Papers by Zhihong Zhu

HTML: Hierarchical Topology Multi-task Learning for Semantic Parsing in Knowledge Base Question Answering (2025.findings-acl)

Challenge:	zero-shot cross-lingual SLU is a challenging task in low-resource languages . a lack of labeled training data makes it difficult to align representations of similar sentences .
Approach:	They propose a framework that uses cyclical contrastive learning to achieve consistency between languages . they propose to use geodesic to measure the similarity to construct positive and negative pairs .
Outcome:	The proposed framework achieves state-of-the-art performance on multiATIS++ and MTOP datasets.

Copied to clipboard

Aziguli Wulamu, Lyu Zhengyu, Kaiyuan Gong, Yu Han, Zewen Wang, Zhihong Zhu, Bowen Xing

Code-Switching Can be Better Aligners: Advancing Cross-Lingual SLU through Representation-Level and Prediction-Level Alignment (2024.acl-short)

Challenge:	Existing approaches struggle with mapping questions to precise logical forms . Existing frameworks struggle with complex mapping of questions to logical form .
Approach:	They propose a framework that leverages a hierarchical multi-task learning paradigm to enhance the performance of logical form generation.
Outcome:	The proposed framework outperforms supervised fine-tuning methods and training-free ones on large language models.

Copied to clipboard

Zhihong Zhu, Xuxin Cheng, Zhanpeng Chen, Xianwei Zhuang, Zhiqi Huang, Yuexian Zou

Multilinguality

Challenge:	Existing code-switching-based cross-lingual spoken language understanding frameworks are limited to low-resource languages.
Approach:	They propose a cross-lingual spoken language understanding framework that leverages both code-switched and original sentences to achieve multi-level alignment.
Outcome:	The proposed framework can achieve multi-level alignment on two benchmarks across ten languages.

Knowledge-enhanced Prompt Tuning for Dialogue-based Relation Extraction with Trigger and Label Semantic (2024.lrec-main)

Copied to clipboard

Hao An, Zhihong Zhu, Xuxin Cheng, Zhiqi Huang, Yuexian Zou

Learning to Match Representations is Better for End-to-End Task-Oriented Dialog System (2024.findings-emnlp)

Challenge:	Existing methods to determine semantic relation between two arguments in dialogues are limited due to the low information density of text.
Approach:	They propose a Knowledge-Enhanced Prompt-Tuning method to enhance DRE model by exploiting trigger and label semantics.
Outcome:	The proposed method achieves state-of-the-art in F1 and F1c scores on a DialogRE dataset.

Copied to clipboard

Wanshi Xu, Xuxin Cheng, Zhihong Zhu, Zhanpeng Chen, Yuexian Zou

Natural Language Interfaces

Challenge:	Existing systems for task-oriented dialogue lack belief states as supervisory signals.
Approach:	They propose a method for knowledge retrieval driven by matching representations . they use a matching signal extractor to extract matching representation between contexts and entities .
Outcome:	Experiments on three standard benchmarks show that the proposed method performs better than existing approaches.

Multimodal Dual-Path Decoding for Medical Report Generation (2026.findings-acl)

Copied to clipboard

Jinghan Sun, Dong Wei, Zhihong Zhu, Yuyang Xue, Steven McDonagh, Xian Wu

Can We Trust AI Doctors? A Survey of Medical Hallucination in Large Language and Large Vision-Language Models (2025.findings-acl)

Challenge:	Current methods for radiology report generation rely on encoder-decoder based frameworks that fail to integrate multimodal clinical evidence with domain-specific knowledge.
Approach:	They propose a multimodal dual-path framework that synergistically integrates large vision-language models and large language models for radiology report generation.
Outcome:	The proposed framework improves on the public MIMIC-CXR benchmark and shows that it is superior to state-of-the-art models.

Copied to clipboard

Zhihong Zhu, Yunyan Zhang, Xianwei Zhuang, Fan Zhang, Zhongwei Wan, Yuyan Chen, QingqingLong QingqingLong, Yefeng Zheng, Xian Wu

Mitigating Hallucinations of Large Language Models in Medical Information Extraction via Contrastive Decoding (2024.findings-emnlp)

Challenge:	Hallucination is a critical challenge for large language models and large vision-language models (LVLMs) however, dedicated research on medical hallucinations remains unexplored.
Approach:	They provide a unified perspective on medical hallucination for both LLMs and LVLMs, and delve into its causes.
Outcome:	The proposed models have demonstrated impressive performance on a variety of medical benchmarks.

Copied to clipboard

Derong Xu, Ziheng Zhang, Zhihong Zhu, Zhenxi Lin, Qidong Liu, Xian Wu, Tong Xu, Xiangyu Zhao, Yefeng Zheng, Enhong Chen

Information Extraction & Text Mining

Challenge:	Medical Information Extraction (MIE) tasks are a fundamental component of medical NLP.
Approach:	They propose an alternative adaptive constraint strategy to adjust the scale and scope of contrastive tokens.
Outcome:	The proposed approach selectively enhances the identification and classification capabilities while minimizing the influence of other inherent abilities in LLMs.

Accelerating Multiple Intent Detection and Slot Filling via Targeted Knowledge Distillation (2023.findings-emnlp)

Copied to clipboard

Xuxin Cheng, Zhihong Zhu, Wanshi Xu, Yaowei Li, Hongxiang Li, Yuexian Zou

Dual-oriented Disentangled Network with Counterfactual Intervention for Multimodal Intent Detection (2024.emnlp-main)

Challenge:	Existing non-autoregressive Spoken Language Understanding models suffer from multi-modality problem . current methods have little prior knowledge about the reference during inference .
Approach:	They propose a Targeted Knowledge Distillation Framework (TKDF) for multi-intent SLU that utilizes the knowledge distillation method to improve the performance.
Outcome:	The proposed model outperforms existing models on two public multi-intent datasets while speeding up by over 4.5 times.

Copied to clipboard

Zhanpeng Chen, Zhihong Zhu, Xianwei Zhuang, Zhiqi Huang, Yuexian Zou

Sentiment Analysis

Challenge:	Existing methods for multimodal intent detection have two limitations: (i) close entanglement of multimodal semantics with modal structures; (ii) insufficient learning of causal effects of semantic and modality-specific information on the final predictions.
Approach:	They propose a Dual-oriented Disentangled Network with Counterfactual Intervention model that decouples semantics-oriented and modality-oriented representations and a Counterfective Intervention Module that applies causal inference to understand causal effects by injecting confounders.
Outcome:	The proposed model overcomes key limitations in existing systems by effectively disentangling and utilizing modality-specific and multimodal semantic information.

Enhancing Code-Switching for Cross-lingual SLU: A Unified View of Semantic and Grammatical Coherence (2023.emnlp-main)

Copied to clipboard

Zhihong Zhu, Xuxin Cheng, Zhiqi Huang, Dongsheng Chen, Yuexian Zou

Multilinguality

Challenge:	Existing models rely on annotated training data, limiting their scalability to low-resource languages.
Approach:	They propose a method termed SoGo for zero-shot cross-lingual SLU that uses keywords as substitution options to extract keywords and a token-level alignment strategy to ensure grammatical coherence.
Outcome:	The proposed method improves zero-shot cross-lingual SLU across nine languages on MultiATIS++.

ML-LMCL: Mutual Learning and Large-Margin Contrastive Learning for Improving ASR Robustness in Spoken Language Understanding (2023.findings-acl)

Copied to clipboard

Xuxin Cheng, Bowen Cao, Qichen Ye, Zhihong Zhu, Hongxiang Li, Yuexian Zou

Towards Unified Spoken Language Understanding Decoding via Label-aware Compact Linguistics Representations (2023.findings-acl)

Challenge:	Despite efforts to improve ASR robustness, errors from pipeline approaches can lead to error propagation.
Approach:	They propose a framework for improving ASR robustness in SLU by using mutual learning and large-margin contrastive learning.
Outcome:	The proposed framework outperforms existing models and achieves new state-of-the-art performance on three datasets.

Copied to clipboard

Zhihong Zhu, Xuxin Cheng, Zhiqi Huang, Dongsheng Chen, Yuexian Zou

AutoPRM: Automating Procedural Supervision for Multi-Step Reasoning via Controllable Question Decomposition (2024.naacl-long)

Challenge:	Existing methods for intent detection and slot filling decoders could result in misaligned predictions for both tasks.
Approach:	They propose a method that leverages label embeddings to jointly guide the decoding process.
Outcome:	The proposed method outperforms existing methods on two single- and multi-intent SLU benchmarks and can be incorporated into existing models.

Copied to clipboard

Zhaorun Chen, Zhuokai Zhao, Zhihong Zhu, Ruiqi Zhang, Xiang Li, Bhiksha Raj, Huaxiu Yao

Reasoning

Challenge:	Recent advances in large language models (LLMs) have shown promise in multi-step reasoning tasks, yet relying on extensive manual labeling to provide procedural feedback remains a significant impediment.
Approach:	They propose a self-supervised framework that decomposes complex problems into manageable subquestions with a controllable granularity switch and sequentially applies reinforcement learning to iteratively improve the subquest solver.
Outcome:	The proposed framework improves performance on mathematical and commonsense reasoning tasks over SOTA.

What are the Generator Preferences for End-to-end Task-Oriented Dialog System? (2024.emnlp-main)

Copied to clipboard

Wanshi Xu, Xianwei Zhuang, Zhanpeng Chen, Zhihong Zhu, Xuxin Cheng, Yuexian Zou

Natural Language Interfaces

Challenge:	Existing methods to improve the accuracy of entity retrieval are not effective.
Approach:	They propose a framework that improves the performance of task-oriented dialogue systems by obtaining fine-grained matching information between contexts and entities and extracting the entity attribute shift matrix as preference signals.
Outcome:	The proposed framework outperforms existing methods and improves the quality of the dialogue.

MMErroR: A Benchmark for Erroneous Reasoning in Vision-Language Models (2026.acl-long)

Copied to clipboard

Yang Shi, Yifeng Xie, Minzhe Guo, Liangsi Lu, Mingxuan Huang, Jingchao Wang, Zhihong Zhu, Boyan Xu, Zhiqi Huang

Long and Diverse Text Generation with Planning-based Hierarchical Variational Model (D19-1)

Challenge:	Recent advances in vision-language models have improved performance in multi-modal learning.
Approach:	They propose a multi-modal benchmark that embeds a single coherent reasoning error in 1997 samples.
Outcome:	The proposed benchmark is based on a set of 1997 samples embedding a single coherent reasoning error.

Copied to clipboard

Zhihong Shao, Minlie Huang, Jiangtao Wen, Wenfei Xu, Xiaoyan Zhu

Text Generation

Challenge:	Existing methods for data-to-text generation are insufficient to produce long and diverse texts.
Approach:	They propose a planning-based hierarchical variational model that plans a sequence of groups and then realizes each sentence conditioned on the planning result and the previously generated context.
Outcome:	The proposed model outperforms state-of-the-art models in long and diverse text generation.

DGLF: A Dual Graph-based Learning Framework for Multi-modal Sarcasm Detection (2024.emnlp-main)

Copied to clipboard

Zhihong Zhu, Kefan Shen, Zhaorun Chen, Yunyan Zhang, Yuyan Chen, Xiaoqi Jiao, Zhongwei Wan, Shaorong Xie, Wei Liu, Xian Wu, Yefeng Zheng

InfoEnh: Towards Multimodal Sentiment Analysis via Information Bottleneck Filter and Optimal Transport Alignment (2024.lrec-main)

Challenge:	Existing methods for multimodal sarcasm detection neglect high-order relationships and underestimate high-frequency messages.
Approach:	They propose a Dual Graph-based Learning Framework to capture inter-modal inconsistencies . they propose combining a hypergraph and a vanilla graph to achieve enhanced propagation .
Outcome:	The proposed model outperforms existing state-of-the-art methods on two benchmark datasets.

Copied to clipboard

Yifeng Xie, Zhihong Zhu, Xuan Lu, Zhiqi Huang, Haoran Xiong

Towards Multi-modal Sarcasm Detection via Disentangled Multi-grained Multi-modal Distilling (2024.lrec-main)

Challenge:	Existing methods for multi-modal sentiment analysis have been developed to overcome these challenges.
Approach:	They propose a method that utilizes a masking technique as the bottleneck for information filtering and integrates all modalities into a common feature space via domain adaptation.
Outcome:	Extensive experiments on two benchmark MSA datasets show the proposed method performs better than baselines.

Copied to clipboard

Zhihong Zhu, Xuxin Cheng, Guimin Hu, Yaowei Li, Zhiqi Huang, Yuexian Zou

Sentiment Analysis

Challenge:	Existing approaches to sarcasm detection focus on textual and intra-modal incongruity . mainstream approaches process input of each modality in a holistic manner, resulting in redundant and unrefined information.
Approach:	They propose a framework for multi-modal sarcasm detection that disentangles modality representations into latent spaces and conducts multi-grained knowledge distilling.
Outcome:	The proposed framework overpowers existing methods on a common benchmark.

Relevance Is a Guiding Light: Relevance-aware Adaptive Learning for End-to-end Task-oriented Dialogue System (2024.emnlp-main)

Copied to clipboard

Zhanpeng Chen, Zhihong Zhu, Wanshi Xu, Xianwei Zhuang, Yuexian Zou

Information Retrieval

Challenge:	Existing approaches to training task-oriented dialogue systems struggle with the Distractive Attributes Problem (DAP) Existing methods struggle to deal with false but similar knowledge (hard negative entities)
Approach:	They propose a two-stage training framework that eliminates hard negatives step-by-step and aligns retrieval with generation.
Outcome:	The proposed method eliminates hard negatives step-by-step and aligns retrieval with generation.

Zero-Shot Spoken Language Understanding via Large Language Models: A Preliminary Study (2024.lrec-main)

Copied to clipboard

Zhihong Zhu, Xuxin Cheng, Hao An, Zhichang Wang, Dongsheng Chen, Zhiqi Huang

MCLF: A Multi-grained Contrastive Learning Framework for ASR-robust Spoken Language Understanding (2023.findings-emnlp)

Challenge:	Recent advances in large language models (LLMs) have shown promising results in zero-shot settings, which motivates us to explore prompt-based methods.
Approach:	They propose a two-stage framework which transforms the SLU task into a question-answering problem by directly prompting LLMs.
Outcome:	The proposed framework can be built by directly prompting LLMs to understand user needs without training data.

Copied to clipboard

Zhiqi Huang, Dongsheng Chen, Zhihong Zhu, Xuxin Cheng

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

Challenge:	Trending ASR-robust SLU systems have seen impressive improvements through global contrastive learning, but they can easily lead to severe semantic changes.
Approach:	They propose a two-stage multi-grained contrastive learning framework to improve ASR robustness . they first adapt pre-trained language models to downstream SLU datasets and then fine-tune it on the corresponding dataset.
Outcome:	The proposed framework improves on four datasets and four BERT-like backbone models.

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.

Syntax Matters: Towards Spoken Language Understanding via Syntax-Aware Attention (2023.findings-emnlp)

Copied to clipboard

Yifeng Xie, Zhihong Zhu, Xuxin Cheng, Zhiqi Huang, Dongsheng Chen

Syntactic Text Processing

Challenge:	Existing studies on SLU systems have focused on integrating syntactic information into language models.
Approach:	They propose a model where attention scopes are constrained based on syntactic relationships.
Outcome:	The proposed model improves on three datasets and can be integrated into other language models to further boost their performance.

AceGPT, Localizing Large Language Models in Arabic (2024.naacl-long)

Copied to clipboard

Huang Huang, Fei Yu, Jianqing Zhu, Xuening Sun, Hao Cheng, Song Dingjie, Zhihong Chen, Mosen Alharthi, Bang An, Juncai He, Ziche Liu, Junying Chen, Jianquan Li, Benyou Wang, Lian Zhang, Ruoyu Sun, Xiang Wan, Haizhou Li, Jinchao Xu

CMedCalc-Bench: A Fine-Grained Benchmark for Chinese Medical Calculations in LLM (2025.emnlp-main)

Challenge:	Significant concerns emerge when addressing cultural sensitivity and local values.
Approach:	They propose a localized Large Language Model (LLM) specifically for Arabic, a language imbued with unique cultural characteristics inadequately addressed by current mainstream models.
Outcome:	The proposed model sets the state-of-the-art standard for open Arabic LLMs across various benchmarks.

Copied to clipboard

Yunyan Zhang, Zhihong Zhu, Xian Wu

Reasoning

Challenge:	Existing medical NLP benchmarks focus on qualitative reasoning and textual comprehension, but lack of fine-grained evaluation of intermediate reasoning.
Approach:	They propose a Chinese medical calculation benchmark that disentangles clinical entity extraction from numerical computation.
Outcome:	The proposed framework disentangles clinical entity extraction from numerical computation, enabling systematic diagnosis of model deficiencies.

Game on Tree: Visual Hallucination Mitigation via Coarse-to-Fine View Tree and Game Theory (2024.emnlp-main)

Copied to clipboard

Xianwei Zhuang, Zhihong Zhu, Zhanpeng Chen, Yuxin Xie, Liming Liang, Yuexian Zou

Reasoning

Challenge:	Large vision-language models produce unfaithful visual hallucinations, also known as visual halluinations, which hinders their application in multimodal understanding and decision-making.
Approach:	They propose a plug-and-play train-free decoding algorithm for mitigating visual hallucinations . they leverage visual information to construct a coarse-to-fine visual view tree .
Outcome:	The proposed algorithm reduces visual hallucinations (VH) by leveraging visual information to construct a coarse-to-fine visual view tree (CFTree)

A Survey on Multi-modal Intent Recognition: Recent Advances and New Frontiers (2025.findings-emnlp)

Copied to clipboard

Zhihong Zhu, Fan Zhang, Yunyan Zhang, Jinghan Sun, Zhiqi Huang, Qingqing Long, Bowen Xing, Xian Wu

MoE-SLU: Towards ASR-Robust Spoken Language Understanding via Mixture-of-Experts (2024.findings-acl)

Challenge:	Multi-modal intent recognition (MIR) requires integrating non-verbal cues from real-world contexts to enhance human intention understanding.
Approach:	They present a comprehensive review of multi-modal intent recognition . they provide a survey of the field covering textual, visual, and acoustic signals .
Outcome:	The present survey summarises the current state of multi-modal intent recognition . it includes a comprehensive taxonomy and advanced methods .

Copied to clipboard

Xuxin Cheng, Zhihong Zhu, Xianwei Zhuang, Zhanpeng Chen, Zhiqi Huang, Yuexian Zou

Robustness in NLP

Challenge:	Spoken language understanding (SLU) is a crucial task in task-oriented dialogue systems.
Approach:	They propose an ASR-Robust SLU framework based on the mixture-of-experts technique to generate additional transcripts from clean transcripts and use it to weigh the representations of the generated transcripts, ASR transcripts .
Outcome:	The proposed framework achieves state-of-the-art on three benchmark SLU datasets.

Alignment before Awareness: Towards Visual Question Localized-Answering in Robotic Surgery via Optimal Transport and Answer Semantics (2024.lrec-main)

Copied to clipboard

Zhihong Zhu, Yunyan Zhang, Xuxin Cheng, Zhiqi Huang, Derong Xu, Xian Wu, Yefeng Zheng

UniMEEC: Towards Unified Multimodal Emotion Recognition and Emotion Cause (2024.findings-emnlp)

Challenge:	Recent models for visual question localized-answering (VQLA) lack the ability to relate these answers to their localization at an instance level.
Approach:	They propose a model which introduces optimal transport to achieve bidirectional and fine-grained alignment between images and questions, enabling more precise localization.
Outcome:	The proposed model outperforms state-of-the-art models on two widely-used datasets on surgical scenes and surgical instruments.

Copied to clipboard

Guimin Hu, Zhihong Zhu, Daniel Hershcovich, Lijie Hu, Hasti Seifi, Jiayuan Xie

Beyond Surface Features: Advancing Medical Vision-Language Alignment via Dynamic Evidence-Guided Preference Optimization (2026.acl-long)

Challenge:	Existing studies treat emotion recognition and emotion cause extraction as two individual problems, ignoring their natural causality.
Approach:	They propose a Unified Multimodal Emotion recognition and Emotion-Cause analysis framework to explore the causality between emotion and emotion cause.
Outcome:	The proposed framework reformulates MERC and MECPE tasks as mask prediction problems and unifies them with a causal prompt template.

Copied to clipboard

Zixuan Huang, Zhihong Zhu, Xiaolong Liu, Yanchao Hao, Manman Zhang, Zheng Wei, Bowen Xing, Xian Wu, Ye Li, Fen Miao, Yefeng Zheng

A Survey on Foundation Language Models for Single-cell Biology (2025.acl-long)

Challenge:	Existing preference-based methods for medical large vision-Language Models face limitations in medical settings . existing methods are limited by overfitting to superficial cues and pseudo convergence of the preference signal.
Approach:	They propose a framework that enables evidence-aware and adaptive preference learning for Med-LVLMs.
Outcome:	The proposed framework improves evidence-aware and adaptive preference learning for Med-LVLMs.

Copied to clipboard

Fan Zhang, Hao Chen, Zhihong Zhu, Ziheng Zhang, Zhenxi Lin, Ziyue Qiao, Yefeng Zheng, Xian Wu

Multi-perspective Improvement of Knowledge Graph Completion with Large Language Models (2024.lrec-main)

Challenge:	Existing single-cell foundation language models are based on pre-trained and large language models.
Approach:	They review the development of single-cell foundation language models . they discuss data tokenization strategies and pre-training paradigms .
Outcome:	The proposed models have shown remarkable performance in a variety of single-cell data analysis tasks.

Copied to clipboard

Derong Xu, Ziheng Zhang, Zhenxi Lin, Xian Wu, Zhihong Zhu, Tong Xu, Xiangyu Zhao, Yefeng Zheng, Enhong Chen