7 papers
From Task Success to Productive Success: Evaluating Human-AI Collaboration by Quality and Cost
Saki Imai, Mert İnan, Malihe Alikhani
AI productivity is often measured by task completion time, economic value, or improvements in outcome quality. However, these measures usually treat collaboration as a black box wh…
Every Eval Ever: A Unifying Schema and Community Repository for AI Evaluation Results
Jan Batzner, Sree Harsha Nelaturu, Damian Stachura +45
AI evaluations are widely used for testing and understanding progress. However, the diverse evaluators bring with them inconsistencies that challenge analysis and comparison. First…
MixDPO: Modeling Preference Strength for Pluralistic Alignment
Saki Imai, Pedram Heydari, Anthony Sicilia +3
Preference based alignment objectives implicitly assume that all human preferences are expressed with equal strength. In practice, however, preference strength varies across indivi…
"Nothing about us without us": Perspectives of Global Deaf and Hard-of-hearing Community Members on Sign Language Technologies
Katherine Atwell, Saki Imai, Danielle Bragg +1
There is accelerating interest in sign language technologies (SLTs), with increasing attention from both industry and academia. However, the perspectives of Deaf and Hard-of-hearin…
How Pragmatics Shape Articulation: A Computational Case Study in STEM ASL Discourse
Saki Imai, Lee Kezar, Laurel Aichler +5
Most state-of-the-art sign language models are trained on interpreter or isolated vocabulary data, which overlooks the variability that characterizes natural dialogue. However, hum…
Measuring How (Not Just Whether) VLMs Build Common Ground
Saki Imai, Mert İnan, Anthony Sicilia +1
Large vision language models (VLMs) increasingly claim reasoning skills, yet current benchmarks evaluate them in single-turn or question answering settings. However, grounding is a…
SiLVERScore: Semantically-Aware Embeddings for Sign Language Generation Evaluation
Saki Imai, Mert İnan, Anthony Sicilia +1
Evaluating sign language generation is often done through back-translation, where generated signs are first recognized back to text and then compared to a reference using text-base…