6 papers
When Seeing Is Not Enough: Benchmarking Interactive Visual Grounding in LVLMs
Zhengxiang Wang, Owen Rambow
Visual grounding is typically evaluated as a one-shot mapping from an informative referring expression to a visual target. This formulation misses a central property of real-world…
LVLMs and Humans Ground Differently in Referential Communication
Peter Zeng, Weiling Li, Amie J. Paige +6
For generative AI agents to partner effectively with human users, the ability to accurately predict human intent is critical. But this ability to collaborate remains limited by a c…
LVLMs are Bad at Overhearing Human Referential Communication
Zhengxiang Wang, Weiling Li, Panagiotis Kaliosis +2
During spontaneous conversations, speakers collaborate on novel referring expressions, which they can then re-use in subsequent conversations. Understanding such referring expressi…
LLMs can Perform Multi-Dimensional Analytic Writing Assessments: A Case Study of L2 Graduate-Level Academic English Writing
Zhengxiang Wang, Veronika Makarova, Zhi Li +2
The paper explores the performance of LLMs in the context of multi-dimensional analytic writing assessments, i.e. their ability to provide both scores and comments based on multipl…
Evaluating LLMs with Multiple Problems at once
Zhengxiang Wang, Jordan Kodner, Owen Rambow
This paper shows the benefits and fruitfulness of evaluating LLMs with multiple problems at once, a paradigm we call multi-problem evaluation (MPE). Unlike conventional single-prob…
Clustering Document Parts: Detecting and Characterizing Influence Campaigns from Documents
Zhengxiang Wang, Owen Rambow
We propose a novel clustering pipeline to detect and characterize influence campaigns from documents. This approach clusters parts of document, detects clusters that likely reflect…