Papers by Fukun Ma

8 papers
Improving Preference Alignment of LLM with Inference-Free Self-Refinement (2025.findings-emnlp)

Copied to clipboard

Challenge: Large language models (LLMs) develop in-context learning capability through pretraining and instruction tuning.
Approach: Large language models (LLMs) develop in-context learning capability through pretraining and instruction tuning.
Outcome: Experiments show that incorporating IFSR into preference alignment yields performance improvement over 10%.
Character-level White-Box Adversarial Attacks against Transformers via Attachable Subwords Substitution (2022.emnlp-main)

Copied to clipboard

Challenge: Existing methods to attack transformer models are not effective at character level, but they are a natural attack scenario.
Approach: They propose a character-level adversarial attack method against transformer models . they use a gradient-based method to find the most vulnerable words in a sentence .
Outcome: The proposed method outperforms previous methods on sentence-level and token-level tasks.
On the Robustness of Document-Level Relation Extraction Models to Entity Name Variations (2024.findings-acl)

Copied to clipboard

Challenge: Existing DocRE models which perform well may make more mistakes when merely changing the entity names in the document, hindering the generalization to novel entity names.
Approach: They propose a pipeline to generate entity-renamed documents by replacing the original entity names with names from Wikidata.
Outcome: The proposed pipeline generates entity-renamed documents by replacing the original entity names with names from Wikidata.
RAPL: A Relation-Aware Prototype Learning Approach for Few-Shot Document-Level Relation Extraction (2023.emnlp-main)

Copied to clipboard

Challenge: Existing methods to identify semantic relations between entities are time-consuming and labor-intensive.
Approach: They propose a relation-aware prototype learning method for document-level relation extraction (FSDLRE) they propose RAPL, which judiciously leverages relation descriptions and real NOTA instances as guidance .
Outcome: The proposed method outperforms state-of-the-art approaches by 2.61% F1 . it generates task-specific NOTA prototypes and refines relation prototypes .
AMR-based Network for Aspect-based Sentiment Analysis (2023.acl-long)

Copied to clipboard

Challenge: Recent studies have used dependency trees to extract relation between aspects and contexts, but there is a potential mismatch between the dependency tree and sentiment classification as a semantic task.
Approach: They propose to replace the syntactic dependency tree with a semantic structure to capture the relation between an aspect and a context.
Outcome: The proposed model improves ABSA on four public datasets with 1.13% improvement over baselines.
Enhancing Cross-lingual Natural Language Inference by Soft Prompting with Multilingual Verbalizer (2023.findings-acl)

Copied to clipboard

Challenge: Existing approaches to cross-lingual natural language inference lack annotated parallel corpora.
Approach: They propose a new prompt learning framework with the Multilingual Verbalizer for XNLI that uses a multilingual verbalizer to align the representations of original and augmented multilingual questions into a unified semantic space with consistency regularization.
Outcome: The proposed framework outperforms existing methods under few-shot and full-shot cross-lingual transfer settings.
Semi-supervised Relation Extraction via Incremental Meta Self-Training (2021.findings-emnlp)

Copied to clipboard

Challenge: Existing methods suffer from the gradual drift problem, where noisy pseudo labels are incorporated during training.
Approach: They propose a method that uses pseudo labels to assess quality on unlabeled samples . they use a relation label generation network to learn from successful and failed attempts .
Outcome: Experimental results show the proposed method can improve on two public datasets.
Exploring the Compositional Generalization in Context Dependent Text-to-SQL Parsing (2023.findings-acl)

Copied to clipboard

Challenge: Existing models struggle on the text-to-SQL benchmarks, but we propose a method to improve their generalization ability.
Approach: They propose a method to improve the combinatorial generalization of Text-to-SQL models by aligning previous SQL statements with the input utterance.
Outcome: The proposed method improves the generalization ability of Text-to-SQL models.

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