Seung-won Hwang

XINA: Explainable Instance Alignment Using Dominance Relationship

2018 · IEEE Transactions on Knowledge and Data Engineering

Over the past few years, knowledge bases (KBs) like DBPedia, Freebase, and YAGO have accumulated a massive amount of knowledge from web data. Despite their seemingly large size, however, individual KBs often lack comprehensive information …

ReACC: A Retrieval-Augmented Code Completion Framework

2022 · arXiv (Cornell University)

Code completion, which aims to predict the following code token(s) according to the code context, can improve the productivity of software development. Recent work has proved that statistical language modeling with transformers can greatly improve …

Intervention-Based Alignment of Code Search with Execution Feedback

2023

One of the fundamental goals in code search is to retrieve a functionally correct code for a given natural language query. As annotating for correctness requires executing test cases (i.e. obtaining execution feedback), existing code …

Disentangling Questions from Query Generation for Task-Adaptive Retrieval

2024

This paper studies the problem of information retrieval, to adapt to unseen tasks.Existing work generates synthetic queries from domainspecific documents to jointly train the retriever.However, the conventional query generator assumes the query as a question, …

ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answering

2025 · arXiv (Cornell University)

Retrieval-Augmented Generation (RAG) systems are increasingly diverse, yet many suffer from monolithic designs that tightly couple core functions like query reformulation, retrieval, reasoning, and verification. This limits their interpretability, systematic evaluation, and targeted improvement, especially …

KBQA

2017 · Proceedings of the VLDB Endowment

Question answering (QA) has become a popular way for humans to access billion-scale knowledge bases. Unlike web search, QA over a knowledge base gives out accurate and concise results, provided that natural language questions can …

Paraphrase Diversification Using Counterfactual Debiasing

2019 · Proceedings of the AAAI Conference on Artificial Intelligence

The problem of generating a set of diverse paraphrase sentences while (1) not compromising the original meaning of the original sentence, and (2) imposing diversity in various semantic aspects, such as a lexical or syntactic …