NeurIPS 2024 Workshop Pluralistic-Alignment Submissions

Aligning to Thousands of Preferences via System Message Generalization
Seongyun Lee, Sue Hyun Park, Seungone Kim, Minjoon Seo
- Published: 10 Oct 2024, Last Modified: 15 Nov 2024
- Pluralistic-Alignment 2024
- Readers: Everyone
Group Robust Best-of-K Decoding of Language Models for Pluralistic Alignment
Sangwoong Yoon, William Bankes, Seongho Son, Anja Petrovic, Shyam Sundhar Ramesh, Xiaohang Tang, Ilija Bogunovic
- Published: 10 Oct 2024, Last Modified: 15 Nov 2024
- Pluralistic-Alignment 2024
- Readers: Everyone
Multilingual Trolley Problems for Language Models
Zhijing Jin, Max Kleiman-Weiner, Giorgio Piatti, Sydney Levine, Jiarui Liu, Fernando Gonzalez Adauto, Francesco Ortu, András Strausz, Mrinmaya Sachan, Rada Mihalcea, Yejin Choi, Bernhard Schölkopf
- Published: 10 Oct 2024, Last Modified: 15 Nov 2024
- Pluralistic-Alignment 2024
- Readers: Everyone
Can Language Models Reason about Individualistic Human Values and Preferences?
Liwei Jiang, Sydney Levine, Yejin Choi
- Published: 10 Oct 2024, Last Modified: 15 Nov 2024
- Pluralistic-Alignment 2024
- Readers: Everyone
Evaluating the Prompt Steerability of Large Language Models
Erik Miehling, Michael Desmond, Karthikeyan Natesan Ramamurthy, Elizabeth M. Daly, Pierre Dognin, Jesus Rios, Djallel Bouneffouf, Miao Liu
- Published: 10 Oct 2024, Last Modified: 15 Nov 2024
- Pluralistic-Alignment 2024
- Readers: Everyone
Representative Social Choice: From Learning Theory to AI Alignment
Tianyi Qiu
- Published: 10 Oct 2024, Last Modified: 15 Nov 2024
- Pluralistic-Alignment 2024
- Readers: Everyone
Critique-out-Loud Reward Models
Zachary Ankner, Mansheej Paul, Brandon Cui, Jonathan Daniel Chang, Prithviraj Ammanabrolu
- Published: 10 Oct 2024, Last Modified: 15 Nov 2024
- Pluralistic-Alignment 2024
- Readers: Everyone
Being Considerate as a Pathway Towards Pluralistic Alignment for Agentic AI
Parand A. Alamdari, Toryn Q. Klassen, Rodrigo Toro Icarte, Sheila A. McIlraith
- Published: 10 Oct 2024, Last Modified: 15 Nov 2024
- Pluralistic-Alignment 2024
- Readers: Everyone
Pluralistic Alignment Over Time
Toryn Q. Klassen, Parand A. Alamdari, Sheila A. McIlraith
- Published: 10 Oct 2024, Last Modified: 15 Nov 2024
- Pluralistic-Alignment 2024
- Readers: Everyone
Value-Aligned Imitation via focused Satisficing
Rushit N. Shah, Nikolaos Agadakos, Synthia Sasulski, Ali Farajzadeh, Sanjiban Choudhury, Brian D Ziebart
- Published: 10 Oct 2024, Last Modified: 15 Nov 2024
- Pluralistic-Alignment 2024
- Readers: Everyone
Plurals: A system for pluralistic AI via simulated social ensembles
Joshua Ashkinaze, Eric Gilbert, Ceren Budak
- Published: 10 Oct 2024, Last Modified: 15 Nov 2024
- Pluralistic-Alignment 2024
- Readers: Everyone
Mechanism Design for LLM Fine-tuning with Multiple Reward Models
Haoran Sun, Yurong Chen, Siwei Wang, Wei Chen, Xiaotie Deng
- Published: 10 Oct 2024, Last Modified: 15 Nov 2024
- Pluralistic-Alignment 2024
- Readers: Everyone
Diverging Preferences: When do Annotators Disagree and do Models Know?
Michael JQ Zhang, Zhilin Wang, Jena D. Hwang, Yi Dong, Olivier Delalleau, Yejin Choi, Eunsol Choi, Xiang Ren, Valentina Pyatkin
- Published: 10 Oct 2024, Last Modified: 15 Nov 2024
- Pluralistic-Alignment 2024
- Readers: Everyone
MID-Space: Aligning Diverse Communities' Needs to Inclusive Public Spaces
Shravan Nayak, Rashid Mushkani, Hugo Berard, Allison Cohen, Shin Koseki, Hadrien Bertrand
- Published: 10 Oct 2024, Last Modified: 15 Nov 2024
- Pluralistic-Alignment 2024
- Readers: Everyone
Efficacy of the SAGE-RT Dataset for Model Safety Alignment: A Comparative Study
Tanay Baswa, Nitin Aravind Birur, Divyanshu Kumar, Jatan Loya, Anurakt Kumar, Prashanth Harshangi, Sahil Agarwal
- Published: 10 Oct 2024, Last Modified: 15 Nov 2024
- Pluralistic-Alignment 2024
- Readers: Everyone
Policy Aggregation
Parand A. Alamdari, Soroush Ebadian, Ariel D. Procaccia
- Published: 10 Oct 2024, Last Modified: 15 Nov 2024
- Pluralistic-Alignment 2024
- Readers: Everyone
"There are no solutions, only trade-offs.'' Taking A Closer Look At Safety Data Annotations.
Elle Michelle Yang, Matthias Gallé, Seraphina Goldfarb-Tarrant
- Published: 10 Oct 2024, Last Modified: 15 Nov 2024
- Pluralistic-Alignment 2024
- Readers: Everyone
FairPlay: A Collaborative Approach to Mitigate Bias in Datasets for Improved AI Fairness
Tina Behzad, Mithilesh Kumar Singh, Anthony J. Ripa, Klaus Mueller
- Published: 10 Oct 2024, Last Modified: 22 Nov 2024
- Pluralistic-Alignment 2024
- Readers: Everyone
Virtual Personas for Language Models via an Anthology of Backstories
Suhong Moon, Marwa Abdulhai, Minwoo Kang, Joseph Suh, Widyadewi Soedarmadji, Eran Kohen Behar, David Chan
- Published: 10 Oct 2024, Last Modified: 15 Nov 2024
- Pluralistic-Alignment 2024
- Readers: Everyone
Toward Democracy Levels for AI
Aviv Ovadya, Luke Thorburn, Kyle Redman, Flynn Devine, Smitha Milli, Manon Revel, Andrew Konya, Atoosa Kasirzadeh
- Published: 10 Oct 2024, Last Modified: 15 Nov 2024
- Pluralistic-Alignment 2024
- Readers: Everyone
Chain of Alignment: Integrating Public Will with Expert Intelligence for Language Model Alignment
Andrew Konya, Aviv Ovadya, Kevin Feng, Quan Ze Chen, Lisa Schirch, Colin Irwin, Amy X Zhang
- Published: 10 Oct 2024, Last Modified: 15 Nov 2024
- Pluralistic-Alignment 2024
- Readers: Everyone
Intuitions of Compromise: Utilitarianism vs. Contractualism
Jared Moore, Yejin Choi, Sydney Levine
- Published: 10 Oct 2024, Last Modified: 15 Nov 2024
- Pluralistic-Alignment 2024
- Readers: Everyone
Rules, Cases, and Reasoning: Positivist Legal Theory as a Framework for Pluralistic AI Alignment
Nicholas A. Caputo
- Published: 10 Oct 2024, Last Modified: 15 Nov 2024
- Pluralistic-Alignment 2024
- Readers: Everyone
Value Alignment from Unstructured Text
Inkit Padhi, Karthikeyan Natesan Ramamurthy, Prasanna Sattigeri, Manish Nagireddy, Pierre Dognin, Kush R. Varshney
- Published: 10 Oct 2024, Last Modified: 15 Nov 2024
- Pluralistic-Alignment 2024
- Readers: Everyone
Plurality of value pluralism and AI value alignment
Atoosa Kasirzadeh
- Published: 10 Oct 2024, Last Modified: 15 Nov 2024
- Pluralistic-Alignment 2024
- Readers: Everyone