6 papers
Instruction Quality Matters: Refining Instructions for Effective Preference Learning
Seohyeong Lee, Hwaran Lee, Buru Chang
Preference learning optimizes models using response pairs, yet the informativeness of these pairs is fundamentally shaped by the instructions from which they are generated. We iden…
HarDBench: A Benchmark for Draft-Based Co-Authoring Jailbreak Attacks for Safe Human-LLM Collaborative Writing
Euntae Kim, Soomin Han, Buru Chang
Large language models (LLMs) are increasingly used as co-authors in collaborative writing, where users begin with rough drafts and rely on LLMs to complete, revise, and refine thei…
Improving Fisher Information Estimation and Efficiency for LoRA-based LLM Unlearning
Yejin Kim, Eunwon Kim, Buru Chang +1
LLMs have demonstrated remarkable performance across various tasks but face challenges related to unintentionally generating outputs containing sensitive information. A straightfor…
Alignment Data Map for Efficient Preference Data Selection and Diagnosis
Seohyeong Lee, Eunwon Kim, Hwaran Lee +1
Human preference data is essential for aligning large language models (LLMs) with human values, but collecting such data is often costly and inefficient-motivating the need for eff…
SHARE: Shared Memory-Aware Open-Domain Long-Term Dialogue Dataset Constructed from Movie Script
Eunwon Kim, Chanho Park, Buru Chang
Shared memories between two individuals strengthen their bond and are crucial for facilitating their ongoing conversations. This study aims to make long-term dialogue more engaging…
ConVis: Contrastive Decoding with Hallucination Visualization for Mitigating Hallucinations in Multimodal Large Language Models
Yeji Park, Deokyeong Lee, Junsuk Choe +1
Hallucinations in Multimodal Large Language Models (MLLMs) where generated responses fail to accurately reflect the given image pose a significant challenge to their reliability. T…