Papers by Xiaojing Yu
Dataset and Enhanced Model for Eligibility Criteria-to-SQL Semantic Parsing (2020.lrec-1)
Copied to clipboard
| Challenge: | Clinical trials require that patients meet eligibility criteria to ensure safety and effectiveness of studies. |
| Approach: | They propose a dataset that includes the first-of-its-kind eligibility-criteria corpus and queries for criteria-to-sql . they propose 'neuro semantic parser' which can translate eligibility criteria to executable SQL queries . |
| Outcome: | The proposed parser outperforms existing state-of-the-art general-purpose models while highlighting the challenges presented by the new dataset. |
RIVAL: Reinforcement Learning with Iterative and Adversarial Optimization for Machine Translation (2025.findings-emnlp)
Copied to clipboard
Tianjiao Li, Mengran Yu, Chenyu Shi, Yanjun Zhao, Xiaojing Liu, Qi Zhang, Xuanjing Huang, Qiang Zhang, Jiayin Wang
| Challenge: | Using reinforcement learning from human feedback, large language models perform poorly when applied to colloquial subtitle translation tasks. |
| Approach: | They propose an adversarial training framework that iteratively updates the offline reward model and the online LLM to improve training outcomes. |
| Outcome: | The proposed training framework significantly improves upon translation baselines. |
Expanding, Retrieving and Infilling: Diversifying Cross-Domain Question Generation with Flexible Templates (2021.eacl-main)
Copied to clipboard
| Challenge: | Existing models for question generation suffer from lack of diversity and bad sentence structures. |
| Approach: | They propose a framework that integrates flexible templates with a neural-based model to generate diverse expressions of questions with sentence structure guidance. |
| Outcome: | The proposed framework generates diverse expressions of questions with sentence structure guidance while maintaining high quality and consistency under automatic evaluation and human evaluation. |
ESF: Efficient Sensitive Fingerprinting for Black-Box Tamper Detection of Large Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) are increasingly utilized in diverse applications, including code generation, legal document analysis, medical diagnosis, and decision-making. |
| Approach: | They propose a fingerprinting method tailored for black-box tamper detection of large language models. |
| Outcome: | The proposed method detects tampering with a 99.2% detection rate using 5 fingerprint samples across state-of-the-art LLMs. |