1 citations · 1 across the 11 of their papers we have counts for
11 papers
Are Single-Token Sparse Autoencoder Features Causally Necessary? Layer-Depth and SAE-Family Effects
Seonglae Cho, Zekun Wu, Kleyton Da Costa +3
Sparse autoencoder (SAE) features are used to interpret and steer large language models, yet nobody has tested whether a feature's causal role is stable across SAE families. Single…
AgentRoom: Concurrent Multi-Agent Coding in a CRDT-Backed Shared Workspace
Seonglae Cho, Donghyun Lee
Concurrent multi-agent coding promises division of labor across modules, robustness through redundancy, and parallel exploration at the natural granularity of multi-file projects.…
Automata from Agent Traces: Failure and Next-Step Prediction
Seonglae Cho, Franklin Cardenoso Fernandez, Umar Mohammed +4
LLM-based agents execute multi-step tasks, but their behavioral structure remains opaque: long unstructured traces resist the safety auditing and runtime monitoring that deployment…
OptimismBench: Forecasting Bias and the Alignment Effect in Language Model Judgment
Seonglae Cho, Adriano Koshiyama
Large language models are increasingly used as decision aids whose probability judgments shape downstream choices. Whether those judgments carry a systematic directional tilt has b…
Tool Calling is Linearly Readable and Steerable in Language Models
Zekun Wu, Ze Wang, Seonglae Cho +4
Language-model agents can take real actions by calling tools, so choosing the wrong tool can cause errors that are difficult to undo. Most evaluations only observe the tool choice…
Control Reinforcement Learning: Interpretable Token-Level Steering of LLMs via Sparse Autoencoder Features
Seonglae Cho, Zekun Wu, Adriano Koshiyama
Sparse autoencoders (SAEs) decompose language model activations into interpretable features, but existing methods reveal only which features activate, not which change model output…
The Confidence Manifold: Geometric Structure of Correctness Representations in Language Models
Seonglae Cho, Zekun Wu, Kleyton Da Costa +1
When a language model asserts that "the capital of Australia is Sydney," does it know this is wrong? Models assert misconceptions with the same fluency as facts, so the question ca…
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…
LibVulnWatch: A Deep Assessment Agent System and Leaderboard for Uncovering Hidden Vulnerabilities in Open-Source AI Libraries
Zekun Wu, Seonglae Cho, Umar Mohammed +7
Open-source AI libraries are foundational to modern AI systems, yet they present significant, underexamined risks spanning security, licensing, maintenance, supply chain integrity,…
FaithfulSAE: Towards Capturing Faithful Features with Sparse Autoencoders without External Dataset Dependencies
Seonglae Cho, Harryn Oh, Donghyun Lee +3
Sparse Autoencoders (SAEs) have emerged as a promising solution for decomposing large language model representations into interpretable features. However, Paulo and Belrose (2025)…
RTSUM: Relation Triple-based Interpretable Summarization with Multi-level Salience Visualization
Seonglae Cho, Yonggi Cho, HoonJae Lee +3
In this paper, we present RTSUM, an unsupervised summarization framework that utilizes relation triples as the basic unit for summarization. Given an input document, RTSUM first se…