activity
20242026
collaborators
Showing cs.CLShow all

15 papers · 1 filter

cs.CL2026

Routing Is Least Learnable Where It Is Most Valuable: Bounds on Representation Routing for Web Agents

Jiaming Wei, Zekun Wu, Adriano Koshiyama +1

Web agents observe a browser through text, pixels, or both, and the choice is usually fixed once for all tasks. We measure six observation modes across eight site-model combination…

cs.CL2026

Tool Calling is Linearly Readable and Steerable in Language Models

Zekun Wu, Ze Wang, Seonglae Cho +4

When a tool-calling agent picks the wrong tool, the failure is invisible until execution: the email gets sent, the meeting gets missed. As agents take on consequential actions, one…

cs.CL2026

Sell Me This Stock: Unsafe Recommendation Drift in LLM Agents

Zekun Wu, Adriano Koshiyama, Sahan Bulathwela +1

People increasingly use LLM agents for multi-turn financial recommendations, where the agent pulls market data through tools and tracks user preferences across turns. When tool out…

cs.CL2025

Knowledge Collapse in LLMs: When Fluency Survives but Facts Fail under Recursive Synthetic Training

Figarri Keisha, Zekun Wu, Ze Wang +2

Large language models increasingly rely on synthetic data due to human-written content scarcity, yet recursive training on model-generated outputs leads to model collapse, a degene…

cs.CL2025

Personality as a Probe for LLM Evaluation: Method Trade-offs and Downstream Effects

Gunmay Handa, Zekun Wu, Adriano Koshiyama +1

Personality manipulation in large language models (LLMs) is increasingly applied in customer service and agentic scenarios, yet its mechanisms and trade-offs remain unclear. We pre…

cs.CL2025

CorrSteer: Generation-Time LLM Steering via Correlated Sparse Autoencoder Features

Seonglae Cho, Zekun Wu, Adriano Koshiyama

Sparse Autoencoders (SAEs) can extract interpretable features from large language models (LLMs) without supervision. However, their effectiveness in downstream steering tasks is li…