Papers by Jingun Kwon
Length Representations in Large Language Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models (LLMs) have shown remarkable capabilities across various tasks, that are learned from massive amounts of text-based data. |
| Approach: | They propose to scale hidden units within the model to control output sequence length without losing the informativeness of the generated text. |
| Outcome: | The output sequence length is controlled by multiple head attention mechanisms, which can be adjusted in a disentangled manner. |
Abstractive Document Summarization with Summary-length Prediction (2023.findings-eacl)
Copied to clipboard
| Challenge: | Existing abstractive summarization models do not consider summarizing-specific information such as the target summary length. |
| Approach: | They propose a method for enabling a model to understand summarization-specific information by predicting the summary length in the encoder and generating a summary of the predicted length in fine-tuning. |
| Outcome: | The proposed method improves ROUGE scores on the WikiHow, NYT, and CNN/DM datasets. |
Considering Nested Tree Structure in Sentence Extractive Summarization with Pre-trained Transformer (2021.emnlp-main)
Copied to clipboard
| Challenge: | Sentence extractive summarization shortens a document by selecting sentences for a summary while preserving its important contents. |
| Approach: | They propose a nested tree-based extractive summarization model on RoBERTa that uses syntactic and discourse trees to represent sentences in a given document. |
| Outcome: | The proposed model outperforms baseline models on the CNN/DailyMail dataset and achieves significantly better scores than the baseline models in terms of coherence and comparable scores to the state-of-the-art models. |
gMBA: Expression Semantic Guided Mixed Boolean-Arithmetic Deobfuscation Using Transformer Architectures (2025.findings-acl)
Copied to clipboard
| Challenge: | Mixed Boolean-Arithmetic (MBA) obfuscation protects intellectual property by converting programs into complex forms that are difficult to analyze. |
| Approach: | They propose a mixed-boolean-arithmetic (MBA) obfuscation framework that transforms a Transformer-based neural encoder-decoder into a truth table that is an automatically constructed semantic representation of an expression's behavior. |
| Outcome: | The proposed framework improves performance and highlights the importance of internal semantic expressions in recovering obfuscated code to its original form. |
Measuring Watermarking under Jailbreaking: ASR Inflation and Goal-Compliance Mismatch (2026.findings-acl)
Copied to clipboard
| Challenge: | Recent work studies watermarking under benign prompts, but its behavior under jailbreaking prompts remains underexplored. |
| Approach: | They evaluate six methods on four LLMs using two jailbreak benchmarks and three settings: Static, AutoDAN, and DSN. |
| Outcome: | The proposed methods inflate judge-based attack success rate under jailbreaking, but not harmful-goal compliance. |
Hierarchical Trivia Fact Extraction from Wikipedia Articles (2020.coling-main)
Copied to clipboard
| Challenge: | Existing methods for extracting trivia facts for Wikipedia categories are not efficient . a trivia fact is an interesting fact that is unusual, unexpected, or unique . |
| Approach: | They propose an unsupervised algorithm that automatically mines trivia facts for a given entity . they propose to target at a single Wikipedia article and leverage its hierarchical structure . |
| Outcome: | The proposed algorithm outperforms existing methods and is 100 times faster than existing methods. |
A New Surprise Measure for Extracting Interesting Relationships between Persons (2021.eacl-demos)
Copied to clipboard
| Challenge: | Interesting facts are useful information for a variety of important tasks. |
| Approach: | They propose a method that extracts all personal relationships from dependency trees and calculates surprise scores for distributed representations of the extracted relationships in an unsupervised manner. |
| Outcome: | The proposed method extracts all personal relationships from dependency trees for the texts and calculates surprise scores for distributed representations of the extracted relationships in an unsupervised manner. |
Hierarchical Label Generation for Text Classification (2023.findings-eacl)
Copied to clipboard
| Challenge: | None Hierarchical text classification (HTC) aims to assign the most relevant labels with their structure for a given document. |
| Approach: | They propose a method that captures the label hierarchy for real-world classification applications by using a taxonomic hierarchy. |
| Outcome: | The proposed method can generate unseen labels in subword level. |
InstructCMP: Length Control in Sentence Compression through Instruction-based Large Language Models (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing sentences do not consider the length constraints in extractive summarization because of their limited model abilities. |
| Approach: | They propose an approach that incorporates length constraints without model modifications into sentences . they use traditional sentence compression datasets to transform them into instruction format . |
| Outcome: | The proposed method can consider the length constraint through instructions without model modifications. |
Considering Length Diversity in Retrieval-Augmented Summarization (2025.findings-naacl)
Copied to clipboard
| Challenge: | Existing methods that require exhaustive exemplar-exemplar relevance comparisons do not consider summary lengths. |
| Approach: | They propose a Diverse Length-aware Maximal Marginal Relevance algorithm to better control summary lengths. |
| Outcome: | The proposed algorithm reduces the computational cost and memory consumption while maintaining the same level of informativeness. |
Beyond Sampling: Self-Sorting for Long-Context Ranking (2026.findings-eacl)
Copied to clipboard
| Challenge: | Large language models (LLMs) remain unstable on long-context ranking. |
| Approach: | They propose a method that fuses explicit within-list positions with implicit cross-list preferences to score entities and return a top-k set. |
| Outcome: | Experimental results show that large language models remain unstable on long-context ranking . |
ConRAS: Contrastive In-context Learning Framework for Retrieval-Augmented Summarization (2026.findings-eacl)
Copied to clipboard
| Challenge: | Despite progress in natural language processing, the potential of contrastive learning remains unexplored. |
| Approach: | They propose a framework that injects contrastive objectives into in-context learning-based retrieval-augmented summarization. |
| Outcome: | The proposed framework outperforms state-of-the-art retrieval-augmented methods on three summarization benchmarks showing that it can distinguish between positive and negative samples without parameter updates. |
Enhancing Factuality through Consensus and Consistency in Summarization Using Minimum Bayes Risk Decoding (2026.findings-acl)
Copied to clipboard
Riza Setiawan Soetedjo, Yusuke Sakai, Hidetaka Kamigaito, Jingun Kwon, Manabu Okumura, Taro Watanabe
| Challenge: | Existing methods to improve summarization quality are limited to using source as guidance . reranking can be effective, but there are limitations, such as relying on reference-free metrics and rely on a single metric. |
| Approach: | They propose a model that reranks model-generated summaries by considering consistency to the source document and consensus among the other candidates. |
| Outcome: | The proposed system is competitive with existing methods, with human evaluations further confirming that it is superior. |