Papers by Xinyu Jiang

Towards General Agentic Intelligence via Environment Scaling (2026.findings-acl)

Challenge:	Rather than pursuing the reachless SOTA accuracy, researchers are focusing on model efficiency and usability.
Approach:	They propose an evaluation and a public leaderboard for efficient NLP models that depicts the Pareto Frontier for various language understanding tasks.
Outcome:	The proposed model outperforms or performs on par with SOTA compressed and early exiting models.

Copied to clipboard

Runnan Fang, Shihao Cai, Baixuan Li, Jialong Wu, Guangyu Li, Wenbiao Yin, Xinyu Wang, Xiaobin Wang, Liangcai Su, Zhen Zhang, Shibin Wu, Zhengwei Tao, Yong Jiang, Pengjun Xie, Ningyu Zhang, Fei Huang, Wentao Zhang, Jingren Zhou

HierGR: Hierarchical Semantic Representation Enhancement for Generative Retrieval in Food Delivery Search (2025.acl-industry)

Challenge:	Diverse real-world APIs require precise, robust function-calling intelligence, which needs agents to develop these capabilities through interaction in varied environments.
Approach:	They propose a framework that scales up environments to enable agentic intelligence . they use a two-phase agent fine-tuning strategy to first endow agents with basic agentic capabilities, then specializing them for domain-specific contexts.
Outcome:	Experiments on -bench, -Bench, and ACEBench show that the model significantly enhances the models’ function-calling capability.

Copied to clipboard

Fuwei Zhang, Xiaoyu Liu, Xinyu Jia, Yingfei Zhang, Zenghua Xia, Fei Jiang, Fuzhen Zhuang, Wei Lin, Zhao Zhang

AutoConv: Automatically Generating Information-seeking Conversations with Large Language Models (2023.acl-short)

Challenge:	Generative retrieval (GR) is an emerging search paradigm for food delivery search.
Approach:	They propose a method that harnesses the advanced query understanding capabilities of large language models to enhance the retrieval of results for complex and long-tail queries in food delivery search scenarios.
Outcome:	The proposed method increases the number of online orders by 0.68% for complex search intents.

Copied to clipboard

Siheng Li, Cheng Yang, Yichun Yin, Xinyu Zhu, Zesen Cheng, Lifeng Shang, Xin Jiang, Qun Liu, Yujiu Yang

Dialogue Systems & Conversational Agents

Challenge:	Existing research on information-seeking conversations is stymied by the lack of training data.
Approach:	They propose to use autoconv for synthetic conversation generation to capture the characteristics of the information-seeking process and fine tune an LLM with a few human conversations to generate synthetic conversations with high quality.
Outcome:	The proposed model improves on two commonly-used datasets and alleviates the dependence on human annotation.

KBM: Delineating Knowledge Boundary for Adaptive Retrieval in Large Language Models (2025.findings-emnlp)

Copied to clipboard

Zhen Zhang, Xinyu Wang, Yong Jiang, Zile Qiao, Zhuo Chen, Guangyu Li, Feiteng Mu, Mengting Hu, Pengjun Xie, Fei Huang

Improving Named Entity Recognition by External Context Retrieving and Cooperative Learning (2021.acl-long)

Challenge:	Retrieval-augmented generation (RAG) is employed to tackle these challenges . a Knowledge Boundary Model (KBM) is used to express the known/unknown of a given question .
Approach:	They propose a Knowledge Boundary Model to express the known/unknown of a given question . they find that not all questions need to trigger RAG to improve performance .
Outcome:	The proposed model reduces time and computational costs by retrieving parts of unknown knowledge . the proposed model can express the known/unknown of a given question and determine whether a RAG needs to be triggered .

Copied to clipboard

Xinyu Wang, Yong Jiang, Nguyen Bach, Tao Wang, Zhongqiang Huang, Fei Huang, Kewei Tu

Error-Robust Retrieval for Chinese Spelling Check (2024.lrec-main)

Challenge:	Recent work shows document-level contexts can significantly improve Named Entity Recognition models.
Approach:	They propose to find external contexts of a sentence by retrieving and selecting a set of semantically relevant texts through a search engine with the original sentence as the query.
Outcome:	The proposed approach can achieve new state-of-the-art performance on 8 NER data sets across 5 domains.

Copied to clipboard

Xunjian Yin, Xinyu Hu, Jin Jiang, Xiaojun Wan

Information Retrieval

Challenge:	Chinese Spelling Check (CSC) aims to detect and correct spelling errors in Chinese texts . current methods may not fully leverage existing datasets, resulting in insufficient annotated data .
Approach:	They propose a plug-and-play retrieval method with error-robust information for Chinese Spelling Check . they employ multimodal representations that fuse phonetic, morphologic, and contextual information .
Outcome:	The proposed method improves on the SIGHAN benchmarks on Chinese spelling check (CSC) the proposed method is based on training data and lacks adequate parallel corpora .

Structural Knowledge Distillation: Tractably Distilling Information for Structured Predictor (2021.acl-long)

Copied to clipboard

Xinyu Wang, Yong Jiang, Zhaohui Yan, Zixia Jia, Nguyen Bach, Tao Wang, Zhongqiang Huang, Fei Huang, Kewei Tu

Green & Sustainable NLP

Challenge:	Knowledge distillation is a technique to transfer knowledge between models, typically from a large model (the teacher) to a more fine-grained one (the student).
Approach:	They propose a factorized form of the knowledge distillation objective for structured prediction which is tractable for many typical choices of the teacher and student models.
Outcome:	The proposed model is able to transfer knowledge between teacher and student models without loss of accuracy under four different scenarios.

Named Entity and Relation Extraction with Multi-Modal Retrieval (2022.findings-emnlp)

Copied to clipboard

Xinyu Wang, Jiong Cai, Yong Jiang, Pengjun Xie, Kewei Tu, Wei Lu

Parenting: Optimizing Knowledge Selection of Retrieval-Augmented Language Models with Parameter Decoupling and Tailored Tuning (2025.acl-long)

Challenge:	Existing approaches to name entity recognition and relation extraction are knowledge-based and may not be highly relevant.
Approach:	They propose a multi-modal named entity recognition framework that leverages image information to improve the performance of NER and relation extraction.
Outcome:	The proposed framework can achieve state-of-the-art on four multi-modal named entity recognition datasets and one multi-module relation extraction dataset.

Copied to clipboard

Yongxin Xu, Ruizhe Zhang, Xinke Jiang, Yujie Feng, Yuzhen Xiao, Xinyu Ma, Runchuan Zhu, Xu Chu, Junfeng Zhao, Yasha Wang

Automated Concatenation of Embeddings for Structured Prediction (2021.acl-long)

Challenge:	Existing methods for integrating internal and external knowledge lack effective control mechanisms for generating hallucinations and dealing with outdated knowledge.
Approach:	They propose a framework that decouples, identifies, and purposefully optimizes parameter subspaces related to adherence and robustness.
Outcome:	The proposed framework decouples, identifies, and purposefully optimizes parameter subspaces related to adherence and robustness.

Copied to clipboard

Xinyu Wang, Yong Jiang, Nguyen Bach, Tao Wang, Zhongqiang Huang, Fei Huang, Kewei Tu

Representation Learning

Challenge:	Recent work shows that better word representations can be obtained by concatenating different types of embeddings.
Approach:	They propose to automate the process of finding better concatenated embeddings for structured prediction tasks by concatending different types of embeddables.
Outcome:	The proposed approach outperforms baselines and achieves state-of-the-art with fine-tuned embeddings on 6 tasks and 21 datasets.

Revisiting Pre-trained Language Models and their Evaluation for Arabic Natural Language Processing (2022.emnlp-main)

Copied to clipboard

Abbas Ghaddar, Yimeng Wu, Sunyam Bagga, Ahmad Rashid, Khalil Bibi, Mehdi Rezagholizadeh, Chao Xing, Yasheng Wang, Xinyu Duan, Zhefeng Wang, Baoxing Huai, Xin Jiang, Qun Liu, Phillippe Langlais

Rhythm Controllable and Efficient Zero-Shot Voice Conversion via Shortcut Flow Matching (2025.acl-long)

Challenge:	Existing pre-trained language models are not well-explored and are not reproducible in the literature.
Approach:	They propose to improve existing Arabic language pre-trained language models using a more methodical approach.
Outcome:	The proposed models outperform existing models on ALUE, a leaderboard-powered benchmark for Arabic NLU and NLG tasks.

Copied to clipboard

Jialong Zuo, Shengpeng Ji, Minghui Fang, Mingze Li, Ziyue Jiang, Xize Cheng, Xiaoda Yang, Chen Feiyang, Xinyu Duan, Zhou Zhao

Responsible & Trustworthy NLP

Challenge:	Existing methods focus on disentangling speakers and content, while others focus on preserving the source's prosody.
Approach:	They propose a rhythm-controllable and efficient zero-shot voice conversion model that transforms the source speaker’s timbre into an unseen one while retaining speech content.
Outcome:	The proposed model adapts the linguistic content duration to the desired speaking style, facilitating the transfer of the target speaker’s rhythm.

Generalized Supervised Attention for Text Generation (2021.findings-acl)

Copied to clipboard

Yixian Liu, Liwen Zhang, Xinyu Zhang, Yong Jiang, Yue Zhang, Kewei Tu

Text Generation

Challenge:	Existing supervised attention methods that use human knowledge to learn better alignments are costly or infeasible.
Approach:	They propose a generalized supervised attention method based on quasi alignments that are easier to obtain than ideal alignments.
Outcome:	The proposed framework improves generation performance and is robust against errors in attention supervision.

UniMoE-Audio: Unified Speech and Music Generation with Dynamic-Capacity Mixture-of-Experts (2026.acl-long)

Copied to clipboard

Zhenyu Liu, Yunxin li, Xuanyu Zhang, Qixun Teng, Shenyuan Jiang, Xinyu Chen, Haoyuan Shi, Haolan Chen, Fanbo Meng, Mingjun Zhao, Yu Xu, Yancheng He, Baotian Hu, Haizhou Li, Min Zhang

Multimodality

Challenge:	Recent advances in unified multimodal models indicate a clear trend towards comprehensive content generation.
Approach:	They propose a unified speech and music generation model built upon a novel framework . they propose specialized MoE architectures and curated training strategies to tackle data imbalances .
Outcome:	The proposed model achieves state-of-the-art performance on major speech and music generation benchmarks.

Detecting Knowledge Boundary of Vision Large Language Models by Sampling-Based Inference (2025.emnlp-main)

Copied to clipboard

Zhuo Chen, Xinyu Wang, Yong Jiang, Zhen Zhang, Xinyu Geng, Pengjun Xie, Fei Huang, Kewei Tu

ITA: Image-Text Alignments for Multi-Modal Named Entity Recognition (2022.naacl-main)

Challenge:	Existing methods to detect the knowledge boundary of Vision Large Language Models (VLLMs) are expensive and require indiscriminate retrieval to address questions that require real-time information or are knowledge-intensive.
Approach:	They propose a method that fine-tunes a VLLM on an automatically constructed dataset for boundary identification.
Outcome:	The proposed method reduces indiscriminate retrieval while maintaining or improving the performance of a VLLM on an automatically constructed dataset.

Copied to clipboard

Xinyu Wang, Min Gui, Yong Jiang, Zixia Jia, Nguyen Bach, Tao Wang, Zhongqiang Huang, Kewei Tu

The CRECIL Corpus: a New Dataset for Extraction of Relations between Characters in Chinese Multi-party Dialogues (2022.lrec-1)

Challenge:	Recent work on Multi-modal Named Entity Recognition (MNER) relies on image information to model interactions between image and text representations.
Approach:	They propose to align image features into the textual space to better utilize attention mechanisms . they use regional object tags, captions and optical characters as visual contexts .
Outcome:	The proposed model can achieve state-of-the-art accuracy on multi-modal Named Entity Recognition datasets even without image information.

Copied to clipboard

Yuru Jiang, Yang Xu, Yuhang Zhan, Weikai He, Yilin Wang, Zixuan Xi, Meiyun Wang, Xinyu Li, Yu Li, Yanchao Yu

Structure-Level Knowledge Distillation For Multilingual Sequence Labeling (2020.acl-main)

Challenge:	Existing datasets focus on relation extraction between two entities in one sentence, and some focus on cross-sentence relationships.
Approach:	They propose to use a Chinese multi-party dialogue dataset for automatic extraction of dialogue-based character relationships.
Outcome:	The proposed dataset extracts relationships between 140 entities on the CRECIL corpus and another existing relation extraction corpus.

Copied to clipboard

Xinyu Wang, Yong Jiang, Nguyen Bach, Tao Wang, Fei Huang, Kewei Tu

MemTR: Enhancing Tool-Calling Reliability via Uncertainty-Triggered FFN-Space Retracing (2026.findings-acl)

Challenge:	Existing multilingual models still underperform individual monolingual models due to model capacity limitations.
Approach:	They propose to distill the structural knowledge of several monolingual models (teachers) to the unified multilingual model (student).
Outcome:	The proposed model outperforms strong baseline models and teacher models on 4 multilingual tasks with 25 datasets and has stronger zero-shot generalizability.

Copied to clipboard

Hongtao Duan, Lu Jiang, Minying Zhang, Xiaobing Zhu, Tianpeng Bu, Hao Jiang, Xinyu Wei, Lulu hu

Let LLMs Take on the Latest Challenges! A Chinese Dynamic Question Answering Benchmark (2025.coling-main)

Challenge:	Existing tool-calling methods rely on costly tool-use training data or only constrain syntax, leaving tool selection and argument value errors largely unsolved.
Approach:	They propose a method that decodes tool evidence from the tool library and mixes it into the output at the uncertain layer.
Outcome:	The proposed method reduces tool calling failures by 2%–9% with only 1%–2% runtime overhead.

Copied to clipboard

Zhikun Xu, Yinghui Li, Ruixue Ding, Xinyu Wang, Boli Chen, Yong Jiang, Haitao Zheng, Wenlian Lu, Pengjun Xie, Fei Huang

Natural Language Interfaces

Challenge:	Recent work has noted that due to the extremely high cost of iterative updates of LLMs, they are often unable to answer dynamic questions well.
Approach:	They propose a Chinese Dynamic QA benchmark containing question-answer pairs related to the latest dynamic questions on the Chinese Internet.
Outcome:	The proposed benchmark will be one of the key data resources for improving LLMs’ Chinese question-answering ability in the future.

More Embeddings, Better Sequence Labelers? (2020.findings-emnlp)

Copied to clipboard

Xinyu Wang, Yong Jiang, Nguyen Bach, Tao Wang, Zhongqiang Huang, Fei Huang, Kewei Tu

Scaling up Open Tagging from Tens to Thousands: Comprehension Empowered Attribute Value Extraction from Product Title (P19-1)

Challenge:	Existing work suggests contextual embeddings improve sequence labeling accuracy . but, there is no definite conclusion on whether concatenating different kinds of embeddables is effective .
Approach:	They propose a family of contextual embeddings that improves sequence labeling accuracy . they conduct extensive experiments on 3 tasks over 18 datasets and 8 languages .
Outcome:	The proposed family of contextual embeddings improves the accuracy of sequence labelers over non-contextual embedders.

Copied to clipboard

Huimin Xu, Wenting Wang, Xin Mao, Xinyu Jiang, Man Lan

RaFe: Ranking Feedback Improves Query Rewriting for RAG (2024.findings-emnlp)

Challenge:	Existing models treat each attribute as an entity type and build one set of NER tags for each of them, leading to scalability issues.
Approach:	They propose to regard attribute as a query and adopt only one global set of BIO tags for any attributes to reduce the burden of attribute tag or model explosion.
Outcome:	The proposed model outperforms state-of-the-art models and generates promising results for 8,906 attributes.

Copied to clipboard

Shengyu Mao, Yong Jiang, Boli Chen, Xiao Li, Peng Wang, Xinyu Wang, Pengjun Xie, Fei Huang, Huajun Chen, Ningyu Zhang

Text Generation

Challenge:	Large Language Models (LLMs) and Retrieval Augmentation Generation (RAG) techniques have evolved to enhance document retrieval by reformulating queries.
Approach:	They propose a framework for training query rewriting models that leverages a reranker framework.
Outcome:	The proposed framework provides ranking feedback aligned well with the rewriting objectives without needing signals from annotations and supports both online and offline training models.

AIN: Fast and Accurate Sequence Labeling with Approximate Inference Network (2020.emnlp-main)

Copied to clipboard

Xinyu Wang, Yong Jiang, Nguyen Bach, Tao Wang, Zhongqiang Huang, Fei Huang, Kewei Tu

Challenge:	Existing approaches to sequence labeling require sequential computation that makes parallelization impossible.
Approach:	They propose to employ a parallelizable approximate variational inference algorithm for the CRF model.
Outcome:	The proposed approach improves decoding speed and accuracy with long sentences and is parallelizable for faster training and prediction.

AraMUS: Pushing the Limits of Data and Model Scale for Arabic Natural Language Processing (2023.findings-acl)

Copied to clipboard

Asaad Alghamdi, Xinyu Duan, Wei Jiang, Zhenhai Wang, Yimeng Wu, Qingrong Xia, Zhefeng Wang, Yi Zheng, Mehdi Rezagholizadeh, Baoxing Huai, Peilun Cheng, Abbas Ghaddar

Hyperlink-induced Pre-training for Passage Retrieval in Open-domain Question Answering (2022.acl-long)

Challenge:	Developing monolingual large Pre-trained Language Models (PLMs) is shown to be very successful in handling different tasks in Natural Language Processing (NLP).
Approach:	They present AraMUS, the largest Arabic PLM with 11B parameters trained on 529GB of high-quality Arabic textual data.
Outcome:	The proposed model achieves state-of-the-art performance on a diverse set of Arabic classification and generative tasks.

Copied to clipboard

Jiawei Zhou, Xiaoguang Li, Lifeng Shang, Lan Luo, Ke Zhan, Enrui Hu, Xinyu Zhang, Hao Jiang, Zhao Cao, Fan Yu, Xin Jiang, Qun Liu, Lei Chen

Improving Retrieval Augmented Open-Domain Question-Answering with Vectorized Contexts (2024.findings-acl)

Challenge:	Existing methods to train dense passage retrieval have a large data gap between upstream and downstream relevance.
Approach:	They propose a method to pre-train the dense retriever with the text relevance induced by hyperlinks within Web documents.
Outcome:	The proposed method outperforms existing methods under different scenarios and in the open-domain question answering domain.

Copied to clipboard

Zhuo Chen, Xinyu Wang, Yong Jiang, Pengjun Xie, Fei Huang, Kewei Tu

UOUO: Uncontextualized Uncommon Objects for Measuring Knowledge Horizons of Vision Language Models (2024.emnlp-main)

Challenge:	Retrieval Augmented Generation can be used to process long contexts in Open-Domain Question-Answering tasks.
Approach:	They propose a method to cover longer contexts in Open-Domain Question-Answering tasks by using a small encoder language model and cross-attention with origin inputs.
Outcome:	The proposed method can cover longer contexts while keeping the computing requirements close to the baseline.

Copied to clipboard

Xinyu Pi, Mingyuan Wu, Jize Jiang, Haozhen Zheng, Beitong Tian, ChengXiang Zhai, Klara Nahrstedt, Zhiting Hu