Papers by Yingming Li

8 papers
When Long Helps Short: How Context Length in Supervised Fine-tuning Affects Behavior of Large Language Models (2025.emnlp-main)

Copied to clipboard

Challenge: Large language models (LLMs) have achieved impressive performance across NLP tasks.
Approach: They propose to use long-context SFT to improve short-contemporary performance . they also decouple and analyze two key components, Multi-Head Attention and Feed-Forward Network .
Outcome: The proposed model improves short-context performance, contrary to pretraining.
Beyond Surface Simplicity: Revealing Hidden Reasoning Attributes for Precise Commonsense Diagnosis (2025.acl-long)

Copied to clipboard

Challenge: Existing commonsense question answering benchmarks often treat these aspects in isolation, resulting in evaluation accuracy differences of up to 24.8% across different difficulty levels.
Approach: They propose a framework that reveals hidden reasoning attributes behind commonsense questions by leveraging the knowledge generated during the reasoning process.
Outcome: The proposed framework reveals hidden reasoning attributes behind commonsense questions by leveraging the knowledge generated during the reasoning process.
BERT-enhanced Relational Sentence Ordering Network (2020.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to improve coherence modeling for paragraphs have been developed.
Approach: They propose a BERT-enhanced Relational Sentence Ordering Network to capture better dependency relationship among sentences and exploit it with a deep relational module.
Outcome: The proposed model shows significant improvement over the state-of-the-art on six datasets.
Low-Rank HOCA: Efficient High-Order Cross-Modal Attention for Video Captioning (D19-1)

Copied to clipboard

Challenge: Existing studies on video captioning focus on the association relationships between multiple modalities.
Approach: They propose a video captioning model with high-order cross-modal attention (HOCA) they propose low-rank HOCA which adopts tensor decomposition to reduce the space requirement .
Outcome: The proposed model captures cross-modal interaction of different modalities and reduces space requirement.
LNE-Blocking: An Efficient Framework for Contamination Mitigation Evaluation on Large Language Models (2025.findings-emnlp)

Copied to clipboard

Challenge: a problem of data contamination is now almost inevitable during the development of large language models, with the training data often integrating evaluation benchmarks even unintentionally.
Approach: They propose a framework to restore model performance prior to data contamination on potentially leaked datasets by using contamination detection and disruption operation.
Outcome: The proposed framework restores model performance prior to contamination on potentially leaked datasets.
Deep Attentive Sentence Ordering Network (D18-1)

Copied to clipboard

Challenge: Existing methods for sentence ordering tasks rely on linguistic knowledge and are domain specific.
Approach: They propose a deep attentive sentence ordering network which integrates self-attention mechanism with LSTMs in the encoding of input sentences.
Outcome: The proposed model outperforms the state-of-the-art models on Sentence Ordering and Order Discrimination tasks and is shown to be highly efficient.
Dual Low-Rank Multimodal Fusion (2020.findings-emnlp)

Copied to clipboard

Challenge: Existing tensor-based fusion methods make poor use of fine-grained temporal dynamics of multimodal sequential features.
Approach: They propose a novel multimodal fusion method called Fine-Grained Temporal Low-Rank Multimodal Fusion that uses low-rank tensor approximation along dual dimensions of input features.
Outcome: The proposed method outperforms the state-of-the-art tensor-based methods with a similar computational complexity.
Fine-tune BERT with Sparse Self-Attention Mechanism (D19-1)

Copied to clipboard

Challenge: Existing sparse self-attention fine-tuning models have been used to improve sentiment analysis, question answering, and natural language inference tasks.
Approach: They propose a Sparse Self-Attention Fine-tuning model which integrates sparsity into self-attention mechanism to enhance the fine-tune performance of BERT.
Outcome: The proposed model outperforms the baseline models on sentiment analysis, question answering, and natural language inference tasks and is able to interpret the input better.

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