5 papers
PsychoAgent: An Affect-Sensitive Cognitive Architecture for Conflict-Aware Memory in LLM Agents
Mohammad Amanlou, Parham Abed Azad, Farbod Davoodi +3
Human-like cognition does not select past experience by topical similarity alone: affective significance and unresolved conflict also shape what becomes accessible. We present Psyc…
ValueGraph: Value-Signal Guided Graph Pre-training for Contextualized User Representation
Yitong Han, Wei Gao, Yi Zhao +3
Value signals are aggregated user-level moral representations that capture users' inferred value-related tendencies from their online discourse. User behavior on social media is sh…
Beyond Access: Guided LLM Scaffolding for Independent Learning in Undergraduate Statistics
Mohammad Amanlou, Yasaman Amou-Jafari, Fereshte Bagheri +5
Large language models (LLMs) are increasingly entering students' learning practices, but their educational value may depend on whether they are used to support reasoning or to comp…
KNIGHT: Knowledge Graph-Driven Multiple-Choice Question Generation with Adaptive Hardness Calibration
Mohammad Amanlou, Erfan Shafiee Moghaddam, Yasaman Amou Jafari +3
With the rise of large language models (LLMs), they have become instrumental in applications such as Retrieval-Augmented Generation (RAG). Yet evaluating these systems remains bott…
FIRE: Faithful Interpretable Recommendation Explanations
S. M. F. Sani, Asal Meskin, Mohammad Amanlou +1
Natural language explanations in recommender systems are often framed as a review generation task, leveraging user reviews as ground-truth supervision. While convenient, this appro…