Papers by Kevin Chen-Chuan Chang

15 papers
Coordinated Topic Modeling (2022.emnlp-main)

Copied to clipboard

Challenge: Rather than finding arbitrary topics, people often want to explore the text based on some welldefined topics.
Approach: They propose a problem called coordinated topic modeling that imitates human behavior while describing a text corpus.
Outcome: The proposed model is superior to baseline models on multiple domains.
Are Large Pre-Trained Language Models Leaking Your Personal Information? (2022.findings-emnlp)

Copied to clipboard

Challenge: Pre-trained language models (PLMs) are prone to leaking personal information due to memorization, but the risk of specific personal information being extracted by attackers is low.
Approach: They analyze whether large pre-trained language models are prone to leaking personal information due to memorization.
Outcome: The proposed model is weak at association, so the risk of specific personal information being extracted by attackers is low.
Descriptive Knowledge Graph in Biomedical Domain (2023.emnlp-demo)

Copied to clipboard

Challenge: Existing systems that retrieve unconnected passages do not provide efficient search for relational knowledge.
Approach: They propose a system that automatically extracts and generates informative and descriptive sentences from the biomedical corpus and facilitates efficient search for relational knowledge.
Outcome: The proposed system extracts and generates informative and descriptive sentences from the biomedical corpus and facilitates the efficient search for relational knowledge.
MiniELM: A Lightweight and Adaptive Query Rewriting Framework for E-Commerce Search Optimization (2025.findings-acl)

Copied to clipboard

Challenge: Existing methods for rewriting query terms struggle with natural language understanding . generative methods face high inference latency and cost in offline settings .
Approach: They propose a hybrid pipeline for rewriting query queries using offline knowledge distillation and online reinforcement learning.
Outcome: The proposed pipeline improves query relevance, diversity, adaptability and cost-effective evaluation without manual annotations on Amazon ESCI dataset.
DEER: Descriptive Knowledge Graph for Explaining Entity Relationships (2022.emnlp-main)

Copied to clipboard

Challenge: Existing knowledge graphs lack two desired features for modeling entity relationships: openness and informativeness.
Approach: They propose a self-supervised learning method to extract relation descriptions with the analysis of dependency patterns and generate relation descriptions using a transformer-based relation description synthesizing model.
Outcome: The proposed system extracts and generates high-quality relation descriptions without human labeling.
Query Optimization for Parametric Knowledge Refinement in Retrieval-Augmented Large Language Models (2025.findings-emnlp)

Copied to clipboard

Challenge: Extract-Refine-Retrieve-Read is a query optimization framework for large language models . it is designed to bridge the pre-retrieval information gap in Retriev-Augmented Generation systems .
Approach: They propose a framework to extract parametric knowledge from Large Language Models and refine them using a specialized query optimizer.
Outcome: The extract-refine-retrieve-read framework outperforms baselines on QA datasets . it is designed to meet the knowledge requirements of large language models (LLMs)
Understanding Jargon: Combining Extraction and Generation for Definition Modeling (2022.emnlp-main)

Copied to clipboard

Challenge: Existing methods for generating definitions of words/phrases perform poorly on jargon.
Approach: They propose to combine extraction and generation for jargon definition modeling by extracting definitional information from the Web and incorporating extracted definitional data.
Outcome: The proposed method outperforms state-of-the-art models significantly on jargon definitions.
Understanding Cross-Domain Adaptation in Low-Resource Topic Modeling (2025.acl-long)

Copied to clipboard

Challenge: Existing topic modeling models struggle in low-resource settings where data is limited . et al., 2003: domain adaptation for low-source topic modeling is challenging in low resources .
Approach: They propose a domain adaptation framework that disentangles domaininvariant and domain-specific components to improve topic adaptation.
Outcome: The proposed model outperforms state-of-the-art methods on low-resource datasets on diverse datasets.
Towards Reasoning in Large Language Models: A Survey (2023.findings-acl)

Copied to clipboard

Challenge: Reasoning is a fundamental aspect of human intelligence that plays a crucial role in many intellectual activities.
Approach: They propose to improve LLMs' ability to elicit reasoning by providing exemplars or prompts to model reasoning.
Outcome: This paper provides a comprehensive overview of the state of knowledge on reasoning in large language models.
DimonGen: Diversified Generative Commonsense Reasoning for Explaining Concept Relationships (2023.acl-long)

Copied to clipboard

Challenge: Existing models that describe concepts in everyday situations are difficult to summarize in a single sentence.
Approach: They propose DimonGen, which generates sentences describing concept relationships in everyday scenarios.
Outcome: The proposed model outperforms baseline models in terms of quality and diversity of generated sentences.
Unsupervised Open-domain Keyphrase Generation (2023.acl-long)

Copied to clipboard

Challenge: Existing models that generate keyphrases without human-labeled data are lacking in this area.
Approach: They propose a model that consists of two modules that can be built in an unsupervised fashion and can perform consistently across domains.
Outcome: The proposed model performs consistently across domains and narrows the gap between supervised and unsupervised models down to about 16%.
ERU-KG: Efficient Reference-aligned Unsupervised Keyphrase Generation (2025.acl-long)

Copied to clipboard

Challenge: Existing methods for keyphrase prediction rely on heuristicically defined importance scores . existing methods lack consideration for time efficiency .
Approach: They propose an unsupervised keyphrase generation model that combines informativeness and phraseness modules.
Outcome: The proposed model outperforms baseline models and achieves 89% of the performance of a supervised model for top 10 predictions.
Writing Like the Best: Exemplar-Based Expository Text Generation (2025.acl-long)

Copied to clipboard

Challenge: Existing methods for expository text generation rely on extensive domain corpora and are difficult to adapt topic-specific content.
Approach: They propose a task to generate an expository text on a new topic using an exemplar on . they propose Adaptive Imitation and a Recurrent Plan-then-Adapt framework that leverages large language models for effective adaptive imitation.
Outcome: The proposed framework surpasses existing baselines in producing factual, consistent, and relevant texts for this task.
When to Use What: An In-Depth Comparative Empirical Analysis of OpenIE Systems for Downstream Applications (2023.acl-long)

Copied to clipboard

Challenge: Existing consensus on which OpenIE model is best for each application is lacking . different assumptions made by different models and datasets have a statistically significant effect on performance, making it important to choose the most appropriate OpenIE system for one’s applications.
Approach: They propose to use OpenIE to extract relation tuples from plain text to compare different models and training sets to find the best model for their applications.
Outcome: The proposed models perform well on a Complex QA application.
Can Language Models Be Specific? How? (2023.findings-acl)

Copied to clipboard

Challenge: Existing pre-trained language models have a preference for more specific answers . however, there may exist multiple answers for a query, while not all answers are equally specific.
Approach: They propose to build a benchmark for specificity testing by forming masked token prediction tasks with prompts.
Outcome: The proposed methods improve the specificity of pre-trained language models without additional training.

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