Results 291 to 300 of about 5,543,464 (336)

Gender and User Feedback: An Exploratory Study

2019 IEEE 27th International Requirements Engineering Conference (RE), 2019
Through app stores, users can submit feedback in the form of user reviews. Previous work has found that these reviews contain useful information such as user requirements and bug reports; and has presented approaches for automatically extracting this information.
Guzman, Emitza, Paredes Rojas, Andres
openaire   +1 more source

Personalized Language Modeling from Personalized Human Feedback

arXiv.org
Personalized large language models (LLMs) are designed to tailor responses to individual user preferences. While Reinforcement Learning from Human Feedback (RLHF) is a commonly used framework for aligning LLMs with human preferences, vanilla RLHF assumes
Xinyu Li, Z. Lipton, Liu Leqi
semanticscholar   +1 more source

No Explainability without Accountability: An Empirical Study of Explanations and Feedback in Interactive ML

International Conference on Human Factors in Computing Systems, 2020
Automatically generated explanations of how machine learning (ML) models reason can help users understand and accept them. However, explanations can have unintended consequences: promoting over-reliance or undermining trust.
Alison Smith-Renner, Ron Fan, M. Birchfield, Tongshuang Sherry Wu, Jordan L. Boyd-Graber, Daniel S. Weld, Leah Findlater   +6 more
semanticscholar   +1 more source

On Targeted Manipulation and Deception when Optimizing LLMs for User Feedback

International Conference on Learning Representations
As LLMs become more widely deployed, there is increasing interest in directly optimizing for feedback from end users (e.g. thumbs up) in addition to feedback from paid annotators.
Marcus Williams, Micah Carroll, Adhyyan Narang, C. Weisser, Brendan P. Murphy, Anca Dragan   +5 more
semanticscholar   +1 more source

Feedback in the K-user interference channel

2012 IEEE International Symposium on Information Theory Proceedings, 2012
We consider the scalar K-user Gaussian interference channel (IC) with feedback, where channel coefficients are fixed over time and frequency. We focus on two feedback models: (1) each receiver feeds back its received signal to all the transmitters and (2) functions of the received signals are fed back through a backward IC.
Dimitris S. Papailiopoulos, Changho Suh, Alexandros G. Dimakis   +2 more
openaire   +1 more source

Getting User Feedback

2012
One of the main reasons the Web has revolutionized working life and communications is its immediacy. Unlike printed media, websites can be continually updated at relatively minimal cost and also be available worldwide on a 24/7 basis. However, communication isn’t one-way, and the Web makes it very easy to enable site users to offer feedback.
Craig Grannell, Victor Sumner, Dionysios Synodinos   +2 more
openaire   +1 more source

Adaptive OCR with limited user feedback

Eighth International Conference on Document Analysis and Recognition (ICDAR'05), 2005
A methodology is proposed for processing noisy printed documents with limited user feedback. Without the support of ground truth, a specific collection of scanned documents can be processed to extract character templates. The adaptiveness of this approach lies in that the extracted templates are used to train an OCR classifier quickly and with limited ...
Huanfeng Ma, David S. Doermann
openaire   +1 more source

WildFeedback: Aligning LLMs With In-situ User Interactions And Feedback

arXiv.org
As large language models (LLMs) continue to advance, aligning these models with human preferences has emerged as a critical challenge. Traditional alignment methods, relying on human or LLM annotated datasets, are limited by their resource-intensive ...
Taiwei Shi, Zhuoer Wang, Longqi Yang, Ying-Chun Lin, Zexue He, Mengting Wan, Pei Zhou, S. Jauhar, Xiaofeng Xu, Xia Song, Jennifer Neville   +10 more
semanticscholar   +1 more source

Failure Feedback for User Obligation Systems

2010 IEEE Second International Conference on Social Computing, 2010
In recent years, several researchers have proposed techniques for providing users with assistance in understanding and overcoming authorization denials. The incorporation of environmental factors into authorization decisions has made this particularly important and challenging.
Murillo Pontual, Keith Irwin, Omar Chowdhury, William H. Winsborough, Ting Yu 0001   +4 more
openaire   +1 more source

User Feedback and Preferences Mining

2012
In this paper, we present our vision and some initial experiments on how to anticipate significance, similarity or polarity of various types of (preferably implicit) user feedback and how to form individual user preference for recommendation. Throughout the corporate web, we can observe the same patterns or actions in user behavior (e.g.
openaire   +1 more source