Loading activity…
@windx0303
Ran #HCOMP2026 - https://hcomp.acm.org I create things that help users. Associate Prof @ISTatPENNSTATE @PSUCrowdAILab. #HCI #NLProc
AI
A user at Berkeley praised the talk as an ideal start to the week.
AI
A CI ’26 program listing on SIGCHI’s site is titled “Enhancing LLM-Based Data Annotation through Error Decomposition: A Human-in-the-Loop Evaluation Paradigm.”
AI
An ACM description of the paper says common summarization metrics miss how useful a summary is to an individual reader.
AI
A post says the FIBB paper opened the last paper session of HCOMP 2026 and CI 2026. ACM's description says people use online and physical-world observations to assess newly presented false information.
AI
A September 29 post identifies the paper as “Adaptive Selection of Effective AI Assistance in AI-assisted Decision Making Using Multi-Armed Bandits” and says Lu’s new group is hiring.
AI
A September 29 post identifies “One AI Signal, Many Human Judgments” as an honorable mention presented at HCOMP 2026/CI 2026. The ACM abstract describes users seeing an AI prediction alongside earlier judgments shaped by the same AI.
AI
An ACM paper argues that averaged measures of belief updates can obscure a key distinction: whether a reported belief changes at all and how it changes if it does.
AI
The ACM abstract says the study evaluates how LLM-generated explanations support human moderators detecting hate speech, particularly when discriminatory intent is implicit or nuanced.
AI
A September 29 post said Dr. Diyi Yang was delivering her keynote on Day 2, tagging both HCOMP2026 and CI2026.
AI
A post describes the work as an approach to auditing LLM annotators, similar to qualifying crowd workers.
AI
The ACM paper describes “proof burden” as what workers may have to do to show a paid task was completed, potentially revealing their identity or location.
AI
The ACM paper defines socio-technical congruence as the fit between the coordination a project requires and what its participants actually do. It says assumptions developed for human software teams break down when AI agents join.
AI
An ACM conference paper describes AgentDynEx as an AI system for multi-agent language-model simulations, where enforcing the rules while allowing unexpected social dynamics is a challenge.
AI
A September 28 post identified “Partner-Adaptive Delegation in Ad Hoc Teamwork” as the first paper in an HCOMP2026/CI2026 afternoon session. The ACM proceedings description says a teammate’s skills can vary by subtask.
AI
A September 28 post says Harang Ju (JHU) is presenting the talk and tags HCOMP2026 and CI2026.
AI
A September 28 post highlighted a DoubleAgents talk at HCOMP2026 and CI2026. The project page describes a coordination agent, a legible dashboard and a policy module that turns edits into reusable alignment artifacts.
AI
A September 28 post says Vincenzo Marco De Luca is presenting “Towards Actionable Surgical Team Dynamics: from Teamwork to Counterfactual Annotations” at #HCOMP2026 and #CI2026.
AI
The ACM paper describes schema induction as learning implicit structures from examples, noting that surface-level differences can obscure shared patterns.
AI
An ACM conference paper describes InterviewBot, a voice-based system that pairs a real-time multimodal AI model with a researcher-authored interview outline.
AI
A September 28 post says CMU researchers Jessica Mindel and Sijia Xie are presenting the paper at HCOMP 2026 and CI 2026.
