Heuiseok Lim

The paper introduces Privacy-Preserving Fine-Tuning (PPFT), a novel two-stage pipeline that allows LLMs to process sensitive data via pooled embeddings rather than raw text, achieving a strong balance between privacy and model performance.

HiKEY proposes a hierarchical, tree-based multimodal retrieval framework that significantly improves open-domain document question answering by addressing document routing and evidence fragmentation.

The paper proposes MIMO, a two-stage framework that improves Multilingual Information Retrieval (MLIR) by stabilizing cross-lingual alignment and enhancing retrieval discrimination using a combination of knowledge distillation and joint contrastive learning.

This paper systematically evaluates LLMs' ability to infer pragmatic meaning from non-verbal responses, finding that their accuracy significantly drops compared to verbal inputs.

The paper introduces LAMAR, a language aware multilingual cross encoder for multilingual retrieval augmented generation, which prioritizes documents written in the same language as the query for language coherence while maintaining semantic relevance.