Papers by Che Liu

Slot-consistent NLG for Task-oriented Dialogue Systems with Iterative Rectification Network (2020.acl-main)

Challenge:	Current methods for multimodal representation learning for electrocardiograms often result in suboptimal alignment of ECG signals with their corresponding text reports.
Approach:	They propose a framework to learn ECG representations by aligning ECG signals with paired free-text reports.
Outcome:	The proposed framework outperforms existing methods in zero-shot classification and linear probing tasks using 12 leads.

Copied to clipboard

Yangming Li, Kaisheng Yao, Libo Qin, Wanxiang Che, Xiaolong Li, Ting Liu

RepoAgent: An LLM-Powered Open-Source Framework for Repository-level Code Documentation Generation (2024.emnlp-demo)

Challenge:	Existing approaches to natural language generation are prone to errors, such as neglecting input slot values and generating redundant slot values.
Approach:	They propose an iterative rectification network to improve general NLG systems . they apply bootstrapping algorithms to sample training candidates and incorporate reward .
Outcome:	The proposed methods significantly reduce the slot error rate for strong baselines.

Copied to clipboard

Qinyu Luo, Yining Ye, Shihao Liang, Zhong Zhang, Yujia Qin, Yaxi Lu, Yesai Wu, Xin Cong, Yankai Lin, Yingli Zhang, Xiaoyin Che, Zhiyuan Liu, Maosong Sun

LoopCoder: Scaling Code Intelligence via Looped Language Models (2026.findings-acl)

Challenge:	Xia et al., 2018) demonstrate that a large language model can generate and maintain high-quality code documentation.
Approach:	They propose a large language model powered open-source framework for generating, maintaining, and updating code documentation.
Outcome:	The proposed framework generates high-quality documentation for the entire project.

Copied to clipboard

Jian Yang, Wei Zhang, Shuyue Guo, Yizhi LI, Linzheng Chai, Zhengmao Ye, Shukai Liu, Yuyang Song, Jiajun Wu, Che Liu, Tianyu Zheng, Siwei Wu, Leo L, Xudong Ma, Chuan Hao, Ran Tao, Yan Xing, Jianzhou Wang, Mingjie Tang, Aishan Liu, Zhoujun Li, Xianglong Liu, Weifeng Lv, Bryan Dai

Make Some Noise: Unlocking Language Model Parallel Inference Capability through Noisy Training (2024.emnlp-main)

Challenge:	Large language models have mastered syntax-level code generation, but complex algorithmic reasoning remains a challenge.
Approach:	They propose a recurrent inductive bias that aligns with the recursive nature of programming logic.
Outcome:	The proposed model achieves comparable performance to standard dense models with more parameters.

Copied to clipboard

Yixuan Wang, Xianzhen Luo, Fuxuan Wei, Yijun Liu, Qingfu Zhu, Xuanyu Zhang, Qing Yang, Dongliang Xu, Wanxiang Che

Entity-Consistent End-to-end Task-Oriented Dialogue System with KB Retriever (D19-1)

Challenge:	Existing speculative decoding methods require additional model structure and training processes to assist the model for draft token generation.
Approach:	They propose a make some noise training framework that introduces some noise at the input for the model to learn the denoising task.
Outcome:	The proposed model improves inference speed by 2.3-2.7x times without compromising model performance.

Copied to clipboard

Libo Qin, Yijia Liu, Wanxiang Che, Haoyang Wen, Yangming Li, Ting Liu

Allocating Large Vocabulary Capacity for Cross-Lingual Language Model Pre-Training (2021.emnlp-main)

Challenge:	Existing work on sequence-to-sequence dialogues treats the KB query as an attention over the entire KB without the guarantee that the generated entities are consistent with each other.
Approach:	They propose a framework which queries the knowledge base in two steps to improve consistency . they first return the most relevant KB row given a dialogue history .
Outcome:	The proposed framework outperforms baseline models and produces entity-consistent responses.

Copied to clipboard

Bo Zheng, Li Dong, Shaohan Huang, Saksham Singhal, Wanxiang Che, Ting Liu, Xia Song, Furu Wei

Conversational Graph Grounded Policy Learning for Open-Domain Conversation Generation (2020.acl-main)

Challenge:	Existing models require a more expressive vocabulary to represent all languages . however, increasing the vocabulary size significantly slows down the pre-training speed .
Approach:	They propose an algorithm VoCap to determine the desired vocabulary capacity of each language.
Outcome:	The proposed algorithm improves cross-lingual model pre-training while reducing side effects of increasing vocabulary size.

Copied to clipboard

Jun Xu, Haifeng Wang, Zheng-Yu Niu, Hua Wu, Wanxiang Che, Ting Liu

Cross-Lingual Machine Reading Comprehension (D19-1)

Challenge:	Existing word-level policy models that learn dialog policy and language generation from dialog corpora often lead to degeneration issues where the utterances become ungrammatical or repetitive.
Approach:	They propose to represent prior dialog transitions as a graph and learn a CG grounded dialog policy that can foster a more coherent and controllable dialog.
Outcome:	The proposed framework is able to learn dialog policy in open-domain multi-turn conversation.

Copied to clipboard

Yiming Cui, Wanxiang Che, Ting Liu, Bing Qin, Shijin Wang, Guoping Hu

Machine Reading Comprehension

Challenge:	Existing work on machine reading comprehension task is focused on English, but there are few efforts on other languages due to the lack of large-scale training data.
Approach:	They propose a cross-lingual machine reading comprehension task for other languages . they propose cloze-style reading comprehension and various neural network approaches .
Outcome:	The proposed model improves reading comprehension performance of Chinese datasets over state-of-the-art systems by a large margin over existing systems.

Two-Stage Regularization-Based Structured Pruning for LLMs (2026.acl-long)

Copied to clipboard

Mingkuan Feng, Jinyang Wu, Siyuan Liu, Shuai Zhang, Hongjian Fang, Ruihan Jin, Feihu Che, Pengpeng Shao, Zhengqi Wen, Jianhua Tao

A Stack-Propagation Framework with Token-Level Intent Detection for Spoken Language Understanding (D19-1)

Challenge:	Structural pruning is a promising solution for large language models . prior structured pruning methods remove unimportant parameters based on certain metrics .
Approach:	They propose a structural pruning method that iteratively learns the weights of transformer layers by adding their l1-norm to the loss function.
Outcome:	The proposed pruning method outperforms strong layer-wise pruning methods without requiring retraining.

Copied to clipboard

Libo Qin, Wanxiang Che, Yangming Li, Haoyang Wen, Ting Liu

Sentiment Analysis

Challenge:	Intent detection and slot filling are two main tasks for building a spoken language understanding system.
Approach:	They propose a framework to incorporate intent information into slot filling tasks . they use a joint model with Stack-Propagation to capture intent semantic knowledge .
Outcome:	The proposed model outperforms existing models on two publicly available datasets and outperformed existing models by a large margin.

Learning to Bridge Metric Spaces: Few-shot Joint Learning of Intent Detection and Slot Filling (2021.findings-acl)

Copied to clipboard

Yutai Hou, Yongkui Lai, Cheng Chen, Wanxiang Che, Ting Liu

Does RLVR Extend Reasoning Boundaries? Investigating Capability Expansion in Vision-Language Models (2026.acl-long)

Challenge:	Existing few-shot learning methods learn a single task each time with a few examples . but, real-world applications often contain multiple closely related tasks .
Approach:	They propose a few-shot joint learning scheme that captures intent and slot relationships from only a handful of examples and adapts the bridged metric space to specific few- shot domain.
Outcome:	The proposed model outperforms baseline models on two public datasets on intent and slot . the proposed model significantly outperformed baseline models in one and five shots settings.

Copied to clipboard

Minghe Shen, Zhuo Zhi, Chonghan Liu, Shuo Xing, Zhengzhong Tu, Che Liu

Adversarial Training for Machine Reading Comprehension with Virtual Embeddings (2021.starsem-1)

Challenge:	Recent studies suggest that RLVR amplifies behaviors inherent to the pre-training distribution rather than inducing new capabilities.
Approach:	They propose a framework for RLVR that extends the spatial reasoning boundary . they use a mapping framework where the difficulty is precisely regulated by path length and number of turns .
Outcome:	The proposed framework extends the spatial reasoning boundary on two real-world navigation benchmarks.

Copied to clipboard

Ziqing Yang, Yiming Cui, Chenglei Si, Wanxiang Che, Ting Liu, Shijin Wang, Guoping Hu

Reasoning

Challenge:	Neural networks are vulnerable to adversarial examples that have been mixed with certain perturbations.
Approach:	They propose a novel adversarial training method that perturbs the embedding matrix instead of word vectors to differentiate the roles of passages and questions.
Outcome:	The proposed method is effective universally and further improves the performance of MRC tasks.

Combining Self-Training and Self-Supervised Learning for Unsupervised Disfluency Detection (2020.emnlp-main)

Copied to clipboard

Shaolei Wang, Zhongyuan Wang, Wanxiang Che, Ting Liu

Low-Resource NLP

Challenge:	Existing approaches to disfluency detection rely on human annotations, which are expensive to obtain.
Approach:	They propose an unsupervised learning paradigm which can work with unlabeled text corpora.
Outcome:	The proposed method performs better than existing supervised systems using word embeddings.

KwaiChat: A Large-Scale Video-Driven Multilingual Mixed-Type Dialogue Corpus (2025.findings-naacl)

Copied to clipboard

Xiaoming Shi, Zeming Liu, Yiming Lei, Chenkai Zhang, Haitao Leng, Chuan Wang, Qingjie Liu, Wanxiang Che, Yunhong Wang

Sequence-to-Sequence Learning for Task-oriented Dialogue with Dialogue State Representation (C18-1)

Challenge:	Currently, video-based dialogue systems rely on a single dialogue type, hindering their versatility in practical applications.
Approach:	They propose to generate video-driven multilingual mixed-type dialogues using KwaiChat . they propose to create a video-based multilingual mix of 4 dialogue types, 30 domains, 4 languages, 13 topics .
Outcome:	The proposed model performs best on KwaiChat but is not perfect in this situation.

Copied to clipboard

Haoyang Wen, Yijia Liu, Wanxiang Che, Libo Qin, Ting Liu

On Safety Risks in Experience-Driven Self-Evolving Agents (2026.findings-acl)

Challenge:	Existing pipeline models for task-oriented dialogue system require explicit modeling of dialogue states and hand-crafted action spaces to query domain-specific knowledge base.
Approach:	They propose a framework that leverages the advantages of classic pipeline and sequence-to-sequence models.
Outcome:	The proposed framework outperforms baseline models on automatic and human evaluation on a Stanford Multi-turn Multi-domain task-oriented dialogue dataset.

Copied to clipboard

Weixiang Zhao, Yichen Zhang, Yingshuo Wang, Yang Deng, Yanyan Zhao, Xuda Zhi, Yongbo Huang, Hao He, Wanxiang Che, Bing Qin, Ting Liu

Challenge:	Experience-driven self-evolution has emerged as a promising paradigm for improving the autonomy of large language model agents, yet its reliance on self-curated experience introduces underexplored safety risks.
Approach:	They investigate how experience accumulation and utilization in self-evolving agents affect safety performance across web-based and embodied environments.
Outcome:	The findings expose inherent limitations of current self-evolving agents and call for more principled strategies to ensure safe and reliable adaptation.

Fine-grained Knowledge Enhancement for Retrieval-Augmented Generation (2025.findings-acl)

Copied to clipboard

Jingxuan Han, Zhendong Mao, Yi Liu, Yexuan Che, Zheren Fu, Quan Wang

Information Retrieval

Challenge:	Existing studies rely on semantic similarity to retrieve knowledge but ignore fine-grained information within documents.
Approach:	They propose a fine-grained knowledge enhancement method to fill knowledge gaps with retrieved external information by a Chain-of-Thought prompting procedure and a decoding enhancement strategy to constrain the document-based decoding process.
Outcome:	The proposed method can be applied in a plug-and-play manner to enhance its performance with no additional modules or training process.

Sequence-to-Sequence Data Augmentation for Dialogue Language Understanding (C18-1)

Copied to clipboard

Yutai Hou, Yijia Liu, Wanxiang Che, Ting Liu

Low-Resource NLP

Challenge:	Existing work which augments an utterance without considering its relation with other utterrances, however, has failed to improve the language understanding module.
Approach:	They propose a sequence-to-sequence generation based data augmentation framework that leverages one utterance’s same semantic alternatives in the training data.
Outcome:	The proposed framework achieves 6.38 and 10.04 F-scores on the Airline Travel Information System dataset and a newly created semantic frame annotation on the Stanford Multi-turn, Multi-domain Dialogue Dataset.

Conversational Recommender System and Large Language Model Are Made for Each Other in E-commerce Pre-sales Dialogue (2023.findings-emnlp)

Copied to clipboard

Yuanxing Liu, Weinan Zhang, Yifan Chen, Yuchi Zhang, Haopeng Bai, Fan Feng, Hengbin Cui, Yongbin Li, Wanxiang Che

Towards Knowledge-Intensive Text-to-SQL Semantic Parsing with Formulaic Knowledge (2022.emnlp-main)

Challenge:	E-commerce pre-sales dialogues elicit user needs and preferences for items . large language models lack domain-specific knowledge for accurate recommendations .
Approach:	They propose two collaboration strategies to integrate CRS and large language models in pre-sales dialogues.
Outcome:	The proposed methods can be very effective in some cases, the authors say .

Copied to clipboard

Longxu Dou, Yan Gao, Xuqi Liu, Mingyang Pan, Dingzirui Wang, Wanxiang Che, Dechen Zhan, Min-Yen Kan, Jian-Guang Lou

Programming Languages in NLP

Challenge:	Existing approaches to text-to-SQL require domain knowledge to parse expert questions into SQL queries.
Approach:	They propose a framework to leverage domain knowledge during parsing by building a new benchmark KnowSQL with domain-specific questions.
Outcome:	The proposed framework improves the performance of the proposed benchmark by 28.2%.

Stealthy Jailbreak Attacks on Large Language Models via Benign Data Mirroring (2025.naacl-long)

Copied to clipboard

Honglin Mu, Han He, Yuxin Zhou, Yunlong Feng, Yang Xu, Libo Qin, Xiaoming Shi, Zeming Liu, Xudong Han, Qi Shi, Qingfu Zhu, Wanxiang Che

Seer Self-Consistency: Advance Budget Estimation for Adaptive Test-Time Scaling (2026.findings-acl)

Challenge:	Existing black-box jailbreak methods often rely on model feedback . existing methods may be intercepted by content moderators during the search process .
Approach:	They propose a method that guides malicious prompt construction by local training a mirror model of the target black-box model through benign data distillation.
Outcome:	The proposed method achieves a 92% attack success rate and 80% stealth rate on a subset of AdvBench.

Copied to clipboard

Shiyu Ji, Yixuan Wang, Yijun Liu, Qingfu Zhu, Wanxiang Che

Challenge:	Large Language Models (LLMs) have demonstrated exceptional performance in reasoning tasks, particularly in mathematics.
Approach:	They propose a dynamic self-consistency framework that integrates System 1 and System 2 reasoning to improve token efficiency and latency.
Outcome:	The proposed method outperforms existing methods, achieving up to 47% reduction in token consumption and 43% reduction in inference latency without significant performance loss.

Dynamic Fusion Network for Multi-Domain End-to-end Task-Oriented Dialog (2020.acl-main)

Copied to clipboard

Libo Qin, Xiao Xu, Wanxiang Che, Yue Zhang, Ting Liu

A Sentence Cloze Dataset for Chinese Machine Reading Comprehension (2020.coling-main)

Challenge:	Recent studies show remarkable success in end-to-end task-oriented dialog systems . however, most models rely on large training data, which is difficult to scalable for new domains with limited labeled data.
Approach:	They propose a shared-private network which exploits the relevance between the target domain and each domain.
Outcome:	The proposed model outperforms existing methods on multi-domain dialogue by 13.9% on average.

Copied to clipboard

Yiming Cui, Ting Liu, Ziqing Yang, Zhipeng Chen, Wentao Ma, Wanxiang Che, Shijin Wang, Guoping Hu

Reasoning

Challenge:	Using cloze-style reading comprehension, Chinese machine reading comprehension datasets are becoming more and more popular . a new task is proposed to fill the right candidate sentence into the passage with several blanks .
Approach:	They propose a Chinese task to fill the right candidate sentence into a passage with blanks . they build a dataset to evaluate the difficulty of the task and make fake candidates .
Outcome:	The proposed task fills the right candidate sentence into the passage with blanks . the proposed dataset contains over 100K blanks within over 10K passages based on Chinese narrative stories .

TextBrewer: An Open-Source Knowledge Distillation Toolkit for Natural Language Processing (2020.acl-demos)

Copied to clipboard

Ziqing Yang, Yiming Cui, Zhipeng Chen, Wanxiang Che, Ting Liu, Shijin Wang, Guoping Hu

EvoR: Evolving Retrieval for Code Generation (2024.findings-emnlp)

Challenge:	Large pre-trained language models have hundreds of millions of parameters and take several gigabytes of memory to train and inference.
Approach:	They propose an open-source knowledge distillation toolkit designed for natural language processing that provides a set of predefined distillation methods and can be extended with custom code.
Outcome:	The proposed method is comparable with or even higher than the public distilled BERT models with similar numbers of parameters.

Copied to clipboard

Hongjin Su, Shuyang Jiang, Yuhang Lai, Haoyuan Wu, Boao Shi, Che Liu, Qian Liu, Tao Yu

Text Generation

Challenge:	Existing pipelines for retrieval-augmented code generation (RACG) use static knowledge bases with a single source, limiting adaptation capabilities of Large Language Models (LLMs) Extensive experiments demonstrate that EVOR achieves two to four times of execution accuracy compared to other methods such as Reflexion.
Approach:	They propose a retrieval-augmented code generation pipeline that employs the synchronous evolution of queries and diverse knowledge bases.
Outcome:	The proposed pipeline achieves two to four times of execution accuracy compared to other methods.

DialogBench: Evaluating LLMs as Human-like Dialogue Systems (2024.naacl-long)

Copied to clipboard

Jiao Ou, Junda Lu, Che Liu, Yihong Tang, Fuzheng Zhang, Di Zhang, Kun Gai

CGIM: A Cycle Guided Interactive Learning Model for Consistency Identification in Task-oriented Dialogue (2022.coling-1)

Challenge:	Existing benchmarks only evaluate LLMs' abilities for task completion as assistant AI.
Approach:	They propose a dialogue evaluation benchmark that contains 12 dialogue tasks to evaluate LLMs' capabilities as human-like dialogue systems.
Outcome:	The proposed benchmark contains 12 tasks to evaluate LLMs' capabilities . it shows that instruction tuning improves human likeness, but not as human-like systems .

Copied to clipboard

Libo Qin, Qiguang Chen, Tianbao Xie, Qian Liu, Shijue Huang, Wanxiang Che, Zhou Yu

N-LTP: An Open-source Neural Language Technology Platform for Chinese (2021.emnlp-demo)

Challenge:	Consistency identification in task-oriented dialog usually consists of three subtasks . a proposed model for consistency identification in dialog is based on an explicit interaction paradigm .
Approach:	They propose a cycle guided interactive learning model that makes information exchange explicit from all the three tasks.
Outcome:	The proposed model achieves state-of-the-art performance pushing the overall score to 56.3% (5.0% point absolute improvement)

Copied to clipboard

Wanxiang Che, Yunlong Feng, Libo Qin, Ting Liu

ClueAnchor: Clue-Anchored Knowledge Reasoning Exploration and Optimization for Retrieval-Augmented Generation (2025.findings-emnlp)

Challenge:	Existing tools that teach an independent model for each task are not supported in Chinese.
Approach:	They propose an open-source neural language platform supporting six Chinese NLP tasks . source code, documentation, and pre-trained models are available at https://github.com/hit-SCIR/ltp .
Outcome:	The proposed platform supports six Chinese NLP tasks.

Copied to clipboard

Hao Chen, Yukun Yan, Sen Mei, Wanxiang Che, Zhenghao Liu, Qi Shi, Xinze Li, Yuchun Fan, Pengcheng Huang, Qiushi Xiong, Zhiyuan Liu, Maosong Sun

Reasoning

Challenge:	Existing RAG systems often underutilize the retrieved documents, authors say . they fail to extract and integrate key clues needed to support faithful and interpretable reasoning .
Approach:	a new framework extracts key clues from retrieved content and generates multiple reasoning paths . the framework optimizes the model by selecting the most appropriate reasoning path .
Outcome:	Experiments show that ClueAnchor outperforms baseline RAG frameworks in completeness and robustness.

Improving Grammatical Error Correction via Contextual Data Augmentation (2024.findings-acl)

Copied to clipboard

Yixuan Wang, Baoxin Wang, Yijun Liu, Qingfu Zhu, Dayong Wu, Wanxiang Che

Low-Resource NLP

Challenge:	Increasing use of synthetic data due to inconsistent error distribution and noisy labels is limiting the use of these data.
Approach:	They propose a method for augmentation of synthetic data with a more consistent error distribution.
Outcome:	The proposed method outperforms strong baselines and achieves state-of-the-art with only a few synthetic data.

A Survey on Natural Language Processing for Programming (2024.lrec-main)

Copied to clipboard

Qingfu Zhu, Xianzhen Luo, Fang Liu, Cuiyun Gao, Wanxiang Che

A Span-Extraction Dataset for Chinese Machine Reading Comprehension (D19-1)

Challenge:	Natural language processing for programming is a field of NLP and software engineering . it is used to assist programming, and is increasingly prevalent for its effectiveness in improving productivity.
Approach:	They propose to use NLP techniques to assist programming by obtaining a structure-based representation and a functionality-oriented algorithm.
Outcome:	The proposed approach could relieve developers from laborious work while improving efficiency for non-professional users.

Copied to clipboard

Yiming Cui, Ting Liu, Wanxiang Che, Li Xiao, Zhipeng Chen, Wentao Ma, Shijin Wang, Guoping Hu

Machine Reading Comprehension

Challenge:	Existing reading comprehension datasets are mostly in English . MRC is a new field of research that aims to comprehend the context of articles and answer the questions based on them.
Approach:	They propose a Span-Extraction dataset for Chinese machine reading comprehension to add language diversities to existing reading comprehension datasets.
Outcome:	The proposed dataset is composed of 20,000 real questions annotated on Wikipedia paragraphs by human experts.

A Closer Look into the Robustness of Neural Dependency Parsers Using Better Adversarial Examples (2021.findings-acl)

Copied to clipboard

Yuxuan Wang, Wanxiang Che, Ivan Titov, Shay B. Cohen, Zhilin Lei, Ting Liu

Robustness in NLP

Challenge:	Neural network-based models have been successful in a wide range of NLP tasks, but their performance is undermined by adversarial examples that would pose no confusion for humans.
Approach:	They propose a method to generate high-quality adversarial examples with a higher number of candidate generators and stricter filters and then verify their quality using automatic and human evaluations.
Outcome:	The proposed method improves the robustness of English parsing models by relying on adversarial training and model ensembling.

Towards Conversational Recommendation over Multi-Type Dialogs (2020.acl-main)

Copied to clipboard

Zeming Liu, Haifeng Wang, Zheng-Yu Niu, Hua Wu, Wanxiang Che, Ting Liu

DialogueCSE: Dialogue-based Contrastive Learning of Sentence Embeddings (2021.emnlp-main)

Challenge:	In recent years, there has been a significant increase in the work of conversational recommendation due to the rise of voice-based bots.
Approach:	They use a Chinese dialog dataset DuRecDial to study conversational recommendation in the context of multi-type dialogs where bots can proactively lead a conversation from a non-recommendation dialog to a recommendation dialog.
Outcome:	The proposed dataset allows to investigate different parts of the overall problem, e.g., how to naturally lead a dialog, how interact with users for recommendation.

Copied to clipboard

Che Liu, Rui Wang, Jinghua Liu, Jian Sun, Fei Huang, Luo Si

DLPO: Towards a Robust, Efficient, and Generalizable Prompt Optimization Framework from a Deep-Learning Perspective (2025.findings-emnlp)

Challenge:	Conventional approaches to learning sentence embeddings from dialogues employ the siamese-network for this task, but such architecture yields a large gap between training and evaluating.
Approach:	They propose a dialogue-based contrastive learning approach to learn sentence embeddings from dialogues using a siamese-network.
Outcome:	The proposed model outperforms baseline methods on three multi-turn dialogue datasets in terms of MAP and Spearman’s correlation measures.

Copied to clipboard

Dengyun Peng, Yuhang Zhou, Qiguang Chen, JinHao Liu, Jingjing Chen, Libo Qin, Wanxiang Che

Inductive-Deductive Strategy Reuse for Multi-Turn Instructional Dialogues (2024.emnlp-main)

Challenge:	Existing methods for prompt optimization still face challenges in robustness, efficiency, and generalization.
Approach:	They propose 7 new approaches inspired by traditional deep learning paradigms for prompt optimization that integrate text-based gradient optimization.
Outcome:	The proposed methods integrate deep learning paradigms into text-based gradient optimization.

Copied to clipboard

Jiao Ou, Jiayu Wu, Che Liu, Fuzheng Zhang, Di Zhang, Kun Gai

SuPreME: A Supervised Pre-training Framework for Multimodal ECG Representation Learning (2025.findings-emnlp)

Challenge:	Existing methods target instruction dialogues as learning goal and fine-tune user simulators to pose instructions.
Approach:	They propose to use real instruction dialogues to model complex dialogue flows and pose high-quality instructions.
Outcome:	The proposed method generates diverse, in-depth, and insightful instructions for a given dialogue history.

Copied to clipboard

Mingsheng Cai, Jiuming Jiang, Wenhao Huang, Che Liu, Rossella Arcucci

An AMR Aligner Tuned by Transition-based Parser (D18-1)

Challenge:	Recent ECG Self-Supervised Learning methods mitigate this by learning features without extensive labels but fail to capture fine-grained clinical semantics and require extensive task-specific fine-tuning.
Approach:	They propose a supervised pre-training framework for Multimodal ECG representation learning that combines structured diagnostic labels with large language models to help denoise, standardize cardiac concepts and improve clinical representation learning.
Outcome:	The proposed framework improves on six downstream datasets covering 106 cardiac conditions and achieves a zero-shot AUC performance of 77.20% over state-of-the-art eSSLs.

Copied to clipboard

Yijia Liu, Wanxiang Che, Bo Zheng, Bing Qin, Ting Liu

Dial2vec: Self-Guided Contrastive Learning of Unsupervised Dialogue Embeddings (2022.emnlp-main)

Challenge:	Experimental results show that our AMR aligner outperforms the rule-based aligner by achieving higher alignment F1 score and consistently improving two open-source AMR parsers.
Approach:	They propose a rich resource enhanced AMR aligner which produces multiple alignments and a new transition system for AMR parsing along with its oracle parser.
Outcome:	The proposed AMR aligner outperforms the current state-of-the-art parser by achieving higher alignment F1 score and consistently improving two open-source AMR parsers.

Copied to clipboard

Che Liu, Rui Wang, Junfeng Jiang, Yongbin Li, Fei Huang

Revisiting Pre-Trained Models for Chinese Natural Language Processing (2020.findings-emnlp)

Challenge:	Dialogue embeddings are a critical prerequisite for semantically understanding dialogues.
Approach:	They propose a self-guided contrastive learning approach called dial2vec that captures interaction patterns between interlocutors and leverages them to guide the learning of the embeddings corresponding to each interlocuter.
Outcome:	The proposed approach achieves 8.7, 9.0, and 13.8 points absolute improvements over the strongest baseline on the three evaluation tasks respectively.

Copied to clipboard

Yiming Cui, Wanxiang Che, Ting Liu, Bing Qin, Shijin Wang, Guoping Hu

MEIT: Multimodal Electrocardiogram Instruction Tuning on Large Language Models for Report Generation (2025.findings-acl)

Challenge:	Existing pre-trained language models have shown tremendous improvements across various NLP tasks.
Approach:	They propose to revisit Chinese pre-trained language models to examine their effectiveness in a non-English language and release the Chinese pretrained model series to the community.
Outcome:	The proposed model improves on RoBERTa in several ways, especially the masking strategy that adopts MLM as correction (Mac).

Copied to clipboard

Zhongwei Wan, Che Liu, Xin Wang, Chaofan Tao, Hui Shen, Jing Xiong, Rossella Arcucci, Huaxiu Yao, Mi Zhang

Argus: Benchmarking and Enhancing Vision-Language Models for 3D Radiology Report Generation (2025.findings-acl)

Challenge:	Recent studies have focused on classifying cardiac conditions using ECG data but have overlooked ECG report generation, which is time-consuming and requires clinical expertise.
Approach:	They propose a Multimodal ECG Instruction Tuning framework that extends the capability of large language models (LLMs) for the task.
Outcome:	The proposed framework outperforms open-source LLMs and LLM backbones across two large-scale ECG datasets.

Copied to clipboard

Che Liu, Zhongwei Wan, Yuqi Wang, Hui Shen, Haozhe Wang, Kangyu Zheng, Mi Zhang, Rossella Arcucci

Federated Learning of Large Language Models with Parameter-Efficient Prompt Tuning and Adaptive Optimization (2023.emnlp-main)

Challenge:	Existing work on 3D radiograph report generation focuses on 2D images, but 3D medical images provide more comprehensive diagnostic information.
Approach:	They propose a comprehensive training recipe for building high-performing VLMs for 3DRRG using a publicly available 3D CT-report dataset.
Outcome:	The proposed model achieves superior performance across different model sizes and input 3D medical image resolutions.

Copied to clipboard

Tianshi Che, Ji Liu, Yang Zhou, Jiaxiang Ren, Jiwen Zhou, Victor Sheng, Huaiyu Dai, Dejing Dou

MEDA: Dynamic KV Cache Allocation for Efficient Multimodal Long-Context Inference (2025.naacl-long)

Challenge:	Prompt tuning of Large Language Models (LLMs) can incur performance degradation or low training efficiency.
Approach:	They propose a prompt tuning approach with Adaptive Optimization to enable efficient FL of LLMs.
Outcome:	The proposed approach improves performance and efficiency simultaneously and addresses client drift problems on both the device and server sides.

Copied to clipboard

Zhongwei Wan, Hui Shen, Xin Wang, Che Liu, Zheda Mai, Mi Zhang

MLLM-I2W: Harnessing Multimodal Large Language Model for Zero-Shot Composed Image Retrieval (2025.coling-main)

Challenge:	Long-context Multimodal Large Language Models (MLLMs) require substantial computational resources as their multimodal Key-Value (KV) cache grows with increasing input lengths, challenging memory and time efficiency.
Approach:	They propose a dynamic multimodal KV cache allocation strategy that dynamically allocating KV size based on attention entropy to better adapt to multimodal interactions.
Outcome:	The proposed model achieves up to 72% KV cache memory reduction and 2.82 faster decoding speeds while maintaining or enhancing performance on various multimodal tasks in a long context.

Copied to clipboard

Tong Bao, Che Liu, Derong Xu, Zhi Zheng, Tong Xu

Distilling Knowledge for Search-based Structured Prediction (P18-1)

Challenge:	Existing methods for combining image retrieval are supervised and zero-shot . however, the challenge of mapping pseudo-words to images within the joint image-text embedding space is still a challenge.
Approach:	They propose a novel image-text mapping network which converts description-related image information into pseudo-word markers for precise ZS-CIR.
Outcome:	The proposed model improves on COCO, CIRR, and Fashion-IQ benchmarks.

Copied to clipboard

Yijia Liu, Wanxiang Che, Huaipeng Zhao, Bing Qin, Ting Liu

LOOK-M: Look-Once Optimization in KV Cache for Efficient Multimodal Long-Context Inference (2024.findings-emnlp)

Challenge:	Existing studies have focused on the performance of structured prediction models, but they are often limited by the ambiguities of the reference policy.
Approach:	They propose to distill an ensemble of multiple models trained with different initializations into a single model and use it to explore the search space.
Outcome:	The proposed model outperforms the greedy models on two typical search-based structured prediction tasks and achieves 1.32 in LAS and 2.65 in BLEU over strong baselines.

Copied to clipboard

Zhongwei Wan, Ziang Wu, Che Liu, Jinfa Huang, Zhihong Zhu, Peng Jin, Longyue Wang, Li Yuan

Visual Data in NLP

Challenge:	Long-context Multimodal Large Language Models (MLLMs) require substantial computational resources for inference . the growth of their multimodal Key-Value (KV) cache challenges memory and time efficiency.
Approach:	They propose a fine-tuning-free approach that efficiently reduces the multimodal KV cache size while maintaining performance comparable to a full cache.
Outcome:	The proposed method reduces the multimodal KV cache size while maintaining performance comparable to a full cache.

LM-Combiner: A Contextual Rewriting Model for Chinese Grammatical Error Correction (2024.lrec-main)

Copied to clipboard

Yixuan Wang, Baoxin Wang, Yijun Liu, Dayong Wu, Wanxiang Che

Text Generation

Challenge:	Recent work using model ensemble methods based on voting can effectively mitigate over-correction and improve the precision of the GEC system.
Approach:	They propose a rewriting model that can directly modify the over-correction of GEC system outputs without a model ensemble.
Outcome:	The proposed model can mitigate over-correction and improve accuracy of Chinese grammatical error correction tasks without a model ensemble.

Experiential Co-Learning of Software-Developing Agents (2024.acl-long)

Copied to clipboard

Chen Qian, Yufan Dang, Jiahao Li, Wei Liu, Zihao Xie, YiFei Wang, Weize Chen, Cheng Yang, Xin Cong, Xiaoyin Che, Zhiyuan Liu, Maosong Sun

DuRecDial 2.0: A Bilingual Parallel Corpus for Conversational Recommendation (2021.emnlp-main)

Challenge:	Recent advances in large language models (LLMs) have brought significant changes to various domains, especially through autonomous agents.
Approach:	They propose a framework that lets agents learn shortcuts from their past tasks and use them for future task execution.
Outcome:	The proposed framework enables agents to tackle unseen software-developing tasks more effectively.

Copied to clipboard

Zeming Liu, Haifeng Wang, Zheng-Yu Niu, Hua Wu, Wanxiang Che

GL-GIN: Fast and Accurate Non-Autoregressive Model for Joint Multiple Intent Detection and Slot Filling (2021.acl-long)

Challenge:	Existing datasets for conversational recommendation are limited to English and Chinese .
Approach:	They propose a bilingual parallel human-to-human recommendation dialog dataset . the data item is annotated in two languages, both English and Chinese .
Outcome:	The proposed dataset provides a testbed for future studies of multilingual and cross-lingual conversational recommendation.

Copied to clipboard

Libo Qin, Fuxuan Wei, Tianbao Xie, Xiao Xu, Wanxiang Che, Ting Liu

Sentiment Analysis

Challenge:	Existing joint models for multi-intent SLU only consider intent detection while ignoring slot filling task.
Approach:	They propose a non-autoregressive model for joint multiple intent detection and slot filling . their framework is 11.5 times faster than existing joint models .
Outcome:	The proposed model is 11.5 times faster than existing models and is faster than current models.

Recall and Learn: Fine-tuning Deep Pretrained Language Models with Less Forgetting (2020.emnlp-main)

Copied to clipboard

Sanyuan Chen, Yutai Hou, Yiming Cui, Wanxiang Che, Ting Liu, Xiangzhan Yu

E-ViC: Reasoning Beyond Text via Embodied Visual Chain for Spatial Intelligence (2026.acl-long)

Challenge:	Existing methods to fine-tune deep pretrained language models face catastrophic forgetting problems.
Approach:	They propose a recall and learn mechanism which integrates pretraining and downstream tasks into a single mechanism.
Outcome:	The proposed method achieves state-of-the-art performance on the GLUE benchmark and better average performance than directly fine-tuning of BERT-large.

Copied to clipboard

Junbo Qi, Yi Zhang, Hanchu Ni, Che Liu, Zhimin Yao, Ruilin Yang, Xiancong Ren, Liangjian Wen, Wei Ge, Yuya Ieiri, Osamu Yoshie, Yong Dai, Xiaozhu Ju

Cross-Lingual BERT Transformation for Zero-Shot Dependency Parsing (D19-1)

Challenge:	Existing Vision-Language Models (VLMs) lack spatial reasoning, despite text-based CoTs . e-ViC reframes spatial intelligence as a verifiable, tool-using capability, argues a new study.
Approach:	They propose a framework that moves reasoning beyond text into the visual domain . they ground reasoning in pixel-level interactions to enable human-like "look-and-confirm" strategies .
Outcome:	The proposed framework outperforms existing Vision-Language Models with an average gain of 10.1%.

Copied to clipboard

Yuxuan Wang, Wanxiang Che, Jiang Guo, Yijia Liu, Ting Liu

AutoVecCoder: Teaching LLMs to Generate Explicitly Vectorized Code (2026.findings-acl)

Challenge:	Existing approaches to learn cross-lingual word embeddings in a contextual space are lacking.
Approach:	They propose a method to generate cross-lingual contextualized word embeddings using pre-trained BERT models by learning a linear transformation from contextual word alignments.
Outcome:	The proposed approach outperforms state-of-the-art models on zero-shot cross-lingual transfer parsing and is highly competitive with existing models.

Copied to clipboard

ShangZhan Li, Xinyu Yin, Xuanyu Jin, Ye He, Yuxin Zhou, Yuxuan Li, Xu Han, Wanxiang Che, Qi Shi, Ting Liu, Maosong Sun

Programming Languages in NLP

Challenge:	Current development practices face a dichotomy between automation and performance.
Approach:	They propose a framework to empower LLMs with the capability of automated explicit vectorization.
Outcome:	The proposed framework achieves state-of-the-art performance on the SSE and AVX subsets of SimdBench.

Exploring Hybrid Question Answering via Program-based Prompting (2024.acl-long)

Copied to clipboard

Qi Shi, Han Cui, Haofeng Wang, Qingfu Zhu, Wanxiang Che, Ting Liu

Can Medical Vision-Language Pre-training Succeed with Purely Synthetic Data? (2025.findings-acl)

Challenge:	Existing approaches to question answering over heterogeneous data are limited due to large scale of information and organic coupling of heterogenous data.
Approach:	They propose a program-based prompting framework for hybrid question answering tasks . it integrates various functions to perform hybrid information-seeking over data .
Outcome:	The proposed framework surpasses baseline systems and achieves the best performance under the fewshot settings.

Copied to clipboard

Che Liu, Zhongwei Wan, Haozhe Wang, Yinda Chen, Talha Qaiser, Chen Jin, Nikolay Burlutskiy, Fariba Yousefi, Rossella Arcucci

Consistency Regularization for Cross-Lingual Fine-Tuning (2021.acl-long)

Challenge:	Medical Vision-Language Pretraining (MedVLP) models typically require large-scale datasets with paired, high-quality image-text data.
Approach:	They propose to generate large-scale synthetic image-text pairs using off-the-shelf generative models . they propose to isolate model and training settings, focusing entirely from the data perspective.
Outcome:	The proposed pipeline outperforms models trained on real data by 3.8% on averaged AUC on zero-shot classification tasks.

Copied to clipboard

Bo Zheng, Li Dong, Shaohan Huang, Wenhui Wang, Zewen Chi, Saksham Singhal, Wanxiang Che, Ting Liu, Xia Song, Furu Wei

Multilinguality

Challenge:	Experimental results show that consistency regularization improves cross-lingual fine-tuning . pre-trained cross-linguistic models can transfer task-specific supervision from one language to the other .
Approach:	They propose to improve cross-lingual fine-tuning with consistency regularization . they use example consistency regularized to penalize prediction sensitivity to four types of data augmentations .
Outcome:	The proposed method improves cross-lingual fine-tuning across tasks . it can be generalized to other target languages without additional training .

Few-shot Slot Tagging with Collapsed Dependency Transfer and Label-enhanced Task-adaptive Projection Network (2020.acl-main)

Copied to clipboard

Yutai Hou, Wanxiang Che, Yongkui Lai, Zhihan Zhou, Yijia Liu, Han Liu, Ting Liu

Document Modeling with Graph Attention Networks for Multi-grained Machine Reading Comprehension (2020.acl-main)

Challenge:	Existing few-shot learning methods for slot tagging are based on similarity-based methods, but they are difficult to apply to an unseen domain due to the discrepancy of label sets.
Approach:	They propose a label-enhanced task-adaptive projection network to transfer abstract label dependency patterns as transition scores into the conditional random field (CRF) Experimental results show that their model significantly outperforms the strongest few-shot learning baseline by 14.64 F1 scores in the one-shot setting.
Outcome:	The proposed model outperforms the strongest few-shot learning baseline by 14.64 F1 scores in the one-shot setting.

Copied to clipboard

Bo Zheng, Haoyang Wen, Yaobo Liang, Nan Duan, Wanxiang Che, Daxin Jiang, Ming Zhou, Ting Liu

Nirvana: A Specialized Generalist Model With Task-Aware Memory Mechanism (2026.acl-long)

Challenge:	Existing approaches to machine reading comprehension treat documents at their hierarchical nature, ignoring their dependencies.
Approach:	They propose a machine reading comprehension benchmark with two-grained answers . they use graph attention networks to model documents at their hierarchical nature .
Outcome:	The proposed framework outperforms existing systems at long and short answer criteria.

Copied to clipboard

Yuhua Jiang, Shuang Cheng, Yihao Liu, Ermo Hua, Che Jiang, Weigao Sun, Yu Cheng, Feifei Gao, Biqing Qi, Bowen Zhou

AGIF: An Adaptive Graph-Interactive Framework for Joint Multiple Intent Detection and Slot Filling (2020.findings-emnlp)

Challenge:	Existing models lack task-guided specialized memory mechanisms . specialized generalist models excel at general language tasks but struggle in specialized domains.
Approach:	They propose a specialized generalist model with specialized memory and updater that can optimize for specialized domains.
Outcome:	The proposed model matches or surpasses baselines on general benchmarks and achieves lowest perplexity across specialized domains.

Copied to clipboard

Libo Qin, Xiao Xu, Wanxiang Che, Ting Liu

Parsing Tweets into Universal Dependencies (N18-1)

Challenge:	Existing models focus on the single intent scenario, ignoring the fine-grained multiple intents information integration for token-level slot prediction.
Approach:	They propose an Adaptive Graph-Interactive Framework for joint multiple intent detection and slot filling . they propose an intent-slot graph interaction layer to model the strong correlation between the slot and intents .
Outcome:	The proposed framework improves on three multi-intent datasets and new state-of-the-art performance on single-intention datasets.

Copied to clipboard

Yijia Liu, Yi Zhu, Wanxiang Che, Bing Qin, Nathan Schneider, Noah A. Smith

Syntactic Text Processing

Challenge:	a new tweet treebank for English is designed to analyze tweets with universal dependencies (UD).
Approach:	They extend the universal dependencies guidelines to include special constructions in tweets that affect tokenization, part-of-speech tagging, and labeled dependencies.
Outcome:	The proposed method outperforms state-of-the-art parsers on other treebanks in accuracy and speed.

Dynamic Connected Networks for Chinese Spelling Check (2021.findings-acl)

Copied to clipboard

Baoxin Wang, Wanxiang Che, Dayong Wu, Shijin Wang, Guoping Hu, Ting Liu

Parrot: Enhancing Multi-Turn Instruction Following for Large Language Models (2024.acl-long)

Challenge:	Chinese spelling check (CSC) is a task to detect and correct spelling errors in Chinese text.
Approach:	They propose a new architecture which generates Chinese characters via a Pinyin Enhanced Candidate Generator and then utilizes an attention-based network to model the dependencies between two adjacent Chinese characters.
Outcome:	The proposed method achieves state-of-the-art performance on three human-annotated datasets.

Copied to clipboard

Yuchong Sun, Che Liu, Kun Zhou, Jinwen Huang, Ruihua Song, Xin Zhao, Fuzheng Zhang, Di Zhang, Kun Gai