3 papers
cs.CL2025
Chopping Trees: Semantic Similarity Based Dynamic Pruning for Tree-of-Thought Reasoning
Joongho Kim, Xirui Huang, Zarreen Reza +1
Tree-of-Thought (ToT) reasoning boosts the problem-solving abilities of Large Language Models (LLMs) but is computationally expensive due to semantic redundancy, where distinct bra…
cs.AI2025
The Social Laboratory: A Psychometric Framework for Multi-Agent LLM Evaluation
Zarreen Reza
As Large Language Models (LLMs) transition from static tools to autonomous agents, traditional evaluation benchmarks that measure performance on downstream tasks are becoming insuf…
cs.CY2025
Small Models, Big Support: A Local LLM Framework for Educator-Centric Content Creation and Assessment with RAG and CAG
Zarreen Reza, Alexander Mazur, Michael T. Dugdale +1
While Large Language Models (LLMs) are increasingly applied in student-facing educational tools, their potential to directly support educators through locally deployable and custom…