no code implementations • 25 Oct 2023 • Sidharth Mudgal, Jong Lee, Harish Ganapathy, Yaguang Li, Tao Wang, Yanping Huang, Zhifeng Chen, Heng-Tze Cheng, Michael Collins, Trevor Strohman, Jilin Chen, Alex Beutel, Ahmad Beirami
We propose controlled decoding (CD), a novel off-policy reinforcement learning method to control the autoregressive generation from language models towards high reward outcomes.
Multi-Objective Reinforcement Learning
reinforcement-learning
no code implementations • 25 Oct 2023 • Aradhana Sinha, Ananth Balashankar, Ahmad Beirami, Thi Avrahami, Jilin Chen, Alex Beutel
We demonstrate the advantages of this system on the ANLI and hate speech detection benchmark datasets - both collected via an iterative, adversarial human-and-model-in-the-loop procedure.
no code implementations • 25 Oct 2023 • Ananth Balashankar, Xiao Ma, Aradhana Sinha, Ahmad Beirami, Yao Qin, Jilin Chen, Alex Beutel
As large language models (LLMs) are widely adopted, new safety issues and policies emerge, to which existing safety classifiers do not generalize well.
no code implementations • 25 Oct 2023 • Preethi Lahoti, Nicholas Blumm, Xiao Ma, Raghavendra Kotikalapudi, Sahitya Potluri, Qijun Tan, Hansa Srinivasan, Ben Packer, Ahmad Beirami, Alex Beutel, Jilin Chen
A crucial challenge for generative large language models (LLMs) is diversity: when a user's prompt is under-specified, models may follow implicit assumptions while generating a response, which may result in homogenization of the responses, as well as certain demographic groups being under-represented or even erased from the generated responses.
no code implementations • 29 Sep 2023 • Han Zhou, Xingchen Wan, Lev Proleev, Diana Mincu, Jilin Chen, Katherine Heller, Subhrajit Roy
Prompting and in-context learning (ICL) have become efficient learning paradigms for large language models (LLMs).
no code implementations • 11 Jul 2023 • James Atwood, Tina Tian, Ben Packer, Meghana Deodhar, Jilin Chen, Alex Beutel, Flavien Prost, Ahmad Beirami
Despite the rich literature on machine learning fairness, relatively little attention has been paid to remediating complex systems, where the final prediction is the combination of multiple classifiers and where multiple groups are present.
no code implementations • 25 Jun 2023 • Xiao Ma, Swaroop Mishra, Ahmad Beirami, Alex Beutel, Jilin Chen
Language models still struggle on moral reasoning, despite their impressive performance in many other tasks.
no code implementations • 22 May 2023 • Ananth Balashankar, Xuezhi Wang, Yao Qin, Ben Packer, Nithum Thain, Jilin Chen, Ed H. Chi, Alex Beutel
We demonstrate that with a small amount of human-annotated counterfactual data (10%), we can generate a counterfactual augmentation dataset with learned labels, that provides an 18-20% improvement in robustness and a 14-21% reduction in errors on 6 out-of-domain datasets, comparable to that of a fully human-annotated counterfactual dataset for both sentiment classification and question paraphrase tasks.
no code implementations • 28 Oct 2022 • Jieyu Zhao, Xuezhi Wang, Yao Qin, Jilin Chen, Kai-Wei Chang
Large pre-trained language models have shown remarkable performance over the past few years.
no code implementations • 18 Oct 2022 • Meghana Deodhar, Xiao Ma, Yixin Cai, Alex Koes, Alex Beutel, Jilin Chen
We deal with the problem of localized in-video taxonomic human annotation in the video content moderation domain, where the goal is to identify video segments that violate granular policies, e. g., community guidelines on an online video platform.
no code implementations • 14 Oct 2022 • Flavien Prost, Ben Packer, Jilin Chen, Li Wei, Pierre Kremp, Nicholas Blumm, Susan Wang, Tulsee Doshi, Tonia Osadebe, Lukasz Heldt, Ed H. Chi, Alex Beutel
We reconcile these notions and show that the tension is due to differences in distributions of users where items are relevant, and break down the important factors of the user's recommendations.
no code implementations • NAACL (WOAH) 2022 • Zee Fryer, Vera Axelrod, Ben Packer, Alex Beutel, Jilin Chen, Kellie Webster
A common approach for testing fairness issues in text-based classifiers is through the use of counterfactuals: does the classifier output change if a sensitive attribute in the input is changed?
no code implementations • 4 Jun 2021 • Yuyan Wang, Xuezhi Wang, Alex Beutel, Flavien Prost, Jilin Chen, Ed H. Chi
This presents a multi-dimensional Pareto frontier on (1) the trade-off between group fairness and accuracy with respect to each task, as well as (2) the trade-offs across multiple tasks.
no code implementations • 20 May 2021 • Flavien Prost, Pranjal Awasthi, Nick Blumm, Aditee Kumthekar, Trevor Potter, Li Wei, Xuezhi Wang, Ed H. Chi, Jilin Chen, Alex Beutel
In this work we study the problem of measuring the fairness of a machine learning model under noisy information.
no code implementations • 12 Jan 2021 • Sirui Yao, Yoni Halpern, Nithum Thain, Xuezhi Wang, Kang Lee, Flavien Prost, Ed H. Chi, Jilin Chen, Alex Beutel
Using this simulation framework, we can (a) isolate the effect of the recommender system from the user preferences, and (b) examine how the system performs not just on average for an "average user" but also the extreme experiences under atypical user behavior.
no code implementations • 12 Oct 2020 • Kellie Webster, Xuezhi Wang, Ian Tenney, Alex Beutel, Emily Pitler, Ellie Pavlick, Jilin Chen, Ed Chi, Slav Petrov
Pre-trained models have revolutionized natural language understanding.
no code implementations • EMNLP 2020 • Tianlu Wang, Xuezhi Wang, Yao Qin, Ben Packer, Kang Li, Jilin Chen, Alex Beutel, Ed Chi
Experiments on real-world NLP datasets demonstrate that our method can generate more diverse and fluent adversarial texts, compared to many existing adversarial text generation approaches.
5 code implementations • NeurIPS 2020 • Preethi Lahoti, Alex Beutel, Jilin Chen, Kang Lee, Flavien Prost, Nithum Thain, Xuezhi Wang, Ed H. Chi
Much of the previous machine learning (ML) fairness literature assumes that protected features such as race and sex are present in the dataset, and relies upon them to mitigate fairness concerns.
no code implementations • 5 Nov 2019 • Xuezhi Wang, Nithum Thain, Anu Sinha, Flavien Prost, Ed H. Chi, Jilin Chen, Alex Beutel
In addition to the theoretical results, we find on multiple datasets -- including a large-scale real-world recommender system -- that the overall system's end-to-end fairness is largely achievable by improving fairness in individual components.
no code implementations • 25 Oct 2019 • Flavien Prost, Hai Qian, Qiuwen Chen, Ed H. Chi, Jilin Chen, Alex Beutel
As recent literature has demonstrated how classifiers often carry unintended biases toward some subgroups, deploying machine learned models to users demands careful consideration of the social consequences.
no code implementations • RecSys 2019 • Zhe Zhao, Lichan Hong, Li Wei, Jilin Chen, Aniruddh Nath, Shawn Andrews, Aditee Kumthekar, Maheswaran Sathiamoorthy, Xinyang Yi, Ed Chi
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.
no code implementations • 24 Jun 2019 • Candice Schumann, Xuezhi Wang, Alex Beutel, Jilin Chen, Hai Qian, Ed H. Chi
A model trained for one setting may be picked up and used in many others, particularly as is common with pre-training and cloud APIs.
no code implementations • 2 Mar 2019 • Alex Beutel, Jilin Chen, Tulsee Doshi, Hai Qian, Li Wei, Yi Wu, Lukasz Heldt, Zhe Zhao, Lichan Hong, Ed H. Chi, Cristos Goodrow
Recommender systems are one of the most pervasive applications of machine learning in industry, with many services using them to match users to products or information.
no code implementations • 14 Jan 2019 • Alex Beutel, Jilin Chen, Tulsee Doshi, Hai Qian, Allison Woodruff, Christine Luu, Pierre Kreitmann, Jonathan Bischof, Ed H. Chi
In this paper we provide a case-study on the application of fairness in machine learning research to a production classification system, and offer new insights in how to measure and address algorithmic fairness issues.
9 code implementations • 19 Jul 2018 • Jiaqi Ma, Zhe Zhao, Xinyang Yi, Jilin Chen, Lichan Hong, Ed Chi
In this work, we propose a novel multi-task learning approach, Multi-gate Mixture-of-Experts (MMoE), which explicitly learns to model task relationships from data.
no code implementations • 1 Jul 2017 • Alex Beutel, Jilin Chen, Zhe Zhao, Ed H. Chi
How can we learn a classifier that is "fair" for a protected or sensitive group, when we do not know if the input to the classifier belongs to the protected group?
no code implementations • 26 Feb 2014 • Jalal Mahmud, Jilin Chen, Jeffrey Nichols
We present a study to analyze how word use can predict social engagement behaviors such as replies and retweets in Twitter.