Learnability in Online Kernel Selection with Memory Constraint via Data-dependent Regret Analysisby Junfan Li, Shizhong…
BAPO: Base-Anchored Preference Optimization for Overcoming Forgetting in Large Language Models Personalizationby Gihun Lee, Minchan…
ProgressGym: Alignment with a Millennium of Moral Progressby Tianyi Qiu, Yang Zhang, Xuchuan Huang, Jasmine…
The Remarkable Robustness of LLMs: Stages of Inference?by Vedang Lad, Wes Gurnee, Max TegmarkFirst submitted…
Averaging log-likelihoods in direct alignmentby Nathan Grinsztajn, Yannis Flet-Berliac, Mohammad Gheshlaghi Azar, Florian Strub, Bill…
A Teacher Is Worth A Million Instructionsby Nikhil Kothari, Ravindra Nayak, Shreyas Shetty, Amey Patil,…
Contrastive Policy Gradient: Aligning LLMs on sequence-level scores in a supervised-friendly fashionby Yannis Flet-Berliac, Nathan…
Decoding-Time Language Model Alignment with Multiple Objectivesby Ruizhe Shi, Yifang Chen, Yushi Hu, Alisa Liu,…
Semi-supervised Concept Bottleneck Modelsby Lijie Hu, Tianhao Huang, Huanyi Xie, Chenyang Ren, Zhengyu Hu, Lu…
Alignment For Performance Improvement in Conversation Botsby Raghav Garg, Kapil Sharma, Shrey SinglaFirst submitted to…