75 citations · 149 across the 17 of their papers we have counts for
17 papers
Olmo 3
Team Olmo, :, Allyson Ettinger +66
We introduce Olmo 3, a family of state-of-the-art, fully-open language models at the 7B and 32B parameter scales. Olmo 3 model construction targets long-context reasoning, function…
Shrinking the Generation-Verification Gap with Weak Verifiers
Jon Saad-Falcon, E. Kelly Buchanan, Mayee F. Chen +9
Verifiers can improve language model capabilities by scoring and ranking responses from generated candidates. Currently, high-quality verifiers are either unscalable (e.g., humans)…
Smoothie: Label Free Language Model Routing
Neel Guha, Mayee F. Chen, Trevor Chow +2
Large language models (LLMs) are increasingly used in applications where LLM inputs may span many different tasks. Recent work has found that the choice of LLM is consequential, an…
Aioli: A Unified Optimization Framework for Language Model Data Mixing
Mayee F. Chen, Michael Y. Hu, Nicholas Lourie +2
Language model performance depends on identifying the optimal mixture of data groups to train on (e.g., law, code, math). Prior work has proposed a diverse set of methods to effici…
Cookbook: A framework for improving LLM generative abilities via programmatic data generating templates
Avanika Narayan, Mayee F. Chen, Kush Bhatia +1
Fine-tuning large language models (LLMs) on instruction datasets is a common way to improve their generative capabilities. However, instruction datasets can be expensive and time-c…
Skill-it! A Data-Driven Skills Framework for Understanding and Training Language Models
Mayee F. Chen, Nicholas Roberts, Kush Bhatia +4
The quality of training data impacts the performance of pre-trained large language models (LMs). Given a fixed budget of tokens, we study how to best select data that leads to good…
Embroid: Unsupervised Prediction Smoothing Can Improve Few-Shot Classification
Neel Guha, Mayee F. Chen, Kush Bhatia +3
Recent work has shown that language models' (LMs) prompt-based learning capabilities make them well suited for automating data labeling in domains where manual annotation is expens…
Resonant Anomaly Detection with Multiple Reference Datasets
Mayee F. Chen, Benjamin Nachman, Frederic Sala
An important class of techniques for resonant anomaly detection in high energy physics builds models that can distinguish between reference and target datasets, where only the latt…
Ask Me Anything: A simple strategy for prompting language models
Simran Arora, Avanika Narayan, Mayee F. Chen +6
Large language models (LLMs) transfer well to new tasks out-of-the-box simply given a natural language prompt that demonstrates how to perform the task and no additional training.…
TABi: Type-Aware Bi-Encoders for Open-Domain Entity Retrieval
Megan Leszczynski, Daniel Y. Fu, Mayee F. Chen +1
Entity retrieval--retrieving information about entity mentions in a query--is a key step in open-domain tasks, such as question answering or fact checking. However, state-of-the-ar…
Perfectly Balanced: Improving Transfer and Robustness of Supervised Contrastive Learning
Mayee F. Chen, Daniel Y. Fu, Avanika Narayan +4
An ideal learned representation should display transferability and robustness. Supervised contrastive learning (SupCon) is a promising method for training accurate models, but prod…
Shoring Up the Foundations: Fusing Model Embeddings and Weak Supervision
Mayee F. Chen, Daniel Y. Fu, Dyah Adila +4
Foundation models offer an exciting new paradigm for constructing models with out-of-the-box embeddings and a few labeled examples. However, it is not clear how to best apply found…
Mandoline: Model Evaluation under Distribution Shift
Mayee Chen, Karan Goel, Nimit S. Sohoni +3
Machine learning models are often deployed in different settings than they were trained and validated on, posing a challenge to practitioners who wish to predict how well the deplo…
Comparing the Value of Labeled and Unlabeled Data in Method-of-Moments Latent Variable Estimation
Mayee F. Chen, Benjamin Cohen-Wang, Stephen Mussmann +2
Labeling data for modern machine learning is expensive and time-consuming. Latent variable models can be used to infer labels from weaker, easier-to-acquire sources operating on un…
Train and You'll Miss It: Interactive Model Iteration with Weak Supervision and Pre-Trained Embeddings
Mayee F. Chen, Daniel Y. Fu, Frederic Sala +5
Our goal is to enable machine learning systems to be trained interactively. This requires models that perform well and train quickly, without large amounts of hand-labeled data. We…
Network disruption: maximizing disagreement and polarization in social networks
Mayee F. Chen, Miklos Z. Racz
Recent years have seen a marked increase in the spread of misinformation, a phenomenon which has been accelerated and amplified by social media such as Facebook and Twitter. While…
Fast and Three-rious: Speeding Up Weak Supervision with Triplet Methods
Daniel Y. Fu, Mayee F. Chen, Frederic Sala +3
Weak supervision is a popular method for building machine learning models without relying on ground truth annotations. Instead, it generates probabilistic training labels by estima…