Papers by Kevin Chen-Chuan Chang
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. |