Papers by Liqiang Nie

ORPP: Self-Optimizing Role-playing Prompts to Enhance Language Model Capabilities (2025.emnlp-main)

Challenge:	Existing methods for text-to-video retrieval select a subset of frames to represent video content . current methods only explore video contents while ignoring relevancy to texts .
Approach:	They propose to use a subset of frames to represent video content for TVR . they analyze six different frame selection methods to determine their effectiveness .
Outcome:	The proposed method improves retrieval efficiency without sacrificing visual details . the proposed method explores the video contents while ignoring relevancy to texts .

Copied to clipboard

Yifan Duan, Yihong Tang, Kehai Chen, Liqiang Nie, Min Zhang

Make Imagination Clearer! Stable Diffusion-based Visual Imagination for Multimodal Machine Translation (2025.acl-long)

Challenge:	Existing research has explored model-driven strategies for prompt optimization, but these methods suffer from high computational overhead or require strong optimization capabilities from the model itself, which limits their broad applicability.
Approach:	They propose a framework that optimizes and generates role-playing prompts by limiting the prompt search space to role-player scenarios.
Outcome:	The proposed framework matches and surpasses existing prompt optimization methods in terms of performance.

Copied to clipboard

Andong Chen, Yuchen Song, Kehai Chen, Xuefeng Bai, Muyun Yang, Liqiang Nie, Jie Liu, Tiejun Zhao, Min Zhang

MMCoQA: Conversational Question Answering over Text, Tables, and Images (2022.acl-long)

Challenge:	Experimental results show that our model significantly outperforms existing multimodal MT and text-only MT.
Approach:	They propose a stable diffusion-based imagination network into a multimodal large language model to generate an image for each source sentence.
Outcome:	The proposed model outperforms existing multimodal and text-only MT and achieves an average improvement of 14 BLEU points on Multi30K and MSCOCO multimodal MT benchmarks.

Copied to clipboard

Yongqi Li, Wenjie Li, Liqiang Nie

Natural Language Interfaces

Challenge:	Existing conversational QA systems only use a single knowledge source, e.g., paragraphs or knowledge graph, and assume it contains enough evidence to extract answers to users' questions.
Approach:	They propose a task to answer users' questions with multimodal knowledge sources via multi-turn conversations using a multimodal dataset.
Outcome:	The proposed task brings a series of research challenges, including but not limited to priority, consistency, and complementarity of multimodal knowledge.

PersonalAlign: Hierarchical Implicit Intent Alignment for Personalized GUI Agent with Long-Term User-Centric Records (2026.acl-long)

Copied to clipboard

Yibo Lyu, Gongwei Chen, Rui Shao, Weili Guan, Liqiang Nie

Challenge:	GUI agents have shown strong performance under explicit and completion instructions, but real-world deployment requires aligning with users’ more complex implicit intents.
Approach:	They propose a task that requires agents to leverage long-term user records as persistent context to resolve omitted preferences in vague instructions and anticipate latent routines by user state for proactive assistance.
Outcome:	The proposed task improves execution and proactive performance by 15.7% and 7.3% under explicit and completion instructions.

REPT: Bridging Language Models and Machine Reading Comprehension via Retrieval-Based Pre-training (2021.findings-acl)

Copied to clipboard

Fangkai Jiao, Yangyang Guo, Yilin Niu, Feng Ji, Feng-Lin Li, Liqiang Nie

Reasoning

Challenge:	Pre-trained language models have achieved great success on Machine Reading Comprehension (MRC) however, the poor support in evidence extraction hinders them from further advancing MRC.
Approach:	They propose a REtrieval-based pre-training approach that strengthens evidence extraction during pre-training by inherited downstream MRC tasks.
Outcome:	The proposed approach strengthens evidence extraction during pre-training, which is further inherited by downstream tasks.

Aspect-to-Scope Oriented Multi-view Contrastive Learning for Aspect-based Sentiment Analysis (2023.findings-emnlp)

Copied to clipboard

Heyan Chai, Ziyi Yao, Siyu Tang, Ye Wang, Liqiang Nie, Binxing Fang, Qing Liao

LRQuant: Learnable and Robust Post-Training Quantization for Large Language Models (2024.acl-long)

Challenge:	Existing methods for Aspect-based sentiment analysis (ABSA) focus on mining syntactic or semantic information, which suffers from noisy interference when multiple aspects exist in a sentence.
Approach:	They propose a scope-assisted multi-view graph contrastive learning framework that captures correlation and difference between aspect and syntactic/semantic information.
Outcome:	The proposed framework outperforms state-of-the-art methods on five benchmark datasets and verifies its effectiveness and robustness.

Copied to clipboard

Jiaqi Zhao, Miao Zhang, Chao Zeng, Ming Wang, Xuebo Liu, Liqiang Nie

Robustness in NLP

Challenge:	Existing methods for post-training quantization (PTQ) are limited by the complexity of the quantization parameter and performance degradations when tested on unseen datasets.
Approach:	They propose a learnable smooth-based PTQ framework that allows for rapid adaptation during testing.
Outcome:	The proposed framework improves performance on unseen datasets and reduces memory constraints.

Self-chats from Large Language Models Make Small Emotional Support Chatbot Better (2024.acl-long)

Copied to clipboard

Zhonghua Zheng, Lizi Liao, Yang Deng, Libo Qin, Liqiang Nie

GUI-explorer: Autonomous Exploration and Mining of Transition-aware Knowledge for GUI Agent (2025.acl-long)

Challenge:	Large Language Models (LLMs) have shown strong generalization abilities to excel in various tasks, including emotion support conversations.
Approach:	They propose an iterative expansion framework to prompt large teacher model to curate an expansive emotion support dialogue dataset.
Outcome:	The proposed model outperforms the teacher model in some cases . the proposed model is based on an iterative expansion framework and is available on github.com/pandazzh2020/ExTES.

Copied to clipboard

Bin Xie, Rui Shao, Gongwei Chen, Kaiwen Zhou, Yinchuan Li, Jie Liu, Min Zhang, Liqiang Nie

Low-Resource NLP

Challenge:	GUI automation is a key challenge in dynamic environments.
Approach:	They propose a training-free GUI agent that integrates two mechanisms to explore trajectories in GUIs.
Outcome:	The proposed GUI-explorer shows significant improvements over existing agents.

CoRe-MMRAG: Cross-Source Knowledge Reconciliation for Multimodal RAG (2025.acl-long)

Copied to clipboard

Yang Tian, Fan Liu, Jingyuan Zhang, V. W., Yupeng Hu, Liqiang Nie

Weight-Aware Activation Sparsity with Constrained Bayesian Optimization Scheduling for Large Language Models (2025.emnlp-main)

Challenge:	Recent advances in Multimodal Large Language Models have significantly improved reasoning and generation tasks by leveraging joint vision-language representations.
Approach:	They propose a framework that reconciles inconsistencies across knowledge sources . they use a four-stage pipeline to generate an internal response from parametric knowledge .
Outcome:	Experiments on KB-VQA show that CoRe-MMRAG achieves performance gains of 5.6% and 9.3% over baseline methods.

Copied to clipboard

Ming Wang, Miao Zhang, Xuebo Liu, Liqiang Nie

Multi-source Semantic Graph-based Multimodal Sarcasm Explanation Generation (2023.acl-long)

Challenge:	Existing activation sparsification methods rely on activation magnitude and weights for sparsity . authors propose a weight-aware activation-a-ware framework for large language models .
Approach:	They propose a weight-aware activation sparsity framework that uses weight-based scoring to measure activation importance in sparsification and a custom GPU sparse kernel to support it.
Outcome:	The proposed framework outperforms existing methods at 60% model-level sparsity and significantly outperfies them at higher sparsities.

Copied to clipboard

Liqiang Jing, Xuemeng Song, Kun Ouyang, Mengzhao Jia, Liqiang Nie

Reasoning in the Dark: Interleaved Vision-Text Reasoning in Latent Space (2026.findings-acl)

Challenge:	Existing studies can only identify sarcastic post but could not give concrete explanation for why it is sarkastic.
Approach:	They propose a multimodal sarcasm explanation scheme that generates a sentence for a social post to explain why it contains sarkasis.
Outcome:	The proposed model outperforms existing methods on a public dataset.

Copied to clipboard

Chao Chen, Zhixin Ma, Yongqi Li, Yupeng Hu, Yinwei Wei, Wenjie Li, Liqiang Nie

AdaReTaKe: Adaptive Redundancy Reduction to Perceive Longer for Video-language Understanding (2025.findings-acl)

Challenge:	Existing multimodal reasoning methods depend on explicit reasoning steps that require labor-intensive vision-text annotations and inherently introduce significant inference latency.
Approach:	They propose a method that integrates visual and visual information into the reasoning process to improve the performance of multimodal LLMs.
Outcome:	The proposed method achieves an average performance increase of 5.45% while achieving a speed increase of over 5 times compared to existing methods.

Copied to clipboard

Xiao Wang, Qingyi Si, Shiyu Zhu, Jianlong Wu, Li Cao, Liqiang Nie

MERIt: Meta-Path Guided Contrastive Learning for Logical Reasoning (2022.findings-acl)

Challenge:	Multimodal Large Language Models (MLLMs) are limited by context length when processing long videos.
Approach:	They propose a training-free method that flexibly reduces redundancy by allocating compression ratios among time and model layers with theoretical guarantees.
Outcome:	Experiments on videoMME, MLVU, LongVideoBench, and LVBench show that AdaRETAKE outperforms existing methods by 2.3% and 2.8% for 7B and 72B models.

Copied to clipboard

Fangkai Jiao, Yangyang Guo, Xuemeng Song, Liqiang Nie

Efficient Safety Alignment of Large Language Models via Preference Re-ranking and Representation-based Reward Modeling (2025.acl-long)

Challenge:	Existing methods to infer logical relations with annotated training data suffer from over-fitting and poor generalization problems due to the dataset sparsity.
Approach:	They propose a MEta-path guided contrastive learning method for logical ReasonIng of text that performs self-supervised pre-training on abundant unlabeled text data.
Outcome:	The proposed method outperforms the baselines on two logical reasoning benchmarks with significant improvements.

Copied to clipboard

Deng Qiyuan, Xuefeng Bai, Kehai Chen, Yaowei Wang, Liqiang Nie, Min Zhang

Learning to Ask Questions in Open-domain Conversational Systems with Typed Decoders (P18-1)

Challenge:	Existing safety alignment methods for Large Language Models (LLMs) face the distribution shift issue, which requires significant computational resources.
Approach:	They propose a framework that leverages the model’s intrinsic safety judgment capability to extract reward signals, which are then used to calculate label confidence for preference reordering.
Outcome:	The proposed framework improves safety performance while avoiding 300x computational overheads.

Copied to clipboard

Yansen Wang, Chenyi Liu, Minlie Huang, Liqiang Nie

Natural Language Interfaces

Challenge:	Extensive experiments show that typed decoders outperform state-of-the-art baselines and can generate more meaningful questions.
Approach:	They devised two typed decoders that generate questions with different types of interrogatives, topic words, and ordinary words.
Outcome:	Extensive experiments show that the typed decoders outperform state-of-the-art baselines and can generate more meaningful questions.

Self-adaptive Context and Modal-interaction Modeling For Multimodal Emotion Recognition (2023.findings-acl)

Copied to clipboard

Haozhe Yang, Xianqiang Gao, Jianlong Wu, Tian Gan, Ning Ding, Feijun Jiang, Liqiang Nie

Sentiment Analysis

Challenge:	Existing methods to predict emotion label for a given utterance lack modeling of diverse dependency ranges and inconsistent treatment of contribution for various modalities.
Approach:	They propose a multimodal emotion recognition in conversation task that uses context and multiple modalities to predict emotion label for a given utterance.
Outcome:	The proposed method outperforms the state-of-the-art methods on three multimodal datasets.

HAIC: Improving Human Action Understanding and Generation with Better Captions for Multi-modal Large Language Models (2025.acl-long)

Copied to clipboard

Xiao Wang, Jingyun Hua, Weihong Lin, Yuanxing Zhang, Fuzheng Zhang, Jianlong Wu, Di Zhang, Liqiang Nie

Improving Distantly-Supervised Relation Extraction with Joint Label Embedding (D19-1)

Challenge:	Existing studies have shown that high-quality video captions can improve MLLMs' performance on videos involving human actions.
Approach:	They propose a data annotation pipeline to collect videos featuring clear human actions from the Internet and annotate them in a standardized caption format that uses human attributes to distinguish individuals.
Outcome:	The proposed pipeline combines two datasets to evaluate human action understanding.

Copied to clipboard

Linmei Hu, Luhao Zhang, Chuan Shi, Liqiang Nie, Weili Guan, Cheng Yang

Information Extraction & Text Mining

Challenge:	Existing methods for relation extraction treat labels as independent and meaningless one-hot vectors, which cause a loss of potential label information for selecting valid instances.
Approach:	They propose a multi-layer attention-based model to improve relation extraction with joint label embedding by gating integration and using the embeddable entities as an atten- tion.
Outcome:	The proposed model significantly outperforms state-of-the-art methods in relation extraction with joint label embedding.

Generative Cross-Modal Retrieval: Memorizing Images in Multimodal Language Models for Retrieval and Beyond (2024.acl-long)

Copied to clipboard

Yongqi Li, Wenjie Wang, Leigang Qu, Liqiang Nie, Wenjie Li, Tat-Seng Chua

Causal Intervention and Counterfactual Reasoning for Multi-modal Fake News Detection (2023.acl-long)

Challenge:	Recent advances in generative language models have demonstrated their ability to memorize knowledge from documents and recall knowledge to respond to user queries effectively.
Approach:	They propose to enable multimodal large language models to memorize and recall images within their parameters.
Outcome:	The proposed model performs well even with large-scale image candidate sets.

Copied to clipboard

Ziwei Chen, Linmei Hu, Weixin Li, Yingxia Shao, Liqiang Nie

Reasoning

Challenge:	Existing methods for multi-modal fake news detection neglect the fact that some label-specific features cannot generalize well to the testing set, thus suffering from the latent data bias.
Approach:	They propose a Causal intervention and Counterfactual reasoning based debiasing framework for multi-modal fake news detection that eliminates the image-only bias by deducting the direct effect of the image from the total effect on labels.
Outcome:	The proposed framework eliminates the psycholinguistic bias in the text and the bias of inferring news label based on only image features.

Evolving Sparsity: Leveraging Token Importance Dynamics for Efficient LLM Decoding with Sparse Attention (2026.acl-long)

Copied to clipboard

Ruizi Han, Miao Zhang, Ziyue Qiao, Liqiang Nie

Green & Sustainable NLP

Challenge:	Efficient long-context inference remains a major challenge for large language models (LLMs), as the cost of attention computation during auto-regressive decoding grows linearly with the context length.
Approach:	They propose to model token importance as a dynamic process that evolves over decoding steps and propagates through model layers.
Outcome:	The proposed method outperforms baseline sparse attention methods and achieves speedups of up to 5.36 for attention latency and 2.33 for end-to-end decoding.

Parallel Test-Time Scaling for Latent Reasoning Models (2026.acl-long)

Copied to clipboard

Runyang You, Yongqi Li, Meng Liu, Wenjie Wang, Liqiang Nie, Wenjie Li

Reasoning

Challenge:	Parallel test-time scaling is a pivotal approach for enhancing large language models.
Approach:	They propose two uncertainty-inspired stochastic strategies for parallel test-time scaling for latent reasoning models and a Latent Reward Model for aggregation.
Outcome:	The proposed model scales well with compute and enables effective trajectory selection.

TEMA: Anchor the Image, Follow the Text for Multi-Modification Composed Image Retrieval (2026.acl-long)

Copied to clipboard

Zixu Li, Yupeng Hu, Zhiheng Fu, Zhiwei Chen, Yongqi Li, Liqiang Nie

Dually Self-Improved Counterfactual Data Augmentation Using Large Language Model (2025.acl-long)

Challenge:	Composed Image Retrieval (CIR) is an image retrieval paradigm that enables users to retrieve a target image using a multimodal query that consists of a reference image and modification text.
Approach:	They propose a text-oriented entity mapping architecture that allows users to use a reference image and modification text to retrieve a target image.
Outcome:	The proposed framework is superior in both original and multi-modification scenarios while maintaining an optimal balance between retrieval accuracy and computational efficiency.

Copied to clipboard

Luhao Zhang, Xinyu Zhang, Linmei Hu, Dandan Song, Liqiang Nie

Distillation Enhanced Generative Retrieval (2024.findings-acl)

Challenge:	Existing approaches to generate counterfactual data augmentation are limited due to imbalance and biases in real-world training data.
Approach:	They propose a self-improved method for generating high-quality counterfacts using large language models.
Outcome:	The proposed method generates high-quality counterfacts on the natural language inference task using lightweight and task-specific LLMs.

Copied to clipboard

Yongqi Li, Zhen Zhang, Wenjie Wang, Liqiang Nie, Wenjie Li, Tat-Seng Chua

Bi-Tuning with Collaborative Information for Controllable LLM-based Sequential Recommendation (2025.acl-long)

Challenge:	Generative retrieval is a promising new paradigm in text retrieval that generates identifier strings of relevant passages as the retrieval target.
Approach:	They propose a framework that leverages generative language models to enhance generative retrieval by distillation.
Outcome:	The proposed framework achieves state-of-the-art performance among the generative retrieval methods.

Copied to clipboard

Xinyu Zhang, Linmei Hu, Luhao Zhang, Wentao Cheng, Yashen Wang, Ge Shi, Chong Feng, Liqiang Nie

Omni-R1: Towards the Unified Generative Paradigm for Multimodal Reasoning (2026.findings-acl)

Challenge:	Existing approaches to optimize sequential recommendation systems rely on item ID sequences, but they lack collaborative knowledge and limited controllability.
Approach:	They propose a simple bi-tuning framework with collaborative information for controllable Large Language Model-based Sequential Recommendation (Laser) they incorporate learnable virtual tokens at prefix and suffix of input text to adapt LLMs with collaborative knowledge .
Outcome:	The proposed framework outperforms state-of-the-art recommendations on real-world datasets.

Copied to clipboard

Dongjie Cheng, Yongqi Li, Zhixin Ma, Hongru Cai, Yupeng Hu, Wenjie Wang, Liqiang Nie, Wenjie Li