Papers by Yunfei Long
An Element-aware Multi-representation Model for Law Article Prediction (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies have shown that using law articles as external knowledge can improve the performance of the Legal Judgment Prediction. |
| Approach: | They propose a Law Article Element-aware Multi-representation Model which makes full use of law article information and can be used for multi-label samples. |
| Outcome: | The proposed model improves the accuracy of 5.84%, macro F1 of 6.42%, and micro F1 by 4.28% compared with baseline models like TopJudge. |
Ciron: a New Benchmark Dataset for Chinese Irony Detection (2020.lrec-1)
Copied to clipboard
| Challenge: | Automatic Chinese irony detection often lacks labeled benchmark datasets . despite its pervasive nature, irony is a trope whose actual meaning differs from what is literally enunciated. |
| Approach: | They propose to use a Chinese benchmark dataset for automatic Chinese irony detection to provide a benchmark for machine learning models. |
| Outcome: | The proposed dataset includes more than 8.7K posts, collected from Weibo, a micro blogging platform. |
Enhancing Speech Large Language Models with Prompt-Aware Mixture of Audio Encoders (2025.emnlp-main)
Copied to clipboard
Weiqiao Shan, Yuang Li, Yuhao Zhang, Yingfeng Luo, Chen Xu, Xiaofeng Zhao, Long Meng, Yunfei Lu, Min Zhang, Hao Yang, Tong Xiao, JingBo Zhu
| Challenge: | Existing work on integrating audio encoders with large language models (LLMs) has focused on semantic understanding tasks, but different tasks may require distinct features that emphasize either semantic or acoustic aspects. |
| Approach: | They propose to use a prompt-aware mixture to enhance the Speech LLM that uses multiple audio encoders to extract different features based on the prompt. |
| Outcome: | The proposed approach outperforms all single-encoder Speech LLMs on ASR, speaker number verification, and AC tasks. |
NovBench: Evaluating Large Language Models on Academic Paper Novelty Assessment (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for evaluating novelty have been proposed, but there is no systematic evaluation of their ability to generate novelty evaluations. |
| Approach: | They propose a benchmark to evaluate large language models’ ability to generate novelty evaluations in support of human peer review. |
| Outcome: | The proposed framework evaluates the quality of LLM-generated novelty evaluations under different prompting strategies. |
MLD-EA: Check and Complete Narrative Coherence by Introducing Emotions and Actions (2025.coling-main)
Copied to clipboard
| Challenge: | Existing studies focus on summarization and question-answering tasks, but neglect logical coherence within stories. |
| Approach: | They propose a model that leverages large language models to identify narrative gaps and generate coherent sentences that integrate seamlessly with the story’s emotional and logical flow. |
| Outcome: | The proposed model enhances narrative understanding and story generation, highlighting LLMs’ potential as effective logic checkers in story writing with logical coherence and emotional consistency. |
Chinese Synesthesia Detection: New Dataset and Models (2022.findings-acl)
Copied to clipboard
| Challenge: | Synesthesia refers to the description of perceptions in one sensory modality through concepts from other modalities. |
| Approach: | They propose a task called synesthesia detection to extract the sensory word of a sentence and predict the original and synesthetic sensory modalities of the corresponding sensory word. |
| Outcome: | The proposed model achieves state-of-the-art on the Chinese synesthesia dataset. |
Affection Driven Neural Networks for Sentiment Analysis (2020.lrec-1)
Copied to clipboard
| Challenge: | Existing deep neural network models lack mechanisms to highlight important sentiment terms. |
| Approach: | They propose a method to incorporate affective knowledge into deep neural network models by mapping affective influence vectors to an affective impact value and integrating them into long-term memory models to highlight affective terms. |
| Outcome: | The proposed approach improves on three large datasets by 1.0% to 1.5% on the benchmark datasets. |
Generator-Assistant Stepwise Rollback Framework for Large Language Model Agent (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to integrate thoughts with actions can cause irreversible error propagation . Xi et al., 2023; Zhang eet coll., 2023) have focused on enhancing large language model (LLM) agents capable of helping humans tackle real-world challenges. |
| Approach: | They propose a framework called Generator-Assistant Stepwise Rollback to induce better decision-making for LLM agents by integrating a generator and an assistant to examine each action produced by the generator. |
| Outcome: | The proposed framework improves on three widely used benchmarks and can integrate seamlessly with other methods. |
Learning to Play Like Humans: A Framework for LLM Adaptation in Interactive Fiction Games (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches prioritize task-specific performance metrics over human-like comprehension of narrative context and gameplay logic. |
| Approach: | They propose a framework that guides Large Language Models to learn and play IF games systematically. |
| Outcome: | The proposed framework aligns LLMs-based agents’ behavior with narrative intent and commonsense constraints to deliver more interpretable, human-like performance. |
Modeling Intra- and Inter-Modal Relations: Hierarchical Graph Contrastive Learning for Multimodal Sentiment Analysis (2022.coling-1)
Copied to clipboard
| Challenge: | Existing studies in Multimodal Sentiment Analysis lack a mechanism to understand complex relations between different modalities. |
| Approach: | They propose a hierarchical graph contrastive learning framework for multimodal sentiment analysis that explores the relationships between modality representations. |
| Outcome: | The proposed framework outperforms the state-of-the-art in multimodal sentiment analysis on two benchmark datasets. |
Prompting Explicit and Implicit Knowledge for Multi-hop Question Answering Based on Human Reading Process (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing studies have not explored the link between PLMs’ pre-training-based knowledge and input passages. |
| Approach: | They propose a framework that uses prompts to connect explicit and implicit knowledge to elicit type-specific reasoning via prompts, a form of implicit knowledge. |
| Outcome: | The proposed model performs comparable to the state-of-the-art on HotpotQA. |