Papers by Xiaojing Yu

4 papers
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

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.

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