Yeounoh Chung
SystemsResearch@Google.
Authored Publications
Sort By
Fine-Grained Table Retrieval for Open-Domain Tabular Question Answering
Xingyu Ji
Wojciech Kosiuk
Madelon Hulsebos
Proceedings of the 11th Workshop on Automated Knowledge Base Construction (AKBC 2026), Association for Computational Linguistics
Preview abstract
This work introduces a fine-grained table retrieval framework for grounding large
language models in heterogeneous, open-domain relational data. Instead of encoding a query as a single vector, the approach decomposes natural
language queries into semantic components and embeds each independently, enabling
more precise matching of compositional query intent. These representations are used in a staged retrieval pipeline with component-level
search, connectivity-aware grouping, and reranking. Experiments on three TARGET benchmark corpora show consistent improvements in capped recall@k and stronger alignment between query intent and tabular structure over dense retrieval baselines, particularly for longer and more complex queries and when using lightweight embedding models.
View details
Preview abstract
Large Language Models (LLMs) have demonstrated impressive capabilities across a range of natural language processing tasks. In particular, improvements in reasoning abilities and the expansion of context windows have opened new avenues for leveraging these powerful models.
NL2SQL is challenging in that the natural language question is inherently ambiguous, while the SQL generation requires a precise understanding of complex data schema and semantics. One approach to this semantic ambiguous problem is to provide more and sufficient contextual information.
In this work, we explore the performance and the latency trade-offs of the extended context window (a.k.a., long context) offered by Google's state-of-the-art LLM (\textit{gemini-1.5-pro}).
We study the impact of various contextual information, including column example values, question and SQL query pairs, user-provided hints, SQL documentation, and schema. To the best of our knowledge, this is the first work to study how the extended context window and extra contextual information can help NL2SQL generation with respect to both accuracy and latency cost.
We show that long context LLMs are robust and do not get lost in the extended contextual information. Additionally, our long-context NL2SQL pipeline based on Google's \textit{gemini-pro-1.5} achieve a strong performance with 67.41\% on BIRD benchmark (dev) without finetuning and expensive self-consistency based techniques.
View details
Slice Finder: Automated Data Slicing for Model Validation
Neoklis Polyzotis
Steven Whang
Tim Klas Kraska
Proceedings of the IEEE Int' Conf. on Data Engineering (ICDE), 2019 (to appear)
Preview abstract
As machine learning (ML) systems become democratized,
helping users easily debug their models becomes increasingly
important. Yet current data tools are still primitive when
it comes to helping users trace model performance problems
all the way to the data. We focus on the particular prob-
lem of slicing data to identify subsets of the training data
where the model performs poorly. Unlike general techniques
(e.g., clustering) that can find arbitrary slices, our goal is to
find interpretable slices (which are easier to take action com-
pared to arbitrary subsets) that are problematic and large.
We propose Slice Finder, which is an interactive framework
for identifying such slices using statistical techniques. The
slices can be used for applications like diagnosing model fair-
ness and fraud detection where describing slices that are
interpretable to humans is necessary.
View details
Automated Data Slicing for Model Validation: A Big data - AI Integration Approach
Steven Whang
Tim Klas Kraska
Alkis Polyzotis
Ki Hyun Tae
IEEE Transactions on Knowledge and Data Engineering (2019)
Preview abstract
As machine learning systems become democratized, it becomes increasingly important to help users easily debug their
models. However, current data tools are still primitive when it comes to helping users trace model performance problems all the way to
the data. We focus on the particular problem of slicing data to identify subsets of the validation data where the model performs poorly.
This is an important problem in model validation because the overall model performance can fail to reflect that of the smaller subsets,
and slicing allows users to analyze the model performance on a more granular-level. Unlike general techniques (e.g., clustering) that
can find arbitrary slices, our goal is to find interpretable slices (which are easier to take action compared to arbitrary subsets) that are
problematic and large. We propose Slice Finder, which is an interactive framework for identifying such slices using statistical
techniques. Applications include diagnosing model fairness and fraud detection, where identifying slices that are interpretable to
humans is crucial. This research is part of a larger trend of Big data and Artificial Intelligence (AI) integration and opens many
opportunities for new research
View details
Preview abstract
As machine learning (ML) systems become democratized, helping users easily debug their models becomes increasingly important. Yet current data tools are still primitive when it comes to helping users trace model performance problems all the way to the data. We focus on the particular problem of slicing data to identify subsets of the training data where the model performs poorly. Unlike general techniques (e.g., clustering) that can find arbitrary slices, our goal is to find interpretable slices (which are easier to take action compared to arbitrary subsets) that are problematic and large. We propose {\sf Slice Finder}, which is an interactive framework for identifying such slices using statistical techniques. The slices can be used for applications like diagnosing model fairness and fraud detection where describing slices that are interpretable to humans is necessary.
View details
Preview abstract
This is the poster for an existing pub-approved paper: https://pub-tools.googleplex.com/cms/publication/publication-201923585819419475880458635502622248052/change/
View details
