8 citations · 27 across the 14 of their papers we have counts for
9 papers · 1 filter
Establishing Task Scaling Laws via Compute-Efficient Model Ladders
Akshita Bhagia, Jiacheng Liu, Alexander Wettig +9
We develop task scaling laws and model ladders to predict the individual task performance of pretrained language models (LMs) in the overtrained setting. Standard power laws for la…
Tulu 3: Pushing Frontiers in Open Language Model Post-Training
Nathan Lambert, Jacob Morrison, Valentina Pyatkin +20
Language model post-training is applied to refine behaviors and unlock new skills across a wide range of recent language models, but open recipes for applying these techniques lag…
ComPO: Community Preferences for Language Model Personalization
Sachin Kumar, Chan Young Park, Yulia Tsvetkov +2
Conventional algorithms for training language models (LMs) with human feedback rely on preferences that are assumed to account for an "average" user, disregarding subjectivity and…
Merge to Learn: Efficiently Adding Skills to Language Models with Model Merging
Jacob Morrison, Noah A. Smith, Hannaneh Hajishirzi +3
Adapting general-purpose language models to new skills is currently an expensive process that must be repeated as new instruction datasets targeting new skills are created, or can…
Hybrid Preferences: Learning to Route Instances for Human vs. AI Feedback
Lester James V. Miranda, Yizhong Wang, Yanai Elazar +6
Learning from human feedback has enabled the alignment of language models (LMs) with human preferences. However, collecting human preferences is expensive and time-consuming, with…
Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models
Matt Deitke, Christopher Clark, Sangho Lee +47
Today's most advanced vision-language models (VLMs) remain proprietary. The strongest open-weight models rely heavily on synthetic data from proprietary VLMs to achieve good perfor…
The Art of Saying No: Contextual Noncompliance in Language Models
Faeze Brahman, Sachin Kumar, Vidhisha Balachandran +11
Chat-based language models are designed to be helpful, yet they should not comply with every user request. While most existing work primarily focuses on refusal of "unsafe" queries…
Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference Feedback
Hamish Ivison, Yizhong Wang, Jiacheng Liu +6
Learning from preference feedback has emerged as an essential step for improving the generation quality and performance of modern language models (LMs). Despite its widespread use,…
RewardBench: Evaluating Reward Models for Language Modeling
Nathan Lambert, Valentina Pyatkin, Jacob Morrison +9
Reward models (RMs) are at the crux of successfully using RLHF to align pretrained models to human preferences, yet there has been relatively little study that focuses on evaluatio…