Papers by Gyuwan Kim
Subword Language Model for Query Auto-Completion (D19-1)
Copied to clipboard
| Challenge: | Current neural query auto-completion systems rely on character-level language models but they slow down when queries are long. |
| Approach: | They propose to use subword language models for query auto-completion . they propose to implement a retrace algorithm and a method for approximate marginalization . |
| Outcome: | The proposed model achieves 2.5 times faster while maintaining similar quality to character-level baseline. |
PPA-Plan: Proactive Pitfall Avoidance for Reliable Planning in Long-Context LLM Reasoning (2026.acl-long)
Copied to clipboard
| Challenge: | Large language models struggle with reasoning over long contexts where relevant information is sparsely distributed. |
| Approach: | They propose a plan-and-execute framework that decomposes long-context tasks into an explicit planning stage followed by step-by-step step-through planning. |
| Outcome: | Experiments on long-context QA benchmarks show that PPA-Plan outperforms plan-and-execute methods and direct prompting. |
Consistency Training with Virtual Adversarial Discrete Perturbation (2022.naacl-main)
Copied to clipboard
| Challenge: | Existing methods for regularizing a model are agnostic to the training model and may not be effective for perturbed inputs. |
| Approach: | They propose an augmentation method of adding a discrete noise that would incur the highest divergence between predictions by replacing tokens while keeping original semantics. |
| Outcome: | The proposed method outperforms baselines on semi-supervised text classification tasks and a robustness benchmark. |
Large Product Key Memory for Pretrained Language Models (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing product key memory (PKM) models that increase model capacity with insignificant computational overhead are limited to causal language modeling. |
| Approach: | They propose product key memory (PKM) that enables very efficient and exact nearest neighbor search in a large number of learnable memory slots. |
| Outcome: | The proposed product key memory improves model capacity and performance by replacing a feed-forward network with a model weighted model. |
Efficient Dialogue State Tracking by Selectively Overwriting Memory (2020.acl-main)
Copied to clipboard
| Challenge: | Recent work in dialogue state tracking (DST) is inefficient in that it predicts dialogue state at every turn from scratch. |
| Approach: | They propose a method that selectively overwrites memory for dialogue state tracking by predicting dialogue state on each memory slot and overwriting it with new values. |
| Outcome: | The proposed model achieves state-of-the-art joint goal accuracy with 51.72% in MultiWOZ 2.0 and 53.01% in MultiWoz 2.1 in an open vocabulary-based DST setting. |
Bridging the Training-Inference Gap for Dense Phrase Retrieval (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for building dense retrievers are often misaligned and do not reflect retrieval scenario at inference time. |
| Approach: | They propose a way to validate dense retrievers using a small subset of the entire corpus. |
| Outcome: | The proposed model improves top-1 phrase retrieval accuracy by 2 3 points and top-20 passage retrieval by 2 4 points for open-domain question answering. |
Detecting Training Data of Large Language Models via Expectation Maximization (2026.eacl-long)
Copied to clipboard
| Challenge: | Membership inference attacks aim to determine whether a specific example was used to train a given language model. |
| Approach: | They propose a membership inference approach that iteratively refines prefix effectiveness and membership scores using an expectation-maximization strategy without requiring labeled non-member examples. |
| Outcome: | The proposed approach outperforms baselines under systematically varied distributional overlap and difficulty. |
ScholarBench: A Bilingual Benchmark for Abstraction, Comprehension, and Reasoning Evaluation in Academic Contexts (2025.findings-emnlp)
Copied to clipboard
| Challenge: | ScholarBench evaluates domain-specific knowledge of large language models (LLMs) prior benchmarks lack the scalability to handle complex academic tasks. |
| Approach: | ScholarBench evaluates the academic reasoning ability of large language models . the benchmark is constructed through a three-step process . |
| Outcome: | ScholarBench evaluates the academic reasoning ability of large language models . the benchmark comprises 5,031 examples in Korean and 5,309 examples in English . |
Towards standardizing Korean Grammatical Error Correction: Datasets and Annotation (2023.acl-long)
Copied to clipboard
| Challenge: | Despite the growing number of Korean learners, little research has been conducted on Korean grammatical error correction (GEC) despite the difficulties of the Korean language, there is no evaluation benchmark for Korean GEC. |
| Approach: | They propose to use Korean grammar error correction datasets to train a machine learning model that can automatically annotate Korean errors from parallel corpora. |
| Outcome: | The proposed model outperforms the currently used statistical Korean GEC system on a wider range of error types. |
SSMix: Saliency-Based Span Mixup for Text Classification (2021.findings-acl)
Copied to clipboard
| Challenge: | SSMix synthesizes a sentence while preserving the locality of two original texts by span-based mixing and keeping more tokens related to the prediction relying on saliency information. |
| Approach: | They propose a new method where the operation is performed on input text rather than on hidden vectors like previous approaches. |
| Outcome: | The proposed method outperforms hidden-level mixup methods on a wide range of text classification benchmarks including textual entailment, sentiment classification, and questiontype classification. |
Length-Adaptive Transformer: Train Once with Length Drop, Use Anytime with Search (2021.acl-long)
Copied to clipboard
| Challenge: | Pre-trained language models have achieved notable improvements in various NLP tasks. |
| Approach: | They propose a Length-Adaptive Transformer that can be used for various inference scenarios after one-shot training. |
| Outcome: | The proposed model can be used for various inference scenarios after one-shot training. |