Papers by Weining Qian

7 papers
UnifiedGEC: Integrating Grammatical Error Correction Approaches for Multi-languages with a Unified Framework (2025.coling-demos)

Copied to clipboard

Challenge: Existing tools for GEC have been developed to support research on grammatical errors, but there is no comprehensive evaluation on these models.
Approach: They propose an open-source framework for Grammatical Error Correction that integrates 5 widely-used GEC models and compares their performance on 7 datasets in different languages.
Outcome: The proposed framework compares 5 widely-used models on 7 datasets in different languages.
TagRAG: Tag-guided Hierarchical Knowledge Graph Retrieval-Augmented Generation (2026.findings-acl)

Copied to clipboard

Challenge: Existing approaches to retrieval-augmented generation rely on fragment-level retrieval . GraphRAG suffers from inefficiencies in information extraction and costly resource consumption .
Approach: They propose a tag-guided hierarchical knowledge graph RAG framework for efficient global reasoning and scalable graph maintenance.
Outcome: GraphRAG achieves an average win rate of 78.36% on a dataset spanning agriculture, computer science, law, and cross-domain settings compared with baselines .
Learning Knowledge-Enhanced Contextual Language Representations for Domain Natural Language Understanding (2023.emnlp-main)

Copied to clipboard

Challenge: Existing methods for pre-training KEPLMs with relational triples are difficult to adapt to close domains due to the lack of sufficient domain graph semantics.
Approach: They propose a Knowledge-enhanced language representation learning framework for various closed domains that captures the implicit graph structure among the entities.
Outcome: The proposed framework outperforms existing methods for pre-training KEPLMs in closed domains significantly.
Initializing and Retrofitting Key-Value Adaptors for Traceable Model Editing (2025.findings-acl)

Copied to clipboard

Challenge: Language models (LMs) are becoming imperative tools for consulting in realworld scenarios.
Approach: They propose a model editing method that initializes and retrofits key-value pairs into MLP blocks to construct a new mapping of a piece of knowledge without damaging irrelevant knowledge.
Outcome: The proposed method outperforms baseline methods on a series of GPT series models on edit success and generalization without influencing specificity.
Prompting Large Language Models with Chain-of-Thought for Few-Shot Knowledge Base Question Generation (2023.emnlp-main)

Copied to clipboard

Challenge: Existing methods for question generation over knowledge bases rely on annotated data for fine-tuning . emergence of Large Language Models (LLMs) has shown impressive generalization ability in few-shot tasks.
Approach: They propose to use a logical form to generate a question in a reasoning problem . they propose to extend the prompting method into a method that can generate questions in logical forms .
Outcome: The proposed method outperforms baselines on three public KBQG datasets.
Diff4TST: Masked Diffusion Language Model for Text Style Transfer (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for text style transfer rely on task-specific training and expensive training stages.
Approach: They propose a diffusion-based language model that formulates text style transfer as an explicit copy-and-edit process.
Outcome: The proposed model improves style accuracy and controllability while maintaining strong content preservation and fluency.
XtremeCLIP: Extremely Parameter-efficient Tuning for Low-resource Vision Language Understanding (2023.findings-acl)

Copied to clipboard

Challenge: Existing approaches to fine-tune visual-language understanding (VLU) require tasks-specific designs and sufficient training data.
Approach: They propose a simple yet efficient paradigm for low-resource Visual Language Understanding (VLU) they reformulate a series of VLU tasks as an open-book affinity-matching problem.
Outcome: The proposed framework outperforms baselines in low-resource settings.

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