NeurIPS 2023 Workshop SoLaR Submissions

Forbidden Facts: An Investigation of Competing Objectives in Llama 2
Tony Wang, Miles Kai, Kaivalya Hariharan, Nir Shavit
- Published: 23 Oct 2023, Last Modified: 28 Nov 2023
- SoLaR Poster
- Readers: Everyone
Investigating the Fairness of Large Language Models for Predictions on Tabular Data
Yanchen Liu, Srishti Gautam, Jiaqi Ma, Himabindu Lakkaraju
- Published: 23 Oct 2023, Last Modified: 28 Nov 2023
- SoLaR Poster
- Readers: Everyone
Using Chain-of-Thought Prompting for Interpretable Recognition of Social Bias
Jacob-Junqi Tian, Omkar Dige, D. Emerson, Faiza Khattak
- Published: 23 Oct 2023, Last Modified: 28 Nov 2023
- SoLaR Poster
- Readers: Everyone
Towards Auditing Large Language Models: Improving Text-based Stereotype Detection
Zekun Wu, Sahan Bulathwela, Adriano Koshiyama
- Published: 23 Oct 2023, Last Modified: 28 Nov 2023
- SoLaR Poster
- Readers: Everyone
The Empty Signifier Problem: Towards Clearer Paradigms for Operationalising "Alignment'' in Large Language Models
Hannah Kirk, Bertie Vidgen, Paul Rottger, Scott Hale
- Published: 23 Oct 2023, Last Modified: 28 Nov 2023
- SoLaR Poster
- Readers: Everyone
A collection of principles for guiding and evaluating large language models
Konstantin Hebenstreit, Robert Praas, Matthias Samwald
- Published: 23 Oct 2023, Last Modified: 28 Nov 2023
- SoLaR Poster
- Readers: Everyone
Evaluating Superhuman Models with Consistency Checks
Lukas Fluri, Daniel Paleka, Florian Tramèr
- Published: 23 Oct 2023, Last Modified: 28 Nov 2023
- SoLaR Spotlight
- Readers: Everyone
Prompt Risk Control: A Rigorous Framework for Responsible Deployment of Large Language Models
Thomas Zollo, Todd Morrill, Zhun Deng, Jake Snell, Toniann Pitassi, Richard Zemel
- Published: 23 Oct 2023, Last Modified: 28 Nov 2023
- SoLaR Poster
- Readers: Everyone
Compositional preference models for alignment with scalable oversight
Dongyoung Go, Tomasz Korbak, Germàn Kruszewski, Jos Rozen, Marc Dymetman
- Published: 23 Oct 2023, Last Modified: 28 Nov 2023
- SoLaR Spotlight
- Readers: Everyone
Bayesian low-rank adaptation for large language models
Adam Yang, Maxime Robeyns, Xi Wang, Laurence Aitchison
- Published: 23 Oct 2023, Last Modified: 28 Nov 2023
- SoLaR Spotlight
- Readers: Everyone
Language Model Detectors Are Easily Optimized Against
Charlotte Nicks, Eric Mitchell, Rafael Rafailov, Archit Sharma, Christopher Manning, Chelsea Finn, Stefano Ermon
- Published: 23 Oct 2023, Last Modified: 28 Nov 2023
- SoLaR Poster
- Readers: Everyone
Learning Inner Monologue and Its Utilization in Vision-Language Challenges
Diji Yang, Kezhen Chen, Jinmeng Rao, Xiaoyuan Guo, Yawen Zhang, Jie Yang, Yi Zhang
- Published: 23 Oct 2023, Last Modified: 28 Nov 2023
- SoLaR Poster
- Readers: Everyone
User Inference Attacks on LLMs
Nikhil Kandpal, Krishna Pillutla, Alina Oprea, Peter Kairouz, Christopher Choquette-Choo, Zheng Xu
- Published: 23 Oct 2023, Last Modified: 28 Nov 2023
- SoLaR Poster
- Readers: Everyone
An International Consortium for AI Risk Evaluations
Ross Gruetzemacher, Alan Chan, Štěpán Los, Kevin Frazier, Siméon Campos, Matija Franklin, James Fox, Jose Hernandez-Orallo, Christin Manning, Philip Tomei, Kyle Kilian
- Published: 23 Oct 2023, Last Modified: 28 Nov 2023
- SoLaR Poster
- Readers: Everyone
Scalable and Transferable Black-Box Jailbreaks for Language Models via Persona Modulation
Rusheb Shah, Quentin Feuillade Montixi, Soroush Pour, Arush Tagade, Javier Rando
- Published: 23 Oct 2023, Last Modified: 28 Nov 2023
- SoLaR Poster
- Readers: Everyone
Subtle Misogyny Detection and Mitigation: An Expert-Annotated Dataset
Anna Richter, Brooklyn Sheppard, Allison Cohen, Elizabeth Smith, Tamara Kneese, Carolyne Pelletier, Ioana Baldini, Yue Dong
- Published: 23 Oct 2023, Last Modified: 28 Nov 2023
- SoLaR Spotlight
- Readers: Everyone
Developing A Conceptual Framework for Analyzing People in Unstructured Data
Mark Diaz, Sunipa Dev, Emily Reif, Emily Denton, Vinodkumar Prabhakaran
- Published: 23 Oct 2023, Last Modified: 28 Nov 2023
- SoLaR Poster
- Readers: Everyone
Linear Latent World Models in Simple Transformers: A Case Study on Othello-GPT
Dean Hazineh, Zechen Zhang, Jeffrey Chiu
- Published: 23 Oct 2023, Last Modified: 28 Nov 2023
- SoLaR Poster
- Readers: Everyone
Measuring Feature Sparsity in Language Models
Mingyang Deng, Lucas Tao, Joe Benton
- Published: 23 Oct 2023, Last Modified: 28 Nov 2023
- SoLaR Spotlight
- Readers: Everyone
Risk Assessment and Statistical Significance in the Age of Foundation Models
Apoorva Nitsure, Youssef Mroueh, Mattia Rigotti, Kristjan Greenewald, Brian Belgodere, Mikhail Yurochkin, Jiri Navratil, Igor Melnyk, Jarret Ross
- Published: 23 Oct 2023, Last Modified: 28 Nov 2023
- SoLaR Poster
- Readers: Everyone
Social Contract AI: Aligning AI Assistants with Implicit Group Norms
Jan-Philipp Fränken, Samuel Kwok, Peixuan Ye, Kanishk Gandhi, Dilip Arumugam, Jared Moore, Alex Tamkin, Tobias Gerstenberg, Noah Goodman
- Published: 23 Oct 2023, Last Modified: 28 Nov 2023
- SoLaR Spotlight
- Readers: Everyone
Citation: A Key to Building Responsible and Accountable Large Language Models
Jie Huang, Kevin Chang
- Published: 23 Oct 2023, Last Modified: 28 Nov 2023
- SoLaR Poster
- Readers: Everyone
Do Personality Tests Generalize to Large Language Models?
Florian Dorner, Tom Sühr, Samira Samadi, Augustin Kelava
- Published: 23 Oct 2023, Last Modified: 28 Nov 2023
- SoLaR Poster
- Readers: Everyone
Dissecting Large Language Models
Nicky Pochinkov, Nandi Schoots
- Published: 23 Oct 2023, Last Modified: 28 Nov 2023
- SoLaR Poster
- Readers: Everyone
Controlled Decoding from Language Models
Sidharth Mudgal, Jong Lee, Harish Ganapathy, YaGuang Li, Tao Wang, Yanping Huang, Zhifeng Chen, Heng-Tze Cheng, Michael Collins, Jilin Chen, Alex Beutel, Ahmad Beirami
- Published: 23 Oct 2023, Last Modified: 28 Nov 2023
- SoLaR Spotlight
- Readers: Everyone