Papers by Jianyu Liu

6 papers
From Superficial to Deep: Integrating External Knowledge for Follow-up Question Generation Using Knowledge Graph and LLM (2025.coling-main)

Copied to clipboard

Challenge: Existing methods for generating follow-up questions are limited to shallow contextual questions that are uninspiring and have a large gap to the human level.
Approach: They propose a three-stage external knowledge-enhanced follow-up question generation method which generates questions by identifying contextual topics, building a knowledge graph online, and finally combining these with a large language model to generate the final question.
Outcome: The proposed method generates questions by identifying contextual topics, building a knowledge graph (KG) online, and finally combining these with a large language model to generate the final question.
A Web Scale Entity Extraction System (2021.findings-emnlp)

Copied to clipboard

Challenge: Existing systems for large-scale entity extraction are limited by the scale and variety of data available on internet platforms.
Approach: They propose to build an entity extraction system for multiple document types at large scale using multi-modal Transformers.
Outcome: The proposed system extracts multiple types of entities from multiple document types at large scale using multi-modal Transformers.
Detecting AI-Generated Content on Social Media with Multi-modal Language Models (2026.acl-industry)

Copied to clipboard

Challenge: Existing methods for AI-generated content detection face poor generalization to newer models, reliance on single modalities, and lack of interpretable explanations.
Approach: They propose a model that curates diverse social media data and trains a vision-language model for detection and explanation.
Outcome: The proposed model achieves state-of-the-art detection performance on public benchmarks and observes positive downstream impacts on user engagement.
DREAM: Disentangling Risks to Enhance Safety Alignment in Multimodal Large Language Models (2025.naacl-long)

Copied to clipboard

Challenge: Multimodal Large Language Models (MLLMs) pose unique safety challenges due to their integration of visual and textual data.
Approach: They propose a method to disentangle risks through step-by-step reasoning within multimodal inputs.
Outcome: The proposed approach improves safety alignment in MLLMs by fine-tuning and iterative Reinforcement Learning from AI feedback.
SeaLLMs - Large Language Models for Southeast Asia (2024.acl-demos)

Copied to clipboard

Challenge: Existing large language models favor high-resource languages, such as English, at the expense of low-resourced and regional languages.
Approach: They propose a series of language models that specifically focuses on Southeast Asian languages.
Outcome: SeaLLM models outperform ChatGPT-3.5 in non-Latin languages by large margins . linguistic disparity impedes access to state-of-the-art AI technologies for non-English-speaking populations .
PRIMO: Progressive Induction for Multi-hop Open Rule Generation (2024.lrec-main)

Copied to clipboard

Challenge: Existing approaches focus on single-hop open rule generation, ignoring scenarios involving multiple hops, leading to logical inconsistencies between premise and hypothesis atoms, as well as semantic duplication of generated rule atom.
Approach: They propose a multi-stage open rule generation method called PRIMO that introduces ontology information during the rule generation stage to reduce ambiguity and improve rule accuracy.
Outcome: The proposed method reduces the repetition rate of rule atoms while preserving the latent knowledge within the model.

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