75 citations · 103 across the 17 of their papers we have counts for
17 papers
TARDIS: Mitigating Temporal Misalignment via Representation Steering
Changho Shin, Xinya Yan, Suenggwan Jo +3
Language models often struggle with temporal misalignment, performance degradation caused by shifts in the temporal distribution of data. Continuously updating models to avoid degr…
Personalize Your LLM: Fake it then Align it
Yijing Zhang, Dyah Adila, Changho Shin +1
Personalizing large language models (LLMs) is essential for delivering tailored interactions that improve user experience. Many existing personalization methods require fine-tuning…
Weak-to-Strong Generalization Through the Data-Centric Lens
Changho Shin, John Cooper, Frederic Sala
The weak-to-strong generalization phenomenon is the driver for important machine learning applications including highly data-efficient learning and, most recently, performing super…
Evaluating Language Model Context Windows: A "Working Memory" Test and Inference-time Correction
Amanda Dsouza, Christopher Glaze, Changho Shin +1
Large language models are prominently used in real-world applications, often tasked with reasoning over large volumes of documents. An exciting development in this space is models…
Is Free Self-Alignment Possible?
Dyah Adila, Changho Shin, Yijing Zhang +1
Aligning pretrained language models (LMs) often requires large-scale preference data and substantial computational resources. These costs become even more prohibitive for multi-obj…
OTTER: Effortless Label Distribution Adaptation of Zero-shot Models
Changho Shin, Jitian Zhao, Sonia Cromp +2
Popular zero-shot models suffer due to artifacts inherited from pretraining. One particularly detrimental issue, caused by unbalanced web-scale pretraining data, is mismatched labe…
Multimodal Data Curation via Object Detection and Filter Ensembles
Tzu-Heng Huang, Changho Shin, Sui Jiet Tay +2
We propose an approach for curating multimodal data that we used for our entry in the 2023 DataComp competition filtering track. Our technique combines object detection and weak su…
Zero-Shot Robustification of Zero-Shot Models
Dyah Adila, Changho Shin, Linrong Cai +1
Zero-shot inference is a powerful paradigm that enables the use of large pretrained models for downstream classification tasks without further training. However, these models are v…
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…
Geometry-Aware Adaptation for Pretrained Models
Nicholas Roberts, Xintong Li, Dyah Adila +4
Machine learning models -- including prominent zero-shot models -- are often trained on datasets whose labels are only a small proportion of a larger label space. Such spaces are c…
Mitigating Source Bias for Fairer Weak Supervision
Changho Shin, Sonia Cromp, Dyah Adila +1
Weak supervision enables efficient development of training sets by reducing the need for ground truth labels. However, the techniques that make weak supervision attractive -- such…
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…
Lifting Weak Supervision To Structured Prediction
Harit Vishwakarma, Nicholas Roberts, Frederic Sala
Weak supervision (WS) is a rich set of techniques that produce pseudolabels by aggregating easily obtained but potentially noisy label estimates from a variety of sources. WS is th…
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.…
Promises and Pitfalls of Threshold-based Auto-labeling
Harit Vishwakarma, Heguang Lin, Frederic Sala +1
Creating large-scale high-quality labeled datasets is a major bottleneck in supervised machine learning workflows. Threshold-based auto-labeling (TBAL), where validation data obtai…
AutoML for Climate Change: A Call to Action
Renbo Tu, Nicholas Roberts, Vishak Prasad +7
The challenge that climate change poses to humanity has spurred a rapidly developing field of artificial intelligence research focused on climate change applications. The climate c…