Joeun Kim — accepted AI-conference papers

2026

Block-wise Codeword Embedding for Reliable Multi-bit Text Watermarking

Joeun Kim, HoEun Kim, Dongsup Jin, Young-Sik Kim

ICML 2026poster

Recent multi-bit watermarking methods for large language models (LLMs) prioritize capacity over reliability, often conflating decoding with detection. Our analysis reveals that existing ECC-based extractors suffer from catastrophic false positive rates (FPR), and applying rejection thresholds merely…

Cited by 0 Source ↗Scholar ↗

2026

Breaking the Reference Bottleneck via Learning to Rewrite Conversational Queries without Gold Reference Passages

Doyoung Kim, Youngjun Lee, Joeun Kim, Jihwan Bang, Hwanjun Song, Susik Yoon +1

ICML 2026poster

Conversational query reformulation (CQR) has become indispensable for improving retrieval in dialogue-based applications. However, existing approaches typically rely on reference passages for optimization, which are **impractical** to acquire in real-world scenarios. To address this limitation, we i…

Cited by 0 Source ↗Scholar ↗