Papers by Chenhan Yuan
Unsupervised Relation Extraction: A Variational Autoencoder Approach (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for relation extraction use latent variables and supervised training which requires large datasets. |
| Approach: | They propose a VAE-based unsupervised relation extraction technique that uses latent variables as an intermediate variable instead of a latent variable. |
| Outcome: | The proposed method outperforms state-of-the-art methods on the NYT dataset and outperformed existing methods. |
EMPEC: A Comprehensive Benchmark for Evaluating Large Language Models Across Diverse Healthcare Professions (2025.findings-acl)
Copied to clipboard
| Challenge: | Recent advances in Large Language Models (LLMs) show their potential in accurately answering biomedical questions, yet current healthcare benchmarks primarily assess knowledge mastered by medical doctors, neglecting other essential professions. |
| Approach: | They evaluated 17 LLMs including proprietary and open-source models and found they struggled with specialized fields and alternative medicine. |
| Outcome: | The examinations for medical PErsonnel in Chinese (EMPEC) features 157,803 exam questions across 124 subjects and 20 healthcare professions. |
VTechAGP: An Academic-to-General-Audience Text Paraphrase Dataset and Benchmark Models (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing text simplification and paraphrase datasets focus on sentence-level translation. |
| Approach: | They propose a novel academic-to-general-audience text paraphrase dataset . they also propose DSPT5 dynamic soft prompt generative language model . |
| Outcome: | The proposed dataset is the first academic-to-general-audience text paraphrase dataset . it is based on document-level these and dissertation abstract pairs from 8 colleges . |
CAST: Corpus-Aware Self-similarity Enhanced Topic modelling (2025.naacl-long)
Copied to clipboard
Yanan Ma, Chenghao Xiao, Chenhan Yuan, Sabine N Van Der Veer, Lamiece Hassan, Chenghua Lin, Goran Nenadic
| Challenge: | Existing topic modelling methods encode contextual information of documents while ignoring contextual details of candidate centroid words. Existing methods are limited by the contextualization gap. |
| Approach: | They propose a topic modelling method that builds upon candidate centroid word embeddings contextualized on the dataset and a self-similarity-based method to filter out less meaningful tokens. |
| Outcome: | The proposed method significantly enhances the coherence and diversity of generated topics, and handles noisy data, outperforming strong baselines. |
Predicting Rewards Alongside Tokens: Non-disruptive Parameter Insertion for Efficient Inference Intervention in Large Language Model (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to fine tune LLMs produce unsafe responses and unreliable reasoning, but this solution introduces substantial time and space overhead due to the separate models required. |
| Approach: | They propose to insert extra parameters into transformer architecture to predict calibration signals along with original LLM output. |
| Outcome: | The proposed model reduces time and space costs while enabling seamless online deployment. |
ELAINE-medLLM: Lightweight English Japanese Chinese Trilingual Large Language Model for Bio-medical Domain (2025.coling-main)
Copied to clipboard
Ken Yano, Zheheng Luo, Jimin Huang, Qianqian Xie, Masaki Asada, Chenhan Yuan, Kailai Yang, Makoto Miwa, Sophia Ananiadou, Jun’ichi Tsujii
| Challenge: | Existing bilingual or multilingual medical LLMs are limited in multilingual data and therefore perform poorly in non-English languages such as Japanese and Chinese. |
| Approach: | They propose to use a trilingual (English, Japanese, Chinese) large language model adapted for the bio-medical domain to harness the knowledge and abilities of the base model. |
| Outcome: | The proposed model can support English, Japanese, and Chinese and is adapted for a bio-medical domain. |