Papers by Jingyao Li

7 papers
Prototype-based Prompt-Instance Interaction with Causal Intervention for Few-shot Event Detection (2024.lrec-main)

Copied to clipboard

Challenge: Few-shot Event Detection (FSED) requires limited labeled data and expensive manual labeling.
Approach: They propose a prototype-based prompt-instance Interaction with causal Intervention model to utilize both prompts and verbalizers and effectively eliminate all biases.
Outcome: The proposed model utilizes both prompts and verbalizers and eliminates all biases on RAMS and ACE datasets.
Document-level Biomedical Relation Extraction Based on Multi-Dimensional Fusion Information and Multi-Granularity Logical Reasoning (2022.coling-1)

Copied to clipboard

Challenge: Existing models with reasoning are single-granularity based on one element information, ignoring complementary fact of different granularities.
Approach: They propose a document-level biomedical relation extraction model called FILR . it uses multi-dimensional information fusion and multi-granularity logic to obtain rich inferences .
Outcome: The proposed model extracts all relation facts from biomedical documents . it is based on multi-dimensional information fusion and multi-granularity logic reasoning . the proposed model achieves state-of-the-art performance on two widely used biomedically corpora .
Logits-Based Finetuning (2025.emnlp-main)

Copied to clipboard

Challenge: Existing methods for developing compact and efficient large language models lack token-level dependencies and linguistic diversity.
Approach: They propose a logits-based fine-tuning framework that integrates supervised learning and knowledge distillation to build enriched training targets using teacher logits and ground truth labels.
Outcome: The proposed method outperforms existing methods on a large-scale logits dataset and a series of science-focused models.
QuickLLaMA: Query-aware Inference Acceleration for Large Language Models (2025.coling-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) struggle with capturing long-distance dependencies within sequences to deeply understand semantics.
Approach: They propose a system that captures relevant information within a fixed window size and provides precise answers to queries.
Outcome: The proposed system can read Harry Potter within 30s and accurately answer the questions.
Reasoning-Oriented and Analogy-Based Methods for Locating and Editing in Zero-Shot Event-Relational Reasoning (2025.coling-main)

Copied to clipboard

Challenge: Existing methods for zero-shot event-relational reasoning require large computational resources and lack interpretability.
Approach: They propose a method for Reasoning-Oriented Locating and Editing which locates and edits key modules of the language model for reasoning about event relations.
Outcome: The proposed method improves interpretability and efficiency with reduced computational cost and achieves SOTA results in zero-shot event-relational reasoning.
Temporal Cognitive Tree: A Hierarchical Modeling Approach for Event Temporal Relation Extraction (2024.findings-emnlp)

Copied to clipboard

Challenge: Recent studies focus on locating relative position of event pairs on timeline . hierarchical modeling approach neglects multidimensional information in temporal relation and hierarchy of reasoning.
Approach: They propose a novel hierarchical modeling approach that mimics human logical reasoning by introducing a Temporal Cognitive Tree.
Outcome: The proposed model outperforms existing methods on TB-Dense and MATRES datasets.
DAPE V2: Process Attention Score as Feature Map for Length Extrapolation (2025.acl-long)

Copied to clipboard

Challenge: Extensive experiments demonstrate that treating attention as a feature map and applying convolution as . a processing method significantly enhances Transformer performance.
Approach: They propose to use the convolution operator to mimic the processing methods in computer vision to treat attention as a feature map and apply it to neighboring attention scores across different heads.
Outcome: The proposed model can be adapted to various attention-related models and achieves high performance.

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