11 papers
IHDec: Divergence-Steered Contrastive Decoding for Securing Multi-Turn Instruction Hierarchies
Nicole Geumheon Liu, Haeun Jang, Yonghyun Jun +1
Large Language Models (LLMs) often fail to maintain instruction hierarchies (IH) when processing multi-source inputs with varying role-level priorities, paradoxically adhering to l…
Code-Switching Reveals Language Anchoring in Multilingual LLMs
Jeonghyun Park, Seunghyun Yoon, Yonghyun Jun +1
Multilingual Large Language Models (MLLMs) are increasingly expected to handle Code-Switched (CS) inputs, yet mixing languages frequently degrades performance relative to source- o…
Identifying and Mitigating Bottlenecks in Role-Playing Agents: A Systematic Study of Disentangling Character Profile Axes
Yonghyun Jun, Junhyuk Choi, Jeonghyun Park +3
While Large Language Model (LLM) role-playing agents have advanced rapidly, it remains unclear which profile elements genuinely drive role-playing quality. To bridge this gap, we i…
Doc-PP: Document Policy Preservation Benchmark for Large Vision-Language Models
Haeun Jang, Hwan Chang, Hwanhee Lee
The deployment of Large Vision-Language Models (LVLMs) for real-world document question answering is often constrained by dynamic, user-defined policies that dictate information di…
ChatInject: Abusing Chat Templates for Prompt Injection in LLM Agents
Hwan Chang, Yonghyun Jun, Hwanhee Lee
The growing deployment of large language model (LLM) based agents that interact with external environments has created new attack surfaces for adversarial manipulation. One major t…
Hallucinate at the Last in Long Response Generation: A Case Study on Long Document Summarization
Joonho Yang, Seunghyun Yoon, Hwan Chang +2
Large Language Models (LLMs) have significantly advanced text generation capabilities, including tasks like summarization, often producing coherent and fluent outputs. However, fai…