6 papers
Fool Me If You Can: On the Robustness of Binary Code Similarity Detection Models against Semantics-preserving Transformations
Jiyong Uhm, Minseok Kim, Michalis Polychronakis +1
Binary code analysis plays an essential role in cybersecurity, facilitating reverse engineering to reveal the inner workings of programs in the absence of source code. Traditional…
Rescuing the Unpoisoned: Efficient Defense against Knowledge Corruption Attacks on RAG Systems
Minseok Kim, Hankook Lee, Hyungjoon Koo
Large language models (LLMs) are reshaping numerous facets of our daily lives, leading widespread adoption as web-based services. Despite their versatility, LLMs face notable chall…
KRETA: A Benchmark for Korean Reading and Reasoning in Text-Rich VQA Attuned to Diverse Visual Contexts
Taebaek Hwang, Minseo Kim, Gisang Lee +2
Understanding and reasoning over text within visual contexts poses a significant challenge for Vision-Language Models (VLMs), given the complexity and diversity of real-world scena…
Refine-n-Judge: Curating High-Quality Preference Chains for LLM-Fine-Tuning
Derin Cayir, Renjie Tao, Rashi Rungta +6
Large Language Models (LLMs) have demonstrated remarkable progress through preference-based fine-tuning, which critically depends on the quality of the underlying training data. Wh…
PrismRAG: Boosting RAG Factuality with Distractor Resilience and Strategized Reasoning
Mohammad Kachuee, Teja Gollapudi, Minseok Kim +10
Retrieval-augmented generation (RAG) often falls short when retrieved context includes confusing semi-relevant passages, or when answering questions require deep contextual underst…
Aligning Large Language Models via Fine-grained Supervision
Dehong Xu, Liang Qiu, Minseok Kim +2
Pre-trained large-scale language models (LLMs) excel at producing coherent articles, yet their outputs may be untruthful, toxic, or fail to align with user expectations. Current ap…