DY

Diyi Yang

0000-0003-1220-3983

cs.CLcs.AIcs.HCcs.LGcs.CYcs.SIcs.CVcs.SEcs.CRcs.IR

On Valency

published · living versions

Deep Personalization: Continuous Context Observation for Local Proactive Agents

with Yijia Shao, Song Bian, Junxian Guo, Jindong Jiang +3

1 version

W_s6utu6y2v1 · current

SAFE-Teen: Evaluating Chatbot Safety Across Adolescent Mental Health Conversations

W_24jwa5nmv1

Lost in Translation: Investigating Systematic Discrepancies between Parallel English and Chinese Names of American Chinese Restaurants

W_bwbb2w98v1

Preprints & journals

214 papers in the corpus · 2017–2026

Articulation Upper Bounds for Language Models

Alexander Spangher, Daniel E. Ho, Diyi Yang et al.

0 citations

2610.19721v12026arXiv

Sherpa: Teaching LLMs to Teach Adaptively

Weixian Xu, Yanzhe Zhang, Zora Zhiruo Wang et al.

0 citations

2610.08778v12026arXiv

Verifiable, Articulable, and Tacit Components of Preference

Alexander Spangher, Sheldon S. Huang, Andreas Haupt et al.

0 citations

2610.03025v22026arXiv

Emergent Collusion in Long-Horizon LLM Agent Interaction

Xinrui Shi, Yanzhe Zhang, Diyi Yang

0 citations

2609.24967v22026arXiv

LLMs as Oracles: Reliance on LLMs for Subjective Personal Questions

Myra Cheng, Lujain Ibrahim, Grace Liu et al.

0 citations

2609.14849v12026arXiv

When Does AI Augment Work? A Workflow-Level Framework for Human-Agent Collaboration

Jiaying Wu, Caleb Ziems, Raymond Chan et al.

0 citations

2609.12482v12026arXiv

Living with AI Companions: Sustained AI Companionship Predicts Lower Well-Being Through Lower Human Interaction

Yutong Zhang, Dora Zhao, Yixin Wang et al.

0 citations

2609.07243v32026arXiv

Efficient Test-Time Adaptation through Human-AI Interaction

Zora Zhiruo Wang, Apurva Gandhi, Rulin Shao et al.

0 citations

2609.04141v12026arXiv

Inducing Task Models from Computer-Use Traces

Yucheng Jiang, Zora Zhiruo Wang, Ruishi Chen et al.

0 citations

2608.20319v12026arXiv

Do Language Models Consistently Encode the Current Year?

Suze van Adrichem, Aditi Bhaskar, Diyi Yang et al.

0 citations

2608.15507v12026arXiv

Interaction with AI companions and psychological well-being.

Zhang, Yutong, Zhao, Dora, Hancock, Jeffrey T et al.

9 citations

425523932026Nature human behaviour. 2026

The Illusion of Robustness: Aggregate Accuracy Hides Prediction Flips under Task-Irrelevant Context

Yanzhe Zhang, Sanmi Koyejo, Diyi Yang

0 citations

2607.12963v22026arXiv

FaciliTrain: Practicing Facilitation Skills through AI-Simulated Group Dialogue

Hang Jiang, Yuanxin Zhu, Diyi Yang et al.

0 citations

2607.10850v12026arXiv

Humans are Missing from AI Coding Agent Research

Zora Z. Wang, John Yang, Kilian Lieret et al.

0 citations

2608.12355v12026arXiv

Will Scaling Improve Social Simulation with LLMs?

Caleb Ziems, William Held, Su Doga Karaca et al.

0 citations

2607.02464v22026arXiv

A reporting checklist for large language models in behavioural science.

Feuerriegel, Stefan, Barrie, Christopher, Crockett, M J et al.

16 citations

422653312026Nature human behaviour. 2026;10(7):1182-1186

Warning labels shift perceptions of sycophantic AI, but not its influence

Lujain Ibrahim, Myra Cheng, Cinoo Lee et al.

0 citations

2606.21317v22026arXiv

SkillHarm: Lifecycle-Aware Skill-Based Attacks via Automated Construction

Yuting Ning, Zhehao Zhang, Yash Kumar Lal et al.

0 citations

2606.02540v22026arXiv

Offloading Score: Measuring AI Reliance Through Counterfactual Workflows

Vishakh Padmakumar, Lujain Ibrahim, Zora Zhiruo Wang et al.

0 citations

2605.29392v12026arXiv

Sycophantic AI makes human interaction feel more effortful and less satisfying over time

Lujain Ibrahim, Franziska Sofia Hafner, Myra Cheng et al.

1 citation

2605.07912v32026arXiv

SecureForge: Finding and Preventing Vulnerabilities in LLM-Generated Code via Prompt Optimization

Houjun Liu, Lisa Einstein, John Yang et al.

0 citations

2605.08382v12026arXiv

Reflections and New Directions for Human-Centered Large Language Models

Caleb Ziems, Dora Zhao, Rose E. Wang et al.

0 citations

2605.06901v12026arXiv

ProgramBench: Can Language Models Rebuild Programs From Scratch?

John Yang, Kilian Lieret, Jeffrey Ma et al.

0 citations

2605.03546v12026arXiv

SWE-chat: Coding Agent Interactions From Real Users in the Wild

Joachim Baumann, Vishakh Padmakumar, Xiang Li et al.

0 citations

2604.20779v22026arXiv

Putting HUMANS first: Efficient LAM Evaluation with Human Preference Alignment

Woody Haosheng Gan, William Held, Diyi Yang

0 citations

2605.00022v22026arXiv

CollabSkill: Evaluating Human-Agent Collaboration On Real-World Tasks

Yijia Shao, Zora Zhiruo Wang, Neel Ahuja et al.

0 citations

2606.09833v22026arXiv

HorizonBench: Long-Horizon Personalization with Evolving Preferences

Shuyue Stella Li, Bhargavi Paranjape, Kerem Oktar et al.

0 citations

2604.17283v12026arXiv

Generative Experiences for Digital Mental Health Interventions: Evidence from a Randomized Study

Ananya Bhattacharjee, Michael Liut, Matthew Jorke et al.

0 citations

2604.07558v32026arXiv

Behavior Latticing: Inferring User Motivations from Unstructured Interactions

Dora Zhao, Michelle S. Lam, Diyi Yang et al.

0 citations

2604.07629v12026arXiv

Verbalizing LLMs' assumptions to explain and control sycophancy

Myra Cheng, Isabel Sieh, Humishka Zope et al.

1 citation

2604.03058v32026arXiv

Whose Knowledge Counts? Co-Designing Community-Centered AI Auditing Tools with Educators in Hawai`i

Dora Zhao, Hannah Cha, Michael J. Ryan et al.

1 citation

2603.16646v12026arXiv

Practicing with Language Models Cultivates Human Empathic Communication

Aakriti Kumar, Nalin Poungpeth, Diyi Yang et al.

0 citations

2603.15245v22026arXiv

The Unlearning Mirage: A Dynamic Framework for Evaluating LLM Unlearning

Raj Sanjay Shah, Jing Huang, Keerthiram Murugesan et al.

0 citations

2603.11266v12026arXiv

Learning Next Action Predictors from Human-Computer Interaction

Omar Shaikh, Valentin Teutschbein, Kanishk Gandhi et al.

1 citation

2603.05923v12026arXiv

Contextualized Privacy Defense for LLM Agents

Yule Wen, Yanzhe Zhang, Jianxun Lian et al.

0 citations

2603.02983v12026arXiv

How Well Does Agent Development Reflect Real-World Work?

Zora Zhiruo Wang, Sanidhya Vijayvargiya, Aspen Chen et al.

1 citation

2603.01203v22026arXiv

Scaling Open Discrete Audio Foundation Models with Interleaved Semantic, Acoustic, and Text Tokens

Potsawee Manakul, Woody Haosheng Gan, Martijn Bartelds et al.

0 citations

2602.16687v12026arXiv

HumanLM: Simulating Users with State Alignment Beats Response Imitation

Shirley Wu, Evelyn Choi, Arpandeep Khatua et al.

0 citations

2603.03303v12026arXiv

Towards Execution-Grounded Automated AI Research

Chenglei Si, Zitong Yang, Yejin Choi et al.

0 citations

2601.14525v12026arXiv

CooperBench: Why Coding Agents Cannot be Your Teammates Yet

Arpandeep Khatua, Hao Zhu, Peter Tran et al.

0 citations

2601.13295v22026arXiv

DECEPTICON: How Dark Patterns Manipulate Web Agents

Phil Cuvin, Hao Zhu, Diyi Yang

0 citations

2512.22894v22025arXiv

AutoMetrics: Approximate Human Judgements with Automatically Generated Evaluators

Michael J. Ryan, Yanzhe Zhang, Amol Salunkhe et al.

0 citations

2512.17267v12025arXiv

Real-Time Reasoning Agents in Evolving Environments

Yule Wen, Yixin Ye, Yanzhe Zhang et al.

0 citations

2511.04898v12025arXiv

CodeClash: Benchmarking Goal-Oriented Software Engineering

John Yang, Kilian Lieret, Joyce Yang et al.

0 citations

2511.00839v22025arXiv

Culture Cartography: Mapping the Landscape of Cultural Knowledge

Caleb Ziems, William Held, Jane Yu et al.

1 citation

2510.27672v12025arXiv

ReplicationBench: Can AI Agents Replicate Astrophysics Research Papers?

Christine Ye, Sihan Yuan, Suchetha Cooray et al.

1 citation

2510.24591v22025arXiv

Relative Scaling Laws for LLMs

William Held, David Hall, Percy Liang et al.

0 citations

2510.24626v22025arXiv

How Do AI Agents Do Human Work? Comparing AI and Human Workflows Across Diverse Occupations

Zora Zhiruo Wang, Yijia Shao, Omar Shaikh et al.

1 citation

2510.22780v22025arXiv

Blackbox Model Provenance via Palimpsestic Membership Inference

Rohith Kuditipudi, Jing Huang, Sally Zhu et al.

0 citations

2510.19796v12025arXiv

Just-In-Time Objectives: A General Approach for Specialized AI Interactions

Michelle S. Lam, Omar Shaikh, Hallie Xu et al.

3 citations

2510.14591v22025arXiv

Career total: at least 490 works. 214 are in this corpus.Showing the 50 most recent.

Profile built from the corpus for this byline.

Author records are still filling in while the Hub is in beta. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.