TW
Tongshuang Wu
cs.CLcs.AIcs.HCcs.LGcs.SEcs.IRcs.CYComputer Graphicscs.CVcs.DL
On Valency
published · living versionsW_hvdxbc96·v1 · currentpublished
Knowing When to Stop: The Evidence-Action Gap in Coding Agents
with Tianyu Chen, Xinran Zhao, Vijay Viswanathan, Shoubin Yu +1
1 version
Preprints & journals
74 papers in the corpus · 2016–2026Modeling of Therapist-Client Dynamics in Psychotherapy Using LLM-Based Assessments: An Empirical Study.42873163 · Chen, Angela, Jin, Siwei, Wang, Canwen et al.2026 · 0 citationsJMIR mental health. 2026
Align AI to Dynamic Human-AI Workflows2607.14240v2 · Valerie Chen, Cleotilde Gonzalez, Anita Williams Woolley et al.2026 · 0 citationsarXiv
Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation2607.08938v1 · Chenyang Yang, Xinran Zhao, Tongshuang Wu et al.2026 · 0 citationsarXiv
Discretizing Reward Models2606.21795v1 · Vijay Viswanathan, Shiqi Wang, Devamanyu Hazarika et al.2026 · 0 citationsarXiv
OdysSim: Building Foundation Models for Human Behavior Simulation2606.14199v2 · Xuhui Zhou, Weiwei Sun, Weihua Du et al.2026 · 0 citationsarXiv
RECAP: An End-to-End Platform for Capturing, Replaying, and Analyzing AI-Assisted Programming Interactions2605.01104v1 · Keyu He, Qianou Ma, Valerie Chen et al.2026 · 0 citationsarXiv
Practice Less, Explain More: LLM-Supported Self-Explanation Improves Explanation Quality on Transfer Problems in Calculus2604.00142v2 · Eason Chen, Xinyi Tang, Yvonne Zhao et al.2026 · 1 citationarXiv
Improving Attributed Long-form Question Answering with Intent Awareness2603.27435v2 · Xinran Zhao, Aakanksha Naik, Jay DeYoung et al.2026 · 0 citationsICLR 2026
Comparing Developer and LLM Biases in Code Evaluation2603.24586v2 · Aditya Mittal, Ryan Shar, Zichu Wu et al.2026 · 0 citationsarXiv
Evidotes: Integrating Scientific Evidence and Anecdotes to Support Uncertainties Triggered by Peer Health Posts2602.16900v2 · Shreya Bali, Riku Arakawa, Peace Odiase et al.2026 · 1 citationarXiv
Behavioral Indicators of Overreliance During Interaction with Conversational Language Models2602.11567v1 · Chang Liu, Qinyi Zhou, Xinjie Shen et al.2026 · 4 citationsarXiv
Modeling of Therapist-Client Dynamics in Psychotherapy Using LLM-Based Assessments: An Empirical Study2602.12450v3 · Angela Chen, Siwei Jin, Canwen Wang et al.2026 · 0 citationsarXiv
Simulating Couple Conflict: Designing A Multi-Agent System for Therapy Training and Practice2601.10970v2 · Canwen Wang, Angela Chen, Catherine Bao et al.2026 · 0 citationsarXiv
DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research2511.19399v3 · Rulin Shao, Akari Asai, Shannon Zejiang Shen et al.2025 · 0 citationsarXiv
Completion Collaboration: Scaling Collaborative Effort with Agents2510.25744v2 · Shannon Zejiang Shen, Valerie Chen, Ken Gu et al.2025 · 0 citationsarXiv
Not Everyone Wins with LLMs: Behavioral Patterns and Pedagogical Implications for AI Literacy in Programmatic Data Science2509.21890v2 · Qianou Ma, Kenneth Koedinger, Tongshuang Wu2025 · 6 citationsCHI 2026
The Ramon Llull's Thinking Machine for Automated Ideation2508.19200v3 · Xinran Zhao, Boyuan Zheng, Chenglei Si et al.2025 · 0 citationsarXiv
Checklists Are Better Than Reward Models For Aligning Language Models2507.18624v2 · Vijay Viswanathan, Yanchao Sun, Shuang Ma et al.2025 · 1 citationarXiv
cAST: Enhancing Code Retrieval-Augmented Generation with Structural Chunking via Abstract Syntax Tree2506.15655v2 · Yilin Zhang, Xinran Zhao, Zora Zhiruo Wang et al.2025 · 11 citationsarXiv
MoR: Better Handling Diverse Queries with a Mixture of Sparse, Dense, and Human Retrievers2506.15862v1 · Jushaan Singh Kalra, Xinran Zhao, To Eun Kim et al.2025 · 6 citationsarXiv
RARE: Retrieval-Aware Robustness Evaluation for Retrieval-Augmented Generation Systems2506.00789v3 · Yixiao Zeng, Tianyu Cao, Danqing Wang et al.2025 · 0 citationsarXiv
What Prompts Don't Say: Understanding and Managing Underspecification in LLM Prompts2505.13360v3 · Chenyang Yang, Yike Shi, Qianou Ma et al.2025 · 2 citationsarXiv
SOTOPIA-S4: a user-friendly system for flexible, customizable, and large-scale social simulation2504.16122v1 · Xuhui Zhou, Zhe Su, Sophie Feng et al.2025 · 4 citationsarXiv
SPHERE: An Evaluation Card for Human-AI Systems2504.07971v1 · Qianou Ma, Dora Zhao, Xinran Zhao et al.2025 · 2 citationsACL Findings 2025
Improving Automated Feedback Systems for Tutor Training in Low-Resource Scenarios through Data Augmentation2501.09824v2 · Chentianye Xu, Jionghao Lin, Tongshuang Wu et al.2025 · 0 citationsarXiv
Orbit: A Framework for Designing and Evaluating Multi-objective Rankers2411.04798v2 · Chenyang Yang, Tesi Xiao, Michael Shavlovsky et al.2024 · 0 citationsarXiv
HiMemFormer: Hierarchical Memory-Aware Transformer for Multi-Agent Action Anticipation2411.01455v2 · Zirui Wang, Xinran Zhao, Simon Stepputtis et al.2024 · 1 citationarXiv
What Is Wrong with My Model? Identifying Systematic Problems with Semantic Data Slicing2409.09261v1 · Chenyang Yang, Yining Hong, Grace A. Lewis et al.2024 · 3 citationsarXiv
What Should We Engineer in Prompts? Training Humans in Requirement-Driven LLM Use2409.08775v3 · Qianou Ma, Weirui Peng, Chenyang Yang et al.2024 · 39 citationsTOCHI 2025
SELF-GUIDE: Better Task-Specific Instruction Following via Self-Synthetic Finetuning2407.12874v2 · Chenyang Zhao, Xueying Jia, Vijay Viswanathan et al.2024 · 3 citationsarXiv
Synthetic Multimodal Question Generation2407.02233v2 · Ian Wu, Sravan Jayanthi, Vijay Viswanathan et al.2024 · 5 citationsarXiv
WebCanvas: Benchmarking Web Agents in Online Environments2406.12373v3 · Yichen Pan, Dehan Kong, Sida Zhou et al.2024 · 4 citationsarXiv
Beyond Relevance: Evaluate and Improve Retrievers on Perspective Awareness2405.02714v1 · Xinran Zhao, Tong Chen, Sihao Chen et al.2024 · 0 citationsarXiv
Better Synthetic Data by Retrieving and Transforming Existing Datasets2404.14361v3 · Saumya Gandhi, Ritu Gala, Vijay Viswanathan et al.2024 · 12 citationsarXiv
Evaluating Mathematical Reasoning Beyond Accuracy2404.05692v2 · Shijie Xia, Xuefeng Li, Yixin Liu et al.2024 · 18 citationsarXiv
Fact-and-Reflection (FaR) Improves Confidence Calibration of Large Language Models2402.17124v2 · Xinran Zhao, Hongming Zhang, Xiaoman Pan et al.2024 · 7 citationsFindings of the Association for Computational Linguistics ACL 2024
Wikibench: Community-Driven Data Curation for AI Evaluation on Wikipedia2402.14147v1 · Tzu-Sheng Kuo, Aaron Halfaker, Zirui Cheng et al.2024 · 19 citationsProceedings of the 2024 CHI Conference on Human Factors in Computing Systems (CHI '24)
Measuring Adversarial Datasets2311.03566v1 · Yuanchen Bai, Raoyi Huang, Vijay Viswanathan et al.2023 · 1 citationarXiv
The Data Provenance Initiative: A Large Scale Audit of Dataset Licensing & Attribution in AI2310.16787v3 · Shayne Longpre, Robert Mahari, Anthony Chen et al.2023 · 10 citationsarXiv
Beyond Testers' Biases: Guiding Model Testing with Knowledge Bases using LLMs2310.09668v1 · Chenyang Yang, Rishabh Rustogi, Rachel Brower-Sinning et al.2023 · 10 citationsarXiv
How to Teach Programming in the AI Era? Using LLMs as a Teachable Agent for Debugging2310.05292v5 · Qianou Ma, Hua Shen, Kenneth Koedinger et al.2023 · 65 citationsAIED 2024, LNAI 14829, pp. 1-16
From Nuisance to News Sense: Augmenting the News with Cross-Document Evidence and Context2310.04592v1 · Jeremiah Milbauer, Ziqi Ding, Zhijin Wu et al.2023 · 0 citationsarXiv
Selenite: Scaffolding Online Sensemaking with Comprehensive Overviews Elicited from Large Language Models2310.02161v4 · Michael Xieyang Liu, Tongshuang Wu, Tianying Chen et al.2023 · 45 citationsarXiv
Prompt2Model: Generating Deployable Models from Natural Language Instructions2308.12261v1 · Vijay Viswanathan, Chenyang Zhao, Amanda Bertsch et al.2023 · 11 citationsarXiv
LLMs as Workers in Human-Computational Algorithms? Replicating Crowdsourcing Pipelines with LLMs2307.10168v3 · Tongshuang Wu, Haiyi Zhu, Maya Albayrak et al.2023 · 17 citationsCHI 2025 Case Study Track
Large Language Models Enable Few-Shot Clustering2307.00524v1 · Vijay Viswanathan, Kiril Gashteovski, Carolin Lawrence et al.2023 · 74 citationsarXiv
Is AI the better programming partner? Human-Human Pair Programming vs. Human-AI pAIr Programming2306.05153v2 · Qianou Ma, Tongshuang Wu, Kenneth Koedinger2023 · 11 citationsarXiv
Seeing Seeds Beyond Weeds: Green Teaming Generative AI for Beneficial Uses2306.03097v1 · Logan Stapleton, Jordan Taylor, Sarah Fox et al.2023 · 4 citationsarXiv
DataFinder: Scientific Dataset Recommendation from Natural Language Descriptions2305.16636v2 · Vijay Viswanathan, Luyu Gao, Tongshuang Wu et al.2023 · 16 citationsarXiv
BiasX: "Thinking Slow" in Toxic Content Moderation with Explanations of Implied Social Biases2305.13589v1 · Yiming Zhang, Sravani Nanduri, Liwei Jiang et al.2023 · 4 citationsarXiv
Career total: 151 works. 74 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 alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.