Papers by Jingyao Li
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
Chuanyang Zheng, Yihang Gao, Han Shi, Jing Xiong, Jiankai Sun, Jingyao Li, Minbin Huang, Xiaozhe Ren, Michael Ng, Xin Jiang, Zhenguo Li, Yu Li
| 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. |