Papers by Jingjing Xu

Extrapolating Multilingual Understanding Models as Multilingual Generators (2023.findings-emnlp)

Challenge:	Chain-of-Thought prompting is a powerful technique for enhancing language model’s reasoning capabilities, but generating long and correct CoT trajectories is challenging.
Approach:	They propose to align the steps of Chain-of-Thought reasoning with loop iterations and apply intermediate supervision during the training of Looped Transformers.
Outcome:	The proposed method generates accurate reasoning chains for complex problems exceeding training length, and improves performance of the auto-regressive model.

Copied to clipboard

Bohong Wu, Fei Yuan, Hai Zhao, Lei Li, Jingjing Xu

Can We Edit Factual Knowledge by In-Context Learning? (2023.emnlp-main)

Challenge:	Existing multilingual understanding models are not capable of generating high-quality text compared with decoder-based causal language models.
Approach:	They propose a method to adapt a multilingual encoder to a language generator with a small number of additional parameters.
Outcome:	The proposed approach outperforms initialization-based methods with 9.4 BLEU on machine translation, 8.1 Rouge-L on question generation, and 5.5 METEOR on story generation.

Copied to clipboard

Ce Zheng, Lei Li, Qingxiu Dong, Yuxuan Fan, Zhiyong Wu, Jingjing Xu, Baobao Chang

Asking Clarification Questions in Knowledge-Based Question Answering (D19-1)

Challenge:	In-context knowledge editing (IKE) is a new paradigm for NLP research that can be applied to large language models with tens or hundreds of parameters.
Approach:	They propose to use in-context knowledge editing (IKE) without gradient updating to edit factual knowledge without a gradient update.
Outcome:	The proposed method achieves a competitive success rate compared to gradient-based methods on GPT-J but with fewer side effects.

Copied to clipboard

Jingjing Xu, Yuechen Wang, Duyu Tang, Nan Duan, Pengcheng Yang, Qi Zeng, Ming Zhou, Xu Sun

Natural Language Interfaces

Challenge:	Existing clarification datasets with limited annotated examples do not address ambiguous phenomena.
Approach:	They propose a dataset that allows users to ask clarification questions using open-domain examples.
Outcome:	The proposed model achieves better performance than strong baselines and provides new challenges.

An Auto-Encoder Matching Model for Learning Utterance-Level Semantic Dependency in Dialogue Generation (D18-1)

Copied to clipboard

Liangchen Luo, Jingjing Xu, Junyang Lin, Qi Zeng, Xu Sun

Dialogue Systems & Conversational Agents

Challenge:	Experimental results show that our model can generate semantically coherent responses compared to baseline models.
Approach:	They propose an Auto-Encoder Matching model to learn utterance-level semantic dependency . their model contains two auto-encoders and one mapping module .
Outcome:	Experimental results show that the proposed model can generate high coherence and fluency compared to baseline models.

ImageNetVC: Zero- and Few-Shot Visual Commonsense Evaluation on 1000 ImageNet Categories (2023.findings-emnlp)

Copied to clipboard

Heming Xia, Qingxiu Dong, Lei Li, Jingjing Xu, Tianyu Liu, Ziwei Qin, Zhifang Sui

Multimodality

Challenge:	Large Language Models (LLMs) are becoming general-purpose APIs, requiring visual knowledge to be understood.
Approach:	They propose to evaluate the visual capability of large-scale large-language models through visual commonsense evaluation using a human-annotated dataset.
Outcome:	The proposed dataset compares the visual commonsense knowledge of large-scale models with those of unimodal LLMs and visually augmented models.

Discourse-Aware Neural Extractive Text Summarization (2020.acl-main)

Copied to clipboard

Jiacheng Xu, Zhe Gan, Yu Cheng, Jingjing Liu

Information Extraction & Text Mining

Challenge:	Recent studies have shown that sentence-based extractive models result in redundant or uninformative phrases in the extracted summaries.
Approach:	They propose a discourse-aware neural summarization model that extracts sub-sentential discourse units as candidates for extractive selection on a finer granularity.
Outcome:	Experiments show that the proposed model outperforms state-of-the-art models on popular summarization benchmarks.

MTG: A Benchmark Suite for Multilingual Text Generation (2022.findings-naacl)

Copied to clipboard

Yiran Chen, Zhenqiao Song, Xianze Wu, Danqing Wang, Jingjing Xu, Jiaze Chen, Hao Zhou, Lei Li

Text Generation

Challenge:	Using MTG, we train and evaluate multilingual text generation models using human-annotated data.
Approach:	They propose a multilingual multiway text generation dataset with 400k human-annotated data that includes four generation tasks across five languages.
Outcome:	The proposed dataset includes four generation tasks across five languages (English, German, French, Spanish and Chinese) it provides comprehensive evaluations with diverse generation scenarios.

Lego-MT: Learning Detachable Models for Massively Multilingual Machine Translation (2023.findings-acl)

Copied to clipboard

Fei Yuan, Yinquan Lu, Wenhao Zhu, Lingpeng Kong, Lei Li, Yu Qiao, Jingjing Xu

Multilinguality

Challenge:	Existing monolithic models for multilingual neural machine translation encounter parameter interference and inefficient inference for large models.
Approach:	They propose a detachable multi-way model that assigns each language to an individual branch . they use data from OPUS to build a translation benchmark covering 433 languages .
Outcome:	The proposed model outperforms existing models in OPUS and is faster than existing models.

Reasoning Over Semantic-Level Graph for Fact Checking (2020.acl-main)

Copied to clipboard

Wanjun Zhong, Jingjing Xu, Duyu Tang, Zenan Xu, Nan Duan, Ming Zhou, Jiahai Wang, Jian Yin

Reasoning

Challenge:	Existing methods for fact checking use string concatenation or fusing features of isolated evidence sentences.
Approach:	They propose a method suitable for reasoning about the semantic-level structure of evidence . they use graph convolutional network and graph attention network to exploit the structure .
Outcome:	The proposed method improves claim verification accuracy and FEVER score on a benchmark dataset.

Long Chain-of-Thought Fine-tuning via Understanding-to-Reasoning Transition (2025.emnlp-main)

Copied to clipboard

Chenxin An, Zhihui Xie, Xiaonan Li, Ming Zhong, Shansan Gong, Lei Li, Jun Zhang, Jingjing Xu, Lingpeng Kong

SWE-Swiss: A Multi-Task Fine-Tuning and RL Recipe for High-Performance Issue Resolution (2026.findings-acl)

Challenge:	Existing research on long-context scaling in language models has focused on managing lengthy input prompts instead of producing long outputs.
Approach:	They propose a sequence-level curriculum learning framework that shifts a model’s focus from interpreting long chain-of-thoughts to generating them.
Outcome:	Experiments on rigorous reasoning benchmarks, including AIME24 and GPQA Diamond, show that the proposed approach surpasses standard fine-tuning by over 10% while maintaining robust performance on understanding tasks.

Copied to clipboard

Zhenyu He, Qingping Yang, Wei Shen, Xiaojian Zhong, Kechi Zhang, Chenxin An, Wenlei Shi, Tianle Cai, Di He, Jiaze Chen, Jingjing Xu

Review-Driven Multi-Label Music Style Classification by Exploiting Style Correlations (N19-1)

Challenge:	SWE-Swiss-32B demonstrates strong generalization to other common LLM benchmarks.
Approach:	They propose a two-phase training recipe that decomposes issue resolution into three core skills: Localization, Repair, and Unit Test Generation.
Outcome:	The proposed model achieves a 60.2% score on the SWE-bench Verified benchmark and is in the top-tier performance bracket of much larger models.

Copied to clipboard

Guangxiang Zhao, Jingjing Xu, Qi Zeng, Xuancheng Ren, Xu Sun

Information Extraction & Text Mining

Challenge:	Several methods have been proposed for automatic music style classification, but they are limited in two aspects.
Approach:	They propose a deep learning approach to automatically learn and exploit style correlations by reviewing music reviews on websites.
Outcome:	The proposed approach performs well in capturing style correlations.

Multi-task Learning with Sample Re-weighting for Machine Reading Comprehension (N19-1)

Copied to clipboard

Yichong Xu, Xiaodong Liu, Yelong Shen, Jingjing Liu, Jianfeng Gao

AntCritic: Argument Mining for Free-Form and Visually-Rich Financial Comments (2024.lrec-main)

Challenge:	Existing models for Machine Reading Comprehension (MRC) are small, compared to their size, and there are many studies on using pre-trained word embeddings and back-translation approaches to improve model generalization.
Approach:	They propose a multi-task learning framework to learn a machine reading comprehension model that can be applied to a wide range of MRC tasks in different domains.
Outcome:	The proposed model can be applied to a wide range of MRC tasks in different domains.

Copied to clipboard

Huadai Liu, Xu Wenqiang, Xuan Lin, Jingjing Huo, Hong Chen, Zhou Zhao

Visual Data in NLP

Challenge:	Argument mining is a thriving task in natural language processing, but its generalization is limited by existing datasets.
Approach:	They propose to use a dataset to help model argument mining . the dataset AntCritic supports both argument component detection and argument relation prediction tasks.
Outcome:	The proposed model can detect arguments and identify their relationships automatically.

Complex Question Decomposition for Semantic Parsing (P19-1)

Copied to clipboard

Haoyu Zhang, Jingjing Cai, Jianjun Xu, Ji Wang

Specificity-Driven Cascading Approach for Unsupervised Sentiment Modification (D19-1)

Challenge:	Existing methods that ignore the decompositionality of complex questions are not suitable for complex question semantic parsing.
Approach:	They propose a hierarchical semantic parsing method which utilizes the decompositionality of complex questions for semantic paring.
Outcome:	The proposed method improves on a large scale complex question semantic parsing dataset.

Copied to clipboard

Pengcheng Yang, Junyang Lin, Jingjing Xu, Jun Xie, Qi Su, Xu Sun

Sentiment Analysis

Challenge:	Existing methods for unsupervised sentiment modification lack specific information in text generated without parallel data . specificity-driven cascading approach can improve specificity of generated text and content preservation .
Approach:	They propose a specificity-driven cascading approach for unsupervised sentiment modification . the method performs target sentiment addition and content reconstruction independently .
Outcome:	The proposed method outperforms competitive systems by a large margin on Yelp and Amazon datasets.

LexicalAT: Lexical-Based Adversarial Reinforcement Training for Robust Sentiment Classification (D19-1)

Copied to clipboard

Jingjing Xu, Liang Zhao, Hanqi Yan, Qi Zeng, Yun Liang, Xu Sun

Robustness in NLP

Challenge:	Existing text classification models are fragile and sensitive to simple perturbations.
Approach:	They propose a generator-classifier adversarial training approach to improve classification models . they use a large-scale lexical knowledge base to generate attacking examples .
Outcome:	The proposed approach outperforms strong baselines and reduces test errors on neural networks.

INK: Injecting kNN Knowledge in Nearest Neighbor Machine Translation (2023.acl-long)

Copied to clipboard

Wenhao Zhu, Jingjing Xu, Shujian Huang, Lingpeng Kong, Jiajun Chen

Calibrating Factual Knowledge in Pretrained Language Models (2022.findings-emnlp)

Challenge:	Neural machine translation models induce a non-smooth representation space, which harms its generalization results.
Approach:	They propose a framework to smooth the representation space by adjusting neighbor representations with a small number of new parameters.
Outcome:	The proposed framework outperforms the state-of-the-art kNN-MT system with average gains of 1.99 COMET and 1.0 BLEU on four benchmark datasets.

Copied to clipboard

Qingxiu Dong, Damai Dai, Yifan Song, Jingjing Xu, Zhifang Sui, Lei Li

Multilingual Machine Translation with Large Language Models: Empirical Results and Analysis (2024.findings-naacl)

Challenge:	Existing studies show that Pretrained Language Models can store factual knowledge, but facts stored in PLMs are not always correct.
Approach:	They propose a lightweight method to calibrate factual knowledge in PLMs without re-training from scratch.
Outcome:	The proposed method can be used to calibrate factual knowledge in PLMs without re-training from scratch.

Copied to clipboard

Wenhao Zhu, Hongyi Liu, Qingxiu Dong, Jingjing Xu, Shujian Huang, Lingpeng Kong, Jiajun Chen, Lei Li

Multilinguality

Challenge:	Existing studies show that large language models (LLMs) can handle multilingual machine translation (MMT) However, the multilingual translation ability of LLMs remains under-explored.
Approach:	They evaluate eight popular LLMs including ChatGPT and GPT-4 to determine their performance in multilingual machine translation.
Outcome:	The proposed model can generate moderate translation even on zero-resource languages and cross-lingual exemplars can provide better task guidance for low-resourced translation than exemplar in the same language pairs.

A Survey on In-context Learning (2024.emnlp-main)

Copied to clipboard

Qingxiu Dong, Lei Li, Damai Dai, Ce Zheng, Jingyuan Ma, Rui Li, Heming Xia, Jingjing Xu, Zhiyong Wu, Baobao Chang, Xu Sun, Lei Li, Zhifang Sui

Low-Resource NLP

Challenge:	In-context learning (ICL) is a new paradigm for natural language processing . large language models (LLMs) demonstrate the ability to learn from a few examples .
Approach:	They propose to explore ICL to evaluate and extrapolate the ability of large language models.
Outcome:	The proposed methods can be used to evaluate and extrapolate the ability of large language models.

Contextual Representation Learning beyond Masked Language Modeling (2022.acl-long)

Copied to clipboard

Zhiyi Fu, Wangchunshu Zhou, Jingjing Xu, Hao Zhou, Lei Li

Achilles-Bench: A Challenging Benchmark for Low-Resource Evaluation (2024.findings-acl)

Challenge:	masked language models adopt sampled embeddings as anchors to estimate and inject contextual semantics to representations.
Approach:	They propose a representation learning approach that uses embeddings as anchors to model contextual representations.
Outcome:	The proposed model achieves 5x speedup and 1.2 points average improvement over MLM.

Copied to clipboard

Yudong Wang, Chang Ma, Qingxiu Dong, Zhifang Sui, Lingpeng Kong, Jingjing Xu

Responsible & Trustworthy NLP

Challenge:	Existing low-resource datasets that challenge neural networks cause over-estimated performance, despite promising yet saturated results in high-res settings.
Approach:	They propose a benchmark Achilles-Bench to better evaluate the learning ability of neural networks in low-resource settings.
Outcome:	The proposed benchmarks show that even pre-trained language models show performance drops on NLP tasks.

Vocabulary Learning via Optimal Transport for Neural Machine Translation (2021.acl-long)

Copied to clipboard

Jingjing Xu, Hao Zhou, Chun Gan, Zaixiang Zheng, Lei Li

Diversity-Promoting GAN: A Cross-Entropy Based Generative Adversarial Network for Diversified Text Generation (D18-1)

Challenge:	Empirical results show that VOLT beats widely-used vocabularies in diverse scenarios, including WMT-14 English-German translation, TED bilingual translation, and TED multilingual translation.
Approach:	They propose a token dictionary solution that can be used without trial training to find the best dictionary with a proper size.
Outcome:	The proposed solution beats widely-used vocabularies in English-German translation, TED bilingual translation, and TED multilingual translation.

Copied to clipboard

Jingjing Xu, Xuancheng Ren, Junyang Lin, Xu Sun

Robustness in NLP

Challenge:	Existing text generation methods tend to produce repeated and ”boring” expressions.
Approach:	They propose a model that assigns low reward for repeatedly generated text and high reward for ”novel” and fluent text, and a novel language-model based discriminator which can distinguish novel text from repeated text without the saturation problem.
Outcome:	The proposed model generates more diverse and informative text than existing baselines on review generation and dialogue generation tasks.

LegoMT2: Selective Asynchronous Sharded Data Parallel Training for Massive Neural Machine Translation (2025.findings-acl)

Copied to clipboard

Fei Yuan, Yinquan Lu, Lei Li, Jingjing Xu

Unpaired Sentiment-to-Sentiment Translation: A Cycled Reinforcement Learning Approach (P18-1)

Challenge:	Existing methods to train a single model for massive languages have huge communication overheads and parameter interference.
Approach:	They propose an efficient training approach with an asymmetric multi-way model architecture for massive multilingual neural machine translation.
Outcome:	The proposed model is 16.2 faster than the distributed training method for M2M-100-12B while improving the translation performance by an average of 2.2 BLEU on Flores-101.

Copied to clipboard

Jingjing Xu, Xu Sun, Qi Zeng, Xiaodong Zhang, Xuancheng Ren, Houfeng Wang, Wenjie Li

CodeDPO: Aligning Code Models with Self Generated and Verified Source Code (2025.acl-long)

Challenge:	Existing studies for sentiment-to-sentiment "translation" only change the underlying sentiment and fail to keep the semantic content.
Approach:	They propose a cycled reinforcement learning method that combines neutralization module and emotionalization module.
Outcome:	The proposed method outperforms state-of-the-art systems on Yelp and Amazon review datasets.

Copied to clipboard

Kechi Zhang, Ge Li, Yihong Dong, Jingjing Xu, Jun Zhang, Jing Su, Yongfei Liu, Zhi Jin

Programming Languages in NLP

Challenge:	Existing training methods for code generation do not improve code correctness and efficiency.
Approach:	They propose a framework that integrates preference learning into code generation to improve code correctness and efficiency.
Outcome:	The proposed framework improves code correctness and efficiency by integrating preference learning into code generation.

Can Language Models Understand Physical Concepts? (2023.emnlp-main)

Copied to clipboard

Lei Li, Jingjing Xu, Qingxiu Dong, Ce Zheng, Xu Sun, Lingpeng Kong, Qi Liu

OpenICL: An Open-Source Framework for In-context Learning (2023.acl-demo)

Challenge:	Existing language models do not understand basic physical concepts in the human world.
Approach:	They propose a method to transfer embodied knowledge from visual models to LMs . they use visual concepts and embodies concepts learned from interaction with the world .
Outcome:	The proposed method achieves comparable performance with scaling up parameters of LMs 134.

Copied to clipboard

Zhenyu Wu, Yaoxiang Wang, Jiacheng Ye, Zhiyong Wu, Jiangtao Feng, Jingjing Xu, Yu Qiao