6 papers
Mitigating Cognitive Inertia in Large Reasoning Models via Latent Spike Steering
Seojin Lee, ByeongJeong Kim, Hwanhee Lee
While Large Reasoning Models (LRMs) have achieved remarkable performance by scaling test-time compute, they frequently suffer from Cognitive Inertia, a failure pattern manifesting…
Chronological Passage Assembling in RAG framework for Temporal Question Answering
Byeongjeong Kim, Jeonghyun Park, Joonho Yang +1
Long-context question answering over narrative tasks is challenging because correct answers often hinge on reconstructing a coherent timeline of events while preserving contextual…
Personality Editing for Language Models through Adjusting Self-Referential Queries
Seojin Hwang, Yumin Kim, Byeongjeong Kim +2
Large Language Models (LLMs) are integral to applications such as conversational agents and content creation, where precise control over a model's personality is essential for main…
SAFE-SQL: Self-Augmented In-Context Learning with Fine-grained Example Selection for Text-to-SQL
Jimin Lee, Ingeol Baek, Byeongjeong Kim +2
Text-to-SQL aims to convert natural language questions into executable SQL queries. While previous approaches, such as skeleton-masked selection, have demonstrated strong performan…
Investigating Language Preference of Multilingual RAG Systems
Jeonghyun Park, Hwanhee Lee
Multilingual Retrieval-Augmented Generation (mRAG) systems enhance language models by integrating external multilingual information to produce context-aware responses. However, mRA…
Dynamic Label Name Refinement for Few-Shot Dialogue Intent Classification
Gyutae Park, Ingeol Baek, ByeongJeong Kim +2
Dialogue intent classification aims to identify the underlying purpose or intent of a user's input in a conversation. Current intent classification systems encounter considerable c…