7 papers
VELD-QA: A Large-Scale Dataset for Visual Evidence Grounding and Question Answering in Long Documents
Zhivar Sourati, Marianne Menglin Liu, Rongguang Wang +12
Existing long-document QA benchmarks rarely combine large-scale human-authored questions with detailed visual evidence annotations, limiting diagnosis of evidence localization and…
Same Context, Different Agents: A Behavioral Study of Semantic Layers, Multi-Agent Orchestration and Memory Compaction in Data Agents
Zhivar Sourati, Marianne Menglin Liu, Zheng Wang +6
Answering questions over heterogeneous data means combining evidence from files, databases, documents and the web. Data agents automate this, but their success depends on context.…
Cognitive Expert Language Models Better Align with the Corresponding Brain Systems
Zhivar Sourati, Mengxuan Helen Wu, Nona Ghazizadeh +3
Large language models (LLMs) can predict human brain activity across a variety of brain regions during natural language comprehension. Typically, however, LLM-brain alignment is me…
Structural Abstraction as an Inductive Bias for Non-Stationary Language Model Training
Elnaz Rahmati, Nona Ghazizadeh, Zhivar Sourati +2
A foundational principle in cognitive science holds that intelligent agents do not learn by storing experiences as isolated instances, but by forming abstract schemas that capture…
The Subjectivity of Respect in Police Traffic Stops: Modeling Community Perspectives in Body-Worn Camera Footage
Preni Golazizian, Elnaz Rahmati, Jackson Trager +17
Traffic stops are among the most frequent police-civilian interactions, and body-worn cameras (BWCs) provide a unique record of how these encounters unfold. Respect is a central di…
Theory Trace Card: Theory-Driven Socio-Cognitive Evaluation of LLMs
Farzan Karimi-Malekabadi, Suhaib Abdurahman, Zhivar Sourati +2
Socio-cognitive benchmarks for large language models (LLMs) often fail to predict real-world behavior, even when models achieve high benchmark scores. Prior work has attributed thi…
LAD-RAG: Layout-aware Dynamic RAG for Visually-Rich Document Understanding
Zhivar Sourati, Zheng Wang, Marianne Menglin Liu +8
Question answering over visually rich documents (VRDs) requires reasoning not only over isolated content but also over documents' structural organization and cross-page dependencie…