NeurIPS 2023 Workshop SoLaR Submissions

Welfare Diplomacy: Benchmarking Language Model Cooperation
Gabriel Mukobi, Hannah Erlebach, Niklas Lauffer, Lewis Hammond, Alan Chan, Jesse Clifton
- Published: 23 Oct 2023, Last Modified: 28 Nov 2023
- SoLaR Poster
- Readers: Everyone
Reinforcement Learning Fine-tuning of Language Models is Biased Towards More Extractable Features
Diogo Cruz, Edoardo Pona, Alex Holness-Tofts, Elias Schmied, Víctor Abia Alonso, Charlie Griffin, Bogdan-Ionut Cirstea
- Published: 23 Oct 2023, Last Modified: 28 Nov 2023
- SoLaR Poster
- Readers: Everyone
The Effect of Group Status on the Variability of Group Representations in LLM-generated Text
Messi Lee, Jacob Montgomery, Calvin Lai
- Published: 23 Oct 2023, Last Modified: 28 Nov 2023
- SoLaR Poster
- Readers: Everyone
Hazards from Increasingly Accessible Fine-Tuning of Downloadable Foundation Models
Alan Chan, Benjamin Bucknall, Herbie Bradley, David Krueger
- Published: 23 Oct 2023, Last Modified: 28 Nov 2023
- SoLaR Spotlight
- Readers: Everyone
Beyond Reverse KL: Generalizing Direct Preference Optimization with Diverse Divergence Constraints
Chaoqi Wang, Yibo Jiang, Chenghao Yang, Han Liu, Yuxin Chen
- Published: 23 Oct 2023, Last Modified: 28 Nov 2023
- SoLaR Poster
- Readers: Everyone
Low-Resource Languages Jailbreak GPT-4
Zheng Xin Yong, Cristina Menghini, Stephen Bach
- Published: 23 Oct 2023, Last Modified: 28 Nov 2023
- SoLaR Spotlight
- Readers: Everyone
Are Large Language Models Really Robust to Word-Level Perturbations?
Haoyu Wang, Guozheng Ma, Cong Yu, Ning Gui, Linrui Zhang, Zhiqi Huang, Suwei Ma, Yongzhe Chang, Sen Zhang, Li Shen, Xueqian Wang, Peilin Zhao, Dacheng Tao
- Published: 23 Oct 2023, Last Modified: 28 Nov 2023
- SoLaR Poster
- Readers: Everyone
Weakly Supervised Detection of Hallucinations in LLM Activations
Miriam Rateike, Celia Cintas, John Wamburu, Tanya Akumu, Skyler Speakman
- Published: 23 Oct 2023, Last Modified: 28 Nov 2023
- SoLaR Poster
- Readers: Everyone
A Divide-Conquer-Reasoning Approach to Consistency Evaluation and Improvement in Blackbox Large Language Models
Wendi Cui, Jiaxin Zhang, Zhuohang Li, Damien Lopez, Kamalika Das, Bradley Malin, Sricharan Kumar
- Published: 23 Oct 2023, Last Modified: 28 Nov 2023
- SoLaR Poster
- Readers: Everyone
KoMultiText: Large-Scale Korean Text Dataset for Classifying Biased Speech in Real-World Online Services
Dasol Choi, Jooyoung Song, Eunsun Lee, Seo Jin woo, HeeJune Park, Dongbin Na
- Published: 23 Oct 2023, Last Modified: 28 Nov 2023
- SoLaR Poster
- Readers: Everyone