0

Yizhong Wang

UW PhD and AI2 researcher; lead author of Self-Instruct, Tulu, and Tulu 2; foundational figure in open instruction tuning.

Role
researcher
Papers
19

Cite

Notes

Only stored in your browser.

19papers

Authored papers

19

Interactive Evaluation Requires a Design Science

arXiv 2026

2026

Rubrics as an Attack Surface: Stealthy Preference Drift in LLM Judges

arXiv 2026

2026

EvalTree: Profiling Language Model Weaknesses via Hierarchical Capability Trees

arXiv 2025

2025

Tulu 3: Pushing Frontiers in Open Language Model Post-Training

preprint

2024

OLMo: Accelerating the Science of Language Models

arXiv 2024

2024

Tuning Language Models by Proxy

arXiv 2024

2024

Retrieval Head Mechanistically Explains Long-Context Factuality

arXiv 2024

2024

Hybrid Preferences: Learning to Route Instances for Human vs. AI Feedback

arXiv 2024

2024

Evaluating Language Models as Synthetic Data Generators

arXiv 2024

2024

HREF: Human Response-Guided Evaluation of Instruction Following in Language Models

arXiv 2024

2024

Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection

arXiv 2023

2023

Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging

arXiv 2023

2023

BTR: Binary Token Representations for Efficient Retrieval Augmented Language Models

arXiv 2023

2023

TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering

ICCV 2023 1

2023

Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks

arXiv 2022

2022

Self-Instruct: Aligning Language Models with Self-Generated Instructions

arXiv 2022

2022

One Embedder, Any Task: Instruction-Finetuned Text Embeddings

arXiv 2022

2022

Probing Across Time: What Does RoBERTa Know and When?

Findings (EMNLP) 2021 11

2021

Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamics

EMNLP 2020 11

2020

Affiliations

Currently at

Allen Institute for AI (Ai2)

researcher · non profit

Frequent co-authors

10

from 19 papers