Papers by Hogun Park

3 papers
Improving Multi-hop Logical Reasoning in Knowledge Graphs with Context-Aware Query Representation Learning (2024.findings-acl)

Copied to clipboard

Challenge: Existing methods rely on linear sequential operations to solve First-Order Logic queries.
Approach: They propose a model-agnostic approach that fully integrates the context of the query graph.
Outcome: The proposed method improves performance on two datasets by 19.5%.
Enhancing Complex Reasoning in Knowledge Graph Question Answering through Query Graph Approximation (2025.findings-acl)

Copied to clipboard

Challenge: Existing knowledge-grounded question answering frameworks lack essential triplets related to the questions . Existing approaches to knowledge-based QA are incomplete in the context of KGs .
Approach: They propose a framework to provide answers to structured queries by leveraging Knowledge Graphs.
Outcome: The proposed framework outperforms existing methods on QA tasks where KGs are incomplete . the framework is based on a set of data from a dataset of QA questions .
Large Language Models Are Better Logical Fallacy Reasoners with Counterargument, Explanation, and Goal-Aware Prompt Formulation (2025.findings-naacl)

Copied to clipboard

Challenge: Recent large language models have demonstrated improved processing of complex language, but detecting logical fallacies remains a challenge.
Approach: They propose a prompt formulation approach for logical fallacy detection that integrates contextual information into input text and queries for validity within the argument’s context.
Outcome: The proposed approach improves over state-of-the-art models by 0.57 in F1-scores and 0.45 in fine-tuned models.

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