Estimating and Penalizing Induced Preference Shifts in Recommender Systems

25 April 2022

Micah Carroll

Anca Dragan

Stuart J. Russell

Dylan Hadfield-Menell

OffRL

ArXiv PDF HTML

Papers citing "Estimating and Penalizing Induced Preference Shifts in Recommender Systems"

26 / 26 papers shown

Title
MONA: Myopic Optimization with Non-myopic Approval Can Mitigate Multi-step Reward Hacking Sebastian Farquhar Vikrant Varma David Lindner David Elson Caleb Biddulph Ian Goodfellow Rohin Shah 86 1 0 22 Jan 2025
Lookahead Counterfactual Fairness Zhiqun Zuo Tian Xie Xuwei Tan Xueru Zhang Mohammad Mahdi Khalili FaML 80 0 0 02 Dec 2024
ARTAI: An Evaluation Platform to Assess Societal Risk of Recommender Algorithms Qin Ruan Jin Xu Ruihai Dong Arjumand Younus Tai Tan Mai Barry O'Sullivan Susan Leavy 26 0 0 19 Sep 2024
Beyond Preferences in AI Alignment Tan Zhi-Xuan Micah Carroll Matija Franklin Hal Ashton 41 16 0 30 Aug 2024
System-2 Recommenders: Disentangling Utility and Engagement in Recommendation Systems via Temporal Point-Processes Arpit Agarwal Nicolas Usunier A. Lazaric Maximilian Nickel 30 3 0 29 May 2024
Towards Guaranteed Safe AI: A Framework for Ensuring Robust and Reliable AI Systems David Dalrymple Joar Skalse Yoshua Bengio Stuart J. Russell Max Tegmark ... Clark Barrett Ding Zhao Zhi-Xuan Tan Jeannette Wing Joshua Tenenbaum 52 52 0 10 May 2024
Learning under Imitative Strategic Behavior with Unforeseeable Outcomes Tian Xie Zhiqun Zuo Mohammad Mahdi Khalili Xueru Zhang OffRL 38 2 0 03 May 2024
Accounting for AI and Users Shaping One Another: The Role of Mathematical Models Sarah Dean Evan Dong Meena Jagadeesan Liu Leqi 37 6 0 18 Apr 2024
Missing Pieces: How Framing Uncertainty Impacts Longitudinal Trust in AI Decision Aids -- A Gig Driver Case Study Rex Chen Ruiyi Wang Norman M. Sadeh Fei Fang 55 0 0 09 Apr 2024
A Review of Modern Recommender Systems Using Generative Models (Gen-RecSys) Yashar Deldjoo Zhankui He Julian McAuley A. Korikov Scott Sanner Arnau Ramisa René Vidal M. Sathiamoorthy Atoosa Kasirzadeh Silvia Milano VLM 28 40 0 31 Mar 2024
Feedback Loops With Language Models Drive In-Context Reward Hacking Alexander Pan Erik Jones Meena Jagadeesan Jacob Steinhardt KELM 53 26 0 09 Feb 2024
Optimising Human-AI Collaboration by Learning Convincing Explanations Alex J. Chan Alihan Huyuk M. Schaar 37 3 0 13 Nov 2023
Implicit meta-learning may lead language models to trust more reliable sources Dmitrii Krasheninnikov Egor Krasheninnikov Bruno Mlodozeniec Tegan Maharaj David M. Krueger 26 3 0 23 Oct 2023
Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback Stephen Casper Xander Davies Claudia Shi T. Gilbert Jérémy Scheurer ... Erdem Biyik Anca Dragan David M. Krueger Dorsa Sadigh Dylan Hadfield-Menell ALM OffRL 47 473 0 27 Jul 2023
Improved Bayes Risk Can Yield Reduced Social Welfare Under Competition Meena Jagadeesan Michael I. Jordan Jacob Steinhardt Nika Haghtalab 27 11 0 26 Jun 2023
Incentivizing High-Quality Content in Online Recommender Systems Xinyan Hu Meena Jagadeesan Michael I. Jordan Jacob Steinhard 34 10 0 13 Jun 2023
Performative Recommendation: Diversifying Content via Strategic Incentives Itay Eilat Nir Rosenfeld 46 7 0 08 Feb 2023
Understanding or Manipulation: Rethinking Online Performance Gains of Modern Recommender Systems Zhengbang Zhu Rongjun Qin Junjie Huang Xinyi Dai Yang Yu Yong Yu Weinan Zhang 44 2 0 11 Oct 2022
Solutions to preference manipulation in recommender systems require knowledge of meta-preferences Hal Ashton Matija Franklin 13 5 0 14 Sep 2022
Inclusive Ethical Design for Recommender Systems Susan Leavy 17 0 0 13 Sep 2022
Discovering Agents Zachary Kenton Ramana Kumar Sebastian Farquhar Jonathan G. Richens Matt MacDermott Tom Everitt CML 47 31 0 17 Aug 2022
Constrained Reinforcement Learning for Short Video Recommendation Qingpeng Cai Ruohan Zhan Chi Zhang Jie Zheng Guangwei Ding Pinghua Gong Dong Zheng Peng Jiang 20 6 0 26 May 2022
Path-Specific Objectives for Safer Agent Incentives Sebastian Farquhar Ryan Carey Tom Everitt 6 26 0 21 Apr 2022
Explicit User Manipulation in Reinforcement Learning Based Recommender Systems Matthew Sparr OffRL 33 0 0 20 Mar 2022
Measuring Recommender System Effects with Simulated Users Sirui Yao Yoni Halpern Nithum Thain Xuezhi Wang Kang Lee Flavien Prost Ed H. Chi Jilin Chen Alex Beutel 48 49 0 12 Jan 2021
How Algorithmic Confounding in Recommendation Systems Increases Homogeneity and Decreases Utility A. Chaney Brandon M Stewart Barbara E. Engelhardt CML 169 313 0 30 Oct 2017