10 papers
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…
Tracing Moral Foundations in Large Language Models
Chenxiao Yu, Bowen Yi, Farzan Karimi-Malekabadi +5
Large language models often produce human-like moral judgments, but it is unclear whether this reflects an internal conceptual structure or superficial ``moral mimicry.'' Using Mor…
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…
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…
Personalized Group Relative Policy Optimization for Heterogenous Preference Alignment
Jialu Wang, Heinrich Peters, Asad A. Butt +6
Despite their sophisticated general-purpose capabilities, Large Language Models (LLMs) often fail to align with diverse individual preferences because standard post-training method…
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…