9 citations · 24 across the 24 of their papers we have counts for
26 papers
Corrupted but Correct: Why Vision-Language Models Lie to Themselves Internally
Arun Josephraj Arokiaraj, Zekun Wu, Adriano Koshiyama
A targeted adversarial perturbation can drive a vision-language model's (VLM's) teacher-forced training loss for a fixed target caption to near zero, yet the same model, allowed to…
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…
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…
Which Decisions Low-Bit Quantization Breaks, and How to Predict Them
Zekun Wu, Swati Dhiman, Adriano Koshiyama
Quantization saves memory by storing model weights with fewer bits. It can also change model decisions, such as whether to call a tool or which option to choose from a finite set.…
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…
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…
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…
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…
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…
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…
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…
MPF: Aligning and Debiasing Language Models post Deployment via Multi Perspective Fusion
Xin Guan, PeiHsin Lin, Zekun Wu +4
Multiperspective Fusion (MPF) is a novel posttraining alignment framework for large language models (LLMs) developed in response to the growing need for easy bias mitigation. Built…
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,…
Assessing Bias in Metric Models for LLM Open-Ended Generation Bias Benchmarks
Nathaniel Demchak, Xin Guan, Zekun Wu +3
Open-generation bias benchmarks evaluate social biases in Large Language Models (LLMs) by analyzing their outputs. However, the classifiers used in analysis often have inherent bia…
Bias Amplification: Large Language Models as Increasingly Biased Media
Ze Wang, Zekun Wu, Jeremy Zhang +5
Model collapse, a phenomenon characterized by performance degradation due to iterative training on synthetic data, has been widely studied. However, its implications for bias ampli…
HEARTS: A Holistic Framework for Explainable, Sustainable and Robust Text Stereotype Detection
Theo King, Zekun Wu, Adriano Koshiyama +2
Stereotypes are generalised assumptions about societal groups, and even state-of-the-art LLMs using in-context learning struggle to identify them accurately. Due to the subjective…
THaMES: An End-to-End Tool for Hallucination Mitigation and Evaluation in Large Language Models
Mengfei Liang, Archish Arun, Zekun Wu +5
Hallucination, the generation of factually incorrect content, is a growing challenge in Large Language Models (LLMs). Existing detection and mitigation methods are often isolated a…
SAGED: A Holistic Bias-Benchmarking Pipeline for Language Models with Customisable Fairness Calibration
Xin Guan, Ze Wang, Nathaniel Demchak +5
The development of unbiased large language models is widely recognized as crucial, yet existing benchmarks fall short in detecting biases due to limited scope, contamination, and l…
From Text to Emoji: How PEFT-Driven Personality Manipulation Unleashes the Emoji Potential in LLMs
Navya Jain, Zekun Wu, Cristian Munoz +5
The manipulation of the personality traits of large language models (LLMs) has emerged as a key area of research. Methods like prompt-based In-Context Knowledge Editing (IKE) and g…
HyPA-RAG: A Hybrid Parameter Adaptive Retrieval-Augmented Generation System for AI Legal and Policy Applications
Rishi Kalra, Zekun Wu, Ayesha Gulley +4
Large Language Models (LLMs) face limitations in AI legal and policy applications due to outdated knowledge, hallucinations, and poor reasoning in complex contexts. Retrieval-Augme…
JobFair: A Framework for Benchmarking Gender Hiring Bias in Large Language Models
Ze Wang, Zekun Wu, Xin Guan +6
The use of Large Language Models (LLMs) in hiring has led to legislative actions to protect vulnerable demographic groups. This paper presents a novel framework for benchmarking hi…
Stereotype Detection in LLMs: A Multiclass, Explainable, and Benchmark-Driven Approach
Zekun Wu, Sahan Bulathwela, Maria Perez-Ortiz +1
Stereotype detection is a challenging and subjective task, as certain statements, such as "Black people like to play basketball," may not appear overtly toxic but still reinforce r…