Papers by Qing Xie

MLLM-Protector: Ensuring MLLM’s Safety without Hurting Performance (2024.emnlp-main)

Copied to clipboard

Renjie Pi, Tianyang Han, Jianshu Zhang, Yueqi Xie, Rui Pan, Qing Lian, Hanze Dong, Jipeng Zhang, Tong Zhang

Challenge:	MLLMs are deployed on limited image-text pairs, which makes them more vulnerable to catastrophic forgetting of their original abilities during safety fine-tuning.
Approach:	They propose a plug-and-play strategy that detects harmful visual inputs and transforms harmful ones into harmless ones.
Outcome:	The proposed approach mitigates the risks posed by malicious visual inputs without compromising the original performance of MLLMs.

TwiUSD: A Benchmark Dataset and Structure-Aware LLM Framework for User Stance Detection (2026.acl-long)

Copied to clipboard

Fuqiang Niu, Zini Chen, Zhiyu Xie, Hu Huang, Qing Liao, Qianlong Wang, Genan Dai, Bowen Zhang

Sentiment Analysis

Challenge:	Existing benchmarks for political user-level stance detection rely on noisy heuristics or distant supervision.
Approach:	They propose a large-scale, expert-annotated benchmark for political user-level stance detection with explicit social network structure that integrates user content and followee signals.
Outcome:	The proposed framework outperforms baselines in terms of quality and reliability.

Recurrent Attention Networks for Long-text Modeling (2023.findings-acl)

Copied to clipboard

Xianming Li, Zongxi Li, Xiaotian Luo, Haoran Xie, Xing Lee, Yingbin Zhao, Fu Lee Wang, Qing Li

Information Extraction & Text Mining

Challenge:	Existing approaches to encoding long documents using self-attention have been limited by quadratic computational complexities and limited application in long text processing.
Approach:	They propose a long-document encoding model that allows the recurrent operation of self-attention.
Outcome:	The proposed model extracts global semantics in token-level and document-level representations, making it inherently compatible with both sequential and sequential tasks.

Hidden State Variability of Pretrained Language Models Can Guide Computation Reduction for Transfer Learning (2022.findings-emnlp)

Copied to clipboard

Shuo Xie, Jiahao Qiu, Ankita Pasad, Li Du, Qing Qu, Hongyuan Mei

Language Models

Challenge:	Existing approaches to transfer a pretrained language model include fine-tuning all the parameters in the language model and adapting all its subsets.
Approach:	They propose to select layers based on the variability of their hidden states given a task-specific corpus.
Outcome:	The proposed model reduces the computational cost of transfer learning methods without sacrificing performance.

Emotion Classification by Jointly Learning to Lexiconize and Classify (2020.coling-main)

Copied to clipboard

Deyu Zhou, Shuangzhi Wu, Qing Wang, Jun Xie, Zhaopeng Tu, Mu Li

Text Classification

Challenge:	Existing approaches to identify emotions in short text are limited and lack coverage and inaccuracies when applied to informal short text.
Approach:	They propose a novel emotional network to jointly learn sentence emotions and construct emotion lexicons which are dynamically adapted to a given context.
Outcome:	The proposed model outperforms several approaches proposed in previous studies and achieves new state-of-the-art on the benchmark Twitter dataset.

MATO: A Model-Agnostic Training Optimization for Aspect Sentiment Triplet Extraction (2025.naacl-long)

Copied to clipboard

Shaopeng Tang, Lin Li, Xiaohui Tao, Leqi Zhong, Qing Xie

Sentiment Analysis

Challenge:	Existing models with strong in-house performance may struggle to generalize to diverse expressions.
Approach:	They propose a model-agnostic t**raining method to improve ASTE model inference . they propose to compute the violation rate (VR) on each element of one triplet .
Outcome:	The proposed method can improve aspect sentiment triplet extraction models consistent with expected results facing triplet element diversity.

Incorporating Global Information in Local Attention for Knowledge Representation Learning (2021.findings-acl)

Copied to clipboard

Yu Zhao, Han Zhou, Ruobing Xie, Fuzhen Zhuang, Qing Li, Ji Liu

Semantic Text Processing

Challenge:	Graph Attention Networks (GATs) are a promising model that takes advantage of localized attention mechanism to perform knowledge representation learning (KRL) on graph-structure data.
Approach:	They propose to incorporate global information into the GAT family of models by using an attention-based global random walk algorithm.
Outcome:	Experimental results on KG entity prediction against the state-of-the-arts demonstrate the effectiveness of the proposed model.

Reasoning under Uncertainty: Efficient LLM Inference via Unsupervised Confidence Dilution and Convergent Adaptive Sampling (2025.emnlp-main)

Copied to clipboard

Zhenning Shi, Yijia Zhu, Yi Xie, Junhan Shi, Guorui Xie, Haotian Zhang, Yong Jiang, Congcong Miao, Qing Li

Responsible & Trustworthy NLP

Challenge:	Large language models suffer from overconfidence and computational inefficiency due to fixed computation budgets and miscalibrated confidence estimates.
Approach:	They propose a framework for computationally efficient, trustworthy reasoning under uncertainty using Diversity-Aware Self-Signal Dilution and Convergent Adaptive Weighted Sampling techniques.
Outcome:	The proposed framework reduces inference cost by 70% while maintaining accuracy levels while reducing inference costs.

CADReview: Automatically Reviewing CAD Programs with Error Detection and Correction (2025.acl-long)

Copied to clipboard

Jiali Chen, Xusen Hei, HongFei Liu, Yuancheng Wei, Zikun Deng, Jiayuan Xie, Yi Cai, Li Qing

Multimodality

Challenge:	Computer-aided design (CAD) is crucial in prototyping 3D objects through geometric instructions.
Approach:	They propose a CAD review task to automatically detect and correct potential errors . they propose CAD program repairer framework to provide helpful feedback on error correction .
Outcome:	The proposed framework outperforms existing MLLMs in detecting errors and providing feedback on error correction.

Neural Mixed Counting Models for Dispersed Topic Discovery (2020.acl-main)

Copied to clipboard

Jiemin Wu, Yanghui Rao, Zusheng Zhang, Haoran Xie, Qing Li, Fu Lee Wang, Ziye Chen

Information Extraction & Text Mining

Challenge:	Existing methods for inference of parameter parameters are time-consuming and difficult to use.
Approach:	They propose two efficient neural mixed counting models that use the negative binomial distribution as the prior for dispersed topic discovery.
Outcome:	The proposed models outperform state-of-the-art models in terms of perplexity and topic coherence on real-world datasets.

Fine-Grained Features-based Code Search for Precise Query-Code Matching (2025.coling-main)

Copied to clipboard

Xinting Zhang, Mengqiu Cheng, Mengzhen Wang, Songwen Gong, Jiayuan Xie, Yi Cai, Qing Li

Information Retrieval

Challenge:	Existing methods to locate code snippets from databases represent the semantics of code and query by averaging the features of each token and word.
Approach:	They propose a fine-grained code search model that consists of a cross-modal encoder, mapping layer and classification layer to capture fine-granular interactions between code and query.
Outcome:	The proposed model significantly outperforms existing methods across multiple programming language datasets.

VSCBench: Bridging the Gap in Vision-Language Model Safety Calibration (2025.findings-acl)

Copied to clipboard

Jiahui Geng, Qing Li, Zongxiong Chen, Yuxia Wang, Derui Zhu, Zhuohan Xie, Chenyang Lyu, Xiuying Chen, Preslav Nakov, Fakhri Karray

Visual Data in NLP

Challenge:	Existing safety calibration methods focus on model undersafety, where the model responds to hazardous queries, while neglecting oversafetiness, where models refuse to answer safe queries.
Approach:	They propose safety calibration which addresses both undersafety and oversafetiness by comparing model responses to a novel dataset of 3,600 image-text pairs.
Outcome:	The proposed methods have been used to evaluate safety calibration across image-centric and text-centric scenarios.

PENS: A Dataset and Generic Framework for Personalized News Headline Generation (2021.acl-long)

Copied to clipboard

Xiang Ao, Xiting Wang, Ling Luo, Ying Qiao, Qing He, Xing Xie

Text Generation

Challenge:	Using a dataset of Microsoft News, we propose a generic framework to personalize a text generator and establish personalized headlines.
Approach:	They propose a generic framework to personalize a news headline generator and establish personalized headlines by leveraging user behavioral data.
Outcome:	The proposed framework is based on user preference data and user preference injections to personalize a text generator and establish personalized headlines.

Where Did It Go Wrong? Capability-Oriented Failure Attribution for Vision-and-Language Navigation Agents (2026.findings-acl)

Copied to clipboard

Jianming Chen, Yawen Wang, Junjie Wang, Xiaofei Xie, Shoubin Li, Qing Wang, Fanjiang Xu

Multimodality

Challenge:	Existing testing methods are system-level and provide limited insight into which capability deficiencies cause task failures.
Approach:	They propose a capability-oriented testing approach that enables failure detection and attribution by seed selection and mutation.
Outcome:	The proposed method detects more failure cases and pinpoints capability-level deficiencies than state-of-the-art baselines, providing more interpretable and actionable guidance for improving embodied agents.

Descriptive Prompt Paraphrasing for Target-Oriented Multimodal Sentiment Classification (2023.findings-emnlp)

Copied to clipboard

Dan Liu, Lin Li, Xiaohui Tao, Jian Cui, Qing Xie

Information Retrieval

Challenge:	Current researches mainly work on either of two types of targets in a decentralized manner.
Approach:	They propose a model to perform sentiment polarity on a target jointly considering its corresponding multiple modalities including text, image, and others.
Outcome:	The proposed model performs well on four datasets spanning the above two target types and is prompt-based language modelling.