4 papers
Signals: Trajectory Sampling and Triage for Agentic Interactions
Shuguang Chen, Adil Hafeez, Salman Paracha
Agentic applications based on large language models increasingly rely on multi-step interaction loops involving planning, action execution, and environment feedback. While such sys…
Arch-Router: Aligning LLM Routing with Human Preferences
Co Tran, Salman Paracha, Adil Hafeez +1
With the rapid proliferation of large language models (LLMs) -- each optimized for different strengths, style, or latency/cost profile -- routing has become an essential technique…
LLM Reasoning Engine: Specialized Training for Enhanced Mathematical Reasoning
Shuguang Chen, Guang Lin
Large Language Models (LLMs) have shown remarkable performance in various natural language processing tasks but face challenges in mathematical reasoning, where complex problem-sol…
Context-aware Adversarial Attack on Named Entity Recognition
Shuguang Chen, Leonardo Neves, Thamar Solorio
In recent years, large pre-trained language models (PLMs) have achieved remarkable performance on many natural language processing benchmarks. Despite their success, prior studies…