Papers by Xiaochuan Li

2 papers
Evaluating Robustness of Generative Search Engine on Adversarial Factoid Questions (2024.findings-acl)

Copied to clipboard

Challenge: Existing large language models (LLMs)-backed generative search engines may not always be accurate.
Approach: They propose to evaluate the robustness of retrieval-augmented generation in a realistic and high-risk setting where adversaries have only black-box system access.
Outcome: The proposed model exhibits higher susceptibility to factual errors compared to LLMs without retrieval.
Joint Alignment of Multi-Task Feature and Label Spaces for Emotion Cause Pair Extraction (2022.coling-1)

Copied to clipboard

Challenge: Existing methods for ECPE fail to model specific features and interactive features in between, or suffer from inconsistency of label prediction.
Approach: They propose to align ECPE with a feature-task alignment mechanism to model emotion-&cause-specific features and the shared interactive feature.
Outcome: The proposed model outperforms existing systems on all ECA subtasks.

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