Papers by Jingyi Zhang
Multi-pass Decoding for Grammatical Error Correction (2024.emnlp-main)
Copied to clipboard
| Challenge: | Seq2edit models decode only once without aware of subsequent tokens. |
| Approach: | They propose to iteratively refine the correction results of seq2seq models via Multi-Pass Decoding (MPD) to improve performance, but MPD increases inference costs . they propose to merge the source input and previous round correction result into one sequence. |
| Outcome: | Experiments on the CoNLL-14 and BEA-19 test set show that the proposed approach improves over baselines. |
DentalGPT: Incentivizing Multimodal Reasoning in Dentistry (2026.findings-acl)
Copied to clipboard
Zhenyang Cai, Jiaming Zhang, Junjie Zhao, Ziyi Zeng, Yanchao Li, Liang Jingyi, Junying Chen, Yunjin Yang, Jiajun You, Shuzhi Deng, null Xieruiqiii, Yuanting Chen, Xiangyi Feng, Jianquan Li, Liangyi Chen, Junwen Wang, Shan Jiang, Benyou Wang
| Challenge: | Current multimodal large language models (MLLMs) show limited understanding of dental images. |
| Approach: | They propose a dental-specialized multimodal large language model trained via staged multimodal alignment and reinforcement learning. |
| Outcome: | The proposed model outperforms state-of-the-art models on disease classification and dental VQA tasks. |
Exploring Multimodal Relation Extraction of Hierarchical Tabular Data with Multi-task Learning (2025.acl-long)
Copied to clipboard
| Challenge: | Existing studies overlook the need of mining relations among multiple columns rather than just the semantic relation between two specific columns in real-world practice. |
| Approach: | They propose a Chain-of-Thought distillation framework with self-correction mechanism to enhance MLLMs’ reasoning capabilities without increasing parameter scale. |
| Outcome: | The proposed method significantly outperforms baselines on wide datasets. |
Translation Quality Estimation by Jointly Learning to Score and Rank (2020.emnlp-main)
Copied to clipboard
| Challenge: | The translation quality estimation (QE) task aims to evaluate the general quality of a translation without using reference translations. |
| Approach: | They propose a translation quality estimation task that uses translations as reference . they propose supervised learning using cross-lingual sentence embeddings from pre-trained multilingual models. |
| Outcome: | The proposed model outperforms sentBLEU on the WMT 2019 QE as a Metric task and outperformed sentBLUE on the QE in a multilingual language task. |
Flooding-X: Improving BERT’s Resistance to Adversarial Attacks via Loss-Restricted Fine-Tuning (2022.acl-long)
Copied to clipboard
Qin Liu, Rui Zheng, Bao Rong, Jingyi Liu, ZhiHua Liu, Zhanzhan Cheng, Liang Qiao, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Existing approaches to generating adversarial perturbations scale up the cost of training computational complexity by the number of gradient steps it takes to obtain the adversarials. |
| Approach: | They propose a flood method which aims at better generalization and a criterion to bring hyper-parameter-dependent flooding into effect with a narrowed-down search space by measuring how the gradient steps taken within one epoch affect the loss of each batch. |
| Outcome: | The proposed method improves BERT’s resistance to textual adversarial attacks by a large margin and achieves state-of-the-art robust accuracy on various text classification and GLUE tasks. |
Lipschitz Constrained Parameter Initialization for Deep Transformers (2020.acl-main)
Copied to clipboard
| Challenge: | Existing studies show that deep Transformers have difficulty in training even with residual connection and layer normalization. |
| Approach: | They propose a method that leverages the Lipschitz constraint on the initialization of Transformer parameters to ease the optimization difficulties caused by its multi-layer encoder/decoder structure. |
| Outcome: | The proposed model outperforms previous RNN/CNN models but fails to converge with the original computation order. |
Learning Source Phrase Representations for Neural Machine Translation (2020.acl-main)
Copied to clipboard
| Challenge: | Existing approaches to machine translation have been shown to be effective for long sentences . however, the attentional network can't capture long-distance dependencies . |
| Approach: | They propose a multi-head attention mechanism which generates phrase representations from token representations and incorporates them into the Transformer translation model to enhance its ability to capture long-distance relationships. |
| Outcome: | The proposed model can be computed in parallel and improves on the WMT 14 tasks. |
Argument Pair Extraction with Mutual Guidance and Inter-sentence Relation Graph (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies on argumentation mining focus on monological argumentation and dialogical argumentation. |
| Approach: | They propose a mutual guidance framework that could guide arguments in one passage . they propose an inter-sentence relation graph to effectively model the inter-relations between two sentences . |
| Outcome: | The proposed method outperforms the current state-of-the-art model. |
Enhancing Contrastive Learning with Noise-Guided Attack: Towards Continual Relation Extraction in the Wild (2024.acl-long)
Copied to clipboard
| Challenge: | Existing methods for continual relation extraction (CRE) excel in preserving old knowledge but falter when confronted with contaminated data streams. |
| Approach: | They propose a noise-resistant contrastive framework for continual relation extraction (CRE) that preserves old knowledge while learning incremental corrupted relations. |
| Outcome: | The proposed framework outperforms state-of-the-art methods on various benchmarks with increasing noise rates. |
LLMEval-Fair: A Large-Scale Longitudinal Study on Robust and Fair Evaluation of Large Language Models (2026.acl-long)
Copied to clipboard
Ming Zhang, Yujiong Shen, Jingyi Deng, Yuhui Wang, Huayu Sha, Kexin Tan, Qiyuan Peng, Yue Zhang, Junzhe Wang, Shichun Liu, Yueyuan Huang, Jingqi Tong, Changhao Jiang, Yilong Wu, Zhihao Zhang, Mingqi Wu, Mingxu Chai, Zhiheng Xi, Shihan Dou, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Existing evaluation of Large Language Models on static benchmarks is vulnerable to data contamination and leaderboard overfitting. |
| Approach: | LLMEval-Fair framework provides a framework for dynamic evaluation of Large Language Models . evaluators use a proprietary bank of 220k graduate-level questions to analyze model data . |
| Outcome: | LLMEval-Fair provides robust and credible evaluation framework for Large Language Models . it provides a strong empirical validation for the dynamic evaluation paradigm . |
Graph-Guided Textual Explanation Generation Framework (2025.emnlp-main)
Copied to clipboard
Shuzhou Yuan, Jingyi Sun, Ran Zhang, Michael Färber, Steffen Eger, Pepa Atanasova, Isabelle Augenstein
| Challenge: | Existing work has questioned their faithfulness, as they may not accurately reflect the model’s internal reasoning process regarding its predicted answer. |
| Approach: | They propose a Graph-Guided Textual Explanation Generation framework that generates a graph neural network layer that guides the NLE generation and generates explanations with greater semantic and lexical similarity to human-written ones. |
| Outcome: | The proposed framework improves NLE faithfulness by up to 12.12% compared to baseline methods on encoder-decoder and decoder-only models. |
Structure and Label Constrained Data Augmentation for Cross-domain Few-shot NER (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Named entity recognition (NER) tasks require large datasets with accurate annotations that are labor-intensive and time-consuming. |
| Approach: | They propose a method to leverage domain gaps to model cross-domain few-shot named entity recognition (NER) NER is a natural language processing task to detect entity mentions and classify them into predefined labels . |
| Outcome: | The proposed method achieves state-of-the-art or competitive results on standard datasets. |
A Bidirectional Transformer Based Alignment Model for Unsupervised Word Alignment (2021.acl-long)
Copied to clipboard
| Challenge: | Existing methods for learning word alignment include statistical word aligners (e.g. GIZA++) Existing word alignment models employ a target-to-source attention mechanism which can provide rough word alignments but with a low accuracy. |
| Approach: | They propose a bidirectional Transformer based alignment model for unsupervised learning of the word alignment task. |
| Outcome: | The proposed model outperforms both previous neural word alignment approaches and the popular statistical word aligner GIZA++ on three word alignment tasks. |
AirRAG: Autonomous Strategic Planning and Reasoning Steer Retrieval Augmented Generation (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Experimental results show the effectiveness of AirRAG on complex question-answering datasets. |
| Approach: | They propose a new thinking pattern that integrates autonomous strategic planning with efficient reasoning actions. |
| Outcome: | The proposed approach significantly activates intrinsic reasoning capabilities and expands the solution space of specific tasks via Monte Carlo Tree Search. |
Exploring Paracrawl for Document-level Neural Machine Translation (2023.eacl-main)
Copied to clipboard
| Challenge: | Document-level neural machine translation (NMT) has outperformed sentence-level NMT on a number of datasets. |
| Approach: | They use Paracrawl to extract parallel paragraphs from Paracral webpages . they also use the extracted parallel paragraph as parallel documents for training . |
| Outcome: | The proposed model outperforms sentence-level NMT on a number of datasets. |
Guiding Neural Machine Translation with Retrieved Translation Pieces (N18-1)
Copied to clipboard
| Challenge: | Neural machine translation (NMT) has trouble with lowfrequency words or phrases and generalizing across domains. |
| Approach: | They propose a method for recalling low-frequency words and phrases into neural machine translation by retrieving n-grams from a search engine and incorporating them into the decoding process. |
| Outcome: | The proposed method improves translation results up to 6 BLEU points on three narrow domain translation tasks where repetitiveness of the target sentences is particularly salient. |