5 papers
Listwise Explanation of Embedding-Based Rankings via Semantic Chunk Grouping
Hyunkyu Kim, Yeeun Yoo, Youngjun Kwak
Dense embedding rankers score documents through contextual sentence- and passage-level representations. Yet many listwise explanation methods still attribute rankings to isolated w…
Membrane: A Self-Evolving Contrastive Safety Memory for LLM Agent Defense
Minseok Choi, Seungbin Yang, Dongjin Kim +5
Despite advances in safety alignment, large language models remain vulnerable to continuously evolving jailbreaks. Existing fine-tuned safety classifiers cannot adapt to these evol…
K-FinHallu: A Hallucination Detection Benchmark for Multi-Turn RAG in Korean Finance
Eunbyeol Cho, Yunseung Lee, Mirae Kim +3
Large Language Models (LLMs) have advanced financial automation through Retrieval-Augmented Generation (RAG), yet hallucinations remain a critical barrier to deployment in high-sta…
ExpGuard: LLM Content Moderation in Specialized Domains
Minseok Choi, Dongjin Kim, Seungbin Yang +5
With the growing deployment of large language models (LLMs) in real-world applications, establishing robust safety guardrails to moderate their inputs and outputs has become essent…
Query Generation Pipeline with Enhanced Answerability Assessment for Financial Information Retrieval
Hyunkyu Kim, Yeeun Yoo, Youngjun Kwak
As financial applications of large language models (LLMs) gain attention, accurate Information Retrieval (IR) remains crucial for reliable AI services. However, existing benchmarks…