Papers by Lin Zhou

Encoding Spreadsheets for Large Language Models (2024.emnlp-main)

Challenge:	Existing LLMs struggle to reliably detect subtle reasoning errors in ASAS tasks.
Approach:	They propose a dual-model framework with a dedicated Critic model trained for effective reflection that generates precise verbal feedback.
Outcome:	The proposed framework outperforms existing ASAS benchmarks and provides valuable insights into the performance of the proposed framework.

Copied to clipboard

Haoyu Dong, Jianbo Zhao, Yuzhang Tian, Junyu Xiong, Mengyu Zhou, Yun Lin, José Cambronero, Yeye He, Shi Han, Dongmei Zhang

CFSum Coarse-to-Fine Contribution Network for Multimodal Summarization (2023.acl-long)

Challenge:	Spreadsheets are characterized by their extensive two-dimensional grids, flexible layouts, and varied formatting options, which pose significant challenges for large language models (LLMs).
Approach:	They propose a structural-anchor-based compression, inverse index translation, and data-format-aware aggregation module to compress spreadsheets effectively.
Outcome:	The proposed method outperforms the existing model in GPT4 and achieves a state-of-the-art 78.9% F1 score.

Copied to clipboard

Min Xiao, Junnan Zhu, Haitao Lin, Yu Zhou, Chengqing Zong

Backdoor Collapse: Eliminating Unknown Threats Via Known Backdoor Aggregation In Language Models (2026.acl-long)

Challenge:	Existing multimodal summarization models ignore the contribution of visual modalities . we propose a novel contribution network to consider different contributions of images .
Approach:	They propose a Coarse-to-Fine contribution network for multimodal summarization to consider different contributions of images for summarizing.
Outcome:	The proposed system outperforms baselines on the visual and textual modalities.

Copied to clipboard

Liang Lin, Miao Yu, Moayad Aloqaily, Zhenhong Zhou, Kun Wang, Linsey Pang, Prakhar Mehrotra, Qingsong Wen

Are U a Joke Master? Pun Generation via Multi-Stage Curriculum Learning towards a Humor LLM (2024.findings-acl)

Challenge:	Existing defenses rely on impractical assumptions about trigger settings to mitigate backdoor attacks . a recent study found that small amounts of training data can systematically induce harmful behaviors in large language models.
Approach:	They propose a backdoor defense framework that requires no prior knowledge of trigger settings . they use a two-stage process to aggregate backdoor representations and fine-tune recovery .
Outcome:	The proposed defense reduces the average Attack Success Rate to 4.41% across multiple benchmarks . the proposed framework generalizes across different types of backdoors, confirming its robustness in practical deployment scenarios.

Copied to clipboard

Yang Chen, Chong Yang, Tu Hu, Xinhao Chen, Man Lan, Li Cai, Xinlin Zhuang, Xuan Lin, Xin Lu, Aimin Zhou

ToolGrad: Efficient Tool-use Dataset Generation with Textual “Gradients” (2026.findings-acl)

Challenge:	Existing research has demonstrated that the ability of large language models (LLMs) to generate humorous sentences is limited to producing 25 unique jokes.
Approach:	They propose a multi-stage curriculum preference learning framework to optimize both pun structure preferences and humor preferences by a Chinese Pun dataset.
Outcome:	The proposed method significantly outperforms baseline models on Chinese and English benchmark datasets.

Copied to clipboard

Zhongyi Zhou, Kohei Uehara, Haoyu Zhang, Jingtao Zhou, Lin Gu, Ruofei Du, Zheng Xu, Tatsuya Harada

OpenSR: Open-Modality Speech Recognition via Maintaining Multi-Modality Alignment (2023.acl-long)

Challenge:	Prior work synthesizes tool-use LLM datasets by first generating a user query, then complex tool-using annotations like DFS.
Approach:	They propose an agentic framework that synthesizes user queries and generates valid tool-use chains . they propose a dataset with more complex tool use, lower cost, and almost 100% pass rate .
Outcome:	Experiments show that tools trained on ToolGrad outperform expensive baseline datasets and proprietary LLMs.

Copied to clipboard

Xize Cheng, Tao Jin, Linjun Li, Wang Lin, Xinyu Duan, Zhou Zhao

Distilling ChatGPT for Explainable Automated Student Answer Assessment (2023.findings-emnlp)

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

Jiazheng Li, Lin Gui, Yuxiang Zhou, David West, Cesare Aloisi, Yulan He

Soft Language Clustering for Multilingual Model Pre-training (2023.acl-long)

Challenge:	Existing automated student answer assessment models lack explainable and faithful feedback.
Approach:	They propose a framework that leverages ChatGPT for student answer scoring and rationale generation.
Outcome:	The proposed method improves the overall QWK score by 11% compared to ChatGPT.

Copied to clipboard

Jiali Zeng, Yufan Jiang, Yongjing Yin, Yi Jing, Fandong Meng, Binghuai Lin, Yunbo Cao, Jie Zhou

Flames: Benchmarking Value Alignment of LLMs in Chinese (2024.naacl-long)

Challenge:	Multilingual pre-trained language models have demonstrated impressive (zero-shot) cross-lingual transfer abilities, however, their performance is hindered when the target language has distant typology from the source language or when pre-training data is limited in size.
Approach:	They propose a method that contextually retrieves prompts as flexible guidance for encoding instances conditionally.
Outcome:	The proposed method improves on the XTREME task and also for low-resource languages in unsupervised sentence retrieval.

Copied to clipboard

Kexin Huang, Xiangyang Liu, Qianyu Guo, Tianxiang Sun, Jiawei Sun, Yaru Wang, Zeyang Zhou, Yixu Wang, Yan Teng, Xipeng Qiu, Yingchun Wang, Dahua Lin

Automatic Label Sequence Generation for Prompting Sequence-to-sequence Models (2022.coling-1)

Challenge:	Existing benchmarks for large language models (LLMs) do not accurately uncover safety vulnerabilities in LLMs.
Approach:	They propose a value alignment benchmark called Flames that encompasses both harmlessness principles and a unique morality dimension that integrates specific Chinese values such as harmony.
Outcome:	The proposed model performs poorly on Flames, particularly in safety and fairness dimensions.

Copied to clipboard

Zichun Yu, Tianyu Gao, Zhengyan Zhang, Yankai Lin, Zhiyuan Liu, Maosong Sun, Jie Zhou

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

Challenge:	Prompting has shown to be sample efficient compared to fine-tuning with pre-trained models.
Approach:	They propose a fully automatic prompting method that uses natural language prompts on sequence-to-sequence models and a beam search method to generate a large amount of label sequence candidates.
Outcome:	The proposed method significantly outperforms other no-manual-design methods on single label words and generates large amount of label sequence candidates.

Copied to clipboard

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

Reflect, Not Reflex: Inference-Based Common Ground Improves Dialogue Response Quality (2022.emnlp-main)

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.

Copied to clipboard

Pei Zhou, Hyundong Cho, Pegah Jandaghi, Dong-Ho Lee, Bill Yuchen Lin, Jay Pujara, Xiang Ren

RWKV: Reinventing RNNs for the Transformer Era (2023.findings-emnlp)

Challenge:	Currently, human communication models fail to explicitly model common ground (CG) . less than half of the responses in current data is rated as high quality .
Approach:	They propose a dataset that annotates dialogues with explicit CG and solicits 9k diverse responses each following one common ground.
Outcome:	The proposed dataset annotates dialogues with explicit CG and solicits 9k diverse responses each following one common ground.

Copied to clipboard

Bo Peng, Eric Alcaide, Quentin Anthony, Alon Albalak, Samuel Arcadinho, Stella Biderman, Huanqi Cao, Xin Cheng, Michael Chung, Leon Derczynski, Xingjian Du, Matteo Grella, Kranthi Gv, Xuzheng He, Haowen Hou, Przemyslaw Kazienko, Jan Kocon, Jiaming Kong, Bartłomiej Koptyra, Hayden Lau, Jiaju Lin, Krishna Sri Ipsit Mantri, Ferdinand Mom, Atsushi Saito, Guangyu Song, Xiangru Tang, Johan Wind, Stanisław Woźniak, Zhenyuan Zhang, Qinghua Zhou, Jian Zhu, Rui-Jie Zhu

SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator (2026.acl-long)

Challenge:	recurrent neural networks struggle to match the performance of Transformers due to limitations in parallelization and scalability.
Approach:	They propose a model architecture that combines the efficient parallelizable training of transformers with the efficient inference of RNNs.
Outcome:	The proposed model performs on par with similarly sized RNNs, suggesting future work can leverage this architecture to create more efficient models.

Copied to clipboard

Xueyang Zhou, Weidong Wang, Lin Lu, Jiawen Shi, Guiyao Tie, Xu Yongtian, Lixing Chen, Pan Zhou, Neil Zhenqiang Gong, Lichao Sun

Challenge:	SafeAgent improves agent safety through fully automated synthetic data generation.
Approach:	They propose a framework that improves agent safety through fully automated synthetic data generation.
Outcome:	The proposed framework outperforms closed-source models on two safety benchmarks and one real-world task.

FOLIO: Natural Language Reasoning with First-Order Logic (2024.emnlp-main)

Copied to clipboard

Simeng Han, Hailey Schoelkopf, Yilun Zhao, Zhenting Qi, Martin Riddell, Wenfei Zhou, James Coady, David Peng, Yujie Qiao, Luke Benson, Lucy Sun, Alexander Wardle-Solano, Hannah Szabó, Ekaterina Zubova, Matthew Burtell, Jonathan Fan, Yixin Liu, Brian Wong, Malcolm Sailor, Ansong Ni, Linyong Nan, Jungo Kasai, Tao Yu, Rui Zhang, Alexander Fabbri, Wojciech Kryscinski, Semih Yavuz, Ye Liu, Xi Lin, Shafiq Joty, Yingbo Zhou, Caiming Xiong, Rex Ying, Arman Cohan, Dragomir Radev

Probing Commonsense Explanation in Dialogue Response Generation (2021.findings-emnlp)

Challenge:	Existing benchmarks for logical reasoning in large language models lack language naturalness or limited complexity.
Approach:	They propose to use first-order logic annotations to evaluate logical reasoning capabilities of large language models.
Outcome:	The proposed dataset evaluates the FOL reasoning ability of supervised fine-tuning on medium-sized language models.

Copied to clipboard

Pei Zhou, Pegah Jandaghi, Hyundong Cho, Bill Yuchen Lin, Jay Pujara, Xiang Ren

V-ALPHASOCIAL: Benchmark and Self-Reflective Chain-of-Thought Generation for Visual Social Commonsense Reasoning (2025.findings-acl)

Challenge:	Currently, response generation (RG) models do not understand human communication intents.
Approach:	They propose to examine commonsense reasoning implicitly to determine whether RG models produce coherent responses in conversations.
Outcome:	The proposed probing settings show that RG models fail to capture the logical relations between commonsense explanations and responses and fine-tuning on in-domain data do not lead to understanding of CSR for RG.

Copied to clipboard

Zongyu Lin, Zhikun Xu, Xiaohan Song, Yixin Wan, Xingcheng Yao, Tsung-Han Lin, Selina Song, Pranav Subbaraman, Ben Zhou, Kai-Wei Chang, Yizhou Sun

Manifold Learning-based Word Representation Refinement Incorporating Global and Local Information (2020.coling-main)

Challenge:	Social commonsense reasoning is a multimodal task that requires both textual and visual cues.
Approach:	They propose a method that integrates visual cues into social commonsense reasoning tasks.
Outcome:	The proposed method improves social commonsense reasoning on a multimodal foundation model.

Copied to clipboard

Wenyu Zhao, Dong Zhou, Lin Li, Jinjun Chen

Uncovering Scaling Laws for Large Language Models via Inverse Problems (2025.findings-emnlp)

Challenge:	Recent studies show word embedding models underestimate similarities between similar words and overestimate similarities between distant words.
Approach:	They propose two new word embedding methods that align original and re-fined embeddable spaces to a new refined semantic space.
Outcome:	The proposed methods outperform state-of-the-art methods for word representation refinement.

Copied to clipboard

Arun Verma, Zhaoxuan Wu, Zijian Zhou, Xiaoqiang Lin, Zhiliang Chen, Rachael Hwee Ling Sim, Rui Qiao, Jingtan Wang, Nhung Bui, Xinyuan Niu, Wenyang Hu, Gregory Kang Ruey Lau, Zi-Yu Khoo, Zitong Zhao, Xinyi Xu, Apivich Hemachandra, See-Kiong Ng, Bryan Kian Hsiang Low

On LLM-Based Scientific Inductive Reasoning Beyond Equations (2025.emnlp-main)

Challenge:	Large Language Models (LLMs) have achieved remarkable success across diverse domains.
Approach:	inverse problems can efficiently uncover scaling laws that guide the building of LLMs, authors argue . authors propose brute-force approaches to improve LLM training costs due to high costs .
Outcome:	This paper advocates that inverse problems can efficiently uncover scaling laws that guide the building of LLMs to achieve the desirable performance with significantly better cost-effectiveness.

Copied to clipboard

Brian S. Lin, Jiaxin Yuan, Zihan Zhou, Shouli Wang, Shuo Wang, Cunliang Kong, Qi Shi, Yuxuan Li, Liner Yang, Zhiyuan Liu, Maosong Sun

Exploring Mode Connectivity for Pre-trained Language Models (2022.emnlp-main)

Challenge:	Existing research on inductive reasoning models emphasizes rule design without grounding them in specific scenarios.
Approach:	They propose to use LLMs to learn underlying patterns from limited examples in entirely new environments.
Outcome:	The proposed benchmark evaluates the inductive reasoning abilities of large language models in scientific settings.

Copied to clipboard

Yujia Qin, Cheng Qian, Jing Yi, Weize Chen, Yankai Lin, Xu Han, Zhiyuan Liu, Maosong Sun, Jie Zhou

Knowledge Inheritance for Pre-trained Language Models (2022.naacl-main)

Challenge:	Recent years have witnessed the prevalent application of pre-trained language models (PLMs) in NLP. From the perspective of parameter space, PLMs provide generic initialization, starting from which high-performance minima could be found.
Approach:	They investigate the geometric connections of different minima through the lens of mode connectivity, which measures whether two minima can be connected with a low-loss path.
Outcome:	The proposed model can be used to find low-loss paths between two minima, and to understand how their mode connectivity affects their task knowledge.

Copied to clipboard

Yujia Qin, Yankai Lin, Jing Yi, Jiajie Zhang, Xu Han, Zhengyan Zhang, Yusheng Su, Zhiyuan Liu, Peng Li, Maosong Sun, Jie Zhou

MAVEN: A Massive General Domain Event Detection Dataset (2020.emnlp-main)

Challenge:	Existing large-scale pre-trained language models are mainly trained from scratch individually, ignoring that many well-taught PLMs are available.
Approach:	They propose a pre-training framework called knowledge inheritance and propose auxiliary supervision to efficiently learn larger PLMs.
Outcome:	The proposed framework can be used to train large-scale language models with huge parameters and a large dataset can be adapted to domain adaptation and knowledge transfer.

Copied to clipboard

Xiaozhi Wang, Ziqi Wang, Xu Han, Wangyi Jiang, Rong Han, Zhiyuan Liu, Juanzi Li, Peng Li, Yankai Lin, Jie Zhou

Knowledge-Guided Dynamic Modality Attention Fusion Framework for Multimodal Sentiment Analysis (2024.findings-emnlp)

Challenge:	Existing datasets exhibit data scarcity and limited coverage of general-domain events.
Approach:	They present a MAssive eVENt detection dataset which contains 4,480 Wikipedia documents and 168 event types.
Outcome:	The proposed dataset shows that existing methods cannot achieve promising results on the small datasets.

Copied to clipboard

Xinyu Feng, Yuming Lin, Lihua He, You Li, Liang Chang, Ya Zhou

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

Challenge:	Existing methods focus on equally treating the contribution of each modality or statically using text as the dominant modality to conduct interaction, which neglects the situation where each modal may become dominant.
Approach:	They propose a Knowledge-Guided Dynamic Modality Attention Fusion Framework (KuDA) that uses sentiment knowledge to guide the model dynamically selecting the dominant modality and adjusting the contributions of each modality.
Outcome:	The proposed model can be used to highlight the contribution of dominant modality through the correlation evaluation loss.

Copied to clipboard

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

MAVEN-ARG: Completing the Puzzle of All-in-One Event Understanding Dataset with Event Argument Annotation (2024.acl-long)

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

Xiaozhi Wang, Hao Peng, Yong Guan, Kaisheng Zeng, Jianhui Chen, Lei Hou, Xu Han, Yankai Lin, Zhiyuan Liu, Ruobing Xie, Jie Zhou, Juanzi Li

Data Interpreter: An LLM Agent for Data Science (2025.findings-acl)

Challenge:	Existing datasets for event understanding have limited coverage due to complexity of tasks.
Approach:	They propose a dataset that augments MAVEN datasets with event argument annotations . they propose 98,591 events and 290,613 arguments obtained with laborious human annotation .
Outcome:	The proposed dataset is the first all-in-one dataset supporting event detection, event argument extraction, and event relation extraction.

Copied to clipboard

Sirui Hong, Yizhang Lin, Bang Liu, Bangbang Liu, Binhao Wu, Ceyao Zhang, Danyang Li, Jiaqi Chen, Jiayi Zhang, Jinlin Wang, Li Zhang, Lingyao Zhang, Min Yang, Mingchen Zhuge, Taicheng Guo, Tuo Zhou, Wei Tao, Robert Tang, Xiangtao Lu, Xiawu Zheng, Xinbing Liang, Yaying Fei, Yuheng Cheng, Yongxin Ni, Zhibin Gou, Zongze Xu, Yuyu Luo, Chenglin Wu

AMO-Bench: Large Language Models Still Struggle in High School Math Competitions (2026.findings-acl)

Challenge:	Large Language Models (LLMs) excel in various domains but face challenges when applied to data science workflows due to their complex, multi-stage nature.
Approach:	They propose a hierarchical graph-based agent that represents complexity and a progressive strategy for step-by-step verification, refinement, and consistent context management.
Outcome:	The proposed agent surpasses state-of-the-art baselines on the MATH dataset and performs better on InfiAgent-DABench.

Copied to clipboard

Junlin Liu, Shengnan An, Shuang Zhou, Dan Ma, Yehao Lin, Xinxuan Lv, Xuanlin Wang, Xiaoyu Li, Ziwen Wang, Xuezhi Cao, Xunliang Cai

ReCreate: Reasoning and Creating Domain Agents Driven by Experience (2026.acl-long)

Challenge:	Existing benchmarks for mathematical reasoning are becoming less effective due to performance saturation.
Approach:	They propose to use a mathematical reasoning benchmark with Olympiad difficulty to evaluate top-tier LLMs.
Outcome:	The proposed benchmarks are cross-validated by experts to meet IMO difficulty standards and entirely original problems to prevent performance leakages from data memorization.

Copied to clipboard

Zhezheng Hao, Hong Wang, Jian Luo, Jianqing Zhang, Yuyan Zhou, Qiang Lin, Can Wang, Hande Dong, Jiawei Chen

DocMMIR: A Framework for Document Multi-modal Information Retrieval (2025.findings-emnlp)

Challenge:	Large Language Model (LLM) agents are reshaping the industrial landscape, but tasks differ widely, making them labor-intensive to build.
Approach:	They propose an experience-driven framework for the automatic creation of domain agents . they leverage agent interaction histories to provide rich concrete signals on success or failure .
Outcome:	The proposed framework outperforms human-designed agents and existing methods in experiments across diverse domains.

Copied to clipboard

Zirui Li, Siwei Wu, Yizhi Li, Xingyu Wang, Yi Zhou, Chenghua Lin

FPE2M2: Approaching Lossless and Efficient Quantization with Native Floating Point (2025.findings-acl)

Challenge:	Existing multi-modal information retrieval models lack a comprehensive exploration of document-level retrieval . existing models suffer from the absence of cross-domain datasets at this granularity.
Approach:	They propose a multi-modal document retrieval framework to unify diverse document formats and domains with a comprehensive retrieval scenario.
Outcome:	The proposed framework improves document retrieval performance on a large multimodal dataset.

Copied to clipboard

Ke Yi, Jianwei Zhang, Zhiying Xu, Xinlong Yang, Yang Zhou, Minmin Sun, Zengke Liu, Tong Zhang, Junyang Lin, Jingren Zhou

More Data, More Relations, More Context and More Openness: A Review and Outlook for Relation Extraction (2020.aacl-main)

Challenge:	Auto-regressive decoding is a memory-bound job, meaning decoding performance is limited by the bandwidth rather than the computational capabilities of the GPU.
Approach:	They propose a framework that supports lossless weight-only quantization inference and validate it on Qwen and LLaMA Models.
Outcome:	The proposed framework achieves the highest efficiency with lossless accuracy on Qwen and LLaMA Models across various modalities.

Copied to clipboard

Xu Han, Tianyu Gao, Yankai Lin, Hao Peng, Yaoliang Yang, Chaojun Xiao, Zhiyuan Liu, Peng Li, Jie Zhou, Maosong Sun

Topic-Driven and Knowledge-Aware Transformer for Dialogue Emotion Detection (2021.acl-long)

Challenge:	Existing methods for extracting relational facts from text have been successful . but with explosion of Web text, human knowledge is increasing drastically .
Approach:	They propose to improve relation extraction methods to extract relational facts from text . they analyze existing methods and show promising directions towards more powerful RE .
Outcome:	The proposed methods can extract relational facts from text, but they are still lacking in the current field.

Copied to clipboard

Lixing Zhu, Gabriele Pergola, Lin Gui, Deyu Zhou, Yulan He

Tell Me More! Towards Implicit User Intention Understanding of Language Model Driven Agents (2024.acl-long)

Challenge:	Emotion detection in dialogues requires the identification of thematic topics underlying a conversation, commonsense knowledge, and the intricate transition patterns between affective states.
Approach:	They propose a Topic-Driven Knowledge-Aware Transformer model that integrates topic representation and commonsense knowledge from ATOMIC for dialogue emotion detection.
Outcome:	The proposed model outperforms state-of-the-art models on four dialogue datasets . it can detect topics which help distinguish emotion categories, the authors show .

Copied to clipboard

Cheng Qian, Bingxiang He, Zhong Zhuang, Jia Deng, Yujia Qin, Xin Cong, Zhong Zhang, Jie Zhou, Yankai Lin, Zhiyuan Liu, Maosong Sun

CommonGen: A Constrained Text Generation Challenge for Generative Commonsense Reasoning (2020.findings-emnlp)

Challenge:	Current language model-driven agents lack mechanisms for effective user participation, which is crucial given the vagueness commonly found in user instructions.
Approach:	They propose a benchmark to inspect users’ implicit intentions through explicit queries and a model expert as the upstream in agent design to enhance user-agent interaction.
Outcome:	The proposed approach excels at identifying vague user tasks, recovering and summarizing critical missing information, setting precise and necessary agent execution goals, and minimizing redundant tool usage, thus boosting overall efficiency.

Copied to clipboard

Bill Yuchen Lin, Wangchunshu Zhou, Ming Shen, Pei Zhou, Chandra Bhagavatula, Yejin Choi, Xiang Ren

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

Challenge:	Recent studies show that pre-trained language models perform well on commonsense-reasoning benchmark datasets, but building machines with commonsence to compose plausible sentences remains challenging.
Approach:	They propose a constrained text generation task for generative commonsense reasoning that generates a coherent sentence using common concepts.
Outcome:	The proposed task generates a coherent sentence describing an everyday scenario using common concepts over 35k concept-sets.

Copied to clipboard

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

Multi-Path Transformer is Better: A Case Study on Neural Machine Translation (2022.findings-emnlp)

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

Ye Lin, Shuhan Zhou, Yanyang Li, Anxiang Ma, Tong Xiao, Jingbo Zhu

MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing (2026.acl-industry)

Challenge:	Extensive experiments on 12 WMT tasks show that shallower multi-path models can achieve similar or even better performance than the deeper model.
Approach:	They propose to use a parameter-efficient multi-path structure to fuse features extracted from different paths to achieve better performance.
Outcome:	The proposed model can achieve better performance with the same number of parameters than the deeper model.

Copied to clipboard

Junbo Niu, Zheng Liu, Zhuangcheng Gu, Bin Wang, Linke Ouyang, Zhiyuan Zhao, Tao Chu, Tianyao He, Fan Wu, Qintong Zhang, Zhenjiang Jin, Guang Liang, Rui Zhang, Wenzheng Zhang, Yuan Qu, Zhifei Ren, Yuefeng Sun, Zirui Tang, Boyu Niu, Yuanhong Zheng, Dongsheng Ma, Ziyang Miao, Hejun Dong, Siyi Qian, Junyuan Zhang, Fangdong Wang, Jingzhou Chen, Xiaomeng Zhao, Liqun Wei, Wei Li, Shasha Wang, RuiLiang Xu, Yuanyuan Cao, Lu Chen, Qianqian Wu, Huaiyu Gu, Lindong Lu, Dechen Lin, null Shenguanlin, Xuanhe Zhou, Linfeng Zhang, Yuhang Zang, Xiaoyi Dong, Jiaqi Wang, Bo Zhang, Lei Bai, Pei Chu, Weijia Li, Jiang Wu, Lijun Wu, Zhenxiang Li, Guangyu Wang, Zhongying Tu, Chao Xu, Kai Chen, Bowen Zhou, Dahua Lin, Wentao Zhang, Conghui He

LLM×MapReduce-V3: Enabling Interactive In-Depth Survey Generation through a MCP-Driven Hierarchically Modular Agent System (2025.emnlp-demos)

Challenge:	Document images are characterized by higher resolutions, denser content, and more complex structural layouts.
Approach:	They propose a 1.2B-parameter document parsing vision-language model that decouples layout analysis from local content recognition.
Outcome:	The proposed model surpasses general-purpose and domain-specific models on multiple benchmarks while maintaining significantly lower computational overhead.

Copied to clipboard

Yu Chao, Siyu Lin, Xiaorong Wang, Zhu Zhang, Zihan Zhou, Haoyu Wang, Shuo Wang, Jie Zhou, Zhiyuan Liu, Maosong Sun

Challenge:	Generating high-quality long-form survey articles poses significant challenges to AI Agent systems.
Approach:	They propose a hierarchically modular agent system for long-form survey generation . they use atomic models to implement skeleton initialization, digest construction, and skelet refinement . human evaluations demonstrate system surpasses representative baselines .
Outcome:	The proposed system surpasses representative baselines in both content depth and length, highlighting the strength of MCP-based modular planning.

CorefDiffs: Co-referential and Differential Knowledge Flow in Document Grounded Conversations (2022.coling-1)

Copied to clipboard

Lin Xu, Qixian Zhou, Jinlan Fu, Min-Yen Kan, See-Kiong Ng

Enhancing Uncertainty-Based Hallucination Detection with Stronger Focus (2023.emnlp-main)

Challenge:	Document-grounded dialogs need smooth transitions between knowledge selected for generating responses.
Approach:	They propose a multi-document co-referential graph to capture inter- and intra-document relationships . they propose 'Coref-MDG' method to linearize static Coref-mDG into conversational sequence logic.
Outcome:	The proposed method outperforms the state-of-the-art by 9.5%, 7.4% and 8.2% on three public benchmarks.

Copied to clipboard

Tianhang Zhang, Lin Qiu, Qipeng Guo, Cheng Deng, Yue Zhang, Zheng Zhang, Chenghu Zhou, Xinbing Wang, Luoyi Fu

Linguistic Neuron Overlap Patterns to Facilitate Cross-lingual Transfer on Low-resource Languages (2025.emnlp-main)

Challenge:	Existing methods for detecting hallucinations in LLMs rely on external knowledge for reference retrieval or require sampling multiple responses for consistency verification.
Approach:	They propose a reference-free, uncertainty-based method for detecting hallucinations in Large Language Models that imitates human focus in factuality checking from three aspects: focus on the most informative keywords; focus on unreliable tokens in historical context; focus of token properties such as token type and token frequency.
Outcome:	The proposed method achieves state-of-the-art performance across all evaluation metrics and eliminates the need for additional information.

Copied to clipboard

Yuemei Xu, Kexin Xu, Jian Zhou, Ling Hu, Lin Gui

The Mystery of In-Context Learning: A Comprehensive Survey on Interpretation and Analysis (2024.emnlp-main)

Challenge:	Recent studies have focused on data-efficient methods, particularly Cross-lingual In-Context Learning (X-ICL)
Approach:	They propose a method to improve cross-lingual in-context learning for low-resource languages by using language-specific neurons.
Outcome:	The proposed method improves cross-lingual performance on low-resource languages by ensuring full activation of language overlap neurons.

Copied to clipboard

Yuxiang Zhou, Jiazheng Li, Yanzheng Xiang, Hanqi Yan, Lin Gui, Yulan He

Virtual Context Enhancing Jailbreak Attacks with Special Token Injection (2024.findings-emnlp)

Challenge:	In-context learning (ICL) is a capability that enables large language models to excel in proficiency through demonstration examples.
Approach:	They present a survey on the interpretation and analysis of in-context learning . they focus on theoretical and empirical perspectives on the concept .
Outcome:	The proposed model can perform tasks with minimal examples without re-training and has demonstrated proficiency across various tasks with a minimal set of task-oriented examples.

Copied to clipboard

Yuqi Zhou, Lin Lu, Ryan Sun, Pan Zhou, Lichao Sun

ReAct Meets Industrial IoT: Language Agents for Data Access (2025.emnlp-industry)

Challenge:	Existing jailbreak attacks target the two phases of user interaction: prompt input and model computation.
Approach:	They propose a new tool that leverages special tokens to improve jailbreak attacks . they found that the tool can increase success rates of existing jailbreak methods by 40% .
Outcome:	The proposed solution can improve success rates of four widely used jailbreak methods by approximately 40% across various LLMs.

Copied to clipboard

James T Rayfield, Shuxin Lin, Nianjun Zhou, Dhaval C Patel

Efficient Large Scale Language Modeling with Mixtures of Experts (2022.emnlp-main)

Challenge:	a framework for domain-specific language agents is being developed for industrial automation . a novel approach to adapting these systems to domain-based applications poses new challenges .
Approach:	They propose a framework for deploying domain-specific language agents that can query industrial sensor data using natural language.
Outcome:	The proposed framework outperforms standard prompting baselines across multiple LLMs including smaller models.

Copied to clipboard

Mikel Artetxe, Shruti Bhosale, Naman Goyal, Todor Mihaylov, Myle Ott, Sam Shleifer, Xi Victoria Lin, Jingfei Du, Srinivasan Iyer, Ramakanth Pasunuru, Giridharan Anantharaman, Xian Li, Shuohui Chen, Halil Akin, Mandeep Baines, Louis Martin, Xing Zhou, Punit Singh Koura, Brian O’Horo, Jeffrey Wang, Luke Zettlemoyer, Mona Diab, Zornitsa Kozareva, Veselin Stoyanov

Zero-Shot Dialogue State Tracking via Cross-Task Transfer (2021.emnlp-main)

Challenge:	Mixture of Experts layers (MoEs) enable efficient scaling of language models . large autoregressive language models such as GPT-3 can be adapted to a wide range of tasks .
Approach:	They propose to use Mixture of Experts layers to enable efficient scaling of language models . they find that MoEs are substantially more compute efficient than dense models compared to MoE models - but only when they are more modestly trained .
Outcome:	The proposed model outperforms dense models in a wide range of tasks and domains.

Copied to clipboard

Zhaojiang Lin, Bing Liu, Andrea Madotto, Seungwhan Moon, Zhenpeng Zhou, Paul Crook, Zhiguang Wang, Zhou Yu, Eunjoon Cho, Rajen Subba, Pascale Fung

UltraEval-Audio: A Unified Framework for Comprehensive Evaluation of Audio Foundation Models (2026.acl-demo)

Challenge:	Existing approaches to training a dialogue state tracking model require extensive annotated dialogue data.
Approach:	They propose to transfer cross-task knowledge from general question answering corpora to QA model that can handle zero-shot DST.
Outcome:	The proposed model improves existing zero-shot and few-shot results on MultiWoz and shows better generalization ability in unseen domains.

Copied to clipboard

Qundong Shi, Jie Zhou, Biyuan Lin, Junbo Cui, Guoyang Zeng, Yixuan Zhou, Ziyang Wang, Xin Liu, Zhen Luo, Yudong Wang, Zhiyuan Liu

Temporal Precision Matters: Brain-Tuning Speech Language Models with Millisecond-Resolution Neural Signals (2026.acl-long)

Challenge:	Existing evaluation frameworks for audio foundation models are heavily reliant on English, making it difficult to objectively assess models’ performance on Chinese.
Approach:	They propose a unified framework that supports 10 languages, 14 task categories, 24 models, and 36 benchmarks with one-command evaluation and real-time leaderboards.
Outcome:	The proposed framework supports 10 languages, 14 task categories, 24 models, and 36 benchmarks with one-command evaluation and real-time leaderboards.

Copied to clipboard

Zhejun Zhang, Wenqing Zhou, Haozhe Xu, Lin Zhang, Lei Li

ChildMandarin: A Comprehensive Mandarin Speech Dataset for Young Children Aged 3-5 (2025.acl-long)

Challenge:	Language models have emerged as powerful tools for predicting human brain activity during language comprehension.
Approach:	They propose a technique that leverages electrocorticography’s millisecond precision to train speech language models.
Outcome:	The proposed technique improves brain alignment over pretrained and distillation models and produces higher gains in higher-order language regions.

Copied to clipboard

Jiaming Zhou, Shiyao Wang, Shiwan Zhao, Jiabei He, Haoqin Sun, Hui Wang, Cheng Liu, Aobo Kong, Yujie Guo, Xi Yang, Yequan Wang, Yonghua Lin, Yong Qin

Can Large Language Models Always Solve Easy Problems if They Can Solve Harder Ones? (2024.emnlp-main)

Challenge:	Automatic speech recognition systems have advanced significantly with models like Whisper, Conformer, and self-supervised frameworks such as Wav2vec 2.0.
Approach:	They propose to use Mandarin speech datasets to analyze pronunciation and tone of children aged 3 to 5 and evaluate their models on speaker verification (SV) They find that the datasets are more robust than those used by adult speech recognition systems and are open-source and available for all academic purposes.
Outcome:	The proposed dataset includes 41.25 hours of speech with carefully crafted manual transcriptions, collected from 397 speakers across various provinces in China, with balanced gender representation.

Copied to clipboard

Zhe Yang, Yichang Zhang, Tianyu Liu, Jian Yang, Junyang Lin, Chang Zhou, Zhifang Sui

Large Language Models Fall Short: Understanding Complex Relationships in Detective Narratives (2024.findings-acl)

Challenge:	Large language models (LLMs) have impressive capabilities, but still suffer from inconsistency issues.
Approach:	They develop a ConsisEval benchmark to evaluate LLMs' inconsistency . they find that LLM models can paradoxically fail at easier problems .
Outcome:	The proposed model achieves highest consistency score but inconsistent to specific questions due to distraction by redundant information, misinterpretation of questions, etc.

Copied to clipboard

Runcong Zhao, Qinglin Zhu, Hainiu Xu, Jiazheng Li, Yuxiang Zhou, Yulan He, Lin Gui

Code Needs Comments: Enhancing Code LLMs with Comment Augmentation (2024.findings-acl)

Challenge:	Existing datasets for narrative understanding fail to represent complexity and uncertainty of relationships in real-life social scenarios.
Approach:	They propose a benchmark for extracting and analysing intricate character relation graphs from detective narratives using large-scale large-language models.
Outcome:	The proposed dataset extracts and analyses character relation graphs from detective narratives using advanced Large Language Models like GPT-3.5, GPT-4, and Llama2 .

Copied to clipboard

Demin Song, Honglin Guo, Yunhua Zhou, Shuhao Xing, Yudong Wang, Zifan Song, Wenwei Zhang, Qipeng Guo, Hang Yan, Xipeng Qiu, Dahua Lin

LLM Critics Help Catch Bugs in Mathematics: Towards a Better Mathematical Verifier with Natural Language Feedback (2025.findings-acl)

Challenge:	Large Language Models (LLMs) require a deep understanding of programming languages and their correlation with natural languages (NLs).
Approach:	They propose a data augmentation method that generates comments for existing code and a filtering strategy that filters out code data poorly correlated with natural language.
Outcome:	The proposed method outperforms the model trained on the augmented data and the model further trained on data without augmentation on two widely-used programming skill benchmarks.

Copied to clipboard

Bofei Gao, Zefan Cai, Runxin Xu, Peiyi Wang, Ce Zheng, Runji Lin, Keming Lu, Dayiheng Liu, Chang Zhou, Wen Xiao, Tianyu Liu, Baobao Chang

AgentCPM-GUI: Building Mobile-Use Agents with Reinforcement Fine-Tuning (2025.emnlp-demos)

Challenge:	Existing mathematical verifiers are trained with binary classification labels, which are not informative enough for the model to accurately assess the solutions.
Approach:	They propose a natural language feedback-enhanced verifier that can validate the correctness of response generated by policy models by constructing automatically generated training data and a two-stage training paradigm.
Outcome:	The proposed verifier significantly improves in verification and reinforcement learning and alleviates data-demanding problems of the reward model.

Copied to clipboard

Zhong Zhang, Yaxi Lu, Yikun Fu, Yupeng Huo, Shenzhi Yang, Yesai Wu, Han Si, Xin Cong, Haotian Chen, Yankai Lin, Xie Xie, Wei Zhou, Wang Xu, Zhou Su, Zhongwu Zhai, Xiaoming Liu, null Meiyudong, Jianming Xu, Hongyan Tian, Chongyi Wang, Chi Chen, Yuan Yao, Zhiyuan Liu, Maosong Sun

Active Sentence Learning by Adversarial Uncertainty Sampling in Discrete Space (2020.findings-emnlp)

Challenge:	Large language model agents have enabled GUI-based automation, but their deployment is limited by noisy data, poor generalization, and lack of support for non-English GUIs.
Approach:	They propose an 8B-parameter GUI agent built for robust and efficient on-device GUI interaction.
Outcome:	The proposed GUI agent achieves promising performance on five public benchmarks and proposed Chinese benchmark CAGUI.

Copied to clipboard

Dongyu Ru, Jiangtao Feng, Lin Qiu, Hao Zhou, Mingxuan Wang, Weinan Zhang, Yong Yu, Lei Li

CTRLEval: An Unsupervised Reference-Free Metric for Evaluating Controlled Text Generation (2022.acl-long)

Challenge:	Existing uncertainty sampling methods are time-consuming and can't be executed frequently.
Approach:	They propose adversarial uncertainty sampling in discrete space to find informative unlabeled text samples for annotation using adversarials.
Outcome:	The proposed approach outperforms baselines on effectiveness on five datasets.

Copied to clipboard

Pei Ke, Hao Zhou, Yankai Lin, Peng Li, Jie Zhou, Xiaoyan Zhu, Minlie Huang

Low-Resource NLP

Challenge:	Existing reference-free metrics have obvious limitations for evaluating controlled text generation models.
Approach:	They propose an unsupervised reference-free metric which evaluates controlled text generation from different aspects by formulating each aspect into multiple text infilling tasks.
Outcome:	The proposed metric has higher correlations with human judgments while obtaining better generalization of evaluating generated texts from different models and with different qualities.

Turn Waste into Worth: Rectifying Top-k Router of MoE (2024.emnlp-main)

Copied to clipboard

Zhiyuan Zeng, Qipeng Guo, Zhaoye Fei, Zhangyue Yin, Yunhua Zhou, Linyang Li, Tianxiang Sun, Hang Yan, Dahua Lin, Xipeng Qiu

FedGUI: Benchmarking Federated GUI Agents across Heterogeneous Platforms, Devices, and Operating Systems (2026.findings-acl)

Challenge:	Top-k router suffers from redundancy computation and memory costs due to unbalanced routing . some experts are overflow, where exceeding tokens are dropped, while others are empty, which are padded with zeros, negatively impacting model performance.
Approach:	They propose a top-k router that is unbalanced and uses a multi-gPU system to handle dropped tokens and padding.
Outcome:	The proposed model surpasses the top-1 router by 4.7% in terms of performance . the top-k router suffers from redundancy computation and memory costs .

Copied to clipboard

WenHao Wang, Haoting Shi, Mengying Yuan, Yiquan Lin, Panrong Tong, Hanzhang Zhou, Guangyi Liu, Pengxiang Zhao, Yue Wang, Siheng Chen

ConsistentChat: Building Skeleton-Guided Consistent Multi-Turn Dialogues for Large Language Models from Scratch (2025.emnlp-main)

Challenge:	a lack of benchmarks capture real-world, cross-platform heterogeneity in GUI training . traditional methods to train GUI agents rely on centralized data collection and manual labeling .
Approach:	They propose a benchmark for developing and evaluating federated GUI agents across mobile, web and desktop platforms.
Outcome:	The proposed benchmarks show that cross-platform collaboration improves performance and identify platform and OS as the most influential factors.

Copied to clipboard

Jiawei Chen, Xinyan Guan, Qianhao Yuan, Mo Guozhao, Weixiang Zhou, Yaojie Lu, Hongyu Lin, Ben He, Le Sun, Xianpei Han

Controllable Preference Optimization: Toward Controllable Multi-Objective Alignment (2024.emnlp-main)

Challenge:	Existing instruction data synthesis methods focus on single-turn instructions and neglect cross-turn coherence, resulting in context drift and reduced task completion rates.
Approach:	They propose a framework that constrains multi-turn instruction synthesis by explicitly modeling human conversational intent.
Outcome:	The proposed framework outperforms existing models trained on single-turn and multi-turn instruction datasets.

Copied to clipboard

Yiju Guo, Ganqu Cui, Lifan Yuan, Ning Ding, Zexu Sun, Bowen Sun, Huimin Chen, Ruobing Xie, Jie Zhou, Yankai Lin, Zhiyuan Liu, Maosong Sun

Challenge:	Existing algorithms for achieving optimal alignment are mostly unidirectional . a recent study suggests that large language models can be ground with evident preferences .
Approach:	They propose to ground large language models with evident preferences . they propose to use controllable preference optimization to specify different objectives .
Outcome:	The proposed models can provide responses that match various preferences among the ”3H” desiderata.

PaD: Program-aided Distillation Can Teach Small Models Reasoning Better than Chain-of-thought Fine-tuning (2024.naacl-long)

Copied to clipboard

Xuekai Zhu, Biqing Qi, Kaiyan Zhang, Xinwei Long, Zhouhan Lin, Bowen Zhou

Multi-Programming Language Sandbox for LLMs (2025.acl-demo)

Challenge:	Large language models excel in various tasks, but their huge size and inaccessibility of parameters present challenges for practical deployment.
Approach:	They propose to use CoT data to distill task-specific ability from large language models to smaller models . they use reasoning programs to suppress errors in distilled data and improve distillation quality .
Outcome:	The proposed model outperforms LLMs on arithmetic reasoning, symbolic reasoning, and general ability.

Copied to clipboard

Shihan Dou, Jiazheng Zhang, Jianxiang Zang, Yunbo Tao, Weikang Zhou, Haoxiang Jia, Shichun Liu, Yuming Yang, Shenxi Wu, Zhiheng Xi, Muling Wu, Rui Zheng, Changze Lv, Limao Xiong, Shaoqing Zhang, Lin Zhang, Wenyu Zhan, Rongxiang Weng, Jingang Wang, Xunliang Cai, Yueming Wu, Ming Wen, Yixin Cao, Tao Gui, Xipeng Qiu, Qi Zhang, Xuanjing Huang

VIGIL: Defending LLM Agents Against Tool-Stream Injection via Verify-Before-Commit (2026.acl-long)

Challenge:	MPLSandbox is an out-of-the-box multi-programming language sandbox designed to provide unified and comprehensive feedback from compiler and analysis tools for Large Language Models (LLMs).
Approach:	They propose a multi-programming language sandbox that provides unified feedback from compilers and analysis tools for Large Language Models.
Outcome:	The proposed multi-language sandbox can provide comprehensive feedback from compilers and analysis tools for large language models (LLMs).

Copied to clipboard

Junda Lin, Zhaomeng Zhou, Zhi Zheng, Shuochen Liu, Tong Xu, Yong Chen, Enhong Chen

Coarse-to-fine Few-shot Learning for Named Entity Recognition (2023.findings-acl)

Challenge:	Existing defenses for indirect prompt injection are limited by static protection mechanisms . existing models prioritize injected rules due to strict alignment, whereas static protections sever the feedback loop required for adaptive reasoning.
Approach:	They propose a framework that shifts the paradigm from restrictive isolation to a verify-before-commit protocol.
Outcome:	The proposed framework outperforms state-of-the-art dynamic defenses by reducing the attack success rate by over 22% while more thandoubling utility under attack compared to static baselines.

Copied to clipboard

Ruotian Ma, Zhang Lin, Xuanting Chen, Xin Zhou, Junzhe Wang, Tao Gui, Qi Zhang, Xiang Gao, Yun Wen Chen

ProcessBench: Identifying Process Errors in Mathematical Reasoning (2025.acl-long)

Challenge:	Existing few-shot NER solutions do not consider sub-class discrimination and various granularity of new classes during coarse training.
Approach:	They propose a method that uses a cluster-based prototype loss to learn group-wise discriminative representations of coarse-grained classes and a mixture prototype loss for learning the representations.
Outcome:	The proposed method shows superior performance over baseline methods on in-domain and cross-domain settings with various target granularity.

Copied to clipboard

Chujie Zheng, Zhenru Zhang, Beichen Zhang, Runji Lin, Keming Lu, Bowen Yu, Dayiheng Liu, Jingren Zhou, Junyang Lin

RMTBench: Benchmarking LLMs Through Multi-Turn User-Centric Role-Playing (2025.findings-emnlp)

Challenge:	Existing models fail to generalize to more challenging math problems, authors say . existing benchmarks related to assessing language models' reasoning process are limited .
Approach:	They propose a tool to measure language models' ability to identify erroneous steps in reasoning . they use two types of models: process reward models and critic models .
Outcome:	The proposed model outperforms existing models in evaluating language models' reasoning process . the best open-source model has demonstrated the critique capability competitive with the proprietary model .

Copied to clipboard

Hao Xiang, Tianyi Tang, Yang Su, Bowen Yu, An Yang, Fei Huang, Yichang Zhang, Yaojie Lu, Hongyu Lin, Xianpei Han, Jingren Zhou, Junyang Lin, Le Sun

Merger-as-a-Stealer: Stealing Targeted PII from Aligned LLMs with Model Merging (2025.emnlp-main)

Challenge:	Existing benchmarks focus on character-centric approach and fail to reflect real-world applications.
Approach:	RMTBench is a user-centric bilingual role-playing benchmark featuring 80 diverse characters and over 8,000 dialogue rounds.
Outcome:	RMTBench features 80 diverse characters and over 8,000 dialogue rounds.

Copied to clipboard

Lin Lu, Zhigang Zuo, Ziji Sheng, Pan Zhou

QA-MoE: Towards a Continuous Reliability Spectrum with Quality-Aware Mixture of Experts for Robust Multimodal Sentiment Analysis (2026.acl-long)

Challenge:	Model merging is a promising approach for updating large language models . but unmonitored mergers can introduce significant security vulnerabilities .
Approach:	They propose a model merging attack surface where a malicious merger can extract PII from an aligned model with model merg.
Outcome:	The proposed framework can extract PII from an aligned model with model merging.

Copied to clipboard

Yitong Zhu, Yuxuan Jiang, Guanxuan Jiang, Bojing Hou, Peng Yuan Zhou, Ge Lin, Yuyang Wang

LongCLI-Bench: A Preliminary Benchmark and Study for Long-horizon Agentic Programming in Command-Line Interfaces (2026.findings-acl)

Challenge:	Existing models that use multimodal inputs are often noisy or incomplete.
Approach:	They propose a Quality-Aware Mixture-of-Experts framework that quantifies modality reliability via aleatoric uncertainty.
Outcome:	The proposed framework is competitive or state-of-the-art across diverse degradation scenarios and exhibits a promising One-Checkpoint-for-all property in practice.

Copied to clipboard

Yukang Feng, Jianwen Sun, Zelai Yang, Jiaxin Ai, Chuanhao Li, Zizhen Li, Fanrui Zhang, Kang He, Rui Ma, Jifan Lin, Jie Sun, Yang Xiao, Sizhuo Zhou, Wenxiao Wu, Yiming Liu, Pengfei Liu, Shenglin Zhang, Kaipeng Zhang

CrowdSelect: SyntheticInstruction Data Selection with Multi-LLM Wisdom (2026.findings-eacl)

Challenge:	Existing benchmarks for agentic programming in long-horizon command-line interface tasks are limited by short task horizons, data contamination from GitHub scraping, and a lack of fine-grained evaluation metrics.
Approach:	They propose a benchmark to evaluate agentic capabilities across long-horizon command-line interface tasks.
Outcome:	The proposed benchmarks cover four engineering categories: from scratch, feature addition, bug fixing, and refactoring.

Copied to clipboard

Yisen Li, Lingfeng Yang, Wenxuan Shen, Pan Zhou, Yao Wan, Weiwei Lin, Dongping Chen

Machine Translation

Challenge:	Existing methods for capturing instruction-following complexity rely on single-dimensional signals, but they fail to capture complexity across diverse fields.
Approach:	They propose three foundational metrics that leverage Multi-LLMs wisdom to capture instruction-response pair characteristics and propose CrowdSelect, an integrated metric incorporating a clustering-based approach to maintain response diversity.
Outcome:	The proposed metrics outperform existing models on MT-bench and Arena-hard and show improvements of 4.81% on full and LoRA fine-tuning.

RSA-Bench: Benchmarking Audio Large Models in Real-World Acoustic Scenarios (2026.findings-acl)

Copied to clipboard

Yibo Zhang, Kaiwen Luo, Liang Lin, Shilinlu Yan, Jin Wang, Yaoqi Guo, Yitian Chen, Yalan Qin, Zhenhong Zhou, Kun Wang, Li Sun

Transfer Learning for Context-Aware Question Matching in Information-seeking Conversations in E-commerce (P18-2)

Challenge:	Existing evaluations rely on synthetic Gaussian noise or simplistic single-source interference, failing to capture the intricate, multi-layered acoustic dynamics that characterize authentic physical environments.
Approach:	They propose a robustness benchmark to stress-test Audio Large Models (ALLMs) using high-fidelity auditory scene simulations.
Outcome:	The proposed model performs well on a wide range of tasks, including automatic speech recognition, speech translation, and audio-based reasoning.

Copied to clipboard

Minghui Qiu, Liu Yang, Feng Ji, Wei Zhou, Jun Huang, Haiqing Chen, Bruce Croft, Wei Lin

HammerBench: Fine-Grained Function-Calling Evaluation in Real Mobile Assistant Scenarios (2025.findings-acl)

Challenge:	Recent researches focus on deep learning and reinforcement learning for multi-turn information seeking conversation systems.
Approach:	They propose an efficient and effective multi-turn conversation model based on convolutional neural networks and extend it to adapt the knowledge learned from a resource-rich domain to enhance the performance.
Outcome:	The proposed model performs better than the existing model on an industrial chatbot called AliMe Assist.

Copied to clipboard

Jun Wang, Jiamu Zhou, Xihuai Wang, Xiaoyun Mo, Haoyu Zhang, Qiqiang Lin, Jincheng Jincheng, Muning Wen, Weinan Zhang, Qiuying Peng, Jun Wang

SERM: Self-Evolving Relevance Model with Agent-Driven Learning from Massive Query Streams (2026.findings-acl)

Challenge:	Evaluating the performance of LLMs in multi-turn interactions presents significant challenges due to the complexity and variability of user behavior.
Approach:	They propose a benchmark framework for assessing LLMs’ function-calling capabilities in multi-turn dialogues.
Outcome:	The proposed framework is based on a dataset derived from popular mobile apps and anonymized user logs.

Copied to clipboard

Chenglong Wang, Canjia Li, Xingzhao Zhu, Yifu Huo, Huiyu Wang, Weixiong Lin, Yun Yang, Qiaozhi He, Tian Hua Zhou, null Changxiaojia, JingBo Zhu, Tong Xiao

Challenge:	Existing approaches to generate relevance judgments are limited due to dynamic nature of query distributions.
Approach:	They propose a self-evolving relevance model approach to generalize queries to practical search scenarios . they use a multi-agent sample miner and a relevance annotator to generate reliable labels .
Outcome:	The proposed approach can achieve significant performance gains on a large-scale industrial platform, validated by offline multilingual evaluations and online testing.

Stochastic Bridges as Effective Regularizers for Parameter-Efficient Tuning (2023.findings-acl)

Copied to clipboard

Weize Chen, Xu Han, Yankai Lin, Zhiyuan Liu, Maosong Sun, Jie Zhou

Empathetic Dialogue Generation via Sensitive Emotion Recognition and Sensible Knowledge Selection (2022.findings-emnlp)

Challenge:	Existing methods for tuning pre-trained language models ignore the running cost and only optimize the terminal cost.
Approach:	They propose to use stochastic bridges to regularize intermediate states and use regularization as running cost of PETs.
Outcome:	The proposed methods can be used to tune large pre-trained language models . they can be compared to full-parameter fine-tuning by tuning a small number of parameters .

Copied to clipboard

Lanrui Wang, Jiangnan Li, Zheng Lin, Fandong Meng, Chenxu Yang, Weiping Wang, Jie Zhou

ORANGE: Text-video Retrieval via Watch-time-aware Heterogeneous Graph Contrastive Learning (2023.emnlp-industry)

Challenge:	Empathy is a key trait of everyday human conversations.
Approach:	They propose a serial encoding and Emotion-Knowledge interaction method for empathetic dialogue generation which is more sensitive to emotion dynamics in conversations.
Outcome:	The proposed method outperforms baseline evaluations on the utterance-level annotated EMPATHETICDIALOGUES.

Copied to clipboard

Yucheng Lin, Tim Chang, Yaning Chang, Jianqiang Ma, Donghui Li, Ting Peng, Zang Li, Zhiyi Zhou, Feng Wang

GAPO: Robust Advantage Estimation for Real-World Code LLMs (2026.findings-acl)

Challenge:	Existing methods for text-video retrieval focus on informative representations and delicate matching mechanisms, but real-world scenarios often involve brief, ambiguous queries and low-quality videos.
Approach:	They propose a novel method to learn informative embeddings for queries and videos . they use a watch-time-aware contrastive learning paradigm to capture dependencies .
Outcome:	The proposed method is effective in a real-world video-search service.

Copied to clipboard

Jianqing Zhang, Zhezheng Hao, Wei Xia, Hande Dong, Hong Wang, Chenxing Wei, Yuyan Zhou, Yubin Qi, Qiang Lin, Jian Cao

Disentangle-based Continual Graph Representation Learning (2020.emnlp-main)

Challenge:	Reinforcement learning (RL) is widely used for post-training large language models (LLMs) in code editing, but in real-world code editing scenarios, reward distributions are often skewed with unpredictable noise, leading to distorted advantage computation and increased rollout outliers.
Approach:	They propose a group-relative method that finds an interval with the highest SNR and uses the median of that interval as an adaptive Q to replace the group mean in advantage calculation.
Outcome:	The proposed method improves on nine instruction-tuned LLMs while remaining plug-and-play and efficient.

Copied to clipboard

Xiaoyu Kou, Yankai Lin, Shaobo Liu, Peng Li, Jie Zhou, Yan Zhang

RESIN: A Dockerized Schema-Guided Cross-document Cross-lingual Cross-media Information Extraction and Event Tracking System (2021.naacl-demos)

Challenge:	Existing graph embedding methods overlook streaming nature of incoming data in real-world applications.
Approach:	They propose a disentangle-based continual graph representation learning framework inspired by the human’s ability to learn procedural knowledge.
Outcome:	The proposed framework outperforms state-of-the-art continual graph representation learning framework and alleviate catastrophic forgetting problem.

Copied to clipboard

Haoyang Wen, Ying Lin, Tuan Lai, Xiaoman Pan, Sha Li, Xudong Lin, Ben Zhou, Manling Li, Haoyu Wang, Hongming Zhang, Xiaodong Yu, Alexander Dong, Zhenhailong Wang, Yi Fung, Piyush Mishra, Qing Lyu, Dídac Surís, Brian Chen, Susan Windisch Brown, Martha Palmer, Chris Callison-Burch, Carl Vondrick, Jiawei Han, Dan Roth, Shih-Fu Chang, Heng Ji

AED-RAG: Continuous Multi-Granular Context Fusion for Retrieval-Augmented Generation via Adaptive Ensemble Decoding (2026.findings-acl)

Challenge:	We present a new information extraction system that can construct temporal event graphs from news documents.
Approach:	They propose a temporal event graph extraction system that can extract news documents . they extend the system from sentence-level event extraction to cross-document cross-media event extraction .
Outcome:	The proposed system can extract temporal event graphs from news documents in multiple languages and multiple data modalities.

Copied to clipboard

Junzhe Zhou, Fulin Lin, Tairan Cheng, Shaowen Chen, Hongwei Wang

Emergent Modularity in Pre-trained Transformers (2023.findings-acl)

Challenge:	Existing alignment strategies that rely on discrete reranking struggle to address this granularity mismatch or effectively balance external evidence with internal knowledge.
Approach:	They propose a framework that synergizes discrete retrieval with continuous reranking to discern the information density differences between unstructured narrative passages and structured knowledge triplets.
Outcome:	Extensive experiments on four open-domain QA benchmarks show that AED-RAG significantly outperforms competitive baselines.

Copied to clipboard

Zhengyan Zhang, Zhiyuan Zeng, Yankai Lin, Chaojun Xiao, Xiaozhi Wang, Xu Han, Zhiyuan Liu, Ruobing Xie, Maosong Sun, Jie Zhou

RAM-SD: Retrieval-Augmented Multi-agent framework for Sarcasm Detection (2026.acl-long)

Challenge:	Existing studies on pre-trained Transformers show that they learn fine-grained neuron functions.
Approach:	They examine the presence of modularity in pre-trained Transformers . they focus on Mixture-of-Experts, a promising candidate for modularity .
Outcome:	The proposed structure stabilizes at the early stage, which is faster than neuron stabilization.

Copied to clipboard

Ziyang Zhou, Ziqi Liu, Yan Wang, Yiming Lin, Yangbin Chen

ICLEval: Evaluating In-Context Learning Ability of Large Language Models (2025.coling-main)

Challenge:	Existing approaches to sarcastic detection use a uniform reasoning strategy . existing approaches lack a framework to deal with the diverse analytical demands of sarcasm .
Approach:	They propose a Retrieval-Augmented Multi-Agent framework for Sarcasm Detection . the framework provides transparent and interpretable reasoning traces .
Outcome:	The proposed framework outperforms existing methods on four benchmarks and outperformed the strong GPT-4o+CoC baseline.

Copied to clipboard

Wentong Chen, Yankai Lin, ZhenHao Zhou, HongYun Huang, YanTao Jia, Zhao Cao, Ji-Rong Wen

RESIN-11: Schema-guided Event Prediction for 11 Newsworthy Scenarios (2022.naacl-demo)

Challenge:	Existing evaluation frameworks focus on language abilities and knowledge, often overlooking the assessment of ICL ability.
Approach:	They propose to evaluate the ICL ability of Large Language Models (LLMs) using the ICLEval benchmark.
Outcome:	The proposed benchmark demonstrates that ICL ability is universally present in different LLMs and model size is not the sole determinant of ICL efficacy.

Copied to clipboard

Xinya Du, Zixuan Zhang, Sha Li, Pengfei Yu, Hongwei Wang, Tuan Lai, Xudong Lin, Ziqi Wang, Iris Liu, Ben Zhou, Haoyang Wen, Manling Li, Darryl Hannan, Jie Lei, Hyounghun Kim, Rotem Dror, Haoyu Wang, Michael Regan, Qi Zeng, Qing Lyu, Charles Yu, Carl Edwards, Xiaomeng Jin, Yizhu Jiao, Ghazaleh Kazeminejad, Zhenhailong Wang, Chris Callison-Burch, Mohit Bansal, Carl Vondrick, Jiawei Han, Dan Roth, Shih-Fu Chang, Martha Palmer, Heng Ji

Beyond Full Fine-tuning: Harnessing the Power of LoRA for Multi-Task Instruction Tuning (2024.lrec-main)

Challenge:	Existing methods for event prediction are incomplete and noisy.
Approach:	They propose to use news-related event schemas to extract newsworthy events . they build a demo website and include a video demonstrating the framework .
Outcome:	The proposed framework can be applied to a wide variety of newsworthy scenarios.

Copied to clipboard

Chunlei Xin, Yaojie Lu, Hongyu Lin, Shuheng Zhou, Huijia Zhu, Weiqiang Wang, Zhongyi Liu, Xianpei Han, Le Sun

HyperHatePrompt: A Hypergraph-based Prompting Fusion Model for Multimodal Hate Detection (2025.coling-main)

Challenge:	Low-Rank Adaptation (LoRA) is a parameter-efficient fine-tuning algorithm for large-scale language models.
Approach:	They conduct a systematic study of Low-Rank Adaptation (LoRA) on diverse tasks and rich resources with different learning capacities.
Outcome:	The proposed algorithm can achieve remarkable performance in high-resource and multi-task scenarios, even comparable to full fine-tuning.

Copied to clipboard

Bo Xu, Erchen Yu, Jiahui Zhou, Hongfei Lin, Linlin Zong

Leveraging Slot Descriptions for Zero-Shot Cross-Domain Dialogue StateTracking (2021.naacl-main)

Challenge:	Existing models for multimodal hate detection lack implicit hateful cues, cross-modal-induced hate, and diversity of hate target groups.
Approach:	They propose a hypergraph-based prompting fusion model that uses LLMs to generate hate cue prompts and hypergraph learning to merge multimodal hate features.
Outcome:	The proposed model outperforms state-of-the-art models on two benchmark datasets showing that it can detect hate content across multiple modalities.

Copied to clipboard

Zhaojiang Lin, Bing Liu, Seungwhan Moon, Paul Crook, Zhenpeng Zhou, Zhiguang Wang, Zhou Yu, Andrea Madotto, Eunjoon Cho, Rajen Subba

Demons in the Detail: On Implementing Load Balancing Loss for Training Specialized Mixture-of-Expert Models (2025.acl-long)

Challenge:	Existing models for zero-shot cross-domain dialogue state tracking require in-domain data to model a new domain.
Approach:	They propose a slot descriptions enhanced generative approach for zero-shot cross-domain DST by encoding a dialogue context and a slots with a pre-trained encoder and generating slot value in auto-regressive manner.
Outcome:	The proposed model significantly improves state-of-the-art results in zero-shot cross-domain setting.

Copied to clipboard

Zihan Qiu, Zeyu Huang, Bo Zheng, Kaiyue Wen, Zekun Wang, Rui Men, Ivan Titov, Dayiheng Liu, Jingren Zhou, Junyang Lin

Using Intermediate Representations to Solve Math Word Problems (P18-1)

Challenge:	Existing Mixture-of-Experts training frameworks use a micro-batch to calculate LBL . micro-batches are restricted to a single sequence, preventing expert specialization .
Approach:	They propose to use a global-batch to loosen the load balance constraint for MoEs models . they propose to synchronize fi across micro-batches and then use it to calculate the LBL .
Outcome:	The proposed global-batch LBL improves the domain specialization of experts . the micro-battery LBL is almost at the sequence level, and the router is pushed to distribute the token evenly .

Copied to clipboard

Danqing Huang, Jin-Ge Yao, Chin-Yew Lin, Qingyu Zhou, Jian Yin

Numerical Reasoning

Challenge:	Existing approaches to solving math word problems do not include higher-order operations that cannot be explicitly represented in equations.
Approach:	They propose an iterative labeling framework that generates intermediate forms and executes them to obtain the final answers.
Outcome:	The proposed model outperforms existing models in solving math word problems.

X-LeBench: A Benchmark for Extremely Long Egocentric Video Understanding (2025.findings-emnlp)

Copied to clipboard

Wenqi Zhou, Kai Cao, Hao Zheng, Yunze Liu, Xinyi Zheng, Miao Liu, Per Ola Kristensson, Walterio W. Mayol-Cuevas, Fan Zhang, Weizhe Lin, Junxiao Shen

CLEVE: Contrastive Pre-training for Event Extraction (2021.acl-long)

Challenge:	Existing benchmark datasets focus on short to moderately long videos, leaving a substantial gap in evaluating extensive, ultra-long egocentric video recordings.
Approach:	X-LeBench is a benchmark dataset designed to evaluate long egocentric video recordings . it uses a life-logging pipeline to produce realistic, coherent daily plans .
Outcome:	X-LeBench is a new benchmark dataset designed to evaluate long-form egocentric video understanding . the approach produces realistic, coherent daily plans aligned with real-world video data .

Copied to clipboard

Ziqi Wang, Xiaozhi Wang, Xu Han, Yankai Lin, Lei Hou, Zhiyuan Liu, Peng Li, Juanzi Li, Jie Zhou

SEE: Signal Embedding Energy for Quantifying Noise Interference in Large Audio Language Models (2026.acl-long)

Challenge:	Existing EE methods do not model event characteristics from large unsupervised data.
Approach:	They propose a contrastive pre-training framework for event extraction to better learn event knowledge from large unsupervised data and their semantic structures.
Outcome:	The proposed framework improves on ACE 2005 and MAVEN datasets on event extraction tasks.

Copied to clipboard

Yuanhe Zhang, Jiayu Tian, Yibo Zhang, Shilinlu Yan, Liang Lin, Zhenhong Zhou, Li Sun, Sen Su

CIF-Bench: A Chinese Instruction-Following Benchmark for Evaluating the Generalizability of Large Language Models (2024.findings-acl)

Challenge:	Existing studies on noise lack quantitative analysis and rely on intuition and empirical observation, thus failing to understand practical robustness.
Approach:	They propose a method for quantifying the impact of noise intensity on LALM inputs by using a structured activation subspace derived from the model's internal representations.
Outcome:	The proposed method outperforms existing denoising methods and demonstrates that noise is perceived more accurately than raw audio features.

Copied to clipboard

Yizhi Li, Ge Zhang, Xingwei Qu, Jiali Li, Zhaoqun Li, Noah Wang, Hao Li, Ruibin Yuan, Yinghao Ma, Kai Zhang, Wangchunshu Zhou, Yiming Liang, Lei Zhang, Lei Ma, Jiajun Zhang, Zuowen Li, Wenhao Huang, Chenghua Lin, Jie Fu

SwarmAgentic: Towards Fully Automated Agentic System Generation via Swarm Intelligence (2025.emnlp-main)

Challenge:	a recent study shows that large language models have limited generalization in low-resource languages like Chinese.
Approach:	They propose to evaluate the zero-shot generalizability of large language models to the Chinese language . they release only half of the dataset publicly, with the remainder kept private .
Outcome:	The Chinese Instruction-Following Benchmark evaluates the generalizability of LLMs to the Chinese language.

Copied to clipboard

Yao Zhang, Chenyang Lin, Shijie Tang, Haokun Chen, Shijie Zhou, Yunpu Ma, Volker Tresp

Challenge:	Existing agentic system generation frameworks lack autonomy, autonomy, and functionality . current frameworks are too rigid, limiting adaptability and scalability.
Approach:	They propose a framework that fully automates agentic system generation, optimization, and collaboration . they construct agents from scratch and jointly refine functionality and coordination .
Outcome:	The proposed framework outperforms ADAS on six real-world, open-ended, and exploratory tasks on the TravelPlanner benchmark.

Code Generation From Flowcharts with Texts: A Benchmark Dataset and An Approach (2022.findings-emnlp)

Copied to clipboard

Zejie Liu, Xiaoyu Hu, Deyu Zhou, Lin Li, Xu Zhang, Yanzheng Xiang

UICOMPASS: UI Map Guided Mobile Task Automation via Adaptive Action Generation (2025.emnlp-main)

Challenge:	Currently, researchers focus on generating codes from requirement documents.
Approach:	They propose to generate source code from flowcharts with texts instead of directly translating requirements into codes.
Outcome:	The proposed model improves on the baselines by transforming flowcharts into pseudo-code . the proposed model is based on 320 flowchartes with their corresponding source codes .

Copied to clipboard

Yuanzhang Lin, Zhe Zhang, He Rui, Qingao Dong, Mingyi Zhou, Jing Zhang, Xiang Gao, Hailong Sun

Challenge:	Mobile task automation is an emerging technology that leverages AI to automatically execute routine tasks by users’ commands on mobile devices like Android.
Approach:	They propose a UI Map-guided LLM-based approach to automate mobile tasks using static analysis and LLMs.
Outcome:	The proposed approach achieves a 15.87% higher task execution success rate than SOTA approaches even when only APK is available.

Regularized Attentive Capsule Network for Overlapped Relation Extraction (2020.coling-main)

Copied to clipboard

Tianyi Liu, Xiangyu Lin, Weijia Jia, Mingliang Zhou, Wei Zhao

Layer-Level Self-Exposure and Patch: Affirmative Token Mitigation for Jailbreak Attack Defense (2025.naacl-long)

Challenge:	Existing methods to extract relations from distant supervision contain low-quality instances with noisy words and overlapped relations.
Approach:	They propose a Regularized Attentive Capsule Network to better identify overlapped relations in informal sentences . they embed multi-head attention into the capsule network as the low-level capsules .
Outcome:	Extensive experiments show that the proposed model improves relation extraction.

Copied to clipboard

Yang Ouyang, Hengrui Gu, Shuhang Lin, Wenyue Hua, Jie Peng, Bhavya Kailkhura, Meijun Gao, Tianlong Chen, Kaixiong Zhou

Sailor: Open Language Models for South-East Asia (2024.emnlp-demo)

Challenge:	Existing methods to defend against jailbreak attacks exploit vulnerabilities to elicit unintended or harmful outputs.
Approach:	They propose a method to defend against jailbreak attacks by patching specific layers within large language models through self-augmented datasets.
Outcome:	The proposed approach reduces harmfulness and attack success rate of jailbreak attacks without compromising utility for benign queries compared to previous methods.

Copied to clipboard

Longxu Dou, Qian Liu, Guangtao Zeng, Jia Guo, Jiahui Zhou, Xin Mao, Ziqi Jin, Wei Lu, Min Lin

Unsupervised Graph-Text Mutual Conversion with a Unified Pretrained Language Model (2023.acl-long)

Challenge:	Large language models (LLMs) rely on English data for training, but are often not comparable across other languages.
Approach:	They propose to develop a family of open language models for SEA languages . they use BPE dropout, aggressive data cleaning and deduplication to improve model robustness .
Outcome:	The proposed models perform well across four benchmarks, including commonsense reasoning, question answering, reading comprehension and examination.

Copied to clipboard

Yi Xu, Shuqian Sheng, Jiexing Qi, Luoyi Fu, Zhouhan Lin, Xinbing Wang, Chenghu Zhou

Low-Resource NLP

Challenge:	Existing unsupervised approaches for learning knowledge graphs require multiple modules and require entity information or relation type for training.
Approach:	They propose a method that uses a unified pretrained language model to achieve fully unsupervised graph-text mutual conversion for the first time.
Outcome:	The proposed method outperforms state-of-the-art methods for G2T and T2G tasks by fine-tuning only one pretrained model.

Dynamic Model-Bank Test-Time Adaptation for Automatic Speech Recognition (2025.emnlp-main)

Copied to clipboard

Yanshuo Wang, Yanghao Zhou, Yukang Lin, Haoxing Chen, Jin Zhang, Wentao Zhu, Jie Hong, Xuesong Li

Reduce Redundancy Then Rerank: Enhancing Code Summarization with a Novel Pipeline Framework (2024.lrec-main)

Challenge:	Existing ASR TTA methods struggle with instability under continual and long-term distribution shifts.
Approach:	They propose a continuous adaptive model-bank framework that adapts to domain shifts in ASR test-time scenarios.
Outcome:	Experiments on diverse, continuously shifting ASR benchmarks show that DMSUTA outperforms existing continual TTA baselines.

Copied to clipboard

Xiaoyu Hu, Xu Zhang, Zexu Lin, Deyu Zhou

Text Generation

Challenge:	Existing code summarization models lack redundant tokens and are plagued by exposure bias.
Approach:	They propose a pipeline framework to reduce redundancy then rerank that eliminates redundant information in code representation space and a re-ranking model to select more suitable summary candidates.
Outcome:	The proposed framework overrides state-of-the-art approaches on six datasets from the CodeSearchNet benchmark.

P-MMEval: A Parallel Multilingual Multitask Benchmark for Consistent Evaluation of LLMs (2025.emnlp-main)

Copied to clipboard

Yidan Zhang, Yu Wan, Boyi Deng, Baosong Yang, Hao-Ran Wei, Fei Huang, Bowen Yu, Dayiheng Liu, Junyang Lin, Fei Huang, Jingren Zhou

Distilling Rule-based Knowledge into Large Language Models (2025.coling-main)

Challenge:	Recent advances in large language models showcase varied multilingual capabilities across tasks . previous assessments focused on fundamental natural language processing (NLP) or isolated capability-specific tasks.
Approach:	They propose a multilingual multitask benchmark to assess multilingual capabilities . they use a large-scale benchmark covering fundamental and capability-specialized datasets .
Outcome:	The proposed benchmark compares models and tasks across languages and tasks and examines knowledge transfer from English to other languages.

Copied to clipboard

Wenkai Yang, Yankai Lin, Jie Zhou, Ji-Rong Wen

DimABSA: Building Multilingual and Multidomain Datasets for Dimensional Aspect-Based Sentiment Analysis (2026.acl-long)

Challenge:	Recent advances in large language models have broadened their applicability across diverse realworld scenarios.
Approach:	They propose to encode rule-based knowledge into large language models by using strong in-context abilities to extract the knowledge from the textual rules and then explicitly encode it into the parameters of LLMs.
Outcome:	The proposed learning paradigm is much more efficient than example-based learning in both sample size and generalization ability.

Copied to clipboard

Lung-Hao Lee, Liang-Chih Yu, Natalia V Loukachevitch, Ilseyar Alimova, Alexander Panchenko, Tzu-Mi Lin, Zhe-Yu Xu, Jian-Yu Zhou, Guangmin Zheng, Jin Wang, Sharanya Awasthi, Jonas Becker, Jan Philip Wahle, Terry Ruas, Shamsuddeen Hassan Muhammad, Saif M. Mohammad

Sentiment Analysis

Challenge:	Existing ABSA research relies on coarse-grained categorical labels, which limits its ability to capture nuanced affective states.
Approach:	They propose a dimensional approach that represents sentiment with continuous valence–arousal (VA) scores, enabling fine-grained analysis at both the aspect and sentiment levels.
Outcome:	The proposed approach represents sentiment with continuous valence–arousal (VA) scores, enabling fine-grained analysis at both the aspect and sentiment levels.

MAVEN-ERE: A Unified Large-scale Dataset for Event Coreference, Temporal, Causal, and Subevent Relation Extraction (2022.emnlp-main)

Copied to clipboard

Xiaozhi Wang, Yulin Chen, Ning Ding, Hao Peng, Zimu Wang, Yankai Lin, Xu Han, Lei Hou, Juanzi Li, Zhiyuan Liu, Peng Li, Jie Zhou

Pre-training Multilingual Neural Machine Translation by Leveraging Alignment Information (2020.emnlp-main)

Challenge:	Existing datasets only cover limited relation types at once, which prevents models from taking full advantage of relation interactions.
Approach:	They construct a large-scale human-annotated ERE dataset with improved annotation schemes to address these drawbacks.
Outcome:	The proposed dataset is larger than existing datasets of all the ERE tasks by at least an order of magnitude.

Copied to clipboard

Zehui Lin, Xiao Pan, Mingxuan Wang, Xipeng Qiu, Jiangtao Feng, Hao Zhou, Lei Li

MoEfication: Transformer Feed-forward Layers are Mixtures of Experts (2022.findings-acl)

Challenge:	Existing pre-training methods are not effective for machine translation tasks.
Approach:	They propose a method to pre-train a universal multilingual neural machine translation model . they use random aligned substitution technique to bring words and phrases with similar meanings closer in the representation space.
Outcome:	The proposed approach improves translation quality on low, medium, rich resource languages.

Copied to clipboard

Zhengyan Zhang, Yankai Lin, Zhiyuan Liu, Peng Li, Maosong Sun, Jie Zhou

AutoEvolve: Automatically Evolving Queries for Applicable and Scalable Retrieval-Augmented Generation Benchmarking (2025.findings-emnlp)

Challenge:	Recent work has shown that feed-forward networks (FFNs) in pre-trained Transformers are a key component, storing various linguistic and factual knowledge.
Approach:	They propose to convert a model into its MoE version with the same parameters and build expert routers to decide which experts will be used for each input.
Outcome:	The proposed model can use 10% to 30% of FFN parameters while maintaining over 95% original performance.

Copied to clipboard

Ding-Chu Zhang, Xiaowen Zhang, Yue Fei, Renjun Hu, Xiao-Wen Yang, Zhi Zhou, Baixuan Li, Yu-Feng Li, Xing Shi, Wei Lin

MathBench: Evaluating the Theory and Application Proficiency of LLMs with a Hierarchical Mathematics Benchmark (2024.findings-acl)

Challenge:	Existing automated generation methods exhibit Weak Applicability and Weak Scalability . existing methods are limited by their reliance on metadata from specific corpora .
Approach:	They propose an approach to generate scalable RAG benchmarks using corpus-agnostic methods . they propose a difficulty-guided metric that directs query evolution process .
Outcome:	The proposed approach evolves queries significantly more challenging than existing methods . it is able to dynamically increase difficulty, limiting scalability of the query .

Copied to clipboard

Hongwei Liu, Zilong Zheng, Yuxuan Qiao, Haodong Duan, Zhiwei Fei, Fengzhe Zhou, Wenwei Zhang, Songyang Zhang, Dahua Lin, Kai Chen

Numerical Reasoning

Challenge:	Recent advances in large language models have showcased significant improvements in mathematics, but traditional benchmarks like GSM8k offer a unidimensional perspective.
Approach:	MathBench is a benchmark that rigorously assesses the mathematical capabilities of large language models.
Outcome:	MathBench spans a wide range of mathematical disciplines, offering a detailed evaluation of both theoretical understanding and practical problem-solving skills.

ChatMusician: Understanding and Generating Music Intrinsically with LLM (2024.findings-acl)

Copied to clipboard

Ruibin Yuan, Hanfeng Lin, Yi Wang, Zeyue Tian, Shangda Wu, Tianhao Shen, Ge Zhang, Yuhang Wu, Cong Liu, Ziya Zhou, Liumeng Xue, Ziyang Ma, Qin Liu, Tianyu Zheng, Yizhi Li, Yinghao Ma, Yiming Liang, Xiaowei Chi, Ruibo Liu, Zili Wang, Chenghua Lin, Qifeng Liu, Tao Jiang, Wenhao Huang, Wenhu Chen, Jie Fu, Emmanouil Benetos, Gus Xia, Roger Dannenberg, Wei Xue, Shiyin Kang, Yike Guo

Beyond Static Artifacts: An Evolutionary Framework for Synthetic Claim Generation (2026.acl-long)

Challenge:	Despite LLMs' impressive capabilities in musical knowledge, music reasoning remains an unsolved task.
Approach:	They propose an open-source large language model (LLM) that integrates intrinsic musical abilities into LLaMA2 and GPT-3.5.
Outcome:	The proposed model can understand and generate music with a pure text tokenizer without external multi-modal neural structures or tokenizers.

Copied to clipboard

Yeqing Teng, Jiasheng Si, Shuxia Lin, Linhai Zhang, Weiyu Zhang, Wenpeng Lu, Deyu Zhou, Xiaoming Wu

Challenge:	Existing claim detection benchmarks treat claims as static textual artifacts . current research ignores sociological etiology of how information naturally emerges and mutates .
Approach:	They propose a socially generative framework for synthetic claim generation . they propose utterance, proposition and context-based simulations to capture truth decay .
Outcome:	The proposed paradigm models claims as socially evolving entities . it allows precise simulation of truth decay and intervened propagation with multi-auditor oversight .

WebUIBench: A Comprehensive Benchmark for Evaluating Multimodal Large Language Models in WebUI-to-Code (2025.findings-acl)

Copied to clipboard

Zhiyu Lin, Zhengda Zhou, Zhiyuan Zhao, Tianrui Wan, Yilun Ma, Junyu Gao, Xuelong Li

Cogito: A Cognitive Agentic Framework Driven by Dynamic Graph of Thoughts for Financial Report Generation (2026.findings-acl)

Challenge:	Existing benchmarks for large language models focus on webpage generation outcomes.
Approach:	They propose a multi-view evaluation framework to evaluate MLLMs in four key areas: WebUI Perception, HTML Programming, WebUI-HTML Understanding, and WebUI to code.
Outcome:	The proposed framework evaluates MLLMs in four key areas: WebUI Perception, HTML Programming, WebUI-HTML Understanding, and WebUI to code.

Copied to clipboard

Chen Lifan, Wei Ding, Jingwen Yang, Xiuze Zhou, Jingan Chen, Fan Lin

The Lessons of Developing Process Reward Models in Mathematical Reasoning (2025.findings-acl)

Challenge:	Existing approaches to financial report generation are insufficient to handle dynamic uncertainties of real-world financial environments.
Approach:	They propose a cognitively grounded agentic framework for professional financial report generation that is driven by Dynamic Graph of Thoughts and a social collaboration mechanism to facilitate coordinated agent interaction.
Outcome:	The proposed framework is based on a dynamic reasoning model and social collaboration mechanism.

Copied to clipboard

Zhenru Zhang, Chujie Zheng, Yangzhen Wu, Beichen Zhang, Runji Lin, Bowen Yu, Dayiheng Liu, Jingren Zhou, Junyang Lin

Sketch and Refine: Towards Faithful and Informative Table-to-Text Generation (2021.findings-acl)

Challenge:	a recent study shows that process reward models can make mistakes, leading to wrong conclusions.
Approach:	They propose a consensus filtering mechanism that integrates MC estimation with LLM-as-a-judge to improve model performance and data efficiency.
Outcome:	The proposed model outperforms existing open-source alternatives and provides practical guidelines for future research.

Copied to clipboard

Peng Wang, Junyang Lin, An Yang, Chang Zhou, Yichang Zhang, Jingren Zhou, Hongxia Yang

Structured Data in NLP

Challenge:	Existing methods for table-to-text generation suffer from poor faithfulness and low coverage.
Approach:	They propose a method that combines Autoregressive and Non-Autoregressive generation to generate a table-to-text from a key-value table using a skeleton and an edit-based non-autoregressively generation model.
Outcome:	The proposed method outperforms the existing methods on WikiPerson and WikiBio datasets on coverage and faithfulness.

Stable Language Guidance for Vision–Language–Action Models (2026.acl-long)

Copied to clipboard

Zhihao Zhan, Yuhao Chen, Jiaying Zhou, Qinhan Lyu, Hao Liu, Keze Wang, Liang Lin, Guangrun Wang

AntCritic: Argument Mining for Free-Form and Visually-Rich Financial Comments (2024.lrec-main)

Challenge:	Existing vision-Language-Action models are notoriously brittle to linguistic perturbations.
Approach:	They propose a probabilistic framework that disentangles physical affordance from semantic execution.
Outcome:	The proposed framework disentangles physical affordance from semantic execution.

Copied to clipboard

Huadai Liu, Xu Wenqiang, Xuan Lin, Jingjing Huo, Hong Chen, Zhou Zhao

RED: Unleashing Token-Level Rewards from Holistic Feedback via Reward Redistribution (2025.emnlp-main)

Challenge:	Argument mining is a thriving task in natural language processing, but its generalization is limited by existing datasets.
Approach:	They propose to use a dataset to help model argument mining . the dataset AntCritic supports both argument component detection and argument relation prediction tasks.
Outcome:	The proposed model can detect arguments and identify their relationships automatically.

Copied to clipboard

Jiahui Li, Lin Li, Tai-Wei Chang, Kun Kuang, Long Chen, Jun Zhou, Cheng Yang

Negative-Aware Diffusion Process for Temporal Knowledge Graph Extrapolation (2026.findings-eacl)

Challenge:	Experimental results demonstrate the superiority of our approach to aligning large language models with human preferences.
Approach:	They propose a method that evaluates and assigns specific credit to each token using an off-the-shelf reward model.
Outcome:	The proposed method evaluates and assigns specific credit to each token using an off-the-shelf reward model.

Copied to clipboard

Yanglei Gan, Peng He, Yuxiang Cai, Run Lin, Guanyu Zhou, Qiao Liu

An Effective Deployment of Contrastive Learning in Multi-label Text Classification (2023.findings-acl)

Challenge:	Temporal Knowledge Graphs (TKGs) are dynamic structures representing entities and their evolving relationships through time.
Approach:	They propose a non-parametric model that encodes subject-centric histories into sequential embeddings.
Outcome:	The proposed model encodes subject-centric histories of entities, relations and temporal intervals into sequential embeddings.

Copied to clipboard

Nankai Lin, Guanqiu Qin, Gang Wang, Dong Zhou, Aimin Yang

Synthesizing Text-to-SQL Data from Weak and Strong LLMs (2024.acl-long)

Challenge:	Existing studies on contrastive learning in natural language processing tasks have not explored the effectiveness of the technology.
Approach:	They propose five novel contrastive losses for multi-label text classification tasks that exploit the complexity of the input logic and the semantic representation space.
Outcome:	The proposed contrastive losses improve multi-label text classification tasks and can be adapted for multi-task tasks.

Copied to clipboard

Jiaxi Yang, Binyuan Hui, Min Yang, Jian Yang, Junyang Lin, Chang Zhou

XMC-Agent : Dynamic Navigation over Scalable Hierarchical Index for Incremental Extreme Multi-label Classification (2024.findings-acl)

Challenge:	a capability gap exists between open-source and closed-source large language models (LLMs) . the adoption of closed-sourced LLMs introduces concerns pertaining to openness, privacy, and substantial costs.
Approach:	They propose a synthetic data approach that combines strong and weak models for error information . they demonstrate the effectiveness of SENSE, a specialized text-to-SQL model .
Outcome:	The proposed method enhances the domain generalization of text-to-SQL models and explores the potential of error data supervision through preference learning.

Copied to clipboard

Yanjiang Liu, Tianyun Zhong, Yaojie Lu, Hongyu Lin, Ben He, Shuheng Zhou, Huijia Zhu, Weiqiang Wang, Zhongyi Liu, Xianpei Han, Le Sun

On Transferability of Prompt Tuning for Natural Language Processing (2022.naacl-main)

Challenge:	Existing methods for XMC struggle with the growing set of labels due to their static label assumptions, and embedding-based methods struggle with complex mapping relationships due to late interaction paradigm.
Approach:	They propose a large language model (LLM) powered agent framework for extreme multi-label classification, XMC-Agent, which can effectively learn, manage and predict the extremely large and dynamically increasing set of labels.
Outcome:	The proposed framework can learn, manage and predict the extremely large and dynamically growing set of labels and achieves state-of-the-art performance on three standard datasets.

Copied to clipboard

Yusheng Su, Xiaozhi Wang, Yujia Qin, Chi-Min Chan, Yankai Lin, Huadong Wang, Kaiyue Wen, Zhiyuan Liu, Peng Li, Juanzi Li, Lei Hou, Maosong Sun, Jie Zhou

Does Acceleration Cause Hidden Instability in Vision Language Models? Uncovering Instance-Level Divergence Through a Large-Scale Empirical Study (2025.emnlp-main)

Challenge:	Pre-trained language models (PLMs) can achieve comparable performance to full-parameter fine-tuning by tuning a few soft prompts, but require much more training time than fine-timing.
Approach:	They empirically investigate the transferability of soft prompts across different downstream tasks and PLMs to determine what decides prompt transferability.
Outcome:	The proposed method can achieve comparable performance to full-parameter fine-tuning by tuning a few soft prompts, but requires much more training time than fine-timing.

Copied to clipboard

Yizheng Sun, Hao Li, Chang Xu, Hongpeng Zhou, Chenghua Lin, Riza Batista-Navarro, Jingyuan Sun

Plug-and-Play Knowledge Injection for Pre-trained Language Models (2023.acl-long)

Challenge:	Current acceleration evaluations focus on minimal overall performance degradation . however, accelerated models can exhibit significant changes in instance-level predictions .
Approach:	They investigate whether accelerated vision-Language Models can still give the same answers as before . they found that accelerated models changed original answers up to 20% of the time .
Outcome:	The results show that accelerated models changed their original answers up to 20% of the time.

Copied to clipboard

Zhengyan Zhang, Zhiyuan Zeng, Yankai Lin, Huadong Wang, Deming Ye, Chaojun Xiao, Xu Han, Zhiyuan Liu, Peng Li, Maosong Sun, Jie Zhou

Learning Logic Rules for Document-Level Relation Extraction (2021.emnlp-main)

Challenge:	Existing knowledge injection methods are not suitable for enhancing pre-trained language models with external knowledge bases.
Approach:	They propose a plug-and-play knowledge injection method where knowledge bases are injected into frozen existing downstream models by a knowledge plugin.
Outcome:	The proposed method improves the performance of knowledge injection on knowledge-driven tasks while keeping model parameters frozen.

Copied to clipboard

Dongyu Ru, Changzhi Sun, Jiangtao Feng, Lin Qiu, Hao Zhou, Weinan Zhang, Yong Yu, Lei Li

Towards Robust Visual Question Answering: Making the Most of Biased Samples via Contrastive Learning (2022.findings-emnlp)

Challenge:	Existing models for document-level relation extraction relied on implicitly powerful representations, which makes the model less transparent.
Approach:	They propose a probabilistic model for document-level relation extraction by learning logic rules.
Outcome:	The proposed model outperforms baseline models in relation performance and logical consistency.

Copied to clipboard

Qingyi Si, Yuanxin Liu, Fandong Meng, Zheng Lin, Peng Fu, Yanan Cao, Weiping Wang, Jie Zhou

Debiasing In-Context Learning by Instructing LLMs How to Follow Demonstrations (2024.findings-acl)

Challenge:	Recent studies have shown that biased samples can be brittle for VQA models . however, the improvements on OOD data severely sacrifice the performance on the in-distribution (ID) data.
Approach:	They propose a contrastive learning approach that exploits biased samples for unbiased information that contributes to reasoning.
Outcome:	The proposed method achieves competitive performance on the OOD dataset while maintaining robustness on the ID dataset.

Copied to clipboard

Lvxue Li, Jiaqi Chen, Xinyu Lu, Yaojie Lu, Hongyu Lin, Shuheng Zhou, Huijia Zhu, Weiqiang Wang, Zhongyi Liu, Xianpei Han, Le Sun

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

Challenge:	In-context learning (ICL) has gained considerable attention due to its data efficiency and task adaptability.
Approach:	They propose to de-biase demonstration bias in in-context learning by focusing on semantic ambiguity induced by demonstrations and reducing the semantic hazard.
Outcome:	The proposed methods significantly improve performance on six datasets.

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 .

LongWeave: A Long-Form Generation Benchmark Bridging Real-World Relevance and Verifiability (2025.findings-emnlp)

Copied to clipboard

Zikai Xiao, Fei Huang, Jianhong Tu, Jianhui Wei, Wen Ma, Yuxuan Zhou, Jian Wu, Bowen Yu, Zuozhu Liu, Junyang Lin

Challenge:	Existing benchmarks for long-form generation assess real-world queries with hard-to-verify metrics or use synthetic setups that overlook real-life intricacies.
Approach:	They propose a new approach that balances verifiable and real-world assessment with Target-Anchored Evaluation.
Outcome:	The proposed model balances real-world and verifiable assessment with Target-Anchored Evaluation (TAE) it generates queries, textual materials, and anchors based on verifier targets within real-life scenarios .

LongInsightBench: A Comprehensive Benchmark for Evaluating Omni-Modal Models on Human-Centric Long-Video Understanding. (2026.findings-acl)

Copied to clipboard

ZhaoYang Han, Qihan Lin, Hao Liang, Bowen Chen, Zhou Liu, Wentao Zhang

LLaDA 1.5: Variance-Reduced Preference Optimization for Large Language Diffusion Models (2026.acl-long)

Challenge:	LongInsightBench is the first benchmark designed to assess models’ ability to understand long videos, with a focus on human language, viewpoints, actions, and other contextual elements.
Approach:	They propose a benchmark to assess models’ ability to understand long videos with a focus on human language, viewpoints, actions, and other contextual elements.
Outcome:	The proposed model excels in three key areas: a) long-duration, human-centric videos; b) diversifying and challenging task scenarios; c) quality assurance pipeline; and d) reliability.

Copied to clipboard

Fengqi Zhu, Rongzhen Wang, Shen Nie, Xiaolu Zhang, Chunwei Wu, Jun Zhou, Yankai Lin, Ji-Rong Wen, Chongxuan Li

Jailbreaking? One Step Is Enough! (2025.acl-long)

Challenge:	Masked diffusion language models have achieved significant progress in language modeling . however, the systematic analysis and empirical validation of their alignment on general tasks remains underexplored.
Approach:	They propose a framework that analyzes the bias and variance of preference optimization loss and gradient based on Direct Preference Optimization.
Outcome:	The proposed model outperforms its SFT-only predecessor on general benchmarks . it consistently outperformed other strong language models and ARMs on general tasks .

Copied to clipboard

Weixiong Zheng, Peijian Zeng, YiWei Li, Hongyan Wu, Nankai Lin, Junhao Chen, Aimin Yang, Yongmei Zhou

RAP: Robustness-Aware Perturbations for Defending against Backdoor Attacks on NLP Models (2021.emnlp-main)

Challenge:	Large language models (LLMs) excel in various tasks but remain vulnerable to jailbreak attacks, where adversaries manipulate prompts to generate harmful outputs.
Approach:	They propose a Reverse Embedded Defense Attack mechanism that disguises the attack intention as the "defense" intention against harmful content.
Outcome:	The proposed method outperforms existing methods on open-source and closed-source models and enables successful jailbreak in one iteration.

Copied to clipboard

Wenkai Yang, Yankai Lin, Peng Li, Jie Zhou, Xu Sun

From Behavioral Performance to Internal Competence: Interpreting Vision-Language Models with VLM-Lens (2025.emnlp-demos)

Challenge:	Backdoor attacks are a serious threat to the safety of reusing deep neural networks (DNNs).
Approach:	They propose an efficient online defense mechanism based on robustness-aware perturbations to distinguish poisoned and clean samples to defend against backdoor attacks on natural language processing models.
Outcome:	The proposed method achieves better defending performance and lower computational costs than existing defense methods.

Copied to clipboard

Hala Sheta, Eric Haoran Huang, Shuyu Wu, Ilia Alenabi, Jiajun Hong, Ryker Lin, Ruoxi Ning, Daniel Wei, Jialin Yang, Jiawei Zhou, Ziqiao Ma, Freda Shi

IPIGuard: A Novel Tool Dependency Graph-Based Defense Against Indirect Prompt Injection in LLM Agents (2025.emnlp-main)

Challenge:	Existing vision-language models are based on exactmatch based accuracy and its derivations to evaluate performance.
Approach:	They propose a toolkit that supports systematic benchmarking, analysis, and interpretation of vision-language models by extracting intermediate outputs from any layer during the forward pass of open-source VLMs.
Outcome:	The proposed toolkit supports 16 state-of-the-art base VLMs and their over 30 variants and is extensible to accommodate new models without changing the core logic.

Copied to clipboard

Hengyu An, Jinghuai Zhang, Tianyu Du, Chunyi Zhou, Qingming Li, Tao Lin, Shouling Ji

MTAVG-Bench: A Diagnostic Benchmark for Multi-Talker Dialogue-Centric Audio-Video Generation (2026.acl-long)

Challenge:	Existing methods for detecting Indirect Prompt Injection (IPI) attacks rely on assumptions about the model's inherent security, which lacks structural constraints on agent behaviors.
Approach:	They propose a novel task execution paradigm that models the agents’ task execution process as a traversal over a planned Tool Dependency Graph (TDG).
Outcome:	The proposed model reduces unintended tool invocations triggered by injected instructions, enhancing robustness against IPI attacks.

Copied to clipboard

Yanghao Zhou, Haitian Li, Rexar Lin, Heyan Huang, Jinxing Zhou, Changsen Yuan, Tian Lan, Ziqin Zhou, Yudong Li, Jiajun Xu, Jingyun Liao, YiMing Cheng, Xuefeng Chen, Xian-Ling Mao, Yousheng Feng

Self-Steering Optimization: Autonomous Preference Optimization for Large Language Models (2025.findings-acl)

Challenge:	Existing evaluation benchmarks for text-to-audio-video (T2AV) generation are largely designed for human-recorded videos or single-speaker settings.
Approach:	They propose a failure-driven diagnostic benchmark for multi-talker dialogue-centric audio-video generation.
Outcome:	The benchmark evaluates multi-speaker dialogue generation at four levels: audio-visual signal fidelity, temporal attribute consistency, social interaction, and cinematic expression.

Copied to clipboard

Hao Xiang, Bowen Yu, Hongyu Lin, Keming Lu, Yaojie Lu, Xianpei Han, Ben He, Le Sun, Jingren Zhou, Junyang Lin

Boosting Inference Efficiency: Unleashing the Power of Parameter-Shared Pre-trained Language Models (2023.findings-emnlp)

Challenge:	Prior research focused on developing data generation methods, while insufficient attention has been paid to quality control mechanisms and often produces inaccurate and unhelpful data.
Approach:	They propose an algorithm that automatically generates high-quality preference data, eliminating manual annotation requirements.
Outcome:	The proposed algorithm outperforms baselines in human preference alignment and reward optimization.

Copied to clipboard

Weize Chen, Xiaoyue Xu, Xu Han, Yankai Lin, Ruobing Xie, Zhiyuan Liu, Maosong Sun, Jie Zhou

NumNet: Machine Reading Comprehension with Numerical Reasoning (D19-1)

Challenge:	Parameter-shared pre-trained language models (PLMs) have emerged as a successful approach in resource-constrained environments.
Approach:	They propose a method to enhance the inference efficiency of parameter-shared PLMs by pre-training models that can achieve even greater acceleration.
Outcome:	The proposed method improves inference efficiency on autoregressive and autoencoding models.

Copied to clipboard

Qiu Ran, Yankai Lin, Peng Li, Jie Zhou, Zhiyuan Liu

Learning “O” Helps for Learning More: Handling the Unlabeled Entity Problem for Class-incremental NER (2023.acl-long)

Challenge:	Existing numerical MRC models are weak in numerical reasoning, such as addition, subtraction, sorting and counting.
Approach:	They propose a numerical MRC model that integrates numerical reasoning into existing MRC models and achieves an EM-score of 64.56% on the DROP dataset.
Outcome:	The proposed model outperforms all existing machine reading comprehension models by considering the numerical relations among numbers on the DROP dataset.

Copied to clipboard

Ruotian Ma, Xuanting Chen, Zhang Lin, Xin Zhou, Junzhe Wang, Tao Gui, Qi Zhang, Xiang Gao, Yun Wen Chen

Towards Effective and Efficient Continual Pre-training of Large Language Models (2025.acl-long)

Challenge:	Existing Named Entity Recognition systems are typically trained on a large-scale dataset with predefined entity classes, then deployed for entity recognition on the test data without further adaptation or refinement.
Approach:	They propose a representation learning method that adaptively detects entity clusters in "O" and two effective distance-based relabeling strategies for better learning the old classes.
Outcome:	The proposed method achieves 10.62% improvement over the baseline methods.

Copied to clipboard

Jie Chen, Zhipeng Chen, Jiapeng Wang, Kun Zhou, Yutao Zhu, Jinhao Jiang, Yingqian Min, Xin Zhao, Zhicheng Dou, Jiaxin Mao, Yankai Lin, Ruihua Song, Jun Xu, Xu Chen, Rui Yan, Zhewei Wei, Di Hu, Wenbing Huang, Ji-Rong Wen

CoCoST: Automatic Complex Code Generation with Online Searching and Correctness Testing (2024.emnlp-main)

Challenge:	Continual pre-training (CPT) has been an important approach for adapting language models to specific domains or tasks.
Approach:	They propose a Continual pre-training method that can greatly improve Chinese language ability and scientific reasoning ability of LLMs.
Outcome:	The proposed method can greatly improve Chinese language ability and scientific reasoning ability of LLMs.

Copied to clipboard

Xinyi He, Jiaru Zou, Yun Lin, Mengyu Zhou, Shi Han, Zejian Yuan, Dongmei Zhang

Dynamically Fused Graph Network for Multi-hop Reasoning (P19-1)

Challenge:	Existing methods to improve code generation from natural language descriptions are difficult due to complex structure, subtle bugs, and lack of supplementary contents.
Approach:	They propose a framework that enhances complex code generation by online searching for more information with planned queries and correctness testing for code refinement.
Outcome:	The proposed framework improves the quality of complex code generation on the DS-1000 and ClassEval datasets.

Copied to clipboard

Lin Qiu, Yunxuan Xiao, Yanru Qu, Hao Zhou, Lei Li, Weinan Zhang, Yong Yu

Skill-Based Few-Shot Selection for In-Context Learning (2023.emnlp-main)

Challenge:	Text-based question answering (TBQA) has been studied extensively in recent years.
Approach:	They propose a Dynamically Fused Graph Network to answer questions requiring multiple scattered evidence and reasoning over them.
Outcome:	The proposed method achieves competitive results on a public TBQA dataset and produces interpretable reasoning chains.

Copied to clipboard

Shengnan An, Bo Zhou, Zeqi Lin, Qiang Fu, Bei Chen, Nanning Zheng, Weizhu Chen, Jian-Guang Lou

Beyond Code Pairs: Dialogue-Based Data Generation for LLM Code Translation (2026.acl-long)

Challenge:	Existing methods based on pre-trained embeddings can be easily biased by surface features that are not important for the target task.
Approach:	They propose a skill-based few-shot selection method for in-context learning . it generates skill-specific descriptions for each test case and candidate example .
Outcome:	The proposed method significantly outperforms existing methods in five cross-domain semantic parsing datasets and six backbone models.

Copied to clipboard

Le Chen, Nuo Xu, Winson Chen, Bin Lei, Pei-Hung Lin, Dunzhi Zhou, Rajeev Thakur, Caiwen Ding, Ali Jannesari, Chunhua Liao

Text Generation

Challenge:	Large language models (LLMs) have shown remarkable capabilities in code translation, yet their performance deteriorates in low-resource programming domains such as Fortran and emerging frameworks like CUDA .
Approach:	They propose a dual-LLM Questioner–Solver pipeline that integrates external knowledge from compilers and runtime feedback to generate verified translations and multi-turn dialogues.
Outcome:	The proposed model outperforms proprietary models on key metrics like compilation success and accuracy.

Marginal Utility Diminishes: Exploring the Minimum Knowledge for BERT Knowledge Distillation (2021.acl-long)

Copied to clipboard

Yuanxin Liu, Fandong Meng, Zheng Lin, Weiping Wang, Jie Zhou

Instruction-tuned Language Models are Better Knowledge Learners (2024.acl-long)

Challenge:	Knowledge distillation (KD) has shown great success in BERT compression.
Approach:	They propose a knowledge distillation paradigm that extracts the teacher's hidden state knowledge and then compresses it into three dimensions.
Outcome:	The proposed paradigm gives rise to training speedup of 2.7x 3.4x for two kinds of student models and computing devices.

Copied to clipboard

Zhengbao Jiang, Zhiqing Sun, Weijia Shi, Pedro Rodriguez, Chunting Zhou, Graham Neubig, Xi Lin, Wen-tau Yih, Srini Iyer

HAD: HAllucination Detection Language Models Based on a Comprehensive Hallucination Taxonomy (2026.acl-industry)

Challenge:	Large language models store factual knowledge in parameters, but it can become outdated as the work evolves . pre-instruction-tuning improves ability of LLMs to absorb knowledge from new documents .
Approach:	They propose a method that instruction-tunes on questions prior to training on documents . they propose to use QA pairs to update factual knowledge of large language models .
Outcome:	The proposed method outperforms instruction-tuning on documents by 17.8%.

Copied to clipboard

Fan Xu, Xinyu Hu, Zhenghan Yu, Li Lin, Xu Zhang, Yang Zhang, Wei Zhou, Jinjie Gu, Xiaojun Wan

CSDS: A Fine-Grained Chinese Dataset for Customer Service Dialogue Summarization (2021.emnlp-main)

Challenge:	relying on large language models for information has raised concerns about reliability and accuracy of outputs.
Approach:	They propose a hallucination taxonomy with 11 categories for various NLG tasks and propose HAllucination Detection models which integrate hallucinism detection, span-level identification, and correction into a single inference process.
Outcome:	The proposed models outperform baselines on HaluEval, FactCHD, and FaithBench, confirming their robustness and versatility.

Copied to clipboard

Haitao Lin, Liqun Ma, Junnan Zhu, Lu Xiang, Yu Zhou, Jiajun Zhang, Chengqing Zong

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

Challenge:	Existing summarization methods are prone to generate redundant and incoherent summaries, causing the performance to be worse.
Approach:	They propose a Chinese dataset for Customer Service Dialogue Summarization (CSDS) that provides role-oriented summaries to acquire different speakers' viewpoints.
Outcome:	The proposed dataset improves the abstractive summaries in two aspects . it also provides role-oriented summary to acquire different speakers’ viewpoints .

Copied to clipboard

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

CFBench: A Comprehensive Constraints-Following Benchmark for LLMs (2025.acl-long)

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

Tao Zhang, ChengLIn Zhu, Yanjun Shen, Wenjing Luo, Yan Zhang, Hao Liang, Tao Zhang, Fan Yang, Mingan Lin, Yujing Qiao, Weipeng Chen, Bin Cui, Wentao Zhang, Zenan Zhou

Do Pre-trained Models Benefit Knowledge Graph Completion? A Reliable Evaluation and a Reasonable Approach (2022.findings-acl)

Challenge:	Existing evaluations of Large Language Models (LLMs) focus on fragmented constraints or narrow scenarios, but they overlook the comprehensiveness and authenticity of constraints from the user’s perspective.
Approach:	They propose a Chinese Comprehensive Constraints Following Benchmark for LLMs that compiles constraints from real-world instructions and constructs a systematic framework for constraint types.
Outcome:	The proposed framework integrates multi-dimensional assessment criteria with requirement prioritization, covering various perspectives of constraints, instructions, and requirement fulfillment.

Copied to clipboard

Xin Lv, Yankai Lin, Yixin Cao, Lei Hou, Juanzi Li, Zhiyuan Liu, Peng Li, Jie Zhou

WebCPM: Interactive Web Search for Chinese Long-form Question Answering (2023.acl-long)

Challenge:	Pre-trained language models capture factual knowledge from massive texts . but they are still quite behind the SOTA KGC models in terms of performance .
Approach:	They propose to use open-world assumption to evaluate PLM-based knowledge graph completion models . they propose to convert each triple and its support information into natural prompt sentences .
Outcome:	The proposed model is more accurate under the open-world assumption (OWA) this setting manual checks the correctness of knowledge that is not in KGs.

Copied to clipboard

Yujia Qin, Zihan Cai, Dian Jin, Lan Yan, Shihao Liang, Kunlun Zhu, Yankai Lin, Xu Han, Ning Ding, Huadong Wang, Ruobing Xie, Fanchao Qi, Zhiyuan Liu, Maosong Sun, Jie Zhou

Fine-grained Artificial Neurons in Audio-transformers for Disentangling Neural Auditory Encoding (2023.findings-acl)

Challenge:	Long-form question answering requires two procedures: information retrieval and information synthesis.
Approach:	They propose a Chinese long-form question answering dataset called WebCPM . the dataset is based on a web search interface that engages with a search engine in real time .
Outcome:	The proposed dataset generates answers that are no worse than human-written ones . the dataset is the first Chinese LFQA dataset .

Copied to clipboard

Mengyue Zhou, Xu Liu, David Liu, Zihao Wu, Zhengliang Liu, Lin Zhao, Dajiang Zhu, Lei Guo, Junwei Han, Tianming Liu, Xintao Hu

MM-Doc-R1: Training Agents for Long Document Visual Question Answering through Multi-turn Reinforcement Learning (2026.findings-acl)

Challenge:	Existing studies treat each transformer encoding layer as a single artificial neuron . layer-level embeddings aggregate multiple types of contextual attention captured by multiple head modules .
Approach:	They propose to embed each transformer encoding layer as a single artificial neuron . they propose to couple those ANs with their biological-neuron counterparts in the human brain .
Outcome:	The proposed models can be used to link representations to brain activity, the authors say . their results show that the proposed models carry meaningful neurolinguistic information .

Copied to clipboard

Jiahang Lin, Kai Hu, Binghai Wang, Yuhao Zhou, Zhiheng Xi, Honglin Guo, Shichun Liu, Junzhe Wang, Shihan Dou, Enyu Zhou, Hang Yan, Zhenhua Han, Tao Gui, Qi Zhang, Xuanjing Huang

Effective Unsupervised Constrained Text Generation based on Perturbed Masking (2022.findings-acl)

Challenge:	Existing work on long document visual question answering is based on Retrieval-Augmented Generation (RAG) where textual or visual content is encoded into embeddings and relevance is determined by similarity scores with respect to the original query.
Approach:	They propose a framework that employs an agentic, vision-aware workflow to address long document visual question answering through iterative information discovery and synthesis.
Outcome:	The proposed framework outperforms existing RL systems by 10.4% on the MMLongbench-Doc benchmark and demonstrates superior training performance over GRPO.

Copied to clipboard

Yingwen Fu, Wenjie Ou, Zhou Yu, Yue Lin

MAgIC: Investigation of Large Language Model Powered Multi-Agent in Cognition, Adaptability, Rationality and Collaboration (2024.emnlp-main)

Challenge:	Existing methods for constrained text generation stochastically sample edit positions and actions, which cause unnecessary search steps.
Approach:	They propose to extend perturbed masking technique to search for most incongruent token to edit and introduce four multi-aspect scoring functions to select edit action to further reduce search difficulty.
Outcome:	The proposed method achieves state-of-the-art in two representative tasks . it does not require supervised data, so it could be applied to different generation tasks.

Copied to clipboard

Lin Xu, Zhiyuan Hu, Daquan Zhou, Hongyu Ren, Zhen Dong, Kurt Keutzer, See-Kiong Ng, Jiashi Feng

ViT-TTS: Visual Text-to-Speech with Scalable Diffusion Transformer (2023.emnlp-main)

Challenge:	Large language models (LLMs) have advanced natural language processing, demonstrating exceptional reasoning, tool usage, and memory capabilities.
Approach:	They propose a competition-based benchmark framework specifically designed to assess LLMs within multi-agent environments.
Outcome:	The proposed framework enhances the LLMs’ abilities in navigating complex social and cognitive dimensions by over threefold between the strongest and weakest LLM models.

Copied to clipboard

Huadai Liu, Rongjie Huang, Xuan Lin, Wenqiang Xu, Maozong Zheng, Hong Chen, Jinzheng He, Zhou Zhao

Manual Evaluation Matters: Reviewing Test Protocols of Distantly Supervised Relation Extraction (2021.findings-acl)

Challenge:	Text-to-speech (TTS) performance has improved with the advent of denoising Diffusion Probabilistic Models . however, perceived quality of audio depends on content, pitch, rhythm, and energy .
Approach:	They propose a visual TTS model with scalable diffusion transformers that complement phoneme sequences with visual information to generate high-perceived audio.
Outcome:	The proposed model outperforms existing models regardless of visibility of the scene . it can generate high-perceived audio, opening up new avenues for AR and VR applications .

Copied to clipboard

Tianyu Gao, Xu Han, Yuzhuo Bai, Keyue Qiu, Zhiyu Xie, Yankai Lin, Zhiyuan Liu, Peng Li, Maosong Sun, Jie Zhou

Learning to Recover from Multi-Modality Errors for Non-Autoregressive Neural Machine Translation (2020.acl-main)

Challenge:	Distantly supervised relation extraction (RE) has attracted much attention in the past few years . previous methods to evaluate models manually or directly on autolabeled data have produced inaccurate evaluations .
Approach:	They propose to use distant supervision to generate large-scale autolabeled data . they build manually-annotated test sets for two DS-RE datasets and evaluate models .
Outcome:	The proposed method produces 53% wrong labels at the entity pair level in the popular NYT10 dataset.

Copied to clipboard

Qiu Ran, Yankai Lin, Peng Li, Jie Zhou

Evaluating Models’ Local Decision Boundaries via Contrast Sets (2020.findings-emnlp)

Challenge:	Existing non-autoregressive neural machine translation models suffer from multi-modality problem . despite their autoregressivity, most NMT models suffer with slow decoding speed .
Approach:	They propose a semi-autoregressive model which generates a translation as a sequence of segments while each segment is predicted token-by-token.
Outcome:	The proposed model can achieve 4 times speedup while maintaining comparable performance.

Copied to clipboard

Matt Gardner, Yoav Artzi, Victoria Basmov, Jonathan Berant, Ben Bogin, Sihao Chen, Pradeep Dasigi, Dheeru Dua, Yanai Elazar, Ananth Gottumukkala, Nitish Gupta, Hannaneh Hajishirzi, Gabriel Ilharco, Daniel Khashabi, Kevin Lin, Jiangming Liu, Nelson F. Liu, Phoebe Mulcaire, Qiang Ning, Sameer Singh, Noah A. Smith, Sanjay Subramanian, Reut Tsarfaty, Eric Wallace, Ally Zhang, Ben Zhou

Challenge:	Standard test sets for supervised learning evaluate in-distribution generalization but are misleading when a dataset has systematic gaps.
Approach:	They propose a more rigorous annotation paradigm for NLP that helps to close systematic gaps in the test data.
Outcome:	The proposed model performs significantly lower on contrast sets than on the original test sets—up to 25% in some cases.

Neural Topic Model with Reinforcement Learning (D19-1)

Copied to clipboard

Lin Gui, Jia Leng, Gabriele Pergola, Yu Zhou, Ruifeng Xu, Yulan He

HearSay Benchmark: Do Audio LLMs Leak What They Hear? (2026.findings-acl)

Challenge:	Experimental results show superior performance on perplexity and topic coherence measures compared to state-of-the-art topic models.
Approach:	They propose to incorporate topic coherence measures as reward signals to guide the learning of a VAE-based topic model.
Outcome:	The proposed model is able to separating background words dynamically from topic words eliminating the pre-processing step of filtering infrequent and/or top frequent words, typically required for learning traditional topic models.

Copied to clipboard

Jin Wang, Kaiwen Luo, Liang Lin, Weiliu Wang, Yitian Chen, Moayad Aloqaily, Xuehai Tang, Zhenhong Zhou, Kun Wang, Li Sun, Qingsong Wen

Unveiling Opinion Evolution via Prompting and Diffusion for Short Video Fake News Detection (2024.findings-acl)

Challenge:	Recent advances in audio large language models have led to their potential privacy implications unexplored.
Approach:	They propose a benchmark to examine whether ALLMs leak user privacy through acoustic voiceprints.
Outcome:	The proposed benchmark is constructed from over 22,000 real-world audio clips.

Copied to clipboard

Linlin Zong, Jiahui Zhou, Wenmin Lin, Xinyue Liu, Xianchao Zhang, Bo Xu

Learning to Win Lottery Tickets in BERT Transfer via Task-agnostic Mask Training (2022.naacl-main)

Challenge:	Existing methods for short video fake news detection ignore the implicit opinions and evolving nature of opinions across modalities.
Approach:	They propose a short video fake news model that mines implicit opinions within short videos and promotes the evolution of both explicit and implicit opinions across all modalities.
Outcome:	The proposed model outperforms existing methods on a publicly available dataset for short video fake news detection.

Copied to clipboard

Yuanxin Liu, Fandong Meng, Zheng Lin, Peng Fu, Yanan Cao, Weiping Wang, Jie Zhou

Expanding the Boundaries of Vision Prior Knowledge in Multi-modal Large Language Models (2026.eacl-long)

Challenge:	Recent studies show pre-trained language models contain matching subnetworks that have similar transfer learning performance as the original PLM.
Approach:	They propose to prune matching subnetworks using magnitude-based pruning . they propose to optimize the subnetwork structure towards the pre-training objectives .
Outcome:	The proposed method is more efficient in searching subnetworks and advantageous when fine-tuning within a range of data scarcity.

Copied to clipboard

Qiao Liang, Yanjiang Liu, Weixiang Zhou, Ben He, Yaojie Lu, Hongyu Lin, Jia Zheng, Xianpei Han, Le Sun, Yingfei Sun

Action-Based Conversations Dataset: A Corpus for Building More In-Depth Task-Oriented Dialogue Systems (2021.naacl-main)

Challenge:	Existing research treats MLLMs as unified systems optimized through end-to-end training, but the impact of vision encoder’s prior knowledge is seldom investigated.
Approach:	They propose a metric to quantify the effect of prior knowledge on MLLM performance by integrating prior knowledge at the vision encoder level into a training framework.
Outcome:	The proposed training framework incorporates prior knowledge at the vision encoder level, and significantly boosts visual understanding capabilities of MLLMs.

Copied to clipboard

Derek Chen, Howard Chen, Yi Yang, Alexander Lin, Zhou Yu

Navigating the Dual Facets: A Comprehensive Evaluation of Sequential Memory Editing in Large Language Models (2024.acl-long)

Challenge:	Existing goal-oriented dialogue datasets focus on identifying slots and values, but in reality, customer service agents follow multi-step procedures derived from explicit company policies.
Approach:	They propose to use a fully-labeled dataset to study customer service dialogue systems in real-world scenarios.
Outcome:	The proposed dataset outperforms existing models but still lacks 50.8% absolute accuracy to reach human-level performance on the dataset.

Copied to clipboard

Zihao Lin, Mohammad Beigi, Hongxuan Li, Yufan Zhou, Yuxiang Zhang, Qifan Wang, Wenpeng Yin, Lifu Huang

A Law Reasoning Benchmark for LLM with Tree-Organized Structures including Factum Probandum, Evidence and Experiences (2025.findings-acl)

Challenge:	Memory Editing (ME) has emerged as an efficient method to modify erroneous facts or inject new knowledge into Large Language Models (LLMs).
Approach:	They propose to evaluate LLMs with single edit only and parameter-modifying ME with parameter-preserving ME.
Outcome:	The proposed method can maintain LLMs’ fundamental capabilities but struggles to accurately recall edited knowledge presented in a different format.

Copied to clipboard

Jiaxin Shen, Jinan Xu, Huiqi Hu, Luyi Lin, Guoyang Ma, Fei Zheng, Fandong Meng, Jie Zhou, Wenjuan Han

COIG-P: A High-Quality and Large-Scale Chinese Preference Dataset for Alignment with Human Values (2026.findings-eacl)

Challenge:	a recent study focuses on generating impartial and interpretable judicial judgments based on established criminal fact.
Approach:	They propose a law reasoning schema enriched with hierarchical factum probandum, evidence, and implicit experience that enables public scrutiny and preventing bias.
Outcome:	The proposed schema enables public scrutiny and prevents bias in the "Intelligent Court" it employs a suite of legal analysis tools to address the challenge task.

Copied to clipboard

Siwei Wu, JinCheng Ren, Xeron Du, Shuyue Guo, Xingwei Qu, Yiming Liang, Jie Liu, Yunwen Li, Tyler Loakman, Tianyu Zheng, Boyu Feng, Huaqing Yuan, Zili Wang, Jiaheng Liu, Wenhao Huang, Chenglin Cai, Haoran Que, Jian Yang, Yuelin Bai, Zekun Moore Wang, Zhouliang Yu, Qunshu Lin, Ding Pan, Yuchen Eleanor Jiang, Tiannan Wang, Wangchunshu Zhou, Shenzhi Wang, Xingyuan Bu, Minghao Liu, Guoyin Wang, Ge Zhang, Chenghua Lin

A Sentiment-Controllable Topic-to-Essay Generator with Topic Knowledge Graph (2020.findings-emnlp)

Challenge:	Existing Chinese preference datasets suffer from limited scale, restricted domain coverage, and insufficiently rigorous data validation.
Approach:	They propose an LLM-based data annotation pipeline with no human intervention to annotate Chinese preference datasets.
Outcome:	The proposed pipeline outperforms existing Chinese preference datasets on AlignBench and Chinese Reward Benchmark.

Copied to clipboard

Lin Qiao, Jianhao Yan, Fandong Meng, Zhendong Yang, Jie Zhou

Rethinking Stealthiness of Backdoor Attack against NLP Models (2021.acl-long)

Challenge:	Topic-to-essay generation is a promising task for natural language generation.
Approach:	They propose a Sentiment Controllable topic-to- essay generator with a Topic Knowledge Graph enhanced decoder to generate essays with only several given topic words.
Outcome:	The proposed model outperforms the state-of-the-art model on automatic and human evaluation.

Copied to clipboard

Wenkai Yang, Yankai Lin, Peng Li, Jie Zhou, Xu Sun

EmotionTalk: An Interactive Chinese Multimodal Emotion Dataset With Rich Annotations (2026.findings-acl)

Challenge:	Existing backdoor attacks are not stealthy to system deployers or users.
Approach:	They propose a novel backdoor attack method based on negative data augmentation and modifying word embeddings that is much stealthier while maintaining pretty good attacking performance.
Outcome:	The proposed method is much stealthier while maintaining pretty good attacking performance.

Copied to clipboard

Haoqin Sun, Jinghua Zhao, Xuechen Wang, Shiwan Zhao, Jiaming Zhou, Hui Wang, Xi Yang, Yequan Wang, Yonghua Lin

Prompt Tuning for Unified Multimodal Pretrained Models (2023.findings-acl)

Challenge:	Existing datasets face issues such as low quality, limited scale, and incomplete modalities, hindering model performance.
Approach:	They propose to use Chinese multimodal datasets to capture authentic emotional interplay from 19 professional actors.
Outcome:	The EmotionTalk dataset spans 23.6 hours of dyadic conversations across diverse scenarios.

Copied to clipboard

Hao Yang, Junyang Lin, An Yang, Peng Wang, Chang Zhou

Sequential and Repetitive Pattern Learning for Temporal Knowledge Graph Reasoning (2024.lrec-main)

Challenge:	Prompt tuning has demonstrated success in natural language pretraining and even vision pretraining.
Approach:	They propose to apply prompt tuning to a unified sequence-to-sequence pretrained model by adding a sequence of learnable embeddings to each layer and finetuning the pretrained models on downstream tasks.
Outcome:	The proposed method outperforms other parameter-efficient tuning methods on multimodal models and is robust against adversarial attacks.

Copied to clipboard

Xuefei Li, Huiwei Zhou, Weihong Yao, Wenchu Li, Yingyu Lin, Lei Du

Knowledge Representation

Challenge:	Existing methods to learn temporal evolutional representations of entities are hard to capture the complex temporal patterns such as sequential and repetitive.
Approach:	They propose a Sequential and Repetitive Pattern Learning method that captures both sequential and repetitive patterns.
Outcome:	The proposed method outperforms state-of-the-art methods on four representative benchmarks on GDELT dataset, where performance improvement of MRR reaches up to 18.84%.

ICG: Improving Cover Image Generation via MLLM-based Prompting and Personalized Preference Alignment (2025.emnlp-main)

Copied to clipboard

Zhipeng Bian, Jieming Zhu, Qijiong Liu, Wang Lin, Guohao Cai, Zhaocheng Du, Jiacheng Sun, Zhou Zhao, Zhenhua Dong

Fully Hyperbolic Neural Networks (2022.acl-long)

Challenge:	Large language models and diffusion models have opened new possibilities for AI-generated content . personalized cover image generation remains underexplored despite its critical role in boosting user engagement on digital platforms.
Approach:	They propose a framework that integrates MLLM-based prompting with personalized preference alignment to generate high-quality, contextually relevant covers.
Outcome:	The proposed framework improves image quality, semantic fidelity, and personalization, leading to stronger user appeal and offline recommendation accuracy in downstream tasks.

Copied to clipboard

Weize Chen, Xu Han, Yankai Lin, Hexu Zhao, Zhiyuan Liu, Peng Li, Maosong Sun, Jie Zhou

Challenge:	Existing hyperbolic neural networks encode features in the hyperbolical space yet formalize most of their operations in the tangent space.
Approach:	They propose a fully hyperbolic framework to build hyperbolical networks based on the Lorentz model by adapting Lorentzer transformations to formalize essential operations of neural networks.
Outcome:	The proposed framework has better performance on four NLP tasks compared with existing hyperbolic models .

Retrieval Heads are Dynamic (2026.acl-long)

Copied to clipboard

Yuping Lin, Zitao Li, Yue Xing, Pengfei He, Yingqian Cui, Yaliang Li, Bolin Ding, Jingren Zhou, Jiliang Tang

Question-Interlocutor Scope Realized Graph Modeling over Key Utterances for Dialogue Reading Comprehension (2023.findings-acl)

Challenge:	Recent studies have identified "retrieval heads" in Large Language Models responsible for extracting information from input contexts.
Approach:	They propose to examine retrieval heads from a dynamic perspective . they establish that retrieval head activation is highly dynamic and functionally irreplaceable .
Outcome:	The proposed model's hidden state encodes a predictive signal for future retrieval head patterns, indicating an internal planning mechanism.

Copied to clipboard

Jiangnan Li, Mo Yu, Fandong Meng, Zheng Lin, Peng Fu, Weiping Wang, Jie Zhou

Rationales Are Not Silver Bullets: Measuring the Impact of Rationales on Model Performance and Reliability (2025.findings-acl)

Challenge:	Compared to standard RC tasks, dialogue reading comprehension (DRC) has raised challenges because of the complex speaker information and noisy dialogue context.
Approach:	They propose a new method for dialogue reading comprehension that extracts answers from dialogues by using key-utterances-extracting methods and a Question-Interlocutor Scope Realized Graph.
Outcome:	The proposed method achieves state-of-the-art performance against previous works.

Copied to clipboard

Chiwei Zhu, Benfeng Xu, An Yang, Junyang Lin, Quan Wang, Chang Zhou, Zhendong Mao

Variator: Accelerating Pre-trained Models with Plug-and-Play Compression Modules (2023.findings-emnlp)

Challenge:	Existing studies have shown that training language models with rationales augmentation is beneficial, but this view does not hold consistently.
Approach:	They conduct comprehensive investigations to thoroughly inspect the impact of rationales on model performance and a novel perspective of model reliability.
Outcome:	The proposed method outperforms untrained models in several areas and provides informative regulations on the broad utilization of rationales.

Copied to clipboard

Chaojun Xiao, Yuqi Luo, Wenbin Zhang, Pengle Zhang, Xu Han, Yankai Lin, Zhengyan Zhang, Ruobing Xie, Zhiyuan Liu, Maosong Sun, Jie Zhou

Routing to the Expert: Efficient Reward-guided Ensemble of Large Language Models (2024.naacl-long)

Challenge:	Large language models (LLMs) have been successful on NLP tasks but require huge parameter sizes and computational resources.
Approach:	They propose a parameter-efficient acceleration method that enhances computational efficiency through plug-and-play compression plugins.
Outcome:	The proposed method saves 53% computational costs using only 0.9% additional parameters with a performance drop of less than 2%.

Copied to clipboard

Keming Lu, Hongyi Yuan, Runji Lin, Junyang Lin, Zheng Yuan, Chang Zhou, Jingren Zhou

DSMoE: Matrix-Partitioned Experts with Dynamic Routing for Computation-Efficient Dense LLMs (2025.emnlp-main)

Challenge:	Existing ensemble methods for Large Language Models focus on reward model ranking of outputs, leading to significant computation overhead.
Approach:	They propose a reward-guided routing method distilling rewards on training queries to train a routing function.
Outcome:	The proposed method outperforms the best single model and ranks first on 44% of tasks.

Copied to clipboard

Minxuan Lv, Zhenpeng Su, Leiyu Pan, Yizhe Xiong, Zijia Lin, Hui Chen, Wei Zhou, Jungong Han, Guiguang Ding, Wenwu Ou, Di Zhang, Kun Gai, Songlin Hu

ODUTQA-MDC: A Task for Open-Domain Underspecified Tabular QA with Multi-turn Dialogue-based Clarification (2026.acl-long)

Challenge:	Existing sparsification methods like pruning can lose model knowledge through parameter removal.
Approach:	They propose a novel approach that achieves sparsification by partitioning pre-trained FFN layers into computational blocks.
Outcome:	The proposed approach achieves superior performance across language modeling and downstream tasks under equivalent computational constraints.

Copied to clipboard

Zhensheng Wang, ZhanTeng Lin, Wenmian Yang, Kun Zhou, Yiquan Zhang, Weijia Jia

COF: Adaptive Chain of Feedback for Comparative Opinion Quintuple Extraction (2025.coling-main)

Challenge:	Existing approaches to tabular QA are limited to closed-domain scenarios . existing approaches do not solve the core challenge of generating correct answers without user clarification .
Approach:	They propose a benchmark to tackle underspecified or uncertain queries in tabular question answering . they propose ODUTQA-MDC task and a multi-agent framework to detect ambiguities .
Outcome:	The proposed framework excels at detecting ambiguities, clarifying them through dialogue, and refining answers.

Copied to clipboard

Qingting Xu, Kaisong Song, Chaoqun Liu, Yangyang Kang, Xiabing Zhou, Jun Lin, Yu Hong

Low-Resource NLP

Challenge:	Comparative Opinion Quintuple Extraction (COQE) aims to extract all comparative sentiment quintuples from product review text.
Approach:	They propose a model-unaware adaptive chain-of-feedback method to extract quintuples from product review text.
Outcome:	The proposed method improves performance on three benchmarks.

Glancing Transformer for Non-Autoregressive Neural Machine Translation (2021.acl-long)

Copied to clipboard

Lihua Qian, Hao Zhou, Yu Bao, Mingxuan Wang, Lin Qiu, Weinan Zhang, Yong Yu, Lei Li

GeoSQA: A Benchmark for Scenario-based Question Answering in the Geography Domain at High School Level (D19-1)

Challenge:	Existing non-autoregressive neural machine translation methods are either inferior to Transformer or require multiple decoding passes, leading to reduced speedup.
Approach:	They propose a Glancing Language Model (GLM) for single-pass parallel generation models and Glancing Transformer (GLAT) with only single- pass decoding, GLAT is able to generate high-quality translation with 8-15 speedup.
Outcome:	The proposed model outperforms all previous non-autoregressive methods on multiple language directions and is nearly comparable to Transformer.

Copied to clipboard

Zixian Huang, Yulin Shen, Xiao Li, Yu’ang Wei, Gong Cheng, Lin Zhou, Xinyu Dai, Yuzhong Qu

Question Answering

Challenge:	SQA is an emerging application of NLP in the medical, geography, and legal domains.
Approach:	They propose a dataset of 1,981 scenarios and 4,110 multiple-choice questions in geography domain at high school level.
Outcome:	The proposed dataset consists of 1,981 scenarios and 4,110 multiple-choice questions in the geography domain at high school level.

PPTAgent: Generating and Evaluating Presentations Beyond Text-to-Slides (2025.emnlp-main)

Copied to clipboard

Hao Zheng, Xinyan Guan, Hao Kong, Wenkai Zhang, Jia Zheng, Weixiang Zhou, Hongyu Lin, Yaojie Lu, Xianpei Han, Le Sun

Semantic Contribution-Aware Adaptive Retrieval for Black-Box Models (2025.findings-emnlp)

Challenge:	Existing methods for generating presentations from documents focus on improving and evaluating content quality in isolation, overlooking visual appeal and structural coherence.
Approach:	They propose an edit-based presentation generation system that analyzes and iterates on slides to create new slides.
Outcome:	The proposed presentation generation tool outperforms existing methods in three dimensions . it analyzes slides, iterates and generates edit actions based on selected slides .

Copied to clipboard

Qinhong Lin, Zhongliang Yang, Yuang Cai, Dingfu Yu, Xuan Xu, Yu Li, Linna Zhou

RJE: A Retrieval-Judgment-Exploration Framework for Efficient Knowledge Graph Question Answering with LLMs (2025.emnlp-main)

Challenge:	Existing approaches to retrieval-agmented generation fail to generalize effectively in black-box scenarios.
Approach:	They propose a framework that leverages the semantic importance of words to dynamically adjust retrieval thresholds and filter information.
Outcome:	The proposed framework achieves the highest score on four long-form, knowledge-intensive generation datasets.

Copied to clipboard

Can Lin, Zhengwang Jiang, Ling Zheng, Qi Zhao, Yuhang Zhang, Qi Song, Wangqiu Zhou

Question Answering

Challenge:	Knowledge graph question answering (KGQA) aims to answer natural language questions using knowledge graphs.
Approach:	They propose a framework that retrieves refined reasoning paths and evaluates their sufficiency.
Outcome:	The proposed framework outperforms existing baselines while enabling small open-source LLMs to achieve competitive results without fine-tuning LLM.

SACTOR: LLM-Driven Correct and Idiomatic C to Rust Translation with Static Analysis and FFI-Based Verification (2026.acl-long)

Copied to clipboard

Tianyang Zhou, Ziyi Zhang, Haowen Lin, Somesh Jha, Mihai Christodorescu, Kirill Levchenko, Varun Chandrasekaran

LEPO: Latent Reasoning Policy Optimization for Large Language Models (2026.findings-acl)

Challenge:	Large language models (LLMs) have shown promise in producing idiomatic translations, but offer no correctness guarantees.
Approach:	They propose a C-to-Rust translation tool that uses an initial "unidiomatic" translation followed by an "idiomatic refinement" they evaluate SACTOR on 200 programs from two datasets and two more complex scenarios .
Outcome:	The proposed tool delivers high end-to-end correctness and produces safe, idiomatic Rust with up to 7 fewer Clippy warnings.

Copied to clipboard

Yuyan Zhou, Jiarui Yu, Hande Dong, Zhezheng Hao, Hong Wang, Jianqing Zhang, Qiang Lin

LOCR: Location-Guided Transformer for Optical Character Recognition (2024.findings-emnlp)

Challenge:	Existing latent reasoning methods that use chain of thought (CoT) are limited to selecting one discrete token at each reasoning step, which potentially induces information loss.
Approach:	They propose a framework that injects controllable stochasticity into latent reasoning via Gumbel-Softmax, restoring LLMs' exploratory capacity and enhancing their compatibility with Reinforcement Learning (RL).
Outcome:	The proposed framework preserves richer information for more comprehensive reasoning and is compatible with Reinforcement Learning (RL).

Copied to clipboard

Yu Sun, Dongzhan Zhou, Chen Lin, Conghui He, Wanli Ouyang, Han-Sen Zhong

ROSE: Robust Selective Fine-tuning for Pre-trained Language Models (2022.emnlp-main)

Challenge:	Academic documents are packed with texts, equations, tables, and figures, posing challenges for accurate OCR results.
Approach:	They propose a model that integrates location guiding into the transformer architecture during autoregression.
Outcome:	The proposed model outperforms existing methods on an original large-scale dataset comprising 53M text-location pairs from 89K academic document pages.

Copied to clipboard

Lan Jiang, Hao Zhou, Yankai Lin, Peng Li, Jie Zhou, Rui Jiang

Other Roles Matter! Enhancing Role-Oriented Dialogue Summarization via Role Interactions (2022.acl-long)

Challenge:	Recent studies have highlighted the lack of adversarial robustness in pre-trained models.
Approach:	They propose a fine-tuning approach that conducts selective updates when adapting pre-trained models to downstream tasks.
Outcome:	The proposed approach improves adversarial robustness on downstream tasks . it eliminates spurious updates, leading to flatter and wider optima than the conventional method .

Copied to clipboard

Haitao Lin, Junnan Zhu, Lu Xiang, Yu Zhou, Jiajun Zhang, Chengqing Zong

From Mimicking to Integrating: Knowledge Integration for Pre-Trained Language Models (2022.findings-emnlp)

Challenge:	Existing methods for role-oriented dialogue summarization ignore information from other roles, resulting in omitted information.
Approach:	They propose a novel method that uses cross attention and decoder self-attention interactions to acquire other roles' critical information.
Outcome:	The proposed method significantly outperforms baselines on two public role-oriented dialogue summarization datasets.

Copied to clipboard

Lei Li, Yankai Lin, Xuancheng Ren, Guangxiang Zhao, Peng Li, Jie Zhou, Xu Sun

Socratic Human Feedback (SoHF): Expert Steering Strategies for LLM Code Generation (2024.findings-emnlp)

Challenge:	Existing models for natural language processing (NLP) are fine-tuned and released for research and deployments.
Approach:	They propose a PLM reuse paradigm that merges teacher-PLM knowledge into a student model.
Outcome:	The proposed paradigm can reduce the computational cost and environmental side-effects of retraining the PLM from scratch.

Copied to clipboard

Subramanian Chidambaram, Li Li, Min Bai, Xiaopeng Li, Kaixiang Lin, Xiong Zhou, Alex Williams

ERICA: Improving Entity and Relation Understanding for Pre-trained Language Models via Contrastive Learning (2021.acl-long)

Challenge:	Large Language Models (LLMs) are increasingly used for generating code solutions, but struggle with complex programming problems without human guidance.
Approach:	They use the “Socratic Feedback” paradigm to map observed feedback strategies to five stages of Socratic Questioning to identify failures in LLMs.
Outcome:	The proposed models solved 74% of the problems that the models initially failed to solve on their own.

Copied to clipboard

Yujia Qin, Yankai Lin, Ryuichi Takanobu, Zhiyuan Liu, Peng Li, Heng Ji, Minlie Huang, Maosong Sun, Jie Zhou

CodRED: A Cross-Document Relation Extraction Dataset for Acquiring Knowledge in the Wild (2021.emnlp-main)

Challenge:	Existing pre-training objectives do not explicitly model relational facts in text . Experimental results show that ERICA can improve typical PLMs on several language understanding tasks, including relation extraction, entity typing and question answering.
Approach:	They propose a contrastive learning framework ERICA to obtain a deep understanding of entities and relations in text.
Outcome:	The proposed framework can improve PLMs on several language understanding tasks, especially under low-resource settings.

Copied to clipboard

Yuan Yao, Jiaju Du, Yankai Lin, Peng Li, Zhiyuan Liu, Jie Zhou, Maosong Sun

CIA: Inferring the Communication Topology from LLM-based Multi-Agent Systems (2026.acl-long)

Challenge:	Existing relation extraction methods focus on extracting relational facts between entity pairs within single sentences or documents.
Approach:	They present a problem of cross-document relation extraction (CRE) using human annotations.
Outcome:	The proposed dataset is the first human-annotated cross-document RE dataset . it shows that it is challenging to existing RE methods including strong BERT-based models.

Copied to clipboard

Yongxuan Wu, Xixun Lin, He Zhang, Nan Sun, Kun Wang, Chuan Zhou, Shirui Pan, Yanan Cao

MiLe Loss: a New Loss for Mitigating the Bias of Learning Difficulties in Generative Language Models (2024.findings-naacl)

Challenge:	LLM-based multi-agent systems (MAS) have demonstrated remarkable capabilities in solving complex tasks.
Approach:	They propose a communication inference attack that constructs new adversarial queries to induce intermediate agents’ reasoning outputs and models their semantic correlations through the global bias disentanglement and LLM-guided weak supervision.
Outcome:	The proposed attack achieves an average AUC of 0.87 and a peak AUC up to 0.99, revealing the privacy risk in MAS.

Copied to clipboard

Zhenpeng Su, Zijia Lin, Baixue Baixue, Hui Chen, Songlin Hu, Wei Zhou, Guiguang Ding, Xing W

TAKE: Topic-shift Aware Knowledge sElection for Dialogue Generation (2022.coling-1)

Challenge:	Existing generative language models neglect an inherent challenge in text corpus during training, i.e., the imbalance between frequent tokens and infrequent ones.
Approach:	They propose a function to mitigate the imbalance between frequent and infrequent tokens . authors propose 'MiLe Loss' function to assess learning difficulty of tokens during training .
Outcome:	Experiments show that models with proposed model can improve on downstream benchmarks.

Copied to clipboard

Chenxu Yang, Zheng Lin, Jiangnan Li, Fandong Meng, Weiping Wang, Lanrui Wang, Jie Zhou

Noise Robust Named Entity Understanding for Voice Assistants (2021.naacl-industry)

Challenge:	Recent work finds that realizing who holds the initiative can help select knowledge . however, there is a strong semantic transition between two rounds, probably leading to initiative misjudgment .
Approach:	They propose a topic-shift Aware Knowledge sElector(TAKE) model which locates relevant parts from dialogue history to improve knowledge selection.
Outcome:	The proposed model outperforms baseline models on the WoW.

Copied to clipboard

Deepak Muralidharan, Joel Ruben Antony Moniz, Sida Gao, Xiao Yang, Justine Kao, Stephen Pulman, Atish Kothari, Ray Shen, Yinying Pan, Vivek Kaul, Mubarak Seyed Ibrahim, Gang Xiang, Nan Dun, Yidan Zhou, Andy O, Yuan Zhang, Pooja Chitkara, Xuan Wang, Alkesh Patel, Kushal Tayal, Roger Zheng, Peter Grasch, Jason D Williams, Lin Li

Chain-of-Rewrite: Aligning Question and Documents for Open-Domain Question Answering (2024.findings-emnlp)

Challenge:	Named Entity Recognition and Entity Linking are challenging for voice assistants . utterances are relatively short, so there is not much context to help disambiguate .
Approach:	They propose a Named Entity Understanding system that combines NER and EL in a joint reranking module.
Outcome:	The proposed framework improves NER accuracy by up to 3.13% and EL accuracy by 3.6% in F1 score . it also leads to better accuracies in other natural language understanding tasks .

Copied to clipboard

Chunlei Xin, Yaojie Lu, Hongyu Lin, Shuheng Zhou, Huijia Zhu, Weiqiang Wang, Zhongyi Liu, Xianpei Han, Le Sun

HoWToBench: Holistic Evaluation for LLM’s Capability in Human-level Writing using Tree of Writing (2026.acl-long)

Challenge:	Existing approaches to answer open-domain question have encountered term mismatch and limited interaction between IR systems and large language models.
Approach:	They propose a method which leverages the guidance and feedback gained from the analysis to provide faithful and consistent extensions for effective question answering.
Outcome:	Experiments on four open-domain question answering datasets show the proposed method performs well under zero-shot settings.

Copied to clipboard

Andrew Zhuoer Feng, Cunxiang Wang, Yu Luo, Lin Fan, Irene Zhou, Zikang Wang, Xiaotao Gu, Jie Tang, Hongning Wang, Minlie Huang

Challenge:	Evaluating the writing capabilities of large language models remains a significant challenge due to the multidimensional nature of writing skills and the limitations of existing metrics.
Approach:	They propose to model the aggregation weights of sub-features in a tree-structured workflow and propose a Chinese writing benchmark that mitigates biases.
Outcome:	The proposed tree-of-writing (ToW) measures the writing capabilities of large language models (LLMs) in Chinese and shows that it mitigates biases and achieves a 0.93 Pearson correlation with human judgments.

Entropy Ratio Clipping as a Soft Global Constraint for Stable Reinforcement Learning (2026.findings-acl)

Copied to clipboard

Zhenpeng Su, Leiyu Pan, Minxuan Lv, Tiehua Mei, Zijia Lin, Yuntao Li, Wenping Hu, Ruiming Tang, Kun Gai, Guorui Zhou

Continual Relation Learning via Episodic Memory Activation and Reconsolidation (2020.acl-main)

Challenge:	Large language model post-training often adopts an off-policy training paradigm . however, the off-poliicy training model introduces distribution shifts that push the policy beyond the trust region.
Approach:	They propose to use the entropy ratio as a global metric to measure the relative change in policy exploration throughout updates.
Outcome:	Experiments show that the proposed metric improves performance across multiple benchmarks.

Copied to clipboard

Xu Han, Yi Dai, Tianyu Gao, Yankai Lin, Zhiyuan Liu, Peng Li, Maosong Sun, Jie Zhou

Challenge:	Existing methods to learn incessantly emerging novel relations are overfitting the few memorized examples of old relations, causing confusion among existing relations.
Approach:	They introduce episodic memory activation and reconsolidation (EMAR) to continual relation learning.
Outcome:	The proposed method outperforms state-of-the-art models in catastrophic forgetting old relations.

RICA: Evaluating Robust Inference Capabilities Based on Commonsense Axioms (2021.emnlp-main)

Copied to clipboard

Pei Zhou, Rahul Khanna, Seyeon Lee, Bill Yuchen Lin, Daniel Ho, Jay Pujara, Xiang Ren

RASAT: Integrating Relational Structures into Pretrained Seq2Seq Model for Text-to-SQL (2022.emnlp-main)

Challenge:	Pre-trained language models have impressive performance on commonsense inference benchmarks, but their ability to make robust inferences is debated.
Approach:	They propose a challenge that evaluates robust commonsense inference despite textual perturbations using commonsensical knowledge bases and probe PTLMs across two different evaluation settings.
Outcome:	The proposed procedure evaluates robust commonsense inference despite textual perturbations using commonsensense knowledge bases and probe PTLMs across two evaluation settings.

Copied to clipboard

Jiexing Qi, Jingyao Tang, Ziwei He, Xiangpeng Wan, Yu Cheng, Chenghu Zhou, Xinbing Wang, Quanshi Zhang, Zhouhan Lin

A Survey of Large Language Model-Based Search Agents (2026.acl-long)

Challenge:	Experimental results show RASAT can leverage a variety of relational structures while inheriting the pretrained parameters from the T5 model.
Approach:	They propose a Transformer seq2seq architecture augmented with relation-aware self-attention that leverages relational structures while inheriting pretrained parameters from the T5 model.
Outcome:	The proposed model can leverage relational structures while inheriting pretrained parameters from the T5 model effectively.

Copied to clipboard

Yunjia Xi, Jianghao Lin, Yongzhao Xiao, Zheli Zhou, Rong Shan, Te Gao, Jiachen Zhu, Weiwen Liu, Yong Yu, Weinan Zhang

Scaling Behavior for Large Language Models regarding Numeral Systems: An Example using Pythia (2024.findings-emnlp)

Challenge:	Large Language Models (LLMs) have revolutionized web search, but their integration is static and cannot handle complex contexts.
Approach:	They analyze existing research and analyze existing work from the perspectives of architecture, optimization, application, and evaluation.
Outcome:	The proposed models can comprehend user intentions and context and execute multi-turn retrieval with dynamic planning, extending search capabilities far beyond the web.

Copied to clipboard

Zhejian Zhou, JIayu Wang, Dahua Lin, Kai Chen

Wav-BERT: Cooperative Acoustic and Linguistic Representation Learning for Low-Resource Speech Recognition (2021.findings-emnlp)

Challenge:	Large Language Models (LLMs) are struggling with performing numeric operations accurately.
Approach:	They propose to use different numeral systems to scale different numerates in transformer-based large language models.
Outcome:	The proposed model is more data-efficient than base 10 and base 10 3 . the model is also more efficient on addition and multiplication .

Copied to clipboard

Guolin Zheng, Yubei Xiao, Ke Gong, Pan Zhou, Xiaodan Liang, Liang Lin

Learning Relation Alignment for Calibrated Cross-modal Retrieval (2021.acl-long)

Challenge:	Existing methods to learn the transfer from speech to text are unexplored . how to solve the representation discrepancy of speech and text is unexplorable .
Approach:	They propose a cooperative acoustic and linguistic representation learning method to fuse and utilize contextual information of speech and text.
Outcome:	The proposed method outperforms existing methods on low-resource speech recognition.

Copied to clipboard

Shuhuai Ren, Junyang Lin, Guangxiang Zhao, Rui Men, An Yang, Jingren Zhou, Xu Sun, Hongxia Yang

Continual Learning in Task-Oriented Dialogue Systems (2021.emnlp-main)

Challenge:	despite advances in multimodal pre-training, cross-modal retrieval remains challenging . lack of relation consistency impairs contextualized representation of image-text pairs .
Approach:	They propose a new metric to quantify the relation consistency by measuring the semantic distance between linguistic and visual relations.
Outcome:	The proposed method boosts the performance of prevailing models on Flickr30k and MS COCO datasets by a considerable margin.

Copied to clipboard

Andrea Madotto, Zhaojiang Lin, Zhenpeng Zhou, Seungwhan Moon, Paul Crook, Bing Liu, Zhou Yu, Eunjoon Cho, Pascale Fung, Zhiguang Wang

Dialogue Response Selection with Hierarchical Curriculum Learning (2021.acl-long)

Challenge:	Existing continuous learning systems are not designed to add new domains and functionalities through time without incurring the high cost of retraining the whole system.
Approach:	They propose a first-ever continual learning benchmark for task-oriented dialogue systems . they propose 'architecture' method based on residual adapters to implement continual training .
Outcome:	The proposed architectural method performs better than multitask learning while being 20X faster in learning new domains.

Copied to clipboard

Yixuan Su, Deng Cai, Qingyu Zhou, Zibo Lin, Simon Baker, Yunbo Cao, Shuming Shi, Nigel Collier, Yan Wang

Different Tunes Played with Equal Skill: Exploring a Unified Optimization Subspace for Parameter-Efficient Tuning (2022.findings-emnlp)

Challenge:	Empirical studies on three benchmark datasets with three state-of-the-art matching models demonstrate that the proposed learning framework significantly improves the model performance across various evaluation metrics.
Approach:	They propose a hierarchical curriculum learning framework that trains matching models in an “easy-to-difficult” scheme.
Outcome:	The proposed framework significantly improves the model performance across evaluation metrics on three benchmark datasets with three state-of-the-art matching models.

Copied to clipboard

Jing Yi, Weize Chen, Yujia Qin, Yankai Lin, Ning Ding, Xu Han, Zhiyuan Liu, Maosong Sun, Jie Zhou

MMAPS: End-to-End Multi-Grained Multi-Modal Attribute-Aware Product Summarization (2024.lrec-main)

Challenge:	Existing delta tuning algorithms freeze most of the parameters and only optimize minimal adaptive parameters.
Approach:	They propose to decompose DETs into a unified optimization subspace and conduct optimization within the subspace.
Outcome:	The proposed DETs achieve comparable performance to the original DET and can be transferred to another DET with non-trivial performance.

Copied to clipboard

Tao Chen, Ze Lin, Hui Li, Jiayi Ji, Yiyi Zhou, Guanbin Li, Rongrong Ji

COIG-CQIA: Quality is All You Need for Chinese Instruction Fine-tuning (2025.findings-naacl)

Challenge:	Existing product summarization methods lack end-to-end product summaries and multi-grained multi-modal modeling.
Approach:	They propose an end-to-end multi-grained multi-modal attribute-aware product summarization method that jointly models product attributes and generates product summaries.
Outcome:	The proposed method outperforms state-of-the-art product summarization methods on a large-scale Chinese e-commence dataset.

Copied to clipboard

Yuelin Bai, Xeron Du, Yiming Liang, Leo Jin, Junting Zhou, Ziqiang Liu, Feiteng Fang, Mingshan Chang, Tianyu Zheng, Xincheng Zhang, Nuo Ma, Zekun Moore Wang, Ruibin Yuan, Haihong Wu, Hongquan Lin, Wenhao Huang, Jiajun Zhang, Chenghua Lin, Jie Fu, Min Yang, Shiwen Ni, Ge Zhang

A Multi-label Multi-hop Relation Detection Model based on Relation-aware Sequence Generation (2021.findings-emnlp)

Challenge:	Existing datasets for Chinese instruction tuning are not well-aligned with Chinese users’ interaction patterns.
Approach:	They propose to use Chinese instruction tuning datasets to improve instruction fine-tuning for Chinese users.
Outcome:	The proposed dataset shows that Chinese models achieve competitive performance in diverse benchmarks.

Copied to clipboard

Linhai Zhang, Deyu Zhou, Chao Lin, Yulan He

Knowledge Representation

Challenge:	Existing methods treat multi-label learning problem as a single label . Existing approaches focus on measuring semantic similarity of questions and candidate relations .
Approach:	They propose to solve multi-hop relation detection problem by generating sequences of hops and labels.
Outcome:	The proposed method is effective in KBQA, despite the unknown number of labels and hops.

TeachMaster: Generative Teaching via Code (2026.acl-industry)

Copied to clipboard

Yuheng Wang, Runde Yang, Lin Wu, Jie Zhang, Jingru Fan, Tianle Zhou, Ruoyu Fu, Huatao Li, Ruijie Shi, Siheng Chen, Weinan E, Chen Qian

MT-Bench-101: A Fine-Grained Benchmark for Evaluating Large Language Models in Multi-Turn Dialogues (2024.acl-long)

Challenge:	Existing methods for creating video content are limited by high costs and slow update cycles.
Approach:	They propose a paradigm shifting educators from manual creators to high-level directors who focus on pedagogical intents while agents handle execution.
Outcome:	The proposed framework reduces production costs to 0.3% of traditional course videos and provides a robust solution for scalable education.

Copied to clipboard

Ge Bai, Jie Liu, Xingyuan Bu, Yancheng He, Jiaheng Liu, Zhanhui Zhou, Zhuoran Lin, Wenbo Su, Tiezheng Ge, Bo Zheng, Wanli Ouyang

ELLE: Efficient Lifelong Pre-training for Emerging Data (2022.findings-acl)

Challenge:	Large Language Models (LLMs) have greatly enhanced dialogue systems, but evaluation of their capabilities remains a challenge.
Approach:	They propose a model to evaluate the fine-grained abilities of Large Language Models in multi-turn dialogues.
Outcome:	The proposed model evaluates 21 popular chatbots based on MT-Bench-101 . it includes 3 overarching abilities and 13 distinct tasks within multi-turn dialogue scenarios.

Copied to clipboard

Yujia Qin, Jiajie Zhang, Yankai Lin, Zhiyuan Liu, Peng Li, Maosong Sun, Jie Zhou

SciFlow-Bench: Evaluating Structure-Aware Scientific Diagram Generation via Inverse Parsing (2026.acl-long)

Challenge:	Existing pre-trained language models are typically trained with static data, ignoring that streaming data of various sources may continuously grow.
Approach:	They propose to use function preserved model expansion to expand existing PLM's width and depth to improve efficiency of knowledge acquisition.
Outcome:	The proposed model improves pre-training efficiency and performance over existing models on BERT and GPT.

Copied to clipboard

Tong Zhang, Honglin Lin, Zhou Liu, Chong Chen, Wentao Zhang

Leveraging Unimodal Self-Supervised Learning for Multimodal Audio-Visual Speech Recognition (2022.acl-long)

Challenge:	Existing benchmarks for scientific diagram generation rely on image-centric metrics or evaluation of intermediate symbolic representations rather than final rendered images.
Approach:	They propose a structure-first benchmark for evaluating scientific diagram generation from pixel-level outputs.
Outcome:	The proposed benchmark evaluates scientific diagram generation directly from pixel-level outputs.

Copied to clipboard

Xichen Pan, Peiyu Chen, Yichen Gong, Helong Zhou, Xinbing Wang, Zhouhan Lin

Non-Sequential Graph Script Induction via Multimedia Grounding (2023.acl-long)

Challenge:	Existing methods for audio-visual speech recognition use extra data to increase performance . a recent study shows that the use of unimodal self-supervised learning improves performance on multimodal tasks.
Approach:	They propose to use unimodal self-supervised learning to train AVSR models on unlabelled unilateral data.
Outcome:	The proposed model improves on lip reading sentences 2 by 30% even without an external language model.

Copied to clipboard

Yu Zhou, Sha Li, Manling Li, Xudong Lin, Shih-Fu Chang, Mohit Bansal, Heng Ji

Learning from Context or Names? An Empirical Study on Neural Relation Extraction (2020.emnlp-main)

Challenge:	Existing scripts for everyday tasks are presented in a linear manner, which does not reflect the flexibility displayed by people executing tasks in real life.
Approach:	They propose to use loosely aligned videos to train a non-sequential graph script induction task by using a multimodal framework to ground procedural videos to WikiHow textual steps.
Outcome:	The proposed model outperforms the WikiHow linear baseline by 48.76% . it can predict future steps given a partial step sequence and generate explicit graph scripts .

Copied to clipboard

Hao Peng, Tianyu Gao, Xu Han, Yankai Lin, Peng Li, Zhiyuan Liu, Maosong Sun, Jie Zhou

Language Prior Is Not the Only Shortcut: A Benchmark for Shortcut Learning in VQA (2022.findings-emnlp)

Challenge:	Existing datasets may leak shallow heuristics via entity mentions, thus contributing to the high performance on RE benchmarks.
Approach:	They propose an entity-masked contrastive framework for relation extraction to gain a deeper understanding on textual context and type information while avoiding rote memorization of entities.
Outcome:	The proposed framework improves the effectiveness and robustness of neural models in different RE scenarios.

Copied to clipboard

Qingyi Si, Fandong Meng, Mingyu Zheng, Zheng Lin, Yuanxin Liu, Peng Fu, Yanan Cao, Weiping Wang, Jie Zhou

Question Answering

Challenge:	Visual Question Answering (VQA) models are prone to learn the shortcut solution formed by dataset biases rather than the intended solution.
Approach:	They propose a dataset that considers varying types of shortcuts by constructing different distribution shifts in multiple OOD test sets.
Outcome:	The proposed dataset considers varying types of shortcuts by constructing different distribution shifts in multiple OOD test sets.

Stealing Training Data from Large Language Models in Decentralized Training through Activation Inversion Attack (2025.acl-long)

Copied to clipboard

Chenxi Dai, Lin Lu, Pan Zhou

Rethinking Vocabulary Augmentation: Addressing the Challenges of Low-Resource Languages in Multilingual Models (2025.coling-main)

Challenge:	Decentralized training is a resource-efficient framework to democratize training of large language models.
Approach:	They propose an activation inversion attack to exploit privacy leakage from training data . they construct a shadow dataset comprising text labels and corresponding activations .
Outcome:	The proposed attack surface is based on a shadow dataset and public datasets . the proposed attack model reconstructs training data from activations in victim decentralized training.

Copied to clipboard

Nankai Lin, Peijian Zeng, Weixiong Zheng, Shengyi Jiang, Dong Zhou, Aimin Yang

Training Trajectories of Language Models Across Scales (2023.acl-long)

Challenge:	Existing methods to augment vocabularies ignore the disparities between model representation and frequency distributions.
Approach:	They propose an Entropy-Consistency Word Selection method which integrates semantic and frequency metrics for vocabulary augmentation.
Outcome:	The proposed method improves performance for low-resource languages compared to high-resourced ones . it integrates semantic and frequency metrics for vocabulary augmentation .

Copied to clipboard

Mengzhou Xia, Mikel Artetxe, Chunting Zhou, Xi Victoria Lin, Ramakanth Pasunuru, Danqi Chen, Luke Zettlemoyer, Veselin Stoyanov

WildFeedback: Aligning LLMs With In-situ User Interactions And Feedback (2026.acl-long)

Challenge:	Scaling up language models has led to unprecedented performance gains, but little is understood about how the training dynamics change as models get larger.
Approach:	They analyze the training checkpoints of different-sized OPT models on next-token prediction, sequence-level generation and downstream tasks.
Outcome:	The results show that language models of different sizes learn more during training . small models halt at hallucinations, larger ones learn to assign lower probabilities .

Copied to clipboard

Taiwei Shi, Zhuoer Wang, Longqi Yang, Ying-Chun Lin, Zexue He, Mengting Wan, Pei Zhou, Sujay Kumar Jauhar, Sihao Chen, Shan Xia, Hongfei Zhang, Jieyu Zhao, Xiaofeng Xu, Xia Song, Jennifer Neville

Challenge:	Traditional alignment methods rely on human annotations and are subjective and misalignment with real-world user preferences.
Approach:	They propose a framework that leverages in-situ user feedback during conversations with LLMs to create preference datasets automatically.
Outcome:	The proposed framework identifies and classifies user feedback to LLM responses between conversation turns and creates examples of preferred and dispreferred responses according to user preferences.

Privacy-Preserving Reasoning with Knowledge-Distilled Parametric Retrieval Augmented Generation (2026.findings-acl)

Copied to clipboard

Jinwen Chen, Hainan Zhang, Liang Pang, Yongxin Tong, Haibo Zhou, Wei Lin, Zhiming Zheng

Fair Text-Attributed Graph Representation Learning (2025.findings-emnlp)

Challenge:	Existing RAG systems require uploading local documents to the cloud, resulting in inference latency and poor generalization on out-of-distribution (OOD) inputs.
Approach:	They propose a generalizable knowledge-distilled parametric RAG model aligned with standard RAG in document structure and parameter activation.
Outcome:	The proposed model outperforms baselines in accuracy and generalizes well on out-of-distribution (OOD) data.

Copied to clipboard

Ruilin Luo, Tianle Gu, Lin Wang, Yunfeng Zhou, Songtao Jiang, Lei Wang, Yujiu Yang

Sparse Latents Steer Retrieval-Augmented Generation (2025.acl-long)

Challenge:	Text-Attributed Graphs (TAGs) inherit issues from Graph Neural Networks such as fairness.
Approach:	They propose to evolve LM-as-encoder to LM as-fair-encoding process to explore fairness in TAGRL.
Outcome:	The proposed process can be integrated with fairness-enhancing strategies on the GNNs decoder side.

Copied to clipboard

Chunlei Xin, Shuheng Zhou, Huijia Zhu, Weiqiang Wang, Xuanang Chen, Xinyan Guan, Yaojie Lu, Hongyu Lin, Xianpei Han, Le Sun

Transferring General Multimodal Pretrained Models to Text Recognition (2023.findings-acl)

Challenge:	In this study, we uncover interpretable latents that govern RAG behavior in large language models . Sparse Autoencoders are used to control large language model (LLM) behavior .
Approach:	They leverage Sparse Autoencoders within the LLaMA Scope to uncover latents that govern RAG behaviors.
Outcome:	The proposed model can be used to control large language models without architectural modifications.

Copied to clipboard

Junyang Lin, Xuancheng Ren, Yichang Zhang, Gao Liu, Peng Wang, An Yang, Chang Zhou

Hate Speech Detection Based on Sentiment Knowledge Sharing (2021.acl-long)

Challenge:	Existing methods for text recognition rely on large-scale pretraining on human-annotated or synthetic data.
Approach:	They propose a method to transfer multimodal pretrained models to text recognition using image captioning.
Outcome:	The proposed method outperforms the baselines and achieves state-of-the-art performance in the Chinese text recognition benchmark.

Copied to clipboard

Xianbing Zhou, Yang Yong, Xiaochao Fan, Ge Ren, Yunfeng Song, Yufeng Diao, Liang Yang, Hongfei Lin

Sentiment Analysis

Challenge:	Existing methods for hate speech detection are stereotyped and biased . et al., a paper examining the effectiveness of multitask learning in hate speech recognition tasks .
Approach:	They propose a hate speech detection framework based on sentiment knowledge sharing . they extract affective features of the target sentence and use sentiment features from external resources .
Outcome:	The proposed model can detect hate speech over two public datasets.

Position Paper: Data-Centric AI in the Age of Large Language Models (2024.findings-emnlp)

Copied to clipboard

Xinyi Xu, Zhaoxuan Wu, Rui Qiao, Arun Verma, Yao Shu, Jingtan Wang, Xinyuan Niu, Zhenfeng He, Jiangwei Chen, Zijian Zhou, Gregory Kang Ruey Lau, Hieu Dao, Lucas Agussurja, Rachael Hwee Ling Sim, Xiaoqiang Lin, Wenyang Hu, Zhongxiang Dai, Pang Wei Koh, Bryan Kian Hsiang Low

Dynamic Knowledge Distillation for Pre-trained Language Models (2021.emnlp-main)

Challenge:	a paper proposes a data-centric perspective of AI research, focusing on large language models.
Approach:	They propose a data-centric viewpoint of AI research, focusing on large language models . they propose four scenarios centered around data, including data curation, attribution, knowledge transfer .
Outcome:	The proposed research focuses on large language models with data centric benchmarks . the proposed benchmarks can be used to develop new data curation methods .

Copied to clipboard

Lei Li, Yankai Lin, Shuhuai Ren, Peng Li, Jie Zhou, Xu Sun

CascadeBERT: Accelerating Inference of Pre-trained Language Models via Calibrated Complete Models Cascade (2021.findings-emnlp)

Challenge:	Existing methods conduct knowledge distillation statically, e.g., student model aligns output distribution to teacher model on pre-defined training dataset.
Approach:	They propose a dynamic knowledge distillation that empowers the student to adjust the learning procedure according to its competency . they find it is promising and provide discussions on potential future directions towards more efficient methods .
Outcome:	The proposed method can boost student model performance while accelerating training . the proposed method reduces memory usage and accelerates model inference .

Copied to clipboard

Lei Li, Yankai Lin, Deli Chen, Shuhuai Ren, Peng Li, Jie Zhou, Xu Sun

CuBridge: An LLM-Based Framework for Understanding and Reconstructing High-Performance Attention Kernels (2026.acl-long)

Challenge:	Experimental results show that CascadeBERT can achieve an overall 15% improvement under 4x speed-up compared with existing dynamic early exiting methods on six classification tasks.
Approach:	They propose a framework which emits predictions in internal layers without passing through the entire model.
Outcome:	The proposed framework can achieve 15% improvement under 4x speed-up compared with existing methods on six classification tasks yielding more calibrated and accurate predictions.

Copied to clipboard

Xing Ma, Yangjie Zhou, Wu Sun, Zihan Liu, Jingwen Leng, Yun Lin, Shixuan Sun, Minyi Guo, Jin Song Dong

Imitation Learning for Non-Autoregressive Neural Machine Translation (P19-1)

Challenge:	Existing approaches to support diverse attention variants trade performance for flexibility . expert-written kernels achieve high efficiency but are difficult to adapt .
Approach:	They propose a framework that adapts expert-written attention kernels to GPUs . they use a structured lift–transfer–lower workflow to make execution explicit .
Outcome:	The proposed framework outperforms existing frameworks and compilers on diverse variants and GPU platforms.

Copied to clipboard

Bingzhen Wei, Mingxuan Wang, Hao Zhou, Junyang Lin, Xu Sun

Machine Translation

Challenge:	Existing non-autoregressive translation models lack parallel decoding, which is a bottleneck for NMT decoding.
Approach:	They propose a framework for non-autoregressive machine translation that emulates the autoregressive model by sampling sentence length in parallel.
Outcome:	The proposed model achieves 31.85 BLEU on WMT16 RoEn and 30.68 BLUE on IWSLT16 EnDe on the IWSLD16, WMT14 and WMT15 datasets.

DocRED: A Large-Scale Document-Level Relation Extraction Dataset (P19-1)

Copied to clipboard

Yuan Yao, Deming Ye, Peng Li, Xu Han, Yankai Lin, Zhenghao Liu, Zhiyuan Liu, Lixin Huang, Jie Zhou, Maosong Sun

A Universal Discriminator for Zero-Shot Generalization (2023.acl-long)

Challenge:	Existing relation extraction methods focus on extracting intra-sentence relations for single entities.
Approach:	They propose a relation extraction dataset from Wikipedia and Wikidata with three features . document-level relation extraction is a task to identify relational facts between entities .
Outcome:	The proposed dataset is the largest human-annotated dataset for document-level RE from plain text.

Copied to clipboard

Haike Xu, Zongyu Lin, Jing Zhou, Yanan Zheng, Zhilin Yang