4 papers
Over-Personalization Is a Decision Failure: Generation-Induced Apply Bias in LLMs
Haeun Jang, Yonghyun Jun, Hwanhee Lee
Personalized LLMs must decide, for each stored preference, whether the current context calls for applying or suppressing it, which we call its applicability. They frequently over-p…
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…
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…
MARCH: Evaluating the Intersection of Ambiguity Interpretation and Multi-hop Inference
Jeonghyun Park, Ingeol Baek, Seunghyun Yoon +5
Real-world multi-hop QA is naturally linked with ambiguity, where a single query can trigger multiple reasoning paths that require independent resolution. Since ambiguity can occur…