7 papers · 1 filter
ConstructCIE: A Dataset for Extracting Causal Information from Construction Accident Narratives
Hung Nguyen, Jaehoon Lee, Namgyun Kim +1
Construction accident narratives contain rich causal information, but the evidence is often implicit, long-span, and distributed. We introduce ConstructCIE, a manually annotated da…
TRACES: Proactive Safety Auditing for Multi-Turn LLM Agents via Trajectory-State Modeling
Jiaqian Li, Yanshu Li, Boxuan Zhang +2
LLM agents increasingly operate through multi-turn tool use and environment interaction, where safety risks often emerge from intermediate steps long before they surface in the fin…
Language Steering for Multilingual In-Context Learning
Neeraja Kirtane, Kuan-Hao Huang
If multilingual language model representations contain separable language-associated structure, then shifting between languages may require only simple activation-space interventio…
Steering Vector Fields for Context-Aware Inference-Time Control in Large Language Models
Jiaqian Li, Yanshu Li, Kuan-Hao Huang
Steering vectors (SVs) offer a lightweight way to control large language models (LLMs) at inference time by shifting hidden activations, providing a practical middle ground between…
PEPPER: Perception-Guided Perturbation for Robust Backdoor Defense in Text-to-Image Diffusion Models
Oscar Chew, Po-Yi Lu, Jayden Lin +2
Recent studies show that text-to-image (T2I) diffusion models are vulnerable to backdoor attacks, where a trigger in the input prompt can steer generation toward harmful or uninten…
What's Missing in Vision-Language Models? Probing Their Struggles with Causal Order Reasoning
Zhaotian Weng, Haoxuan Li, Xin Eric Wang +2
Despite the impressive performance of vision-language models (VLMs) on downstream tasks, their ability to understand and reason about causal relationships in visual inputs remains…
SHA256 at SemEval-2025 Task 4: Selective Amnesia -- Constrained Unlearning for Large Language Models via Knowledge Isolation
Saransh Agrawal, Kuan-Hao Huang
Large language models (LLMs) frequently memorize sensitive information during training, posing risks when deploying publicly accessible models. Current machine unlearning methods s…