activity
20242026
collaborators

6 papers

cs.DB2026

ThriftLLM: On Cost-Effective Selection of Large Language Models for Classification Queries

Keke Huang, Yimin Shi, Dujian Ding +4

In recent years, large language models (LLMs) have demonstrated remarkable capabilities in comprehending and generating natural language content, attracting widespread attention in…

cs.LG2025

BEST-Route: Adaptive LLM Routing with Test-Time Optimal Compute

Dujian Ding, Ankur Mallick, Shaokun Zhang +7

Large language models (LLMs) are powerful tools but are often expensive to deploy at scale. LLM query routing mitigates this by dynamically assigning queries to models of varying c…

cs.CL2025

Why Prompt Design Matters and Works: A Complexity Analysis of Prompt Search Space in LLMs

Xiang Zhang, Juntai Cao, Jiaqi Wei +2

Despite the remarkable successes of large language models (LLMs), the underlying Transformer architecture has inherent limitations in handling complex reasoning tasks. Chain-of-tho…

cs.CV2025

OCCAM: Towards Cost-Efficient and Accuracy-Aware Classification Inference

Dujian Ding, Bicheng Xu, Laks V. S. Lakshmanan

Classification tasks play a fundamental role in various applications, spanning domains such as healthcare, natural language processing and computer vision. With the growing popular…

cs.AI2024

EcoAct: Economic Agent Determines When to Register What Action

Shaokun Zhang, Jieyu Zhang, Dujian Ding +7

Recent advancements have enabled Large Language Models (LLMs) to function as agents that can perform actions using external tools. This requires registering, i.e., integrating tool…

cs.CL2024

Supervised Chain of Thought

Xiang Zhang, Dujian Ding

Large Language Models (LLMs) have revolutionized natural language processing and hold immense potential for advancing Artificial Intelligence. However, the core architecture of mos…