Papers by Jiayi Deng

5 papers
InstructGEC: Enhancing Unsupervised Grammatical Error Correction with Instruction Tuning (2025.coling-main)

Copied to clipboard

Challenge: Recent studies have proposed methods of generating synthetic data for unsupervised GEC . however, the cost of such methods is high and the quality of the data is poor .
Approach: They propose a method to generate synthetic data automatically for unsupervised GEC . they use a masking strategy to mask an erroneous sentence and the instruction consistently .
Outcome: The proposed method outperforms state-of-the-art unsupervised methods on English and Chinese GEC datasets.
Retrieved Sequence Augmentation for Protein Representation Learning (2024.emnlp-main)

Copied to clipboard

Challenge: Using multiple sequence alignments (MSA) to extract evolutionary knowledge is limited.
Approach: They propose to use multiple sequence alignments to augment protein representations . they propose to employ Retrieved Sequence Augmentation to enhance protein representation learning .
Outcome: The proposed method surpasses MSA Transformer by 5% in structural and property prediction tasks while being 373 times faster.
Projecting Out the Malice: A Global Subspace Approach to LLM Detoxification (2026.acl-long)

Copied to clipboard

Challenge: Large language models (LLMs) exhibit exceptional performance but pose inherent risks of generating toxic content.
Approach: They propose a method that removes toxic subspaces from FFN parameters . they propose to use a lightweight method to eliminate toxic subespaces .
Outcome: The proposed method achieves SOTA detoxification while preserving general capabilities without large-scale retraining.
Can LLMs Act as Historians? Evaluating Historical Research Capabilities of LLMs via the Chinese Imperial Examination (2026.acl-long)

Copied to clipboard

Challenge: Existing benchmarks assess basic knowledge breadth or lexical understanding, failing to capture higher-order skills that are central to historical research.
Approach: They propose a benchmark anchored in the Chinese Imperial Examination system that assesses historical knowledge and lexical understanding.
Outcome: The new benchmark aims to assess the ability of LLMs to process historical materials and documents.
Browsing Like Human: A Multimodal Web Agent with Experiential Fast-and-Slow Thinking (2025.acl-long)

Copied to clipboard

Challenge: Existing web agents lack visual perception, planning, and memory abilities, but their reasoning process is deviate from human cognition.
Approach: They propose a multimodal web agent framework that emulates human planning process to decompose complex user instructions.
Outcome: The proposed framework emulates human planning process to decompose complex user instructions.

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