WG
Werner Geyer
cs.HCcs.AIcs.CLcs.LGcs.CYcs.SE
On Valency
published · living versionsW_r6xkyhyj·v1 · currentpublished
Ask Less, Ask Better: Allocating User Attention in Proactive LLM Agents with Interruption Budgets
with Xuanming Zhang, Amir H. Rezaeian, Miguel Ballesteros, Weiyi Sun +4
1 version
Preprints & journals
24 papers in the corpus · 2023–2026Ask Less, Ask Better: Allocating User Attention in Proactive LLM Agents with Interruption Budgets2610.24411v1 · Xuanming Zhang, Amir H. Rezaeian, Miguel Ballesteros et al.2026 · 0 citationsarXivon Valency
MultEval: Supporting Collaborative Alignment for LLM-as-a-Judge Evaluation Criteria2604.26679v1 · Charles Chiang, Simret Gebreegziabher, Annalisa Szymanski et al.2026 · 0 citationsProceedings of the 5th Annual Symposium on Human-Computer Interaction for Work (CHIWORK '26), June 22--25, 2026, Linz, Austria
Alignment Risks from Capability-Seeking RL Training2602.12124v2 · Yujun Zhou, Yue Huang, Han Bao et al.2026 · 0 citationsarXiv
The Behavioral Fabric of LLM-Powered GUI Agents: Human Values and Interaction Outcomes2601.16356v1 · Simret Araya Gebreegziabher, Yukun Yang, Charles Chiang et al.2026 · 1 citationarXiv
From Verification Burden to Trusted Collaboration: Design Goals for LLM-Assisted Literature Reviews2512.11661v1 · Brenda Nogueira, Werner Geyer, Andrew Anderson et al.2025 · 1 citationarXiv
Generate, Evaluate, Iterate: Synthetic Data for Human-in-the-Loop Refinement of LLM Judges2511.04478v1 · Hyo Jin Do, Zahra Ashktorab, Jasmina Gajcin et al.2025 · 0 citationsarXiv
EvalAssist: A Human-Centered Tool for LLM-as-a-Judge2507.02186v2 · Zahra Ashktorab, Werner Geyer, Michael Desmond et al.2025 · 1 citationarXiv
A Case Study Investigating the Role of Generative AI in Quality Evaluations of Epics in Agile Software Development2505.07664v1 · Werner Geyer, Jessica He, Daita Sarkar et al.2025 · 8 citationsarXiv
Interaction Configurations and Prompt Guidance in Conversational AI for Question Answering in Human-AI Teams2505.01648v2 · Jaeyoon Song, Zahra Ashktorab, Qian Pan et al.2025 · 8 citationsarXiv
Current and Future Use of Large Language Models for Knowledge Work2503.16774v1 · Michelle Brachman, Amina El-Ashry, Casey Dugan et al.2025 · 12 citationsarXiv
"The Diagram is like Guardrails": Structuring GenAI-assisted Hypotheses Exploration with an Interactive Shared Representation2503.16791v2 · Zijian Ding, Michelle Brachman, Joel Chan et al.2025 · 6 citationsarXiv
Agentic AI Needs a Systems Theory2503.00237v1 · Erik Miehling, Karthikeyan Natesan Ramamurthy, Kush R. Varshney et al.2025 · 6 citationsarXiv
LabSafety Bench: Benchmarking LLMs on Safety Issues in Scientific Labs2410.14182v4 · Yujun Zhou, Jingdong Yang, Yue Huang et al.2024 · 7 citationsNat Mach Intell 8, 20-31 (2026)
Black-box Uncertainty Quantification Method for LLM-as-a-Judge2410.11594v1 · Nico Wagner, Michael Desmond, Rahul Nair et al.2024 · 1 citationarXiv
Justice or Prejudice? Quantifying Biases in LLM-as-a-Judge2410.02736v2 · Jiayi Ye, Yanbo Wang, Yue Huang et al.2024 · 11 citationsarXiv
Aligning Human and LLM Judgments: Insights from EvalAssist on Task-Specific Evaluations and AI-assisted Assessment Strategy Preferences2410.00873v2 · Zahra Ashktorab, Michael Desmond, Qian Pan et al.2024 · 3 citationsarXiv
Emerging Reliance Behaviors in Human-AI Content Grounded Data Generation: The Role of Cognitive Forcing Functions and Hallucinations2409.08937v2 · Zahra Ashktorab, Qian Pan, Werner Geyer et al.2024 · 10 citationsarXiv
Human-Centered Design Recommendations for LLM-as-a-Judge2407.03479v1 · Qian Pan, Zahra Ashktorab, Michael Desmond et al.2024 · 25 citationsarXiv
Facilitating Human-LLM Collaboration through Factuality Scores and Source Attributions2405.20434v1 · Hyo Jin Do, Rachel Ostrand, Justin D. Weisz et al.2024 · 3 citationsarXiv
Multi-Level Explanations for Generative Language Models2403.14459v2 · Lucas Monteiro Paes, Dennis Wei, Hyo Jin Do et al.2024 · 1 citationarXiv
Design Principles for Generative AI Applications2401.14484v1 · Justin D. Weisz, Jessica He, Michael Muller et al.2024 · 231 citationsarXiv
Helping the Helper: Supporting Peer Counselors via AI-Empowered Practice and Feedback2305.08982v2 · Shang-Ling Hsu, Raj Sanjay Shah, Prathik Senthil et al.2023 · 44 citationsarXiv
Fairness Evaluation in Text Classification: Machine Learning Practitioner Perspectives of Individual and Group Fairness2303.00673v1 · Zahra Ashktorab, Benjamin Hoover, Mayank Agarwal et al.2023 · 14 citationsarXiv
AutoDOViz: Human-Centered Automation for Decision Optimization2302.09688v1 · Daniel Karl I. Weidele, Shazia Afzal, Abel N. Valente et al.2023 · 10 citationsarXiv
Career total: 145 works. 24 are in this corpus.
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.