Weijia Shi
NLP researcher at University of Washington; first author of REPLUG and many retrieval-augmented LLM and contamination / detection papers.
- Role
- researcher
- Currently at
- University of Washington
- twitter.com/WeijiaShi2
- GitHub
- github.com/swj0419
- Scholar
- scholar.google.com/citations
- Papers
- 21
Cite
Notes
Only stored in your browser.
Authored papers
21s1: Simple Test-Time Scaling
preprint
On the Trustworthiness of Generative Foundation Models: Guideline, Assessment, and Perspective
arXiv 2025
FlexOlmo: Open Language Models for Flexible Data Use
arXiv 2025
UQ: Assessing Language Models on Unsolved Questions
arXiv 2025
OLMoE: Open Mixture-of-Experts Language Models
arXiv 2024
OpenScholar: Synthesizing Scientific Literature with Retrieval-augmented LMs
arXiv 2024
Scaling Retrieval-Based Language Models with a Trillion-Token Datastore
arXiv 2024
MMed-RAG: Versatile Multimodal RAG System for Medical Vision Language Models
arXiv 2024
Do Membership Inference Attacks Work on Large Language Models?
arXiv 2024
Negative Token Merging: Image-based Adversarial Feature Guidance
arXiv 2024
Instruction-tuned Language Models are Better Knowledge Learners
arXiv 2024
Scaling Expert Language Models with Unsupervised Domain Discovery
arXiv 2023
SILO Language Models: Isolating Legal Risk In a Nonparametric Datastore
arXiv 2023
In-context Pretraining: Language Modeling Beyond Document Boundaries
arXiv 2023
Lemur: Harmonizing Natural Language and Code for Language Agents
arXiv 2023
RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentation
arXiv 2023
Knowledge Card: Filling LLMs' Knowledge Gaps with Plug-in Specialized Language Models
arXiv 2023
One Embedder, Any Task: Instruction-Finetuned Text Embeddings
arXiv 2022
PromptCap: Prompt-Guided Task-Aware Image Captioning
arXiv 2022
Selective Annotation Makes Language Models Better Few-Shot Learners
arXiv 2022
Nonparametric Masked Language Modeling
arXiv 2022
Affiliations
Frequent co-authors
10from 21 papers
Luke Zettlemoyer
professor
Noah A. Smith
Hannaneh Hajishirzi
professor
Sewon Min
Pang Wei Koh
Wen-tau Yih
Mike Lewis
Niklas Muennighoff
grad-student
Hongjin Su
Huaxiu Yao