English
Related papers

Related papers: Where Not to Learn: Prior-Aligned Training with Su…

200 papers

Decision-making problems often feature uncertainty stemming from heterogeneous and context-dependent human preferences. To address this, we propose a sequential learning-and-optimization pipeline to learn preference distributions and…

Machine Learning · Computer Science 2026-03-19 Benjamin Hudson , Laurent Charlin , Emma Frejinger

Trained classification models can unintentionally lead to biased representations and predictions, which can reinforce societal preconceptions and stereotypes. Existing debiasing methods for classification models, such as adversarial…

Computation and Language · Computer Science 2021-09-23 Aili Shen , Xudong Han , Trevor Cohn , Timothy Baldwin , Lea Frermann

Learning useful representations with little or no supervision is a key challenge in artificial intelligence. We provide an in-depth review of recent advances in representation learning with a focus on autoencoder-based models. To organize…

Machine Learning · Computer Science 2018-12-13 Michael Tschannen , Olivier Bachem , Mario Lucic

Personalized alignment from preference data has focused primarily on improving personal reward model (RM) accuracy, with the implicit assumption that better preference ranking translates to better personalized behavior. However, in…

Artificial Intelligence · Computer Science 2026-01-09 Fady Rezk , Yuangang Pan , Chuan-Sheng Foo , Xun Xu , Nancy Chen , Henry Gouk , Timothy Hospedales

Our goal is for agents to optimize the right reward function, despite how difficult it is for us to specify what that is. Inverse Reinforcement Learning (IRL) enables us to infer reward functions from demonstrations, but it usually assumes…

Machine Learning · Computer Science 2019-06-25 Rohin Shah , Noah Gundotra , Pieter Abbeel , Anca D. Dragan

The idealization of a static machine-learned model, trained once and deployed forever, is not practical. As input distributions change over time, the model will not only lose accuracy, any constraints to reduce bias against a protected…

Machine Learning · Computer Science 2022-06-15 Abdulaziz A. Almuzaini , Chidansh A. Bhatt , David M. Pennock , Vivek K. Singh

The utility of reinforcement learning is limited by the alignment of reward functions with the interests of human stakeholders. One promising method for alignment is to learn the reward function from human-generated preferences between…

Machine Learning · Computer Science 2023-09-08 W. Bradley Knox , Stephane Hatgis-Kessell , Serena Booth , Scott Niekum , Peter Stone , Alessandro Allievi

Attribution methods provide an insight into the decision-making process of machine learning models, especially deep neural networks, by assigning contribution scores to each individual feature. However, the attribution problem has not been…

Machine Learning · Computer Science 2023-02-28 Huiqi Deng , Na Zou , Mengnan Du , Weifu Chen , Guocan Feng , Xia Hu

Foundation models in healthcare have largely adopted self supervised pretraining objectives inherited from natural language processing and computer vision, emphasizing reconstruction and large scale representation learning prior to…

Machine Learning · Computer Science 2026-03-24 Yang Zhang , Li Fan , Samuel Lawrence , Shi Li

Retrieval-augmented generation promises to ground language model outputs in external evidence, yet the field has no reliable way to verify whether retrieved context actually governs generation -- a prerequisite for any high-stakes…

Artificial Intelligence · Computer Science 2026-05-27 Zhe Yu , Wenpeng Xing , Yunzhao Wei , Bo Yang , Chen Ye , Gaolei Li , Meng Han

Despite the rapid development and great success of machine learning models, extensive studies have exposed their disadvantage of inheriting latent discrimination and societal bias from the training data. This phenomenon hinders their…

Machine Learning · Computer Science 2021-12-30 Tianxiang Zhao , Enyan Dai , Kai Shu , Suhang Wang

Value alignment is the task of creating autonomous systems whose values align with those of humans. Past work has shown that stories are a potentially rich source of information on human values; however, past work has been limited to…

Computation and Language · Computer Science 2022-12-13 Md Sultan Al Nahian , Spencer Frazier , Brent Harrison , Mark Riedl

Large language models (LLMs) sometimes fail to respond appropriately to deterministic tasks -- such as counting or forming acronyms -- because the implicit prior distribution they have learned over sequences of tokens influences their…

Computation and Language · Computer Science 2025-04-18 Liyi Zhang , Veniamin Veselovsky , R. Thomas McCoy , Thomas L. Griffiths

Classical supervised learning produces unreliable models when training and target distributions differ, with most existing solutions requiring samples from the target domain. We propose a proactive approach which learns a relationship in…

Machine Learning · Statistics 2019-03-01 Adarsh Subbaswamy , Peter Schulam , Suchi Saria

Deep neural networks have achieved state of the art accuracy at classifying molecules with respect to whether they bind to specific protein targets. A key breakthrough would occur if these models could reveal the fragment pharmacophores…

Machine Learning · Computer Science 2020-02-12 Kevin McCloskey , Ankur Taly , Federico Monti , Michael P. Brenner , Lucy Colwell

Automated optimization modeling via Large Language Models (LLMs) has emerged as a promising approach to assist complex human decision-making. While post-training has become a pivotal technique to enhance LLMs' capabilities in this domain,…

Machine Learning · Computer Science 2026-02-13 Weiting Liu , Han Wu , Yufei Kuang , Xiongwei Han , Tao Zhong , Jianfeng Feng , Wenlian Lu

Modern large language models (LLMs) are typically trained and deployed using structured role tags (e.g. system, user, assistant, tool) that explicitly mark the source of each piece of context. While these tags are essential for instruction…

Computation and Language · Computer Science 2026-04-21 Xu Pan , Jingxuan Fan , Zidi Xiong , Ely Hahami , Jorin Overwiening , Ziqian Xie

Neural networks have proven successful at learning from complex data distributions by acting as universal function approximators. However, they are often overconfident in their predictions, which leads to inaccurate and miscalibrated…

Machine Learning · Computer Science 2021-02-23 Jeffrey Willette , Juho Lee , Sung Ju Hwang

Automatically assigning tasks to people is challenging because human performance can vary across tasks for many reasons. This challenge is further compounded in real-life settings in which no oracle exists to assess the quality of human…

Human-Computer Interaction · Computer Science 2023-06-01 Vijay Keswani , L. Elisa Celis , Krishnaram Kenthapadi , Matthew Lease

For protein sequence datasets, unlabeled data has greatly outpaced labeled data due to the high cost of wet-lab characterization. Recent deep-learning approaches to protein prediction have shown that pre-training on unlabeled data can yield…

Machine Learning · Computer Science 2020-12-02 Pascal Sturmfels , Jesse Vig , Ali Madani , Nazneen Fatema Rajani