strategy, least-to-most prompting, that ena...
research
∙
03/21/2022
Self-Consistency Improves Chain of Thought Reasoning in Language Models
We explore a simple ensemble strategy, self-consistency, that significan...
research
∙
02/02/2022
Algorithms for Efficiently Learning Low-Rank Neural Networks
We study algorithms for learning low-rank neural networks – networks whe...
research
∙
01/28/2022
Chain of Thought Prompting Elicits Reasoning in Large Language Models
Although scaling up language model size has reliably improved performanc...
research
∙
01/26/2022
Recency Dropout for Recurrent Recommender Systems
Recurrent recommender systems have been successful in capturing the temp...
research
∙
10/05/2020
CAT-Gen: Improving Robustness in NLP Models via Controlled Adversarial Text Generation
NLP models are shown to suffer from robustness issues, i.e., a model's p...
research
∙
02/12/2020
Data Efficient Training for Reinforcement Learning with Adaptive Behavior Policy Sharing
Deep Reinforcement Learning (RL) is proven powerful for decision making ...
research
∙
02/08/2020
BRPO: Batch Residual Policy Optimization
In batch reinforcement learning (RL), one often constrains a learned pol...
research
∙
12/06/2018
Top-K Off-Policy Correction for a REINFORCE Recommender System
Industrial recommender systems deal with extremely large action spaces -...
research
∙
10/04/2018
Seq2Slate: Re-ranking and Slate Optimization with RNNs
Ranking is a central task in machine learning and information retrieval....
research
∙
07/18/2018