6 papers
PageGuide: Browser extension to assist users in navigating a webpage and locating information
Tin Nguyen, Thang T. Truong, Runtao Zhou +3
Users browsing the web daily struggle to quickly locate relevant information in cluttered pages, complete unfamiliar multi-step tasks, and stay focused amid distracting content. St…
ASA: Backbone-Training-Free Representation Engineering for Tool-Calling Agents
Youjin Wang, Run Zhou, Yingjie Ma +6
Adapting LLM agents to domain-specific tool calling remains notably brittle under evolving interfaces. Prompt and schema engineering is easy to deploy but often fragile under distr…
When Graph Tokens Sink: A Mechanistic Analysis of Graph Language Models
Ding Zhang, Runtao Zhou, Wenqing Zheng +3
Graph Language Models (GLMs) have become a promising direction for adapting Large Language Models (LLMs) to graph learning tasks. By transforming graph topology and node informatio…
The Fragility of Chain-of-Thought Monitoring Across Typologically Diverse Languages
Eric Onyame, Runtao Zhou, Kowshik Thopalli +2
Chain-of-thought (CoT) monitoring has been proposed as a promising safety mechanism for detecting misaligned behavior in large language models. However, its reliability remains lar…
Improving Human Verification of LLM Reasoning through Interactive Explanation Interfaces
Runtao Zhou, Giang Nguyen, Nikita Kharya +2
The reasoning capabilities of Large Language Models (LLMs) have led to their increasing employment in several critical applications, particularly education, where they support prob…
Disparities in LLM Reasoning Accuracy and Explanations: A Case Study on African American English
Runtao Zhou, Guangya Wan, Saadia Gabriel +4
Large Language Models (LLMs) have demonstrated remarkable capabilities in reasoning tasks, leading to their widespread deployment. However, recent studies have highlighted concerni…