11 papers
Ready2Blend: From Natural-Language Instructions to Composable Alignment Prompts
Jeesu Jung, Hwan Chang, Juseon Do +5
Continual alignment requires LLMs to adapt to new requirements without forgetting previously acquired behaviors. Natural-language instructions are flexible and composable but offer…
Leveraging Fine-grained Error Correction in Korean Speech Recognition for Consultation Services
Yonghyun Jun, Jimin Lee, Hwan Chang +3
Automatic Speech Recognition (ASR) technology is fundamental to customer service automation and large-scale transcription. However, even advanced ASR models exhibit inevitable erro…
Scaling Creative Writing Beyond Story-Centric Data with Attribute-Guided Genre Expansion
Hwan Chang, Yongil Kim, Heuiyeen Yeen +3
High-quality creative writing data for large language models (LLMs) remains dominated by story-centric data, limiting models' ability to follow the structural and functional conven…
EXAONE 4.5 Technical Report
Eunbi Choi, Kibong Choi, Sehyun Chun +55
This technical report introduces EXAONE 4.5, the first open-weight vision language model released by LG AI Research. EXAONE 4.5 is architected by integrating a dedicated visual enc…
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…
How Do Large Vision-Language Models See Text in Image? Unveiling the Distinctive Role of OCR Heads
Ingeol Baek, Hwan Chang, Sunghyun Ryu +1
Despite significant advancements in Large Vision Language Models (LVLMs), a gap remains, particularly regarding their interpretability and how they locate and interpret textual inf…
Keep Security! Benchmarking Security Policy Preservation in Large Language Model Contexts Against Indirect Attacks in Question Answering
Hwan Chang, Yumin Kim, Yonghyun Jun +1
As Large Language Models (LLMs) are increasingly deployed in sensitive domains such as enterprise and government, ensuring that they adhere to user-defined security policies within…
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…
Which Retain Set Matters for LLM Unlearning? A Case Study on Entity Unlearning
Hwan Chang, Hwanhee Lee
Large language models (LLMs) risk retaining unauthorized or sensitive information from their training data, which raises privacy concerns. LLM unlearning seeks to mitigate these ri…
Probing-RAG: Self-Probing to Guide Language Models in Selective Document Retrieval
Ingeol Baek, Hwan Chang, Byeongjeong Kim +2
Retrieval-Augmented Generation (RAG) enhances language models by retrieving and incorporating relevant external knowledge. However, traditional retrieve-and-generate processes may…