Papers by Cheng Jin

HATA: Trainable and Hardware-Efficient Hash-Aware Top-k Attention for Scalable Large Model Inference (2025.findings-acl)

Challenge:	Speech Recognition often gets stuck in the lack of new domain utterances when training a model of new-domain speech.
Approach:	They propose a training system Open-modality Speech Recognition that enables zero-shot modality transfer . they use multi-modal alignment in phoneme space to maintain multi-modality alignment .
Outcome:	The proposed system achieves zero-shot modality transfer compared to existing methods . it achieves state-of-the-art performance on audio-visual speech recognition and lip-reading with 2.7% and 25.0%, respectively.

Copied to clipboard

Ping Gong, Jiawei Yi, Shengnan Wang, Juncheng Zhang, Zewen Jin, Ouxiang Zhou, Ruibo Liu, Guanbin Xu, Youhui Bai, Bowen Ye, Kun Yuan, Tong Yang, Gong Zhang, Renhai Chen, Feng Wu, Cheng Li

Green & Sustainable NLP

Challenge:	Existing top-k attention methods struggle to strike a balance between efficiency and accuracy.
Approach:	They propose a top-k attention approach that integrates low-overhead techniques into the Top-k Attention process to achieve 7.2 speedup compared to vanilla full attention.
Outcome:	The proposed approach achieves 7.2 speedup compared to current top-k attention methods while maintaining model accuracy.

Search from History and Reason for Future: Two-stage Reasoning on Temporal Knowledge Graphs (2021.acl-long)

Copied to clipboard

Zixuan Li, Xiaolong Jin, Saiping Guan, Wei Li, Jiafeng Guo, Yuanzhuo Wang, Xueqi Cheng

Reasoning

Challenge:	Temporal Knowledge Graphs (TKGs) are used in many different areas of research.
Approach:	They propose to use a beam search policy to induce multiple clues from historical facts . they propose to adopt a graph convolution network based sequence method to deduce answers from clues .
Outcome:	The proposed model can predict future facts in two stages, Clue Searching and Temporal Reasoning.

Semantic-conditioned Dual Adaptation for Cross-domain Query-based Visual Segmentation (2023.findings-acl)

Copied to clipboard

Ye Wang, Tao Jin, Wang Lin, Xize Cheng, Linjun Li, Zhou Zhao

Visual Data in NLP

Challenge:	Existing approaches to visual segmentation from language queries require expensive labeling and degradation when deployed to an unseen domain.
Approach:	They propose a task to adapt a visual segmentation model from a labeled domain to an unseen domain.
Outcome:	The proposed framework achieves precise feature- and relation-invariant across domains via universal semantic structure.

Disentangling Memory and Reasoning Ability in Large Language Models (2025.acl-long)

Copied to clipboard

Mingyu Jin, Weidi Luo, Sitao Cheng, Xinyi Wang, Wenyue Hua, Ruixiang Tang, William Yang Wang, Yongfeng Zhang

Temporal Knowledge Graph Reasoning Based on N-tuple Modeling (2023.findings-emnlp)

Challenge:	Existing LLMs operate as an opaque process without explicit separation between knowledge retrieval and reasoning steps, making the decision-making process unclear and disorganized.
Approach:	They propose a language model inference paradigm that decomposes the complex inference process into two distinct and clear actions: (1) memory recall: which retrieves relevant knowledge, and (2) reasoning: which performs reasoning steps based on the recalled knowledge.
Outcome:	The proposed paradigm decomposes the inference process into two distinct and clear actions, memory and reason, guiding the model to distinguish between steps that require knowledge retrieval and those that involve reasoning.

Copied to clipboard

Zhongni Hou, Xiaolong Jin, Zixuan Li, Long Bai, Saiping Guan, Yutao Zeng, Jiafeng Guo, Xueqi Cheng

HacRED: A Large-Scale Relation Extraction Dataset Toward Hard Cases in Practical Applications (2021.findings-acl)

Challenge:	Existing Temporal Knowledge Graphs (TKGs) only contain their core entities and form them as quadruples.
Approach:	They propose to describe a temporal fact more accurately as an n-tuple . they propose to use a neural network to learn evolutional representations of entities .
Outcome:	The proposed model oversimplifies and causes information loss on two datasets.

Copied to clipboard

Qiao Cheng, Juntao Liu, Xiaoye Qu, Jin Zhao, Jiaqing Liang, Zhefeng Wang, Baoxing Huai, Nicholas Jing Yuan, Yanghua Xiao

TAVT: Towards Transferable Audio-Visual Text Generation (2023.acl-long)

Challenge:	Relation extraction (RE) is an essential topic in natural language processing and has attracted extensive attention.
Approach:	They propose a case-oriented construction framework to build a hard case relation extraction dataset with 65,225 relational facts annotated from 9,231 documents.
Outcome:	The proposed model achieves a high 96% F1 score on data quality and is far lower than humans.

Copied to clipboard

Wang Lin, Tao Jin, Wenwen Pan, Linjun Li, Xize Cheng, Ye Wang, Zhou Zhao

MPRF: Interpretable Stance Detection through Multi-Path Reasoning Framework (2025.emnlp-main)

Challenge:	Existing transfer learning techniques focus on uni-modal analysis and lack consideration of multi-modal content and cross-modal relation.
Approach:	They propose a transferable audio-visual text generation framework that incorporates two components: Audio-Visual Meta-Mapper and Dual Counterfactual Contrastive Learning.
Outcome:	The proposed framework outperforms the state-of-the-art methods across multiple domains and modal settings.

Copied to clipboard

ZhaoDan Zhang, Jin Zhang, Hui Xu, Jiafeng Guo, Xueqi Cheng

Weakly-Supervised Spoken Video Grounding via Semantic Interaction Learning (2023.acl-long)

Challenge:	Existing stance detection methods treat the task as a classification problem, where models output a stance label without providing interpretable reasoning paths.
Approach:	They propose a framework that generates, evaluates, and integrates multiple reasoning paths to improve accuracy, robustness, and transparency in stance detection.
Outcome:	The proposed framework outperforms existing models on the SEM16, VAST, and PStance datasets and is highly interpretable and reliable.

Copied to clipboard

Ye Wang, Wang Lin, Shengyu Zhang, Tao Jin, Linjun Li, Xize Cheng, Zhou Zhao

Decomposition for Enhancing Attention: Improving LLM-based Text-to-SQL through Workflow Paradigm (2024.findings-acl)

Challenge:	Recent work on spoken video grounding challenges extracting semantic information from speech . previous studies focused on textual queries, but recent work focuses on spoken queries .
Approach:	They propose a framework for weakly-supervised spoken video grounding to represent cross-modal semantics without expensive temporal annotations.
Outcome:	The proposed framework is more efficient than existing methods.

Copied to clipboard

Yuanzhen Xie, Xinzhou Jin, Tao Xie, Matrixmxlin Matrixmxlin, Liang Chen, Chenyun Yu, Cheng Lei, Chengxiang Zhuo, Bo Hu, Zang Li

Programming Languages in NLP

Challenge:	In-context learning of large-language models has achieved remarkable success in the field of natural language processing . however, the single-step chain-of-thought prompting approach faces challenges such as attention diffusion and inadequate performance in complex tasks like text-to-SQL.
Approach:	They propose a workflow paradigm method to enhance the attention and problem-solving scope of large-language models through decomposition.
Outcome:	The proposed method outperforms existing methods on three datasets and improves the upper limit of LLM-based approaches.

Balancing Fidelity and Plasticity: Aligning Mixed-Precision Fine-Tuning with Linguistic Hierarchies (2026.findings-acl)

Copied to clipboard

Changhai Zhou, Shiyang Zhang, Yuhua Zhou, Jun Gao, Qian Qiao, Shichao Weng, Weizhong Zhang, Cheng Jin

SciAssess: Benchmarking LLM Proficiency in Scientific Literature Analysis (2025.findings-naacl)

Challenge:	Existing quantization-aware fine-tuning methods decouple weight precision and adapter capacity, overlooking that a layer’s ability to adapt is constrained by the information preserved in its frozen weights.
Approach:	They propose a framework that jointly optimizes per-layer quantization bit-width and LoRA rank.
Outcome:	Experiments on LLaMA and Qwen models show that the proposed framework matches or approaches 16-bit baselines while using substantially less memory.

Copied to clipboard

Hengxing Cai, Xiaochen Cai, Junhan Chang, Sihang Li, Lin Yao, Wang Changxin, Zhifeng Gao, Hongshuai Wang, Li Yongge, Mujie Lin, Shuwen Yang, Jiankun Wang, Mingjun Xu, Jin Huang, Xi Fang, Jiaxi Zhuang, Yuqi Yin, Yaqi Li, Changhong Chen, Zheng Cheng, Zifeng Zhao, Linfeng Zhang, Guolin Ke

Challenge:	Existing benchmarks fail to adequately evaluate the proficiency of Large Language Models (LLMs) Existing standards do not cover the skills needed to evaluate LLMs in scientific literature analysis.
Approach:	They propose a benchmark to evaluate the proficiency of large language models in scientific literature analysis.
Outcome:	SciAssess evaluates 11 LLMs on multiple tasks across scientific fields.

AudioVSR: Enhancing Video Speech Recognition with Audio Data (2024.emnlp-main)

Copied to clipboard

Xiaoda Yang, Xize Cheng, Jiaqi Duan, Hongshun Qiu, Minjie Hong, Minghui Fang, Shengpeng Ji, Jialong Zuo, Zhiqing Hong, Zhimeng Zhang, Tao Jin

RouteRAG: Efficient Retrieval-Augmented Generation from Text and Graph via Reinforcement Learning (2026.findings-acl)

Challenge:	Recent work has shown poor performance with non-Indo-European languages . previous work primarily utilizes video information to build VSR models .
Approach:	They propose a generative model for data inflation that integrates synthetic data with authentic visual data to enhance the VSR model.
Outcome:	The proposed model improves on the audio-visual alignment problem in audio-video tasks.

Copied to clipboard

Yucan Guo, Miao Su, Saiping Guan, Zihao Sun, Xiaolong Jin, Jiafeng Guo, Xueqi Cheng

NeuInfer: Knowledge Inference on N-ary Facts (2020.acl-main)

Challenge:	Existing graph-based or hybrid systems lack the ability to integrate supplementary evidence as reasoning unfolds.
Approach:	They propose a framework that integrates non-parametric knowledge into Large Language Models . they use a RL-based framework to optimize the entire generation process via RL .
Outcome:	The proposed framework outperforms existing RAG frameworks in five question answering benchmarks.

Copied to clipboard

Saiping Guan, Xiaolong Jin, Jiafeng Guo, Yuanzhuo Wang, Xueqi Cheng

HiSMatch: Historical Structure Matching based Temporal Knowledge Graph Reasoning (2022.findings-emnlp)

Challenge:	Existing studies on knowledge inference on binary facts have focused on finding out connotative valid facts.
Approach:	They propose a neural network model, NeuInfer, for knowledge inference on n-ary facts.
Outcome:	The proposed model can cope with the task to infer an unknown element in a whole fact, while ignoring the binary facts.

Copied to clipboard

Zixuan Li, Zhongni Hou, Saiping Guan, Xiaolong Jin, Weihua Peng, Long Bai, Yajuan Lyu, Wei Li, Jiafeng Guo, Xueqi Cheng

T-MAD: Target-driven Multimodal Alignment for Stance Detection (2025.emnlp-main)

Challenge:	Temporal Knowledge Graphs (TKGs) store facts as triples in the form of subject, relation, object, timestamps.
Approach:	They propose a Temporal Knowledge Graph (TKG) model that extends each triple with a timestamp to describe dynamic facts.
Outcome:	The proposed model improves on six benchmark datasets with up to 5.6% performance improvement compared to the state-of-the-art models.

Copied to clipboard

ZhaoDan Zhang, Jin Zhang, Xueqi Cheng, Hui Xu

Sentiment Analysis

Challenge:	Existing methods for Multimodal Stance Detection struggle with generalizing to unseen targets and handling modality inconsistencies.
Approach:	They propose a multimodal stability detection model which captures target-specific relationships and balances modality contributions by iterative reasoning.
Outcome:	Experiments on the MMSD and MultiClimate datasets show that the proposed model outperforms state-of-the-art models with optimal results achieved using RoBERTa, ViT, and an iterative depth of 5.

LiveFact: A Dynamic, Time-Aware Benchmark for LLM-Driven Fake News Detection (2026.acl-long)

Copied to clipboard

Cheng Xu, Changhong Jin, Yingjie Niu, Nan Yan, Yuke Mei, Shuhao Guan, Liming Chen, Tahar Kechadi

Reasoning

Challenge:	Current evaluation frameworks are static and vulnerable to benchmark data contamination . current models are ineffective at assessing reasoning under temporal uncertainty .
Approach:	They propose a live-based benchmark that simulates the real-world "fog of war" they propose evaluating models on their ability to reason with evolving, incomplete information .
Outcome:	The proposed model outperforms proprietary state-of-the-art models in classification and evidence mode . it also provides a component to monitor BDC explicitly .

VisPCO: Visual Token Pruning Configuration Optimization via Budget-Aware Pareto-Frontier Learning for Vision-Language Models (2026.acl-long)

Copied to clipboard

Huawei Ji, Yuanhao Sun, Yuan Jin, Cheng Deng, Jiaxin Ding, Luoyi Fu, Xinbing Wang

Visual Data in NLP

Challenge:	Existing methods for visual token pruning rely on predefined configurations without determining whether they achieve optimal performance.
Approach:	They propose a framework that formulates visual token pruning as a Pareto configuration optimization problem to automatically identify optimal configurations.
Outcome:	The proposed framework approximates the empirical Pareto frontier obtained through grid search and generalizes well across pruning methods and VLM architectures.

Towards Robust Universal Information Extraction: Dataset, Evaluation, and Solution (2025.acl-long)

Copied to clipboard

Jizhao Zhu, Akang Shi, Zixuan Li, Long Bai, Xiaolong Jin, Jiafeng Guo, Xueqi Cheng

Empirical Study on Data Attributes Insufficiency of Evaluation Benchmarks for LLMs (2025.coling-main)

Challenge:	Existing robust benchmark datasets generate only a limited range of perturbations for a single Information Extraction (UIE) task, which fails to evaluate the robustness of UIE models effectively.
Approach:	They propose a new benchmark dataset that utilizes Large Language Models to generate more diverse and realistic perturbations across different IE tasks.
Outcome:	The proposed model performs better with only 15% of the data and is more robust with other models.

Copied to clipboard

Chuang Liu, Renren Jin, Zheng Yao, Tianyi Li, Liang Cheng, Mark Steedman, Deyi Xiong

Challenge:	Existing benchmarks for evaluating large language models neglect key qualitative data attributes that can significantly impact the final rankings of LLMs.
Approach:	They propose a framework with three modules designed to assess diversity, redundancy, and difficulty.
Outcome:	The proposed framework systematically incorporates diversity, redundancy, and difficulty attributes and shows that they influence the ranking of LLMs.

KnowCoder: Coding Structured Knowledge into LLMs for Universal Information Extraction (2024.acl-long)

Copied to clipboard

Zixuan Li, Yutao Zeng, Yuxin Zuo, Weicheng Ren, Wenxuan Liu, Miao Su, Yucan Guo, Yantao Liu, Lixiang Lixiang, Zhilei Hu, Long Bai, Wei Li, Yidan Liu, Pan Yang, Xiaolong Jin, Jiafeng Guo, Xueqi Cheng

Threshold Filtering Packing for Supervised Fine-Tuning: Training Related Samples within Packs (2025.naacl-long)

Challenge:	None. None.. None!
Approach:	None. None.. None!
Outcome:	None. None. No. :

Copied to clipboard

Jiancheng Dong, Lei Jiang, Wei Jin, Lu Cheng

XY-Tokenizer: Mitigating the Semantic-Acoustic Conflict in Low-Bitrate Speech Codecs (2026.acl-long)

Challenge:	Randomly concatenating data points can lead to cross-contamination due to the significant difference in their subject matter.
Approach:	They propose a method that randomly concatenates data of varying lengths until reaching the designed maximum length to optimize context length and reduce padding.
Outcome:	The proposed method significantly improves performance on GSM8K and HumanEval, and also improves fairness and accuracy by 15%.

Copied to clipboard

Yitian Gong, Luozhijie Jin, Kuangwei Chen, Dong Zhang, Ruifan Deng, Xiaogui Yang, Xin Zhang, Zhaoye Fei, Qinyuan Cheng, Shimin Li, Xipeng Qiu

Knowledge-Enhanced Self-Supervised Prototypical Network for Few-Shot Event Detection (2022.findings-emnlp)

Challenge:	Existing speech codecs struggle to balance these objectives at low bitrates . XY-Tokenizer achieves stronger semantic alignment than representative semantic-distillation codec .
Approach:	They propose a low-bitrate speech codec that aligns discrete speech representations with text while preserving fine-grained acoustic details for reconstruction.
Outcome:	The proposed codec outperforms existing low-bitrate speech codecs in speech understanding and generation tasks.

Copied to clipboard

Kailin Zhao, Xiaolong Jin, Long Bai, Jiafeng Guo, Xueqi Cheng

A Good Prompt Is Worth Millions of Parameters: Low-resource Prompt-based Learning for Vision-Language Models (2022.acl-long)

Challenge:	Existing methods for few-shot event detection are inaccurate and lack a prototype representation module.
Approach:	They propose a Knowledge-Enhanced self-supervised prototypical network for few-shot event detection . it adopts hybrid rules which align event types to FrameNet and introduces knowledge to obtain more instances .
Outcome:	The proposed network improves few-shot event detection performance on three benchmark datasets.

Copied to clipboard

Woojeong Jin, Yu Cheng, Yelong Shen, Weizhu Chen, Xiang Ren

Event Detection with Multi-Order Graph Convolution and Aggregated Attention (D19-1)

Challenge:	Recent few-shot learning models such as GPT3 are expensive and slow to deploy for real-world applications.
Approach:	They propose a prompt-based low-resource learning method for VL tasks with a few examples . they pre-train a sequence-to-sequence transformer model with prefix and masked language modeling .
Outcome:	The proposed method outperforms Frozen on vision-language tasks with prompt-based learning by 18.2% point.

Copied to clipboard

Haoran Yan, Xiaolong Jin, Xiangbin Meng, Jiafeng Guo, Xueqi Cheng

Syntactic Text Processing

Challenge:	Existing methods for event detection use first-order syntactic relations to identify trigger words.
Approach:	They propose a dependency tree-based method to model and aggregate multi-order syntactic representations in sentences.
Outcome:	The proposed method outperforms existing methods on a benchmark dataset . it uses a dependency tree based graph convolution network with aggregative attention .

KnowCoder-X: Boosting Multilingual Information Extraction via Code (2025.findings-acl)

Copied to clipboard

Yuxin Zuo, Wenxuan Jiang, Wenxuan Liu, Zixuan Li, Long Bai, Hanbin Wang, Yutao Zeng, Xiaolong Jin, Jiafeng Guo, Xueqi Cheng

Multilinguality

Challenge:	Empirical evidence indicates that Large Language Models exhibit spontaneous cross-lingual alignment in Information Extraction (IE) however, a significant imbalance across languages persists, highlighting an underlying deficiency.
Approach:	They propose a code LLM with advanced cross-lingual and multilingual capabilities for universal IE that standardizes the representation of multilingual schemas using Python classes and conducts IE alignment instruction tuning on translated instance prediction task.
Outcome:	The proposed model surpasses ChatGPT and SoTA by 30.17% without training in 29 unseen languages and significantly improves cross-lingual IE transferability.

Selective Temporal Knowledge Graph Reasoning (2024.lrec-main)

Copied to clipboard

Zhongni Hou, Xiaolong Jin, Zixuan Li, Long Bai, Jiafeng Guo, Xueqi Cheng

GR1: Reinforcement-Enhanced LLM for Geoscience Reasoning (2026.findings-acl)

Challenge:	Existing models cannot abstain from uncertain predictions, which will bring risks in real-world applications.
Approach:	They propose to abstain from uncertain future facts by using a confidence estimator . they take both the certainty of the current prediction and the accuracy of historical predictions into account .
Outcome:	The proposed abstention mechanism helps existing models make selective predictions instead of indiscriminate ones.

Copied to clipboard

Yule Xie, Jiaxin Ding, Cheng Deng, Shiqing Gao, Junran Zhang, Sibo Zhang, Zeyuan Wang, Ke Wu, Xin Ding, Luoyi Fu, Meng Jin, Xinbing Wang

Reasoning

Challenge:	Recent advances in large language models have demonstrated RL's substantial capacity to enhance multi-step reasoning beyond what supervised instruction tuning achieves.
Approach:	They propose a framework that converts multimodal questions into descriptive text . they propose RL-enhanced geoscience reasoning that can be fine-tuned to a text-only level .
Outcome:	The proposed framework improves accuracy and accuracy on multimodal questions while preserving answerability and difficulty.

T2A-Feedback: Improving Basic Capabilities of Text-to-Audio Generation via Fine-grained AI Feedback (2025.acl-long)

Copied to clipboard

Zehan Wang, Ke Lei, Chen Zhu, Jiawei Huang, Sashuai Zhou, Luping Liu, Xize Cheng, Shengpeng Ji, Zhenhui Ye, Tao Jin, Zhou Zhao

RIPRAG: Hack a Black-box Retrieval-Augmented Generation Question-Answering System with Reinforcement Learning (2026.findings-acl)

Challenge:	Text-to-audio (T2A) models still struggle to satisfy human preferences for prompt-following and acoustic quality when generating complex multi-event audio.
Approach:	They propose to use AI feedback learning to enhance basic capabilities of text-to-audio models . they use a large audio preference dataset to evaluate the model's capabilities .
Outcome:	The proposed model improves in simple and complex scenarios with AI feedback learning.

Copied to clipboard

Meng Xi, Sihan Lv, Yechen Jin, Guanjie Cheng, Naibo Wang, Ying Li, Jianwei Yin

Event Coreference Resolution with their Paraphrases and Argument-aware Embeddings (2020.coling-main)

Challenge:	Existing methods to generate RAG documents require knowledge of the target RAG system’s internal composition and implementation details, whereas black-box methods are unable to utilize interactive information.
Approach:	They propose a RIPRAG attack framework that treats the target RAG system as a black box and leverages a Reinforcement Learning from Black-box Feedback (RLBF) method to optimize the generation model for poisoned documents.
Outcome:	The proposed method achieves an attack success rate (ASR) improvement of up to 0.72 compared to baseline methods.

Copied to clipboard

Yutao Zeng, Xiaolong Jin, Saiping Guan, Jiafeng Guo, Xueqi Cheng

Few-shot Link Prediction on Hyper-relational Facts (2024.lrec-main)

Challenge:	Existing methods for event coreference resolution do not identify paraphrase relations between events.
Approach:	They propose a new event-specific paraphrase and argument-aware semantic Embedding model for event coreference resolution based on event-related paraphrases and argument embeddings . EPASE recognizes deep paraphrase relations in an event- specific context of sentences and can cover event paraphrase of more situations .
Outcome:	Experiments on within- and cross-document event coreference show it is superior compared to existing methods.

Copied to clipboard

Jiyao Wei, Saiping Guan, Xiaolong Jin, Jiafeng Guo, Xueqi Cheng

AgentGC: Evolutionary Learning-based Lossless Compression for Genomics Data with LLM-driven Multiple Agent (2026.findings-acl)

Challenge:	Existing methods to predict missing elements in hyper-relational facts require high-quality data.
Approach:	They propose a task to predict a missing entity in a hyper-relational fact with limited support instances.
Outcome:	The proposed model outperforms existing models on three datasets.

Copied to clipboard

Sun Hui, Ding Yanfeng, Huidong Ma, Chang Xu, Keyan Jin, Lizheng Zu, Cheng Zhong, Xiaoguang Liu, Gang Wang, Wentong Cai

Cognitive Modeling

Challenge:	Lossless compression has made significant advancements in Genomics Data storage, sharing and management.
Approach:	They propose a novel agent-based GD Compressor with 3 layers with a multi-agent named Leader and Worker.
Outcome:	The proposed method improves on existing methods with low-level modeling and limited adaptability and user-unfriendly interface.

Nested Event Extraction upon Pivot Element Recognition (2024.lrec-main)

Copied to clipboard

Weicheng Ren, Zixuan Li, Xiaolong Jin, Long Bai, Miao Su, Yantao Liu, Saiping Guan, Jiafeng Guo, Xueqi Cheng

APT: Improving Specialist LLM Performance with Weakness Case Acquisition and Iterative Preference Training (2025.findings-acl)

Challenge:	Nested Event Extraction (NEE) aims to extract complex event structures where an event contains other events as its arguments recursively.
Approach:	They propose a new model that extracts nested events mainly based on recognizing PEs.
Outcome:	The proposed model can extract nested events based on recognizing PEs . it incorporates information from both event types and argument roles to improve performance .

Copied to clipboard

Jun Rao, Zepeng Lin, Xuebo Liu, Xiaopeng Ke, Lian Lian, Dong Jin, Shengjun Cheng, Jun Yu, Min Zhang

Semantically Consistent Data Augmentation for Neural Machine Translation via Conditional Masked Language Model (2022.coling-1)

Challenge:	Large Language Models often require domain-specific fine-tuning to address targeted tasks, which risks degrading their general capabilities.
Approach:	They propose to use self-generated dis-preferred weakness data to enhance model performance with a targeted training approach that minimizes interference with existing knowledge base.
Outcome:	The proposed approach ensures no reduction in generic capacity and achieves superior performance on downstream tasks compared to existing methods.

Copied to clipboard

Qiao Cheng, Jin Huang, Yitao Duan

Machine Translation

Challenge:	Neural network models have a large number of parameters to train, but data augmentation is relatively under-explored in natural language processing.
Approach:	They propose a bi-directional conditional Masked Language Model (CMLM) that can be conditional on both left and right contexts and the label.
Outcome:	The proposed method achieves the best performance on four translation datasets and yields up to 1.90 BLEU points over the baseline.

PACHAT: Persona-Aware Speech Assistant for Multi-party Dialogue (2025.emnlp-main)

Copied to clipboard

Dongjie Fu, Xize Cheng, Linjun Li, Xiaoda Yang, Lujia Yang, Tao Jin

WordArt Designer: User-Driven Artistic Typography Synthesis using Large Language Models (2023.emnlp-industry)

Challenge:	Extensive research on spoken dialogue systems has advanced the development of intelligent voice assistants, but integration of role information within speech remains an underexplored area.
Approach:	They propose a language-based spoken dialogue system that integrates role information within speech to generate contextually appropriate responses.
Outcome:	The proposed architecture achieves speaker-specific responses, character understanding, and the generation of targeted replies in multi-party dialogue scenarios, surpassing existing spoken dialogue systems.

Copied to clipboard

Jun-Yan He, Zhi-Qi Cheng, Chenyang Li, Jingdong Sun, Wangmeng Xiang, Xianhui Lin, Xiaoyang Kang, Zengke Jin, Yusen Hu, Bin Luo, Yifeng Geng, Xuansong Xie

OS-Symphony: A Holistic Framework for Robust and Generalist Computer-Using Agents (2026.acl-long)

Challenge:	Existing typography solutions lack adaptability, creativity, and computational efficiency.
Approach:	They propose a user-driven framework for artistic typography synthesis based on the Large Language Model (LLM) the LLM Engine interprets user inputs and generates actionable prompts for the other modules, transforming abstract concepts into tangible designs.
Outcome:	The proposed framework incorporates four key modules: the LLM Engine, SemTypo, StyTyPo, and TexTyPO.

Copied to clipboard

Bowen Yang, Kaiming Jin, Zhenyu Wu, Zhaoyang Liu, Qiushi Sun, Zehao Li, JingJing Xie, Zhoumianze Liu, Fangzhi Xu, Kanzhi Cheng, Yian Wang, Qingyun Li, Yu Qiao, Zun Wang, Zichen Ding

Semantic Structure Enhanced Event Causality Identification (2023.acl-long)

Challenge:	Vision-Language Models (VLMs) lack visual-aware tutorial retrieval and historical visual context curation and pruning.
Approach:	They propose a framework that integrates an orchestrator and a Reflection-Memory Agent for robust automation.
Outcome:	Experimental results show that OS-Symphony delivers substantial performance gains across model scales.

Copied to clipboard

Zhilei Hu, Zixuan Li, Xiaolong Jin, Long Bai, Saiping Guan, Jiafeng Guo, Xueqi Cheng

Challenge:	Existing methods for Event Causality Identification (ECI) capture implicit associations between events, which are difficult because they lack the ability to understand the associations between two events.
Approach:	They propose a model that captures the implicit associations between two events and integrates the event-centric structure information into a GNN-based event aggregator.
Outcome:	The proposed model improves on three widely used datasets showing that it integrates event-centric and event-associated semantic elements and captures event associations.

Contrastive Token-Wise Meta-Learning for Unseen Performer Visual Temporal-Aligned Translation (2023.findings-acl)

Copied to clipboard

Linjun Li, Tao Jin, Xize Cheng, Ye Wang, Wang Lin, Rongjie Huang, Zhou Zhao

Machine Translation

Challenge:	a novel generalization framework for visual temporal-aligned translation is proposed to transfer recognition skills to unseen performers . ambiguity in the visual sequence can hinder current methods for visual language translation .
Approach:	They propose a generalizable framework to transfer recognition skills to unseen performers . they use visual temporal-aligned translation to generate multiple words autoregressively .
Outcome:	The proposed framework is generalized to transfer recognition skills to unseen performers . it is compared with existing methods on lipreading and fingerspelling datasets .

Towards Event Extraction with Massive Types: LLM-based Collaborative Annotation and Partitioning Extraction (2025.emnlp-main)

Copied to clipboard

Wenxuan Liu, Zixuan Li, Long Bai, Yuxin Zuo, Daozhu Xu, Xiaolong Jin, Jiafeng Guo, Xueqi Cheng

Modeling Human-Like Cognition for Stance Detection: Integrating Intuitive Judgment and Analytical Reasoning (2026.acl-long)

Challenge:	Event Extraction (EE) is a long-standing target, but lacks an efficient and effective annotation framework to construct the corresponding datasets.
Approach:	They propose an LLM-based collaborative annotation framework that refines annotations of triggers from distant supervision and carries out argument annotation.
Outcome:	The proposed framework outperforms state-of-the-art methods on the largest EE dataset to date . it achieves the F1 scores of 90% and 85.3% on the human-annotated test set .

Copied to clipboard

Zhaodan Zhang, Jin Zhang, Jiafeng Guo, Xueqi Cheng

Linguistics & Cognitive NLP

Challenge:	Recent advances in large language models (LLMs) have revolutionized stance detection, enabling complex reasoning strategies such as chain-of-thought prompting.
Approach:	They propose Cognitive-Driven Stance Detection (CDSD) that integrates fast intuitive judgment and analytical reasoning enhanced by three key modules: attention-based cognitive alignment to compare system focus, uncertainty-aware belief update using Bayesian inference, and self-doubt-triggered counterfactual reasoning for re-evaluation under low consistency or high uncertainty.
Outcome:	The proposed method outperforms state-of-the-art methods on SEM16, P-Stance, and VAST.

TrustAgent: Towards Safe and Trustworthy LLM-based Agents (2024.findings-emnlp)

Copied to clipboard

Wenyue Hua, Xianjun Yang, Mingyu Jin, Zelong Li, Wei Cheng, Ruixiang Tang, Yongfeng Zhang

OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis (2025.acl-long)

Challenge:	Existing LLMs are primarily used for simple text-related tasks, but LLM-based agents can undertake more complex tasks that require planning and interaction with the physical world and humans.
Approach:	They propose an Agent-Constitution-based agent framework with a particular focus on improving the LLM-based agents' safety.
Outcome:	The proposed framework can enhance an LLM agent’s safety across multiple domains by identifying and mitigating potential dangers during the planning process.

Copied to clipboard

Qiushi Sun, Kanzhi Cheng, Zichen Ding, Chuanyang Jin, Yian Wang, Fangzhi Xu, Zhenyu Wu, Chengyou Jia, Liheng Chen, Zhoumianze Liu, Ben Kao, Guohao Li, Junxian He, Yu Qiao, Zhiyong Wu

G2S: A General-to-Specific Learning Framework for Temporal Knowledge Graph Forecasting with Large Language Models (2025.findings-acl)

Challenge:	Graphical User Interface (GUI) agents powered by Vision-Language Models (VLMs) have demonstrated human-like computer control capability.
Approach:	They propose a GUI data synthesis pipeline that reverse engineers GUI trajectory construction process by executing pre-defined tasks.
Outcome:	The proposed GUI data synthesis pipeline overcomes the bottlenecks of previous methods that rely on pre-defined tasks and limited data diversity.

Copied to clipboard

Long Bai, Zixuan Li, Xiaolong Jin, Jiafeng Guo, Xueqi Cheng, Tat-Seng Chua

TransFace: Unit-Based Audio-Visual Speech Synthesizer for Talking Head Translation (2024.findings-acl)

Challenge:	Recent studies have introduced Large Language Models (LLMs) for this task to enhance the models’ generalization abilities.
Approach:	They propose a General-to-Specific learning framework that disentangles the learning processes of two kinds of knowledge in a temporal temporal structure.
Outcome:	The proposed framework disentangles the learning processes of the above two kinds of knowledge and improves their generalization abilities.

Copied to clipboard

Xize Cheng, Rongjie Huang, Linjun Li, Zehan Wang, Tao Jin, Aoxiong Yin, Chen Feiyang, Xinyu Duan, Baoxing Huai, Zhou Zhao

Overcoming Catastrophic Forgetting in Massively Multilingual Continual Learning (2023.findings-acl)

Challenge:	Existing methods for talking head translation rely on cascading, resulting in delays and cascadic errors.
Approach:	They propose a model for talking head translation, TransFace, which can translate audio-visual speech into audio-visual speech in other languages.
Outcome:	The proposed model can translate audio-visual speech into audio-visual speech in other languages.

Copied to clipboard

Genta Winata, Lingjue Xie, Karthik Radhakrishnan, Shijie Wu, Xisen Jin, Pengxiang Cheng, Mayank Kulkarni, Daniel Preotiuc-Pietro

Multilinguality

Challenge:	Existing methods to handle catastrophic forgetting fail to retain knowledge learnt in the past when sudden shifts occur in training data distributions.
Approach:	They propose a learning rate scheduling method that preserves new information without strongly overwriting past knowledge.
Outcome:	The proposed method preserves new information without overwriting past knowledge in a multilingual continuous learning framework.

Document Embedding Enhanced Event Detection with Hierarchical and Supervised Attention (P18-2)

Copied to clipboard

Yue Zhao, Xiaolong Jin, Yuanzhuo Wang, Xueqi Cheng

Representation Learning

Challenge:	Existing methods for event detection use sentence-level contextual information.
Approach:	They propose a document embedding enhanced bi-RNN model to detect events in sentences . they use hierarchical and supervised attention based RNN to learn document embeds .
Outcome:	The proposed model compares with state-of-the-art models on a ACE-2005 dataset.

Large-Scale Corpus Construction and Retrieval-Augmented Generation for Ancient Chinese Poetry: New Method and Data Insights (2025.findings-naacl)

Copied to clipboard

Yang Liu, Lan Lan, Jiahuan Cao, Hiuyi Cheng, Kai Ding, Lianwen Jin

Information Retrieval

Challenge:	Ancient Chinese poetry presents unique challenges for Large Language Models due to data scarcity and limited ability of general LLMs when dealing with ACP.
Approach:	They propose a specialized Retrieval-Augmented Generation framework to improve LLMs' performance . they use 1.1 million ancient poems and 990K related texts to address hallucination issues .
Outcome:	The proposed framework improves performance of LLMs in ancient Chinese poetry domain from 49.2% to 89.0%.

Machine Unlearning of Pre-trained Large Language Models (2024.acl-long)

Copied to clipboard

Jin Yao, Eli Chien, Minxin Du, Xinyao Niu, Tianhao Wang, Zezhou Cheng, Xiang Yue

Rethinking the Multimodal Correlation of Multimodal Sequential Learning via Generalizable Attentional Results Alignment (2024.acl-long)

Challenge:	Using curated datasets, we establish a robust benchmark for unlearning performance, demonstrating that these methods are over 105 times more computationally efficient than retraining.
Approach:	They propose a framework for machine unlearning in pre-trained LLMs and integrate gradient ascent with gradient descent on in-distribution data to achieve robustness.
Outcome:	The proposed framework is over 105 times more efficient than retraining on in-distribution data and provides detailed guidelines for efficient hyperparameter tuning in the unlearning process.

Copied to clipboard

Tao Jin, Wang Lin, Ye Wang, Linjun Li, Xize Cheng, Zhou Zhao

SeaPO: Strategic Error Amplification for Robust Preference Optimization of Large Language Models (2025.findings-emnlp)

Challenge:	Existing studies have focused on the alignment of multimodal sequential learning using transformers.
Approach:	They propose a constrained scheme to align the multiple attentional results from both local and global perspectives.
Outcome:	The proposed scheme could align the multiple attentional results from both local and global perspectives, making the information capture more efficient.

Copied to clipboard

Jun Rao, Yunjie Liao, Xuebo Liu, Zepeng Lin, Lian Lian, Dong Jin, Shengjun Cheng, Jun Yu, Min Zhang

Beyond Dialogue Time: Temporal Semantic Memory for Personalized LLM Agents (2026.findings-acl)

Challenge:	Existing methods for preference optimization of large language models use pairs of positive and negative samples, but the quality of positive samples may become similar during training, complicating preference learning.
Approach:	SeaPO introduces error types commonly occurring in large language models to improve preference learning.
Outcome:	SeaPO introduces error types into model Preference Optimization to improve model performance . negative samples are more erroneous than positive samples, and preference-based training mitigates errors .

Copied to clipboard

Miao Su, Yucan Guo, Zhongni Hou, Long Bai, Zixuan Li, Yufei Zhang, Guojun Yin, Wei Lin, Xiaolong Jin, Jiafeng Guo, Xueqi Cheng

Dialogue Systems & Conversational Agents

Challenge:	Existing methods focus on point-wise memory, losing durative information that captures persistent states and evolving patterns.
Approach:	They propose a memory framework that models semantic time for point-wise memory and supports the construction and utilization of durative memory.
Outcome:	Experiments on LongMemEval and LoCoMo show that the proposed method outperforms existing methods and achieves up to 12.2% improvement in accuracy.

Integrating Deep Event-Level and Script-Level Information for Script Event Prediction (2021.emnlp-main)

Copied to clipboard

Long Bai, Saiping Guan, Jiafeng Guo, Zixuan Li, Xiaolong Jin, Xueqi Cheng

Class-Incremental Few-Shot Event Detection (2024.lrec-main)

Challenge:	Existing studies only consider a single event sequence corresponding to one common protagonist.
Approach:	They propose a Transformer-based model which integrates deep event-level and script-level information for script event prediction.
Outcome:	The proposed model is superior to existing models on the New York Times corpus . it utilizes rich information in the text to obtain more comprehensive representations .

Copied to clipboard

Kailin Zhao, Xiaolong Jin, Long Bai, Jiafeng Guo, Xueqi Cheng

Large Language Model-Based Event Relation Extraction with Rationales (2025.coling-main)

Challenge:	Existing methods to deal with new class of events with only a few labeled instances are challenging . old knowledge forgetting and new class overfitting are two problems in this task.
Approach:	They propose a task called class-incremental few-shot event detection to solve old knowledge forgetting and new class overfitting problems.
Outcome:	The proposed method reduces old knowledge forgetting and new class overfitting problems on two benchmark datasets.

Copied to clipboard

Zhilei Hu, Zixuan Li, Xiaolong Jin, Long Bai, Jiafeng Guo, Xueqi Cheng

Metric-guided Distillation: Distilling Knowledge from the Metric to Ranker and Retriever for Generative Commonsense Reasoning (2022.emnlp-main)

Challenge:	Existing methods for ERE rely on large language models, but they face limitations.
Approach:	They propose an LLM-based approach with rationales for the ERE task . LLMERE transforms ERE into a question-and-answer task that may have multiple answers .
Outcome:	Experimental results show that LLMERE improves over existing methods.

Copied to clipboard

Xingwei He, Yeyun Gong, A-Long Jin, Weizhen Qi, Hang Zhang, Jian Jiao, Bartuer Zhou, Biao Cheng, Sm Yiu, Nan Duan

Inductive Link Prediction in N-ary Knowledge Graphs (2025.coling-main)

Challenge:	Existing work on commonsense generation requires models to have relational reasoning and compositional generalization capabilities.
Approach:	They propose a metric distillation rule to distill knowledge from a standard metric to a ranker and transfer it to re-ranking a retriever.
Outcome:	The proposed method surpasses the previous SOTA.

Copied to clipboard

Jiyao Wei, Saiping Guan, Xiaolong Jin, Jiafeng Guo, Xueqi Cheng

Uni-Dubbing: Zero-Shot Speech Synthesis from Visual Articulation (2024.acl-long)

Challenge:	Existing methods to predict missing elements in NKGs are fixed and therefore cannot be used in real-world situations.
Approach:	They propose a task to predict missing elements in unseen facts involving unseent entities and roles in emerging NKGs by embedding unseense entities and role-encoding neural networks.
Outcome:	The proposed task outperforms representative models across all datasets.

Copied to clipboard

Songju Lei, Xize Cheng, Mengjiao Lyu, Jianqiao Hu, Jintao Tan, Runlin Liu, Lingyu Xiong, Tao Jin, Xiandong Li, Zhou Zhao

Learning to Conceal Risk: Controllable Multi-turn Red Teaming for LLMs in the Financial Domain (2026.acl-long)

Challenge:	Multimodal speech synthesis is a key challenge due to the scarcity of datasets that pair audio with corresponding video.
Approach:	They propose a method that incorporates modality alignment during the pre-training phase on multimodal datasets and freezes the video modality extraction component and the encoder module within the pretrained weights.
Outcome:	The proposed method achieves a reduced word error rate (WER) of 31.73%, surpassing the previous best of 33.9% with single-modality audio.

Copied to clipboard

Gang Cheng, Haibo Jin, Wenbin Zhang, Haohan Wang, Jun Zhuang

MetaSLRCL: A Self-Adaptive Learning Rate and Curriculum Learning Based Framework for Few-Shot Text Classification (2022.coling-1)

Challenge:	Large Language Models (LLMs) are increasingly deployed in high-stakes domains such as finance where unsafe behavior can lead to serious regulatory risks.
Approach:	They propose a black-box multi-turn risk-concealed redteaming framework that progressively conceals surface-level risk while exploiting regulatory-violating behaviors.
Outcome:	Experiments on nine widely used LLMs show that the proposed framework achieves 93.19% average attack success rate (ASR) and improves the average ASR to 95.00%.

Copied to clipboard

Kailin Zhao, Xiaolong Jin, Saiping Guan, Jiafeng Guo, Xueqi Cheng

MPVStance: Mitigating Hallucinations in Stance Detection with Multi-Perspective Verification (2025.acl-long)

Challenge:	Existing few-shot text classification methods lack labeled data in many scenarios.
Approach:	They propose a meta learning framework that obtains different learning rates for different tasks and neural network layers to enable the meta learner to quickly adapt to new training data.
Outcome:	The proposed framework can obtain different learning rates for different tasks and neural network layers so as to enable the meta learner to quickly adapt to new tasks.

Copied to clipboard

ZhaoDan Zhang, Zhao Zhang, Jin Zhang, Hui Xu, Xueqi Cheng

Sentiment Analysis

Challenge:	despite advances in large language models, challenges persist due to hallucination-models generating inaccurate content.
Approach:	They propose a framework that integrates multi-perspective verification with Retrieval-Augmented Generation to address these challenges.
Outcome:	The proposed method outperforms existing models on the SemEval-2016 and VAST datasets.

Vision-Flan: Scaling Human-Labeled Tasks in Visual Instruction Tuning (2024.findings-acl)

Copied to clipboard

Zhiyang Xu, Chao Feng, Rulin Shao, Trevor Ashby, Ying Shen, Di Jin, Yu Cheng, Qifan Wang, Lifu Huang

Large Language Models Can Be Contextual Privacy Protection Learners (2024.emnlp-main)

Challenge:	Recent vision-language models (VLMs) have shown impressive capabilities as general visual assistants, but there are two challenges to their performance: (1) lacking task diversity in pretraining and visual instruction tuning; (2) annotation error and bias in GPT-4 synthesized instruction tuning data.
Approach:	They propose a two-stage instruction tuning framework that fine tunes VLMs firstly and further tuned on GPT-4 synthesized data.
Outcome:	The proposed framework outperforms the traditional single-stage visual instruction tuning framework and achieves state-of-the-art performance across a wide range of multi-modal evaluation benchmarks.

Copied to clipboard

Yijia Xiao, Yiqiao Jin, Yushi Bai, Yue Wu, Xianjun Yang, Xiao Luo, Wenchao Yu, Xujiang Zhao, Yanchi Liu, Quanquan Gu, Haifeng Chen, Wei Wang, Wei Cheng

DCR: Quantifying Data Contamination in LLMs Evaluation (2025.emnlp-main)

Challenge:	Large Language Models (LLMs) have demonstrated remarkable linguistic comprehension and generation capability, but when applied to specialized industries, they face challenges such as hallucination, insufficient domain knowledge, and failing to incorporate the latest domain knowledge.
Approach:	They propose a paradigm for fine-tuning LLMs that effectively injects domain-specific knowledge while safeguarding inference-time data privacy.
Outcome:	The proposed model protects private data while enhancing the model's knowledge.

Copied to clipboard

Cheng Xu, Nan Yan, Shuhao Guan, Changhong Jin, Yuke Mei, Yibing Guo, Tahar Kechadi

Challenge:	Large language models (LLMs) memorize evaluation data during training, inflating performance metrics and undermining genuine generalization assessment.
Approach:	They propose a framework to detect and quantify benchmark data contamination (BDC) by synthesizing contamination scores via a fuzzy inference system.
Outcome:	The proposed framework detects and quantifies BDC risk across semantic, informational, data, and label levels.

MCS-Bench: A Comprehensive Benchmark for Evaluating Multimodal Large Language Models in Chinese Classical Studies (2025.acl-long)

Copied to clipboard

Yang Liu, Jiahuan Cao, Hiuyi Cheng, Yongxin Shi, Kai Ding, Lianwen Jin

Rethinking the Role of LLMs for Document-level Relation Extraction: a Refiner with Task Distribution and Probability Fusion (2025.naacl-long)

Challenge:	Multimodal Large Language Models (MLLMs) have advanced visual and language understanding, but their potential in Chinese Classical Studies (CCS) remains underexplored due to the lack of specialized benchmarks.
Approach:	They propose to develop a multimodal benchmark specifically designed for Chinese Classical Studies across multiple subdomains to bridge this gap.
Outcome:	The proposed benchmark spans seven core subdomains with a total of 45 meticulously designed tasks.

Copied to clipboard

Fu Zhang, Xinlong Jin, Jingwei Cheng, Hongsen Yu, Huangming Xu

A Survey of Link Prediction in N-ary Knowledge Graphs (2025.emnlp-main)

Challenge:	Document-level relation extraction (DocRE) provides a broad context for extracting relations for entities.
Approach:	They propose a method that utilizes LLMs as a refiner and task distribution and probability fusion to refine LLM-based relation extraction methods.
Outcome:	The proposed method outperforms existing LLM-based methods without fine-tuning by 25.2% F1.

Copied to clipboard

Jiyao Wei, Saiping Guan, Da Li, Zhongni Hou, Miao Su, Yucan Guo, Xiaolong Jin, Jiafeng Guo, Xueqi Cheng