Papers by Wook-Shin Han

4 papers
TRIAL: Token Relations and Importance Aware Late-interaction for Accurate Text Retrieval (2025.emnlp-main)

Copied to clipboard

Challenge: Late-interaction based multi-vector retrieval systems rely on a naive summation of token-level similarity scores . this leads to inaccurate relevance estimation due to tokenization of semantic units and the influence of low-content words.
Approach: They propose a late-interaction-based multi-vector retrieval system that uses token relations and token importance in relevance scoring.
Outcome: Extensive tests show that TRIAL achieves state-of-the-art accuracy compared to existing methods.
HELIOS: Harmonizing Early Fusion, Late Fusion, and LLM Reasoning for Multi-Granular Table-Text Retrieval (2025.acl-long)

Copied to clipboard

Challenge: Existing methods for table-text retrieval are limited due to the need to bridge structured tables and unstructured passages.
Approach: They propose a table-text retrieval system that combines the strengths of both approaches . they propose bipartite subgraph retrieval and query-relevant node expansion .
Outcome: The proposed method outperforms state-of-the-art models with a 42.6% and 39.9% improvement on the OTT-QA benchmark.
LILaC: Late Interacting in Layered Component Graph for Open-domain Multimodal Multihop Retrieval (2025.emnlp-main)

Copied to clipboard

Challenge: Existing multimodal document retrieval frameworks focus on textual, tabular, and visual elements, but there is a shift toward open-domain multimodal retrieval.
Approach: They propose a multimodal retrieval framework that uses a component graph and a late-interaction-based subgraph retrieval method to capture semantic relationships between components.
Outcome: The proposed framework achieves state-of-the-art retrieval performance on all five benchmarks . it is based on a layered component graph representing multimodal information at two layers .
SAFE: Schema-Driven Approximate Distance Join for Efficient Knowledge Graph Querying (2025.emnlp-main)

Copied to clipboard

Challenge: Existing methods map an LLM-generated query graph onto the KG or let the LLM traverse the entire graph.
Approach: They propose a framework that leverages schema graphs for robust query graph generation and efficient KG retrieval.
Outcome: Extensive experiments on WebQSP, CWQ and GrailQA show that the proposed framework outperforms state-of-the-art methods in accuracy and efficiency.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations