5 papers
Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
Gemini Team, Petko Georgiev, Ving Ian Lei +1132
In this report, we introduce the Gemini 1.5 family of models, representing the next generation of highly compute-efficient multimodal models capable of recalling and reasoning over…
Conditional Language Policy: A General Framework for Steerable Multi-Objective Finetuning
Kaiwen Wang, Rahul Kidambi, Ryan Sullivan +17
Reward-based finetuning is crucial for aligning language policies with intended behaviors (e.g., creativity and safety). A key challenge is to develop steerable language models tha…
Multi-step Problem Solving Through a Verifier: An Empirical Analysis on Model-induced Process Supervision
Zihan Wang, Yunxuan Li, Yuexin Wu +4
Process supervision, using a trained verifier to evaluate the intermediate steps generated by a reasoner, has demonstrated significant improvements in multi-step problem solving. I…
Enabling Language Models to Implicitly Learn Self-Improvement
Ziqi Wang, Le Hou, Tianjian Lu +4
Large Language Models (LLMs) have demonstrated remarkable capabilities in open-ended text generation tasks. However, the inherent open-ended nature of these tasks implies that ther…
Inducing Generalization across Languages and Tasks using Featurized Low-Rank Mixtures
Chu-Cheng Lin, Xinyi Wang, Jonathan H. Clark +4
Adapting pretrained large language models (LLMs) to various downstream tasks in tens or hundreds of human languages is computationally expensive. Parameter-efficient fine-tuning (P…