Papers by Zhao Guo

Scaling Laws for Code: Every Programming Language Matters (2026.findings-acl)

Challenge:	Extensive experiments on large-scale mathematical reasoning and out-of-distribution tasks demonstrate the effectiveness and generalization of the proposed method.
Approach:	They propose a method that quantifies novelty across the outcome space and semantic process space by using reward or solution divergence.
Outcome:	Experiments on Qwen2.5-Math-7B demonstrate the proposed method is general and efficient.

Copied to clipboard

Jian Yang, Shuyue Guo, Linzheng Chai, Wei Zhang, Aishan Liu, Chuan Hao, Zhoujun Li, Xin Zhao, Xianglong Liu, Weifeng Lv, Bryan Dai

The Illusion of Randomness: How LLMs Fail to Emulate Stochastic Decision-Making in Rock-Paper-Scissors Games? (2025.findings-emnlp)

Challenge:	Existing studies focus on language-agnostic settings, neglecting the inherently multilingual nature of modern software development.
Approach:	They propose a proportion-dependent scaling law that prioritizes high-utility languages . they propose PLs to have varying effects during pre-training that affect model performance .
Outcome:	The proposed scaling law is based on 1000+ experiments across multiple languages and models.

Copied to clipboard

Zihao Guo, Hongtao Lv, Chaoli Zhang, Yibowen Zhao, Yixin Zhang, Lizhen Cui

Challenge:	Prior research indicates that large language models articulate the theoretical probability distributions associated with optimal strategic choices, but their actual decision-making diverges from these prescriptions.
Approach:	a systematic evaluation of 20 state-of-the-art LLMs reveals a cognitive bias gap . intrinsic biases inherited from pre-training corpora alone are insufficient to explain deviations . a semantic-free paradigm strips away intrinsic bias to isolate pure positional bias .
Outcome:	a systematic evaluation of 20 state-of-the-art LLMs shows that intrinsic biases are insufficient to explain deviations.

The Elephant in the Room: Exploring the Role of Neutral Words in Language Model Group-Agnostic Debiasing (2025.findings-acl)

Copied to clipboard

Xinwei Guo, Jiashi Gao, Junlei Zhou, Jiaxin Zhang, Guanhua Chen, Xiangyu Zhao, Quanying Liu, Haiyan Wu, Xin Yao, Xuetao Wei

LLMs Assist NLP Researchers: Critique Paper (Meta-)Reviewing (2024.emnlp-main)

Challenge:	Large Language Models (LLMs) are increasingly integrated into our daily lives, raising ethical concerns, especially about perpetuating stereotypes.
Approach:	They propose a method that incorporates a neutral word semantics-based loss function to alleviate the deterioration of the LMS during debiasing.
Outcome:	The proposed method alleviates the deterioration of the Language Modeling Score (LMS) by incorporating a neutral word semantics-based loss function.

Copied to clipboard

Jiangshu Du, Yibo Wang, Wenting Zhao, Zhongfen Deng, Shuaiqi Liu, Renze Lou, Henry Zou, Pranav Narayanan Venkit, Nan Zhang, Mukund Srinath, Haoran Zhang, Vipul Gupta, Yinghui Li, Tao Li, Fei Wang, Qin Liu, Tianlin Liu, Pengzhi Gao, Congying Xia, Chen Xing, Cheng Jiayang, Zhaowei Wang, Ying Su, Raj Shah, Ruohao Guo, Jing Gu, Haoran Li, Kangda Wei, Zihao Wang, Lu Cheng, Surangika Ranathunga, Meng Fang, Jie Fu, Fei Liu, Ruihong Huang, Eduardo Blanco, Yixin Cao, Rui Zhang, Philip Yu, Wenpeng Yin

Challenge:	a comparative analysis of paper (meta-)reviews by large language models (LLMs) aims to identify and distinguish LLMs from human activities .
Approach:	They present a comparative analysis to identify and distinguish LLM activities from human activities.
Outcome:	The proposed analysis aims to improve recognition of instances when someone implicitly uses LLMs for reviewing activities.

Detoxifying Large Language Models via the Diversity of Toxic Samples (2025.emnlp-main)

Copied to clipboard

Ying Zhao, Yuanzhao Guo, Xuemeng Weng, Yuan Tian, Wei Wang, Yi Chang

A Frame-based Sentence Representation for Machine Reading Comprehension (2020.acl-main)

Challenge:	Existing methods for analyzing and utilizing toxic samples are limited . current methods fail to fully harness their potential .
Approach:	They propose a diverse detoxification framework that leverages toxic samples' diversity . they propose MPSG strategy and SC-DPO approach to elicit personalized toxic responses .
Outcome:	The proposed framework could be used to optimize large language models for user safety . it incorporates two components: MPSG strategy and SC-DPO approach .

Copied to clipboard

Shaoru Guo, Ru Li, Hongye Tan, Xiaoli Li, Yong Guan, Hongyan Zhao, Yueping Zhang

Representation Learning

Challenge:	Existing machine learning approaches do not have above semantic knowledge to address complicated MRC questions.
Approach:	They propose a frame-based Sentence Representation method which integrates frame semantic knowledge to facilitate sentence modelling.
Outcome:	The proposed method performs better than state-of-the-art methods on machine reading comprehension task.

EVA: Evolving Semantic Adversaries for Red-Teaming GUI Agents Against Environmental Injection Attacks (2026.findings-acl)

Copied to clipboard

Yijie Lu, Manman Zhao, Tianjie Ju, Zihe Yan, Xinbei Ma, Yuan Guo, Daizong Ding, Gongshen Liu, Zhuosheng Zhang

FLAIR: Steering LLM Mathematical Problem Solving based on A Fuzzy-Logic-AssIsted Reasoner (2026.acl-long)

Challenge:	Existing methods for red-teaming face a trade-off between requiring target-specific knowledge and incurring prohibitive computational costs.
Approach:	They propose a framework that evolves payloads exclusively on the semantic dimension via a discovery-deployment pipeline.
Outcome:	Experiments show that EVA outperforms baselines in terms of attack success rate while evolving benign seeds into successful attacks within 1.18 to 1.71 iterations.

Copied to clipboard

Hao Wu, Hongru Sun, Wanqing Li, Xinguo Yu, Hao Ming, Xiao Luo, Wenbin Zhang, Jiahong Zhao, Yi Guo, Jie Yang

Event-Radar: Event-driven Multi-View Learning for Multimodal Fake News Detection (2024.acl-long)

Challenge:	Existing approaches to mathematical reasoning rely on static heuristics or pre-determined reasoning strategies.
Approach:	They propose an adaptive framework that integrates fuzzy theory into LLM-based mathematical reasoning.
Outcome:	The proposed framework outperforms state-of-the-art models while offering effective and interpretable diagnostics of intermediate problem-solving states.

Copied to clipboard

Zihan Ma, Minnan Luo, Hao Guo, Zhi Zeng, Yiran Hao, Xiang Zhao

STARS: A Unified Framework for Singing Transcription, Alignment, and Refined Style Annotation (2025.findings-acl)

Challenge:	Existing methods for detecting multimedia fake news have demonstrated excellent results . however, addressing event-level inconsistency and learning from poor-quality news remains a challenge .
Approach:	They propose an Event-diven fake news detection framework that integrates visual manipulation, textual emotion and multimodal inconsistency at event-level for fake news identification.
Outcome:	The proposed framework performs well on three large-scale fake news detection benchmarks.

Copied to clipboard

Wenxiang Guo, Yu Zhang, Changhao Pan, Zhiyuan Zhu, Ruiqi Li, ZheTao Chen, Wenhao Xu, Fei Wu, Zhou Zhao

Speech & Audio in NLP

Challenge:	Existing automated singing annotation (ASA) methods tackle isolated aspects of the annotation pipeline.
Approach:	They propose a framework that addresses transcription, alignment, and refined style annotations.
Outcome:	The proposed framework delivers comprehensive multi-level annotations encompassing: (1) precise phoneme-audio alignment, (2) robust note transcription and temporal localization, (3) expressive vocal technique identification, and (4) global stylistic characterization including emotion and pace.

BANER: Boundary-Aware LLMs for Few-Shot Named Entity Recognition (2025.coling-main)

Copied to clipboard

Quanjiang Guo, Yihong Dong, Ling Tian, Zhao Kang, Yu Zhang, Sijie Wang

Information Extraction & Text Mining

Challenge:	Named Entity Recognition (NER) is a fundamental task in Natural Language Processing (NLP) that aims to detect the entity spans of text and classify them into pre-defined set of entity types.
Approach:	They propose a boundary-aware contrastive learning strategy to enhance the LLM’s ability to perceive entity boundaries for generalized entity spans.
Outcome:	The proposed framework outperforms prior methods and validates its effectiveness across a range of LLM architectures.

Code Representation Pre-training with Complements from Program Executions (2024.emnlp-industry)

Copied to clipboard

Jiabo Huang, Jianyu Zhao, Yuyang Rong, Yiwen Guo, Yifeng He, Hao Chen

Towards Advanced Mathematical Reasoning for LLMs via First-Order Logic Theorem Proving (2025.emnlp-main)

Challenge:	Existing languages have syntactic representations of code to improve code intelligence, but they are difficult to learn from code.
Approach:	They propose to embed dynamic information of programs revealed by their test cases into feature representations of code as complements.
Outcome:	The proposed method yields 6%/19% mAP improvements over its masked language modeling counterparts.

Copied to clipboard

Chuxue Cao, Mengze Li, Juntao Dai, Jinluan Yang, Zijian Zhao, Shengyu Zhang, Weijie Shi, Chengzhong Liu, Sirui Han, Yike Guo

Large Language Models Can Learn Representation in Natural Language (2024.findings-acl)

Challenge:	Large language models (LLMs) have shown promising first-order logic (FOL) reasoning capabilities with applications in various areas, but their effectiveness in complex mathematical reasoning involving multi-step FOL deductions remains under-explored.
Approach:	They propose a self-adaptive solution that enhances the Diversity and REAsonability of LLMs’ generation strategies by introducing an Axiom-Driven Strategy Diversification mechanism and a Sub-Proposition Error Feedback to help LLM reflect on and correct their proofs.
Outcome:	The proposed model improves diversity and REAsonability of LLMs’ generation strategies by introducing an Axiom-Driven Strategy Diversification mechanism and a Sub-Proposition Error Feedback to help LLM reflect on and correct proofs.

Copied to clipboard

Yiduo Guo, Yaobo Liang, Dongyan Zhao, Nan Duan

LiveCANNBench: Benchmark SWE AI Coding for Ascend CANN (2026.findings-acl)

Challenge:	Large Language Models (LLMs) are unable to complete complex tasks involving multiple entities, such as tool APIs.
Approach:	They propose a method which uses natural language representations to refine entity descriptions for improved retrieval and LLM utilization.
Outcome:	The proposed method improves GPT-4's performance on classification tasks and API call tasks.

Copied to clipboard

Sijie Wang, Kai Zhao, Wee Peng Tay, Shuo Zhang, Chengwen Liu, Quanjiang Guo, Ren Junhao, Xin Li, Heng Lian, Jingdi Lei, Rui She, Huacan Wang, Ronghao Chen

Challenge:	Recent advances in agents have enabled multi-file, multi-language, and dependency-aware AI coding.
Approach:	They propose an SWE-level benchmark for AI coding in the Huawei Ascend CANN software stack.
Outcome:	The proposed benchmark is constructed from real-world CANN repositories and consists of over 400 task instances spanning multiple file, multi-language, and execution-aware coding challenges.

Importance of Synthesizing High-quality Data for Text-to-SQL Parsing (2023.findings-acl)

Copied to clipboard

Yiqun Hu, Yiyun Zhao, Jiarong Jiang, Wuwei Lan, Henghui Zhu, Anuj Chauhan, Alexander Hanbo Li, Lin Pan, Jun Wang, Chung-Wei Hang, Sheng Zhang, Jiang Guo, Mingwen Dong, Joseph Lilien, Patrick Ng, Zhiguo Wang, Vittorio Castelli, Bing Xiang

English as Defense Proxy: Mitigating Multilingual Jailbreak via Eliciting English Safety Knowledge (2025.findings-emnlp)

Challenge:	Existing text-to-SQL parsers lack the data to perform well with augmented synthetic data.
Approach:	They propose a framework that imposes strong typing constraints and incorporates key relationships from schema.
Outcome:	The proposed framework improves on the high-quality synthesized SQL and natural language question (NLQ) models have significant accuracy boosts and achieve new state-of-the-art performance on spider.

Copied to clipboard

Zekai Zhang, Yiduo Guo, Jiuheng Lin, Shanghaoran Quan, Huishuai Zhang, Dongyan Zhao

Masked Text-to-Audio Flow-Matching and Reward Feedback Optimization (2026.findings-acl)

Challenge:	Large language models excel in many tasks, but their safety guarantees vary by language.
Approach:	They propose a unified approach that leverages English as a universal safety anchor.
Outcome:	The proposed approach leverages English as defense proxy (E-Proxy) to transfer safety knowledge across languages.

Copied to clipboard

Rongjie Huang, Dongchao Yang, Wenxiang Guo, Huadai Liu, Xize Cheng, Zehan Wang, Zhou Zhao, Xixin Wu, Helen M. Meng

Chain of Ideas: Revolutionizing Research Via Novel Idea Development with LLM Agents (2025.findings-emnlp)

Challenge:	Experimental results show that Flow-matching generative models can scale training by increasing data, computational resources, and model size.
Approach:	They propose a flow-matching transformer with masked generative modeling for scaling text-to-audio inference-time prediction.
Outcome:	The proposed model scales inference-time computations by masking generation and re-predicting them through iterative decoding.

Copied to clipboard

Long Li, Weiwen Xu, Jiayan Guo, Ruochen Zhao, Xingxuan Li, Yuqian Yuan, Boqiang Zhang, Yuming Jiang, Yifei Xin, Ronghao Dang, Yu Rong, Deli Zhao, Tian Feng, Lidong Bing

Challenge:	Existing methods for idea generation either trivially prompt LLMs or expose LLM to extensive literature without indicating useful information.
Approach:	They propose a chain-of-ideas agent that organizes literature in a chains structure . they propose evaluating idea-generation methods from different perspectives .
Outcome:	The proposed agent outperforms existing methods and matches human quality in idea generation.

EventOA: An Event Ontology Alignment Benchmark Based on FrameNet and Wikidata (2023.findings-acl)

Copied to clipboard

Shaoru Guo, Chenhao Wang, Yubo Chen, Kang Liu, Ru Li, Jun Zhao

Knowledge Representation

Challenge:	Existing studies on event ontologies focus on entity-based OA, and neglect event-based one . however, independent development of event ontoologies often results in heterogeneous representations that raise the need for establishing alignments between semantically related events.
Approach:	They propose a multi-view event ontology alignment method that utilizes description information and neighbor information to obtain richer representations of the event ontoologies.
Outcome:	The proposed method outperforms existing entity-based methods and can serve as a strong baseline for future research.

Bridging Relevance and Reasoning: Rationale Distillation in Retrieval-Augmented Generation (2025.findings-acl)

Copied to clipboard

Pengyue Jia, Derong Xu, Xiaopeng Li, Zhaocheng Du, Xiangyang Li, Yichao Wang, Yuhao Wang, Qidong Liu, Maolin Wang, Huifeng Guo, Ruiming Tang, Xiangyu Zhao

Beware of Your Po! Measuring and Mitigating AI Safety Risks in Role-Play Fine-Tuning of LLMs (2025.acl-long)

Challenge:	Existing approaches to rerank and align documents based on reasoning capabilities of large language models (LLMs) . prior work shows that LLMs have exceptional reasoning and text generation capabilities .
Approach:	They propose a rationale extraction method that leverages reasoning capabilities of large language models to extract the rationales necessary for answering a query.
Outcome:	The proposed method is compared with baseline methods on two tasks across three datasets.

Copied to clipboard

Weixiang Zhao, Yulin Hu, Yang Deng, Jiahe Guo, Xingyu Sui, Xinyang Han, An Zhang, Yanyan Zhao, Bing Qin, Tat-Seng Chua, Ting Liu

Retrieving Multimodal Information for Augmented Generation: A Survey (2023.findings-emnlp)

Challenge:	Existing role-play fine-tuning techniques improve role adaptability but may degrade safety performance, especially for villainous characters.
Approach:	They propose safety-aware Role-Play Fine-Tuning (SaRFT) to balance role-playing capabilities and safety.
Outcome:	The proposed method outperforms state-of-the-art baselines under both LoRA and full-parameter fine-tuning settings.

Copied to clipboard

Ruochen Zhao, Hailin Chen, Weishi Wang, Fangkai Jiao, Xuan Long Do, Chengwei Qin, Bosheng Ding, Xiaobao Guo, Minzhi Li, Xingxuan Li, Shafiq Joty

LLMs Trust Humans More, That’s a Problem! Unveiling and Mitigating the Authority Bias in Retrieval-Augmented Generation (2025.acl-long)

Challenge:	Large Language Models (LLMs) are increasingly using multimodality to augment their generation ability, but there is no unified perception of at which stage and how to incorporate different modalities.
Approach:	They propose to use multimodality to augment Large Language Models (LLMs) this will provide scholars with a deeper understanding of the methods' applications and encourage them to adapt existing techniques to the fast-growing field of LLMs.
Outcome:	The proposed methods improve factuality, reasoning, interpretability, and robustness of the generated content.

Copied to clipboard

Yuxuan Li, Xinwei Guo, Jiashi Gao, Guanhua Chen, Xiangyu Zhao, Jiaxin Zhang, Quanying Liu, Haiyan Wu, Xin Yao, Xuetao Wei

Rethinking Composed Image Retrieval Evaluation: A Fine-Grained Benchmark from Image Editing (2026.acl-long)

Challenge:	Large language models (LLMs) generate outputs that stray from user input or contravene established knowledge.
Approach:	They propose a new phenomenon, Authority Bias, where LLMs favor one knowledge source over the other . they propose atomic information that generates conflicts and a Conflict Detection Enhanced Query framework .
Outcome:	The proposed framework reduces Authority bias in large language models . it detects conflicts, performs credibility assessment on conflicting paragraphs, and detects perturbed text .

Copied to clipboard

Tingyu Song, Yanzhao Zhang, Mingxin Li, Zhuoning Guo, Dingkun Long, Pengjun Xie, Siyue Zhang, Yilun Zhao, Shu Wu

ConKI: Contrastive Knowledge Injection for Multimodal Sentiment Analysis (2023.findings-acl)

Challenge:	Composed Image Retrieval (CIR) is a complex task in multimodal understanding . current CIR benchmarks lack a robust evaluation pipeline and limited query categories .
Approach:	They construct a fine-grained CIR benchmark that allows for precise control over modification types and content.
Outcome:	The proposed benchmark covers 5,000 high-quality queries structured across five main categories and fifteen subcategories.

Copied to clipboard

Yakun Yu, Mingjun Zhao, Shi-ang Qi, Feiran Sun, Baoxun Wang, Weidong Guo, Xiaoli Wang, Lei Yang, Di Niu

LLMTreeRec: Unleashing the Power of Large Language Models for Cold-Start Recommendations (2025.coling-main)

Challenge:	Existing methods for multimodal sentiment analysis focus on general knowledge, which is inadequate to identify specific sentiments across modalities.
Approach:	They propose a method where specific-knowledge representations for each modality can be learned together with general knowledge representations via knowledge injection based on an adapter architecture.
Outcome:	The proposed method outperforms all prior methods on three popular benchmarks on multimodal sentiment analysis metrics.

Copied to clipboard

Wenlin Zhang, Chuhan Wu, Xiangyang Li, Yuhao Wang, Kuicai Dong, Yichao Wang, Xinyi Dai, Xiangyu Zhao, Huifeng Guo, Ruiming Tang

Turning Failures into Value: Negative Experience Replay for RLVR via Confidence Gating and Boundary Failure Sampling (2026.acl-long)

Challenge:	Lack of training data leads to the system cold-start problem in recommendation systems, making them struggle to provide effective recommendations.
Approach:	They propose a tree-based LLM recommendation framework which structures all items into an item tree to improve the efficiency of LLM’s item retrieval.
Outcome:	The proposed framework outperforms the baseline model in the A/B test on Huawei industrial system.

Copied to clipboard

Jialiang Guo, Fucheng Xiong, Xu He, Haodong Zhao, Xingyang li, Ke Zeng, Xunliang Cai

OpenRT: An Open-source Framework for Reasoning Over Tabular Data (2023.acl-demo)

Challenge:	Existing experience replay methods for RLVR ignore sample inefficiency . expensive reasoning trajectories are discarded immediately after a single gradient update .
Approach:	They propose a method to replay failure trajectories to improve model refinement . they propose 'nexGRPO' which employs mid-confidence gating to filter invalid noise and saturated errors.
Outcome:	The proposed model outperforms strong baaselines and achieves improved out-of-distribution generalization.

Copied to clipboard

Yilun Zhao, Boyu Mi, Zhenting Qi, Linyong Nan, Minghao Guo, Arman Cohan, Dragomir Radev

Dynamic Stashing Quantization for Efficient Transformer Training (2023.findings-emnlp)

Challenge:	Existing table pre-training methods are benchmarked on a limited number of datasets with varying configurations, resulting in a lack of unified, standardized, fair, and comprehensive comparison between methods.
Approach:	They propose to use OpenRT to reproduce existing table pre-training models and develop new models quickly.
Outcome:	The proposed framework reproduces existing table pre-training models and compares them against four question answering, one fact checking, and one faithful text generation datasets.

Copied to clipboard

Guo Yang, Daniel Lo, Robert Mullins, Yiren Zhao

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

Challenge:	Large Language Models (LLMs) have demonstrated impressive performance on a range of Natural Language Processing (NLP) tasks.
Approach:	They propose a dynamic quantization strategy that reduces the amount of memory operations and reduces arithmetic cost by 20.95 on two translation tasks and three classification tasks.
Outcome:	The proposed model reduces the amount of arithmetic operations by 20.95 and the number of DRAM operations by 2.55 on two translation tasks and three classification tasks.

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

Are Multimodal LLMs Robust Against Adversarial Perturbations? RoMMath: A Systematic Evaluation on Multimodal Math Reasoning (2025.naacl-long)

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

Yilun Zhao, Guo Gan, Chen Zhao, Arman Cohan

Deeply Coupled Cross-Modal Prompt Learning (2023.findings-acl)

Challenge:	Recent-released MLLMs have shown remarkable performance on various multimodal math reasoning benchmarks.
Approach:	They introduce RoMMath, the first benchmark designed to evaluate the capabilities and robustness of multimodal large language models in handling multimodal math reasoning.
Outcome:	The proposed model performs well on a broad spectrum of 17 MLLMs and demonstrates that they are robust to adversarial perturbations.

Copied to clipboard

Xuejing Liu, Wei Tang, Jinghui Lu, Rui Zhao, Zhaojun Guo, Fei Tan

ToM: Leveraging Tree-oriented MapReduce for Long-Context Reasoning in Large Language Models (2025.emnlp-main)

Challenge:	Existing prompt-tuning methods focus on language branch or learn vision-language interaction in a shallow mechanism.
Approach:	They propose a Deeply coupled Cross-modal Prompt learning method based on CLIP to facilitate the interplay between vision and language with a Cross-Modal Prompting Attention mechanism.
Outcome:	The proposed method enables the interplay between vision and language with a Cross-Modal Prompt Attention mechanism.

Copied to clipboard

Jiani Guo, Zuchao Li, Jie Wu, Qianren Wang, Yun Li, Lefei Zhang, Hai Zhao, Yujiu Yang

OctoBench: Benchmarking Scaffold-Aware Instruction Following in Repository-Grounded Agentic Coding (2026.acl-long)

Challenge:	Experimental results show ToM outperforms existing divide-and-conquer frameworks . RAG relies on similarity-based rankings to retrieve and reason over chunks based on logical coherence .
Approach:	They propose a Tree-oriented MapReduce framework for long-context reasoning . it leverages the hierarchical structure of long documents by constructing a DocTree .
Outcome:	Experimental results show that ToM outperforms existing divide-and-conquer frameworks and RAGs . the proposed framework improves logical coherence and long-context reasoning on 70B+ LLMs compared to existing approaches .

Copied to clipboard

Deming Ding, Shichun Liu, Enhui Yang, Jiahang Lin, Ziying Chen, Shihan Dou, Honglin Guo, Weiyu Cheng, Pengyu Zhao, Chengjun Xiao, Qunhong Zeng, Qi Zhang, Xuanjing Huang, Qidi Xu, Tao Gui

P2P: A Poison-to-Poison Remedy for Reliable Backdoor Defense in LLMs (2026.findings-acl)

Challenge:	coding scaffolds that follow heterogeneous instructions remain under-examined in software engineering . coding models are capable software agents, but their ability to follow constraints remains under-explored .
Approach:	They introduce OctoBench, which benchmarks scaffold-aware instruction following in agentic coding.
Outcome:	The proposed benchmark aims to accelerate the development of more scaffold-aware agents.

Copied to clipboard

Shuai Zhao, Xinyi Wu, Shiqian Zhao, Xiaobao Wu, Zhongliang Guo, Yanhao Jia, Anh Tuan Luu

STK-Adapter: Incorporating Evolving Graph and Event Chain for Temporal Knowledge Graph Extrapolation (2026.acl-long)

Challenge:	Defending Large Language Models (LLMs) against backdoors has long been trapped in a "cat-and-mouse" dilemma where defenders passively react to ever-shifting attack strategies.
Approach:	They propose a general and effective defense algorithm that implants benign triggers to reshape the model’s decision boundary.
Outcome:	The proposed defense algorithm can neutralize malicious backdoors while preserving task performance.

Copied to clipboard

Shuyuan Zhao, Wei Chen, Weijie Zhang, Xinrui Hou, Junfeng Shen, Boyan Shi, Shengnan Guo, Youfang Lin, Huaiyu Wan

StructuThink: Reasoning with Task Transition Knowledge for Autonomous LLM-Based Agents (2025.findings-emnlp)

Challenge:	Temporal Knowledge Graphs (TKGs) store dynamic facts in the real world.
Approach:	They propose a Spatial-Temporal Knowledge Adapter which integrates the evolving graph encoder and the LLM to facilitate TKG reasoning.
Outcome:	The proposed method outperforms state-of-the-art methods on benchmark datasets and exhibits strong generalization capabilities in cross-dataset task.

Copied to clipboard

Haiyu Zhao, Zhenyu Guo, Chunhong Zhang, Ziyu Zhou, Zheng Hu

A Novel Matching Paradigm: Unified Generative and Discriminative LLM with Prompt Compression for Relevance Learning (2026.acl-industry)

Challenge:	StructuThink framework enhances LLMs' ability to ground decisions in domain-specific scenarios.
Approach:	They propose a knowledge-structured reasoning framework that enhances LLM-based agents with explicit decision constraints.
Outcome:	The proposed framework achieves higher task success rates and more efficient action sequences than baseline methods.

Copied to clipboard

Guoliang Zhao, Zixin Cui, Chao Ye, Dengwu He, Fei Huang, Yubo Liu, Shuanglong Li, Tzungren Kuo, Bin Ding, Shuang Zhang, null KunhongZhu, Zhi Guo, Liu Lin

MIND: From Passive Mimicry to Active Reasoning through Capability-Aware Multi-Perspective CoT Distillation (2026.acl-long)

Challenge:	Existing approaches to matching use Large Language Models as feature extractors, underutilizing their full modeling capabilities.
Approach:	They propose a matching paradigm that integrates two-tower, single-towing, and generative tasks within a unified LLM framework via attention-mask partitioning.
Outcome:	The proposed model achieves superior performance and strong practical value in an industrial search engine.

Copied to clipboard

Jin Cui, Jiaqi Guo, Jiepeng Zhou, Ruixuan Yang, Jiayi Lu, Jiajun Xu, Jiangcheng Song, Boran Zhao, Pengju Ren

ToxiCraft: A Novel Framework for Synthetic Generation of Harmful Information (2024.findings-emnlp)

Challenge:	Existing approaches restrict students to following a single golden rationale and treat different reasoning paths independently, causing suboptimal performance.
Approach:	They propose a capability-adaptive framework that transitions distillation from passive mimicry to active cognitive construction and employ a feedback-driven inertia calibration mechanism to align supervision with the student’s current adaptability.
Outcome:	Experiments show that the proposed framework achieves state-of-the-art performance on both in-distribution and out-of distribution benchmarks.

Copied to clipboard

Zheng Hui, Zhaoxiao Guo, Hang Zhao, Juanyong Duan, Congrui Huang

Learning to Plan by Updating Natural Language (2024.findings-emnlp)

Challenge:	Existing models for detecting harmful content lack diversity and quality of datasets.
Approach:	They propose a framework for synthesizing toxic information from social media datasets . their framework generates a wide variety of synthetic, yet remarkably realistic, examples of toxic information .
Outcome:	The proposed framework can generate a wide variety of synthetic, yet remarkably realistic, examples of toxic information.

Copied to clipboard

Yiduo Guo, Yaobo Liang, Chenfei Wu, Wenshan Wu, Dongyan Zhao, Nan Duan

M3-VQA: A Benchmark for Multimodal, Multi-Entity, Multi-Hop Visual Question Answering (2026.acl-long)

Challenge:	Large Language Models (LLMs) have shown remarkable performance in basic natural language tasks.
Approach:	They propose a method that iteratively updates the task plan with new steps and behavioral instructions to guide LLMs to generate the correct solutions step by step.
Outcome:	The proposed method improves performance on five reasoning type tasks and can be directly applied to other LLMs.

Copied to clipboard

Jiatong Ma, Longteng Guo, Yuchen Liu, Zijia Zhao, Dongze Hao, Xuanxu Lin, Jing Liu

Analyzing and Reducing the Performance Gap in Cross-Lingual Transfer with Fine-tuning Slow and Fast (2023.acl-long)

Challenge:	Existing knowledge-based VQA benchmarks focus on coarse-grained categories and simple reasoning over single entities.
Approach:	They propose a knowledge-based Visual Question Answering benchmark to enhance multimodality evaluation.
Outcome:	The proposed benchmark improves evaluation of multimodal large language models in fine-grained multimodal entity understanding and complex multihop reasoning.

Copied to clipboard

Yiduo Guo, Yaobo Liang, Dongyan Zhao, Bing Liu, Nan Duan

Multimodal Prompt Learning with Missing Modalities for Sentiment Analysis and Emotion Recognition (2024.acl-long)

Challenge:	Existing research shows that a multilingual pre-trained language model fine-tuned with one (source) language performs well on downstream tasks for non-source languages . However, there is a clear performance gap between the source and non-sourced languages - this gap can be reduced by reducing forgetting.
Approach:	They propose a method to fine-tune a multilingual pre-trained language model fine- tuned with one (source) language and four training policies to address the performance gap.
Outcome:	The proposed method outperforms baselines on the XNLI dataset by a clear margin.

Copied to clipboard

Zirun Guo, Tao Jin, Zhou Zhao

PPTC-R benchmark: Towards Evaluating the Robustness of Large Language Models for PowerPoint Task Completion (2024.findings-emnlp)

Challenge:	Existing methods for multimodal sentiment analysis often fail due to equipment failure, data corruption, privacy issues and the like.
Approach:	They propose a multimodal Transformer framework using prompt learning to address the issue of missing modalities.
Outcome:	The proposed framework outperforms existing methods significantly across evaluation metrics.

Copied to clipboard

Zekai Zhang, Yiduo Guo, Yaobo Liang, Dongyan Zhao, Nan Duan

BU-NEmo: an Affective Dataset of Gun Violence News (2022.lrec-1)

Challenge:	Large Language Models (LLMs) are increasingly used for task completion in real-world situations.
Approach:	They propose a PowerPoint Task Completion-Robustness (PPTC-R) benchmark to measure LLMs’ robustness to the user PPT task instruction and software version (Powerpoint).
Outcome:	The proposed benchmark compares 3 closed-source and 4 open-source LLMs to the PowerPoint task instruction and software version (Powerpoint) .

Copied to clipboard

Carley Reardon, Sejin Paik, Ge Gao, Meet Parekh, Yanling Zhao, Lei Guo, Margrit Betke, Derry Tanti Wijaya

Sentiment Analysis

Challenge:	Using a dataset that contains headline and image pairings from 840 news articles, we explore the relationship between image and text influence on human emotional response.
Approach:	They propose to use a U.S. gun violence news dataset that contains headline and image pairings from 840 news articles with 15K high-quality crowdsourced annotations on emotional responses.
Outcome:	The proposed dataset includes annotations on the dominant emotion experienced with the content, the intensity of the selected emotion and an open-ended, written component.

TencentPretrain: A Scalable and Flexible Toolkit for Pre-training Models of Different Modalities (2023.acl-demo)

Copied to clipboard

Zhe Zhao, Yudong Li, Cheng Hou, Jing Zhao, Rong Tian, Weijie Liu, Yiren Chen, Ningyuan Sun, Haoyan Liu, Weiquan Mao, Han Guo, Weigang Gou, Taiqiang Wu, Tao Zhu, Wenhang Shi, Chen Chen, Shan Huang, Sihong Chen, Liqun Liu, Feifei Li, Xiaoshuai Chen, Xingwu Sun, Zhanhui Kang, Xiaoyong Du, Linlin Shen, Kimmo Yan

MPO: Multilingual Safety Alignment via Reward Gap Optimization (2025.acl-long)

Challenge:	Several pre-training models of different modalities are showing a rising trend of homogeneity in their model structures.
Approach:	They propose a toolkit that supports pre-training models of different modalities.
Outcome:	The proposed toolkit can match the performance of the original implementations on text, vision, and audio benchmarks.

Copied to clipboard

Weixiang Zhao, Yulin Hu, Yang Deng, Tongtong Wu, Wenxuan Zhang, Jiahe Guo, An Zhang, Yanyan Zhao, Bing Qin, Tat-Seng Chua, Ting Liu

Multilinguality

Challenge:	Existing preference learning methods for safety alignment are monolingual and struggle with noisy multilingual data.
Approach:	They propose a multilingual reward gaP optimization approach that leverages the well-aligned safety capabilities of the dominant language to improve safety alignment across multiple languages.
Outcome:	Extensive experiments on three LLMs, LLaMA-3.1, Gemma-2 and Qwen2.5, validate MPO’s efficacy in multilingual safety alignment without degrading general multilingual utility.

Tagging-Augmented Generation: Assisting Language Models in Finding Intricate Knowledge In Long Contexts (2025.emnlp-industry)

Copied to clipboard

Anwesan Pal, Karen Hovsepian, Tinghao Guo, Mengnan Zhao, Somendra Tripathi, Nikos Kanakaris, George Mihaila, Sumit Nigam

Syntactic Text Processing

Challenge:	Recent studies into effective context lengths of flagship large language models (LLMs) have revealed major limitations in effective question answering (QA) and reasoning over long and complex contexts for even the largest and most impressive cadre of models.
Approach:	They propose a lightweight data augmentation strategy that boosts LLM performance in long-context scenarios without degrading and altering the integrity and composition of retrieved documents.
Outcome:	The proposed strategy boosts performance in long-context scenarios without degrading and altering the integrity and composition of retrieved documents.

Towards Interpretable Tabular Reasoning: Enhancing LLM Reasoning on Tabular Data with Pre-Constructed Logic Graph (2026.acl-long)

Copied to clipboard

Lirong Gao, Zewei Yu, Zhongrui Yin, Qi Zhang, Yuke Zhu, Bo Zheng, Haobo Wang, Junbo Zhao, Gang Chen, Sheng Guo

SEEKR: Selective Attention-Guided Knowledge Retention for Continual Learning of Large Language Models (2024.emnlp-main)

Challenge:	Tabular data is used in fields such as finance and healthcare due to its heterogeneity and complexity.
Approach:	They propose a Logic-Graph-Enhanced LLM Reasoning framework that integrates the strengths of tree-based models and LLMs to improve their interpretability.
Outcome:	The proposed framework outperforms tree-based models and state-of-the-art LLMs on tabular prediction tasks, achieving superior accuracy and interpretability.

Copied to clipboard

Jinghan He, Haiyun Guo, Kuan Zhu, Zihan Zhao, Ming Tang, Jinqiao Wang

PSSAT: A Perturbed Semantic Structure Awareness Transferring Method for Perturbation-Robust Slot Filling (2022.coling-1)

Challenge:	Existing methods fail to fully exploit the knowledge embedded in models from previous tasks . Existing techniques fail to exploit the information embedded in previous tasks, resulting in a large number of replay samples to achieve good results.
Approach:	They propose a method that uses attention weights to extract knowledge from previous tasks . they use a data replay strategy to extract the knowledge from the previous tasks.
Outcome:	The proposed method achieves comparable or even better performance with only 1/10 of replayed data used by other methods.

Copied to clipboard

Guanting Dong, Daichi Guo, Liwen Wang, Xuefeng Li, Zechen Wang, Chen Zeng, Keqing He, Jinzheng Zhao, Hao Lei, Xinyue Cui, Yi Huang, Junlan Feng, Weiran Xu

DemoNSF: A Multi-task Demonstration-based Generative Framework for Noisy Slot Filling Task (2023.findings-emnlp)

Challenge:	Existing slot filling models memorize inherent patterns of entities and contexts from training data.
Approach:	They propose a perturbed semantic structure awareness transferring method for slot filling models . they use two MLM-based training strategies to learn contextual semantic structure and word distribution .
Outcome:	The proposed method outperforms existing methods and gains strong generalization while preventing model from memorizing inherent patterns of entities and contexts.

Copied to clipboard

Guanting Dong, Tingfeng Hui, Zhuoma GongQue, Jinxu Zhao, Daichi Guo, Gang Zhao, Keqing He, Weiran Xu

When Personalization Legitimizes Risks: Uncovering Safety Vulnerabilities in Personalized Dialogue Agents (2026.acl-long)

Challenge:	Recent prompt-based generative frameworks have shown impressive capabilities in sequence labeling tasks.
Approach:	They propose a multi-task demonstration-based generative framework for noisy slot filling that captures input perturbations at different granularities.
Outcome:	The proposed framework outperforms baseline methods and achieves strong generalization.

Copied to clipboard

Jiahe Guo, Xiangran Guo, Yulin Hu, Zimo Long, Xingyu Sui, Xuda Zhi, Yongbo Huang, Hao He, Weixiang Zhao, Yanyan Zhao, Bing Qin

Dialogue Systems & Conversational Agents

Challenge:	Existing research on personalized LLM agents focuses on the effectiveness of personalized responses.
Approach:	They propose a benchmark to quantify intent legitimation in personalized interactions . they propose 'detection-reflection' method that detects intent legititimation from internal representation space .
Outcome:	The proposed method reduces safety degradation by using internal representation space.

Efficient Mind-Map Generation via Sequence-to-Graph and Reinforced Graph Refinement (2021.emnlp-main)

Copied to clipboard

Mengting Hu, Honglei Guo, Shiwan Zhao, Hang Gao, Zhong Su

Structured Data in NLP

Challenge:	Existing methods to generate mind-maps from text are difficult to capture the overall semantics of a document.
Approach:	They propose an efficient mind-map generation network that converts a document into a graph via sequence-to-graph.
Outcome:	The proposed network reduces inference time by thousands of times compared with existing methods and reveals key semantic structures better than plain text.

SAMoRA: Semantic-Aware Mixture of LoRA Experts for Task-Adaptive Learning (2026.findings-acl)

Copied to clipboard

Boyan Shi, Wei Chen, Shuyuan Zhao, Junfeng Shen, Shengnan Guo, Shaojiang Wang, Huaiyu Wan

Can LLMs Hear the Dogwhistle? (2026.findings-acl)

Challenge:	Existing methods for multitask learning fail to match input semantics with expert capabilities, leading to weak expert specialization.
Approach:	They propose a parameter-efficient mixture-of-experts framework for task-adaptive learning that aligns textual semantics with the most suitable experts for precise routing.
Outcome:	The proposed framework outperforms the state-of-the-art methods and holds excellent task generalization capabilities.

Copied to clipboard

Yifan Liu, Yi Lin, Xinwei Guo, Ziwei Wang, Jiaxin Zhang, Guanhua Chen, Haiyan Wu, Xiangyu Zhao, Xin Yao, Xuetao Wei

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

Challenge:	Existing safety benchmarks focus on explicitly harmful content, but ignore context-dependent expressions such as dogwhistles.
Approach:	They propose a benchmark for evaluating LLM safety under dogwhistle-driven prompts . their findings expose a blind spot in current safety evaluation practices .
Outcome:	The proposed benchmark compared safety performance with toxic terms using dogwhistle-driven prompts.

Copied to clipboard

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

CL-QR: Cross-Lingual Enhanced Query Reformulation for Multi-lingual Conversational AI Agents (2023.emnlp-industry)

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

Copied to clipboard

Zhongkai Sun, Zhengyang Zhao, Sixing Lu, Chengyuan Ma, Xiaohu Liu, Xing Fan, Wei Shen, Chenlei Guo

Multilinguality

Challenge:	Existing QR systems that reformulate defective user queries are limited in English due to the scarcity of non-English QR labels.
Approach:	They propose a query reformulation method which reformulates defective user queries to improve non-English QR performance.
Outcome:	The proposed framework improves non-English QR performance by leveraging abundant reformulation resources in English.

IFIR: A Comprehensive Benchmark for Evaluating Instruction-Following in Expert-Domain Information Retrieval (2025.naacl-long)

Copied to clipboard

Tingyu Song, Guo Gan, Mingsheng Shang, Yilun Zhao

AGENTVIGIL: Automatic Black-Box Red-teaming for Indirect Prompt Injection against LLM Agents (2025.findings-emnlp)

Challenge:	Current information retrieval systems struggle to handle complex instructions, despite its critical importance . current models struggle to follow complex instructions in real-world applications, resulting in user-specific tasks.
Approach:	They propose a benchmark to evaluate instruction-following information retrieval in expert domains.
Outcome:	The proposed method improves on existing models and provides valuable insights to guide future advancements in retrieval.

Copied to clipboard

Zhun Wang, Vincent Siu, Zhe Ye, Tianneng Shi, Yuzhou Nie, Xuandong Zhao, Chenguang Wang, Wenbo Guo, Dawn Song

Multi-Label Few-Shot Learning for Aspect Category Detection (2021.acl-long)

Challenge:	AGENTVIGIL is a black-box optimization framework to exploit indirect prompt injection vulnerabilities . indirect prompts compromise the core of LLM agents by manipulating contextual information rather than direct user prompts.
Approach:	They propose a black-box optimization framework to exploit indirect prompt injection vulnerabilities . they use a Monte Carlo tree-based algorithm to iteratively refine inputs .
Outcome:	The proposed framework achieves 71% and 70% success rates against two public benchmarks .

Copied to clipboard

Mengting Hu, Shiwan Zhao, Honglei Guo, Chao Xue, Hang Gao, Tiegang Gao, Renhong Cheng, Zhong Su

Comprehensive Benchmarking of Long-Form Speech Generation in Diverse Scenarios (2026.findings-acl)

Challenge:	Existing few-shot learning methods focus on single-label predictions, which can not work well for ACD since a sentence may contain multiple aspect categories.
Approach:	They propose a few-shot learning method that uses the prototypical network to learn aspects from a set of aspects.
Outcome:	The proposed method significantly outperforms baseline methods on three datasets.

Copied to clipboard

Changhao Pan, Rui Yang, Han Wang, Zhuan Zhou, Xuming He, Wenxiang Guo, Ziyue Jiang, Ruiqi Li, Yu Zhang, Chenyuhao Wen, Ke Lei, Xiang Yin, Jingyu Lu, Zhiyuan Zhu, Zhou Zhao

A Label-Aware Autoregressive Framework for Cross-Domain NER (2022.findings-naacl)

Challenge:	Existing evaluation benchmarks for long-form speech are limited to limited domains, creating a significant gap with the diverse downstream applications.
Approach:	They propose a benchmark that decomposes "long-form speech quality" into specific, disentangled dimensions.
Outcome:	The proposed benchmark decomposes “long-form speech quality” into specific, disentangled dimensions.

Copied to clipboard

Jinpeng Hu, He Zhao, Dan Guo, Xiang Wan, Tsung-Hui Chang

PRIME: A Process-Outcome Alignment Benchmark for Verifiable Reasoning in Mathematics and Engineering (2026.acl-long)

Challenge:	Existing approaches to named entity recognition (NER) focus on reducing discrepancy between tokens and tokens, but transfer of valuable label information is often not considered or ignored.
Approach:	They propose a framework that borrows entity information from the source domain to enhance NER in the target domain.
Outcome:	The proposed model improves over the state-of-the-art model on several datasets.

Copied to clipboard

Xiangfeng Wang, Hangyu Guo, Yanlin Lai, Mitt Huang, Liang Zhao, Chengyuan Yao, Yinmin Zhang, Qi Han, null Xiaoxiaoren, Chun Yuan, Tong Xu, Zheng Ge, Xiangyu Zhang, Daxin Jiang

Curr-ReFT: Overcoming Training Bottlenecks in Small-scale Vision-Language Models via Curriculum Reinforcement Finetuning (2025.findings-emnlp)

Challenge:	Current outcome-centric verification paradigms neglect potential errors in the derivation process.
Approach:	They propose a process-aware RLVR training paradigm utilizing verifiers selected via PRIME.
Outcome:	The proposed approach outperforms the baseline verification paradigm on AIME24, AIME25, and Beyond-AIME models.

Copied to clipboard

Huilin Deng, Ding Zou, Xinghao Zhao, Rui Ma, Yanming Guo, Yang Cao, Yu Kang

Look before You Leap: Dual Logical Verification for Knowledge-based Visual Question Generation (2024.lrec-main)

Challenge:	State-of-the-art vision-language models require massive scaling that limits practical deployment.
Approach:	They propose to use supervised fine-tuning to train small-scale vision-language models but face out-of-domain collapse when trained with traditional supervised learning (SFT).
Outcome:	Experiments show that curr-reFT achieves state-of-the-art performance across visual tasks in both in- and out-of domain settings and benchmarks.

Copied to clipboard

Xumeng Liu, Wenya Guo, Ying Zhang, Xubo Liu, Yu Zhao, Shenglong Yu, Xiaojie Yuan

ChildTalk: A Multi-Dialect Chinese Child Speech Corpus with Full-Length Child–Caregiver Conversations for Speech Recognition (2026.findings-acl)

Challenge:	Existing methods for visual question generation focus on leveraging the semantics of inputs to propose questions, ignoring the logical coherence between generated questions and images.
Approach:	They propose a logical verification method that checks logical structure between Q, images, answers and acquired outside knowledge by incorporating logical coherence between Q and Q twice in the whole procedure.
Outcome:	The proposed method can generate diverse and insightful knowledge-based visual questions on two common datasets.

Copied to clipboard

Jiaming Zhou, Yujie Guo, Shiwan Zhao, Yao Lu, Jianye Wang, Haoqin Sun, Hui Wang, Yong Qin

Dialogue Systems & Conversational Agents

Challenge:	Automatic speech recognition (ASR) for children remains challenging due to developmental variability and the scarcity of high-quality corpora.
Approach:	They propose a large-scale Chinese child speech corpus that contains 112.5 hours of speech from 498 children and 500 caregivers.
Outcome:	The proposed model improves in-domain and cross-domain performance on children's speech.

LLM-Driven Multi-Perspective Location Completion for Next Location Prediction (2026.findings-acl)

Copied to clipboard

Pengxiang Lan, Enneng Yang, Yuliang Liang, Jianzhe Zhao, Linying Jiang, Guibing Guo

Challenge:	Existing methods assume that check-in data is complete, overlooking the subjective nature of user behavior, leading to inaccurate capture of user preferences.
Approach:	They propose a framework that uses spatial coordinates to augment location completion by transforming geographic coordinates into text.
Outcome:	The proposed framework outperforms state-of-the-art methods on three real-world datasets.

Efficient and Effective Prompt Tuning via Prompt Decomposition and Compressed Outer Product (2025.naacl-long)

Copied to clipboard

Pengxiang Lan, Haoyu Xu, Enneng Yang, Yuliang Liang, Guibing Guo, Jianzhe Zhao, Xingwei Wang

From Script to Stage: Automating Experimental Design for Social Simulations with LLMs (2026.findings-acl)

Challenge:	Existing methods for fine-tuning pre-trained language models overlook intrinsic semantic associations between soft prompt tokens, leading to high discreteness and limited interactions.
Approach:	They propose a low-parameters Prompt Tuning method which leverages prompt decomposition and compressed outer product to facilitate multiple interactions among prompt tokens.
Outcome:	Experiments on six architectures and eight datasets show that the proposed method outperforms state-of-the-art methods in performance and efficiency.

Copied to clipboard

Yuwei Guo, Zihan Zhao, Xiaowei Liu, Xiangning Yu, Qun Ma, Deyu Zhou, Xiao Xue

Challenge:	Xu et al., 2024): multi-agent simulations based on large language models are a new paradigm for social science research . traditional experimental design relies on interdisciplinary expertise and technical barriers . Xiaoping and Xin eli argue that LLM-driven agents are unreliable for rigorous experimental design due to hallucinations and limited verifiability.
Approach:	They propose a framework for multi-agent experiment design based on script generation . Script Composition, Script Finalization, and Actor Generation are the core phases of the framework .
Outcome:	The proposed framework lowers the barrier for social science experimental design and provides scientifically grounded decision support for policy-making.

View-R1: Asymmetric Policy Optimization for Difficulty-Aware Multimodal Reinforcement Learning (2026.findings-acl)

Copied to clipboard

Minjie Hong, Zirun Guo, Jiabao Zhang, Zehan Wang, Ziang Zhang, Tao Jin, Zhou Zhao

LICHEE: Improving Language Model Pre-training with Multi-grained Tokenization (2021.findings-acl)

Challenge:	Multimodal Large Language Models (MLLMs) are powerful at integrating diverse data but struggle with complex reasoning.
Approach:	They propose a method which separates responses into positive and negative groups to stabilize training and preserve knowledge.
Outcome:	The proposed model View-R1 achieves a 10.55% improvement in reasoning and outperforms larger models while maintaining and improving performance on general tasks.

Copied to clipboard

Weidong Guo, Mingjun Zhao, Lusheng Zhang, Di Niu, Jinwen Luo, Zhenhua Liu, Zhenyang Li, Jianbo Tang

Domain-Invariant Feature Distillation for Cross-Domain Sentiment Classification (D19-1)

Challenge:	Pre-trained language models are trained based on single-grained tokenization, making it hard to learn the precise meaning of coarse-grain words and phrases.
Approach:	They propose a language model pretraining method that incorporates multi-grained information of input text into pre-trained language models.
Outcome:	The proposed method improves performance on CLUE and SuperGLUE in Chinese and English with little extra inference cost.

Copied to clipboard

Mengting Hu, Yike Wu, Shiwan Zhao, Honglei Guo, Renhong Cheng, Zhong Su

Rethinking Semantic Parsing for Large Language Models: Enhancing LLM Performance with Semantic Hints (2025.acl-short)

Challenge:	Existing approaches to cross-domain sentiment classification focus on domain-invariant representations, but few focus on the domain-specific information.
Approach:	They propose to distill domain-invariant sentiment features with an orthogonal domain-dependent task . the orthogonalist task is built on the aspects varying widely in different domains .
Outcome:	The proposed method improves domain-invariant features and transfer performance on three public datasets.

Copied to clipboard

Kaikai An, Shuzheng Si, Helan Hu, Haozhe Zhao, Yuchi Wang, Qingyan Guo, Baobao Chang

Multi-stage Distillation Framework for Cross-Lingual Semantic Similarity Matching (2022.findings-naacl)

Challenge:	Semantic Parsing improves performance of smaller models, but it is unclear whether it extends similarly to large language models.
Approach:	They propose a prompting approach that embeds semantic hints within the prompt to improve LLM performance.
Outcome:	The proposed approach improves LLMs’ performance across various tasks, highlighting the potential of integrating semantic information to improve LLM capabilities.

Copied to clipboard

Kunbo Ding, Weijie Liu, Yuejian Fang, Zhe Zhao, Qi Ju, Xuefeng Yang, Rong Tian, Zhu Tao, Haoyan Liu, Han Guo, Xingyu Bai, Weiquan Mao, Yudong Li, Weigang Guo, Taiqiang Wu, Ningyuan Sun

Global Attention Decoder for Chinese Spelling Error Correction (2021.findings-acl)

Challenge:	Existing studies have shown that cross-lingual knowledge distillation can improve the performance of pre-trained models for cross-linguistic similarity matching tasks.
Approach:	They propose a multi-stage distillation framework for constructing a small-size but high-performance cross-lingual model using contrastive learning, bottleneck, and parameter recurrent strategies.
Outcome:	The proposed model can compress the size of XLM-R and MiniLM by more than 50% while the performance is only reduced by about 1%.

Copied to clipboard

Zhao Guo, Yuan Ni, Keqiang Wang, Wei Zhu, Guotong Xie

Learning Numeral Embedding (2020.findings-emnlp)

Challenge:	Existing methods for Chinese spelling error correction focus on local contextual information, thus misleading the user and reducing performance.
Approach:	They propose a global attention decoder that learns the global relationship of correct input characters and candidates of potential error characters.
Outcome:	The proposed method outperforms all competitor models by a large margin of up to 6.2% on three human-annotated datasets.

Copied to clipboard

Chengyue Jiang, Zhonglin Nian, Kaihao Guo, Shanbo Chu, Yinggong Zhao, Libin Shen, Kewei Tu

Representation Learning

Challenge:	Existing word embedding methods do not learn numeral embedds well because numerals are limited in number and their appearances in training corpora are highly scarce.
Approach:	They propose two numeral embedding methods that can handle the out-of-vocabulary problem for numerals.
Outcome:	The proposed methods can handle the out-of-vocabulary problem for numerals.

Knowledge Decoupling via Orthogonal Projection for Lifelong Editing of Large Language Models (2025.acl-long)

Copied to clipboard

Haoyu Xu, Pengxiang Lan, Enneng Yang, Guibing Guo, Jianzhe Zhao, Linying Jiang, Xingwei Wang

MultiFinBen: Benchmarking Large Language Models for Multilingual and Multimodal Financial Application (2026.acl-long)

Challenge:	Existing methods for enhancing large language models (LLMs) have achieved some success, but their knowledge understanding and memory capacity significantly degrades after extensive editing.
Approach:	They propose a method that stores the basis vectors of the representation space of past edits in a knowledge cache and projects the gradient of the current edit onto a space orthogonal to previous knowledge for updating.
Outcome:	The proposed method improves question-answering ability and hallucination mitigation by 14% and 61% for large language models after 3,000 edits.

Copied to clipboard

Xueqing Peng, Lingfei Qian, Yan Wang, Ruoyu Xiang, Yueru He, Yang Ren, Mingyang Jiang, Vincent Jim Zhang, Yuqing Guo, Jeff Zhao, Huan He, Yi Han, Yun Feng, Yuechen Jiang, Yupeng Cao, Haohang Li, Yangyang Yu, Xiaoyu Wang, Penglei Gao, Shengyuan Lin, Keyi Wang, Shanshan Yang, Yilun Zhao, Zhiwei Liu, Peng Lu, Jerry Huang, Suyuchen Wang, Triantafillos Papadopoulos, Polydoros Giannouris, Efstathia Soufleri, Nuo Chen, Zhiyang Deng, Heming Fu, Yijia Zhao, Mingquan Lin, Meikang Qiu, Kaleb E Smith, Arman Cohan, Xiao-Yang Liu, Jimin Huang, Guojun Xiong, Alejandro Lopez-Lira, Xi Chen, Junichi Tsujii, Jian-Yun Nie, Sophia Ananiadou, Qianqian Xie

QiMeng-Attention: SOTA Attention Operator is generated by SOTA Attention Algorithm (2025.findings-acl)

Challenge:	Existing evaluations of LLMs in finance are text-only, monolingual, and largely saturated by current models.
Approach:	They propose a multilingual and multimodal benchmark for evaluating LLMs in real financial contexts.
Outcome:	The first expert-annotated multilingual and multimodal benchmark is released . it evaluates 21 leading LLMs and shows they perform better in multilingual settings .

Copied to clipboard

Qirui Zhou, Shaohui Peng, Weiqiang Xiong, Haixin Chen, Yuanbo Wen, Haochen Li, Ling Li, Qi Guo, Yongwei Zhao, Ke Gao, Ruizhi Chen, Yanjun Wu, Zhao Chen, Yunji Chen

SAM3-I: Segment Anything with Instructions (2026.acl-long)

Challenge:	Existing LLMs cannot comprehend the complex data flow and computation process of the attention operator and utilize low-level primitive to exploit GPU performance.
Approach:	They propose an LLM-friendly Thinking Language (LLM-TL) that can decouple the generation of high-level optimization logic and low-level implementation on GPU and enhance LLMs’ understanding of attention operator.
Outcome:	The proposed method outshines existing LLMs on A100, RTX8000, and T4 GPUs, achieving a speed-up of up to 35.16.

Copied to clipboard

Jingjing Li, Yue Feng, Yuchen Guo, Jincai Huang, Wei Ji, Qi Bi, Yongri Piao, Miao Zhang, Xiaoqi Zhao, Qiang Chen, Shihao Zou, Huchuan Lu, Li Cheng

Low-Resource NLP

Challenge:	Existing methods for concept-level grounding and instruction-level reasoning use coarse representations and iterative mask filtering.
Approach:	They propose an instruction-following extension of the Segment Anything Model 3 family that unifies concept-level grounding and instruction-level reasoning within a single segmentation framework.
Outcome:	Experiments show that SAM3-I achieves appealing performance across referring and reasoning-based segmentation while maintaining its strong concept recall ability.

Understanding the Modality Gap: An Empirical Study on the Speech-Text Alignment Mechanism of Large Speech Language Models (2025.emnlp-main)

Copied to clipboard

Bajian Xiang, Shuaijiang Zhao, Tingwei Guo, Wei Zou

Question-guided Knowledge Graph Re-scoring and Injection for Knowledge Graph Question Answering (2024.findings-emnlp)

Challenge:	LSLMs have impressive conversational generation abilities, but consistently fall short of traditional pipeline systems on semantic understanding benchmarks.
Approach:	They propose to analyze the performance gap between speech and text inputs through a systematic experiment . they find that representation similarity is strongly correlated with the modality gap .
Outcome:	The proposed models improve the accuracy of speech inputs and their semantic understanding benchmarks.

Copied to clipboard

Yu Zhang, Kehai Chen, Xuefeng Bai, Zhao Kang, Quanjiang Guo, Min Zhang

Structured Data in NLP

Challenge:	Knowledge graph question answering (KGQA) aims to provide factual answers to natural language questions by leveraging structured information stored in a knowledge graph.
Approach:	They propose a Question-guided Knowledge Graph Re-scoring method to eliminate noisy pathways for the input question, thereby focusing specifically on pertinent factual knowledge.
Outcome:	The proposed method eliminates noisy pathways for the input question, thereby focusing specifically on pertinent factual knowledge.

Chain of Strategy Optimization Makes Large Language Models Better Emotional Supporter (2025.findings-emnlp)

Copied to clipboard

Weixiang Zhao, Xingyu Sui, Xinyang Han, Yang Deng, Yulin Hu, Jiahe Guo, Libo Qin, Qianyun Du, Shijin Wang, Yanyan Zhao, Bing Qin, Ting Liu

Which Reasoning Trajectories Teach Students to Reason Better? A Simple Metric of Informative Alignment (2026.acl-long)

Challenge:	Existing supervised fine-tuning (SFT) fails to address these issues, as it trains models on single gold-standard responses without modeling nuanced strategy trade-offs.
Approach:	They propose a two-stage framework that optimizes strategy selection preferences at each dialogue turn.
Outcome:	The proposed framework improves strategy selection preferences at each dialogue turn.

Copied to clipboard

Yuming Yang, Mingyoung Lai, Wanxu Zhao, Xiaoran Fan, Zhiheng Xi, Mingqi Wu, Chiyue Huang, Jun Zhao, Haijun Lv, Jian Tong, Yunhua Zhou, Yicheng Zou, Qipeng Guo, Tao Gui, Qi Zhang, Xuanjing Huang

From Objectives to Questions: A Planning-based Framework for Educational Mathematical Question Generation (2025.acl-long)

Challenge:	Existing methods assess suitability primarily through student likelihood, favoring trajectories that align closely with the student model’s current behavior but overlooking more informative ones.
Approach:	They propose a Rank–Surprisal Ratio metric that captures both alignment and informativeness to assess the suitability of a reasoning trajectory.
Outcome:	The proposed metric captures both alignment and informativeness to assess the suitability of a reasoning trajectory.

Copied to clipboard

Cheng Cheng, Zhenya Huang, GuanHao Zhao, Yuxiang Guo, Xin Lin, Jinze Wu, Xin Li, Shijin Wang

Text Generation

Challenge:	Traditional generation methods focus primarily on textual quality, but they fail to meet complex, multifaceted educational requirements.
Approach:	They propose a method for automatic generating high-quality mathematical problems that align with educational objectives using a dataset of 16k mathematical questions with multi-dimensional educational objectives.
Outcome:	The proposed method improves generating high-quality mathematical questions that meet multi-dimensional educational objectives.

Sentence-Permuted Paragraph Generation (2021.emnlp-main)

Copied to clipboard

Wenhao Yu, Chenguang Zhu, Tong Zhao, Zhichun Guo, Meng Jiang

Text Generation

Challenge:	Existing models produce similar contents from homogenized contexts due to the fixed left-to-right sentence order.
Approach:	They propose a framework permuting sentence orders to improve content diversity of multi-sentence paragraphs by permutating the sentence orders.
Outcome:	The proposed framework produces more diverse outputs with higher quality than existing models.

MAS-Bench: A Unified Benchmark for Shortcut-Augmented Hybrid Mobile GUI Agents (2026.acl-long)

Copied to clipboard

Pengxiang Zhao, Guangyi Liu, Yaozhen Liang, Weiqing He, Zhengxi Lu, WenHao Wang, Yuehao Huang, Yuxiang Chai, Zhaolu Kang, Yaxuan Guo, Hao Wang, Kexin Zhang, Liang Liu, Yong Liu

Green & Sustainable NLP

Challenge:	Shortcuts such as APIs and deep-links have emerged as efficient complements to flexible GUI operations, but systematic evaluation of GUI–shortcut hybrid agents remains underexplored.
Approach:	They propose a benchmark that evaluates GUI-shortcut hybrid agents with a specific focus on the mobile domain.
Outcome:	MAS-Bench evaluates agent's ability to generate shortcuts by discovering and creating reusable, low-cost workflows.

Decoding Fatphobia: Examining Anti-Fat and Pro-Thin Bias in AI-Generated Images (2025.findings-naacl)

Copied to clipboard

Jane Warren, Gary M. Weiss, Fernando Martinez, Annika Guo, Yijun Zhao

Visual Data in NLP

Challenge:	Existing studies have shown that AI-generated images reinforce social biases, including those related to race and gender.
Approach:	They use DALL-E 3 to examine weight bias in AI-generated images . authors discuss findings and their impact on existing research on weight bias .
Outcome:	The study examines stereotypical associations between moral character and body weight . it finds that fatphobia is a feature of social systems that rank fatter bodies inferior to thinner bodies .

Unveiling the Deficiencies of Pre-trained Text-and-Layout Models in Real-world Visually-rich Document Information Extraction (2026.findings-eacl)

Copied to clipboard

Chong Zhang, Yixi Zhao, Yulu Xie, Chenshu Yuan, Yi Tu, Ya Guo, Mingxu Chai, Ziyu Shen, Yue Zhang, Qi Zhang

Modeling Layout Reading Order as Ordering Relations for Visually-rich Document Understanding (2024.emnlp-main)

Challenge:	PTLMs have shown remarkable success in multiple information extraction tasks . however, their performance in real-world scenarios falls short of expectations .
Approach:	They propose to use an entity-centric dataset to evaluate PTLMs' performance . they find that inadequate annotations in benchmark datasets lead to spurious correlations .
Outcome:	The proposed dataset disentangles the falsely-coupled segment and entity annotations that arises from the block-level annotation of FUNSD.

Copied to clipboard

Chong Zhang, Yi Tu, Yixi Zhao, Chenshu Yuan, Huan Chen, Yue Zhang, Mingxu Chai, Ya Guo, Huijia Zhu, Qi Zhang, Tao Gui

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

Challenge:	Existing models of layout reading order do not convey the complete reading order information in the layout.
Approach:	They propose to model layout reading order as ordering relations over layout elements . they propose a reading-order-relation-enhancing pipeline to improve model performance .
Outcome:	The proposed model outperforms existing models on a visual-rich document dataset and on eight cross-domain VrD-IE/QA tasks without targeted optimization.

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

Versatile Framework for Song Generation with Prompt-based Control (2025.findings-emnlp)

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

Yu Zhang, Wenxiang Guo, Changhao Pan, Zhiyuan Zhu, Ruiqi Li, Jingyu Lu, Rongjie Huang, Ruiyuan Zhang, Zhiqing Hong, Ziyue Jiang, Zhou Zhao

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

Challenge:	Existing methods for song generation fail to generate vocals with prompt-based control and proper alignment.
Approach:	VersBand is a multi-task song generation framework for synthesizing high-quality songs with prompt-based control.
Outcome:	Experimental results show that VersBand performs better than baseline models across multiple song generation tasks.

Copied to clipboard

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

PPTC Benchmark: Evaluating Large Language Models for PowerPoint Task Completion (2024.findings-acl)

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

Copied to clipboard

Yiduo Guo, Zekai Zhang, Yaobo Liang, Dongyan Zhao, Nan Duan

TCSinger 2: Customizable Multilingual Zero-shot Singing Voice Synthesis (2025.findings-acl)

Challenge:	Recent evaluations of Large Language Models (LLMs) focus on their zero-shot/few-shot capabilities for basic natural language tasks and their ability to translate instructions into tool APIs.
Approach:	They propose a PowerPoint Task Completion benchmark to assess LLMs’ ability to create and edit PPT files based on user instructions.
Outcome:	The proposed system outperforms open-source and closed LLMs with 75.1% accuracy in single-turn dialogue testing but only achieves 6% session accuracy.

Copied to clipboard

Yu Zhang, Wenxiang Guo, Changhao Pan, Dongyu Yao, Zhiyuan Zhu, Ziyue Jiang, Yuhan Wang, Tao Jin, Zhou Zhao

Benchmarking Hallucination in Large Language Models Based on Unanswerable Math Word Problem (2024.lrec-main)

Challenge:	Existing zero-shot singing voice synthesis models depend on phoneme and note boundary annotations, limiting their robustness and producing poor transitions between phonemes and notes.
Approach:	They propose a multi-task multilingual zero-shot SVS model with style transfer and style control based on various prompts.
Outcome:	Experimental results show that TCSinger 2 outperforms baseline models in subjective and objective metrics across multiple related tasks.

Copied to clipboard

YuHong Sun, Zhangyue Yin, Qipeng Guo, Jiawen Wu, Xipeng Qiu, Hui Zhao

AdaSteer: Your Aligned LLM is Inherently an Adaptive Jailbreak Defender (2025.emnlp-main)

Challenge:	Large language models (LLMs) are highly effective in various natural language processing tasks, but can produce unreliable conjectures in ambiguous contexts, which is known as hallucination.
Approach:	They propose a method to evaluate LLM hallucination in Question Answering based on the unanswerable math word problem (UMWP) . they combine text similarity and mathematical expression detection to determine whether LLM considers the question unanswered.
Outcome:	The proposed method combines text similarity and mathematical expression detection to determine whether the LLM considers the question unanswerable.

Copied to clipboard

Weixiang Zhao, Jiahe Guo, Yulin Hu, Yang Deng, An Zhang, Xingyu Sui, Xinyang Han, Yanyan Zhao, Bing Qin, Tat-Seng Chua, Ting Liu

Class-Incremental Learning based on Label Generation (2023.acl-short)

Challenge:	Activation steering offers training-free defense but relies on fixed steering coefficients, resulting in suboptimal protection and increased false rejections of benign inputs.
Approach:	They propose an adaptive activation steering method that dynamically adjusts model behavior based on input characteristics.
Outcome:	The proposed method outperforms baseline methods across multiple jailbreak attacks with minimal impact on utility.

Copied to clipboard

Yijia Shao, Yiduo Guo, Dongyan Zhao, Bing Liu

DeepSieve: Information Sieving via LLM-as-a-Knowledge-Router (2026.findings-eacl)

Challenge:	Existing studies on pre-trained language models focus on task-incremental learning (TIL) but they perform poorly in a more challenging setting of class-incremental learning.
Approach:	They propose a method which solves CIL based on label generation by using sparse vocabulary and creates pseudo-replay samples by using label semantics.
Outcome:	The proposed method outperforms baseline models by a large margin in the class-incremental learning setting.

Copied to clipboard

Minghao Guo, Qingcheng Zeng, Xujiang Zhao, Yanchi Liu, Wenchao Yu, Mengnan Du, Haifeng Chen, Wei Cheng

Understanding Programs by Exploiting (Fuzzing) Test Cases (2023.findings-acl)

Challenge:	Existing RAG methods lack fine-grained control over query and source sides, resulting in noisy retrieval and shallow reasoning.
Approach:	They propose an agentic RAG framework that integrates information sieving via LLM-as-a-knowledge-router.
Outcome:	Experiments on multi-hop QA tasks across heterogeneous sources demonstrate improved reasoning depth, retrieval precision, and interpretability over conventional approaches.

Copied to clipboard

Jianyu Zhao, Yuyang Rong, Yiwen Guo, Yifeng He, Hao Chen

Multi-Scale Progressive Attention Network for Video Question Answering (2021.acl-short)

Challenge:	Semantic understanding of programs has attracted great attention in the community . large language models (LLMs) are capable of learning contextual information from data at scale .
Approach:	They propose to incorporate a relationship between inputs and possible outputs into learning for achieving a deeper semantic understanding of programs.
Outcome:	The proposed method outperforms current state-of-the-art on two programming tasks and outperformed current state of the art by large margins.

Copied to clipboard

Zhicheng Guo, Jiaxuan Zhao, Licheng Jiao, Xu Liu, Lingling Li

Safeguarding LLM Fine-tuning via Push-Pull Distributional Alignment (2026.acl-long)

Challenge:	Experimental evaluations on three benchmarks: TGIF-QA, MSVD-QA and MSRVTT-QA show our method has achieved state-of-the-art performance.
Approach:	They propose a multi-scale progressive attention network to fuse visual and text information.
Outcome:	The proposed method achieves state-of-the-art on three benchmarks: TGIF-QA, MSVD-QA and MSRVTT-QA.

Copied to clipboard

Haozhong Wang, Zhuo Li, Yibo Yang, He Zhao, Hongyuan Zha, Dandan Guo

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

Challenge:	Existing safety defenses for large language models fail to explicitly repel harmful patterns . Optimal transport (SOT) allows for safe fine-tuning without sacrificing safety .
Approach:	They propose a framework that reframes safe fine-tuning from instance-level filtering challenge to distribution-level alignment task grounded in Optimal Transport.
Outcome:	a new framework improves safety of large language models while maintaining competitive performance . the proposed framework reduces the risk of errors and improves model performance compared to baselines .

Copied to clipboard

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

RedOne: Revealing Domain-specific LLM Post-Training in Social Networking Services (2025.emnlp-industry)

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

Copied to clipboard

Fei Zhao, Chonggang Lu, null Wangyue, Zheyong Xie, Ziyan Liu, Haofu Qian, Jianzhao Huang, Fangcheng Shi, Zijie Meng, Hongcheng Guo, Mingqian He, Xinze Lyu, Zheyu Ye, Weiting Liu, Boyang Wang, Shaosheng Cao

Efficient Domain Continual pretraining by Mitigating the Stability Gap (2025.acl-long)

Challenge:	Social networking services (SNS) have experienced rapid growth, which has proposed significant challenges for platform content management and interaction quality improvement.
Approach:	They propose a domain-specific LLM to break the performance bottleneck of single-task baselines and establish a comprehensive foundation for social networking services.
Outcome:	The proposed model achieves an average improvement of 14.02% across 8 major tasks and 7.56% in bilingual evaluation benchmark, compared with baseline models.

Copied to clipboard

Yiduo Guo, Jie Fu, Huishuai Zhang, Dongyan Zhao

Give the Truth: Incorporate Semantic Slot into Abstractive Dialogue Summarization (2021.findings-emnlp)

Challenge:	Continual pretraining is an important approach for Large Language Models to improve their performance in target domains, learn new topics and languages, and even boost their general capabilities.
Approach:	They propose a training strategy that mitigates instability by increasing the number of epochs, along with two data sampling strategies targeting data domain relevance and corpus distribution.
Outcome:	The proposed training strategy improves the average medical task performance of the OpenLlama-3B model from 36.2% to 40.7% using only 40% of the original training budget, while also enhancing general task performance without causing forgetting.

Copied to clipboard

Lulu Zhao, Weihao Zeng, Weiran Xu, Jun Guo

Dialogue Systems & Conversational Agents

Challenge:	Abstractive dialogue summarization suffers from a lot of factual errors due to scattered salient elements in multi-speaker information interaction process.
Approach:	They propose a slot-driven beam search algorithm to give priority to generating salient elements in a limited length by "filling-in-the-blanks".
Outcome:	The proposed algorithm improves the slot-driven beam search algorithm on different types of factual errors and human evaluation further verifies the results.

Improving Abstractive Dialogue Summarization with Graph Structures and Topic Words (2020.coling-main)

Copied to clipboard

Lulu Zhao, Weiran Xu, Jun Guo

Prediction of People’s Emotional Response towards Multi-modal News (2022.aacl-main)

Challenge:	Existing approaches to summarize textual information are hard to capture long-distance relationships.
Approach:	They propose a Topic-word Guided Dialogue Graph Attention network to model the dialogue as an interaction graph according to topic word information.
Outcome:	The proposed model outperforms baseline models on two corpus corpus models.

Copied to clipboard

Ge Gao, Sejin Paik, Carley Reardon, Yanling Zhao, Lei Guo, Prakash Ishwar, Margrit Betke, Derry Tanti Wijaya

LLMBox: A Comprehensive Library for Large Language Models (2024.acl-demos)

Challenge:	BU-NEmo dataset extends from 320 to 1,297 news headline and lead image pairings and collects 38,910 annotations in a crowdsourcing experiment.
Approach:	They extend the U.S. gun violence news-to-emotions dataset from 320 to 1,297 news headline and lead image pairings and collect annotations in a crowdsourcing experiment.
Outcome:	The proposed models outperform baseline models on the NEmo+ dataset by large margins across several metrics.

Copied to clipboard

Tianyi Tang, Hu Yiwen, Bingqian Li, Wenyang Luo, ZiJing Qin, Haoxiang Sun, Jiapeng Wang, Shiyi Xu, Xiaoxue Cheng, Geyang Guo, Han Peng, Bowen Zheng, Yiru Tang, Yingqian Min, Yushuo Chen, Jie Chen, Ranchi Zhao, Luran Ding, Yuhao Wang, Zican Dong, Xia Chunxuan, Junyi Li, Kun Zhou, Xin Zhao, Ji-Rong Wen

The GaoYao Benchmark: A Comprehensive Framework for Evaluating Multilingual and Multicultural Abilities of Large Language Models (2026.acl-long)

Challenge:	a library to facilitate the development, use, and evaluation of large language models (LLMs) is presented.
Approach:	They propose a unified library to facilitate the development, use and evaluation of large language models (LLMs).
Outcome:	The proposed library is based on extensive experiments in a variety of evaluation settings.

Copied to clipboard

Yilun Liu, Chunguang Zhao, Mengyao Piao, Lingqi Miao, Shimin Tao, Minggui HE, Chenxin Liu, Zhang Li, null Mahongxia, Jiaxin Guo, Chen Liu, Liqun Deng, Jiansheng Wei, Xiaojun Meng, Fanyi Du, Daimeng Wei, Yanghua Xiao

LeTS: Learning to Think-and-Search via Process-and-Outcome Reward Hybridization (2025.emnlp-main)

Challenge:	Existing multilingual evaluation benchmarks neglect cultural nuances and lack language coverage in subjective tasks.
Approach:	They propose a framework that categorizes evaluation tasks into three cultural layers and nine cognitive sub-layers.
Outcome:	The proposed framework surpasses prior coverage by up to 111% on 20+ LLMs.

Copied to clipboard

Qi Zhang, Shouqing Yang, Lirong Gao, Hao Chen, Xiaomeng Hu, Jinglei Chen, Jiexiang Wang, Sheng Guo, Bo Zheng, Haobo Wang, Junbo Zhao

Stepwise Reasoning Disruption Attack of LLMs (2025.acl-long)

Challenge:	Recent research focuses on integrating reasoning capabilities into the realm of retrieval-augmented generation (RAG) via outcome-supervised reinforcement learning (RL).
Approach:	They propose a process-level reward module to mitigate the unawareness of intermediate reasoning steps in outcome-level supervision without additional annotation.
Outcome:	The proposed framework can boost LLMs’ reasoning ability by integrating external knowledge sources through retrieval-augmented generation (RAG) The proposed model can mitigate the unawareness of intermediate reasoning steps in outcome-level supervision without additional annotation.

Copied to clipboard

Jingyu Peng, Maolin Wang, Xiangyu Zhao, Kai Zhang, Wanyu Wang, Pengyue Jia, Qidong Liu, Ruocheng Guo, Qi Liu

What Makes for Good Visual Instructions? Synthesizing Complex Visual Reasoning Instructions for Visual Instruction Tuning (2025.coling-main)

Challenge:	Existing attacks on LLM reasoning are constrained by specific settings or lack of imperceptibility, limiting their feasibility and generalizability.
Approach:	They propose a stepwise rEasoning error disruption attack that subtly injects errors into prior reasoning steps to mislead the model into producing incorrect subsequent reasoning and final answers.
Outcome:	The proposed attack is compatible with zero-shot and few-shot settings, maintains the natural reasoning flow, and ensures covert execution without modification of the instruction.

Copied to clipboard

Yifan Du, Hangyu Guo, Kun Zhou, Wayne Xin Zhao, Jinpeng Wang, Chuyuan Wang, Mingchen Cai, Ruihua Song, Ji-Rong Wen

TEA-Bench: A Systematic Benchmarking of Tool-enhanced Emotional Support Dialogue Agent (2026.acl-long)

Challenge:	Experimental results show that visual instruction tuning improves performance of Multi-modal Large Language Models (MLLMs) to extend the application scope of Large Language Modells, a surge of work augments LLMs with vision encoders to endow the ability of multi-modal cognition and reasoning.
Approach:	They propose a systematic approach to create high-quality visual reasoning instructions using a synthesize-complicate-reformulate paradigm.
Outcome:	The proposed method improves performance of MLLMs by 27.86% and 27.60% on MME-Perception and MME Cognition.

Copied to clipboard

Xingyu Sui, Yanyan Zhao, Yulin Hu, Jiahe Guo, Weixiang Zhao, Bing Qin

ItiNera: Integrating Spatial Optimization with Large Language Models for Open-domain Urban Itinerary Planning (2024.emnlp-industry)

Challenge:	Existing ESC systems focus on affective support in text-only settings, ignoring how external tools can enable factual grounding and reduce hallucination in multi-turn emotional support.
Approach:	They propose a benchmark for evaluating tool-augmented agents in ESC with realistic emotional scenarios and an MCP-style tool environment.
Outcome:	The proposed benchmarks show that tool augmentation improves emotional support quality and reduces hallucination, but weaker models benefit only marginally.

Copied to clipboard

Yihong Tang, Zhaokai Wang, Ao Qu, Yihao Yan, Zhaofeng Wu, Dingyi Zhuang, Jushi Kai, Kebing Hou, Xiaotong Guo, Jinhua Zhao, Zhan Zhao, Wei Ma

Visually-augmented pretrained language models for NLP tasks without images (2023.acl-long)

Challenge:	Existing urban itinerary planning studies focus on traditional tourism, but they lack the precision and accuracy needed to create a personalized itinerary.
Approach:	They propose an open-domain urban itinerary planning system that integrates spatial optimization with large language models to provide customized urban itineraries based on user needs.
Outcome:	The proposed system can generate personalized urban itineraries based on user needs and scale with existing methods.

Copied to clipboard

Hangyu Guo, Kun Zhou, Wayne Xin Zhao, Qinyu Zhang, Ji-Rong Wen

VF-Eval: Evaluating Multimodal LLMs for Generating Feedback on AIGC Videos (2025.acl-long)

Challenge:	Existing approaches to improve pre-trained language models lack visual commonsense and semantics.
Approach:	They propose a visual-augmented approach to fine-tune pre-trained language models by using retrieved or generated images instead of relying on explicit images.
Outcome:	The proposed approach outperforms baselines on ten tasks and consistently outperformed other approaches.

Copied to clipboard

Tingyu Song, Tongyan Hu, Guo Gan, Yilun Zhao

More Data or Better Data? A Critical Analysis of Data Selection and Synthesis for Mathematical Reasoning (2025.emnlp-industry)

Challenge:	Multimodal large language models (MLLMs) are used for video quality assessment, image captioning and video analysis.
Approach:	They propose a benchmark to evaluate MLLMs on AIGC videos using coherence validation, error awareness, error type detection and reasoning evaluation tasks.
Outcome:	The proposed benchmark evaluates 13 frontier MLLMs on AIGC videos.

Copied to clipboard

Yike Zhao, Simin Guo, Ziqing Yang, Shifan Han, Dahua Lin, Fei Tan

NutFrame: Frame-based Conceptual Structure Induction with LLMs (2024.lrec-main)

Challenge:	Despite various proposed data construction methods, their practical utility in real-world pipelines remains underexplored.
Approach:	They conduct a comprehensive analysis of open-source datasets and data synthesis techniques for mathematical reasoning under a unified pipeline designed to mirror training and deployment scenarios.
Outcome:	The proposed pipelines mirror training and deployment scenarios and are suitable for industrial applications.

Copied to clipboard

Shaoru Guo, Yubo Chen, Kang Liu, Ru Li, Jun Zhao

Challenge:	Existing studies focus on syntactic knowledge and world knowledge, but conceptual structure is not well-understood.
Approach:	They propose a benchmark for coNceptual structure induction based on FrameNet . they use prompts to induce conceptual structure of Framenet with LLMs .
Outcome:	The proposed model is able to induce conceptual structure of FrameNet with LLMs.

A Span-based Multimodal Variational Autoencoder for Semi-supervised Multimodal Named Entity Recognition (2022.emnlp-main)

Copied to clipboard

Baohang Zhou, Ying Zhang, Kehui Song, Wenya Guo, Guoqing Zhao, Hongbin Wang, Xiaojie Yuan

MMEvalPro: Calibrating Multimodal Benchmarks Towards Trustworthy and Efficient Evaluation (2025.naacl-long)

Challenge:	Existing methods for named entity recognition on social media are not efficient for semi-supervised MNER because of the mismatch between the posted text and image.
Approach:	They propose a novel method to fuse the text and image features for multimodal named entity recognition under semi-supervised setting by exploiting modal-specific VAEs.
Outcome:	The proposed method outperforms baselines under supervised setting and improves performance with less labeled data than existing semi-supervised methods.

Copied to clipboard

Jinsheng Huang, Liang Chen, Taian Guo, Fu Zeng, Yusheng Zhao, Bohan Wu, Ye Yuan, Haozhe Zhao, Zhihui Guo, Yichi Zhang, Jingyang Yuan, Wei Ju, Luchen Liu, Tianyu Liu, Baobao Chang, Ming Zhang

Hierarchical Multi-label Text Classification with Horizontal and Vertical Category Correlations (2021.emnlp-main)

Challenge:	Large Multimodal Models (LMMs) exhibit impressive cross-modal understanding and reasoning abilities, but many benchmarks suffer from systematic biases.
Approach:	They propose a benchmark to avoid Type-I errors by creating one perception question and one knowledge anchor question through a meticulous annotation process.
Outcome:	The proposed benchmark avoids Type-I errors while maintaining reliability of MCQ evaluations.

Copied to clipboard

Linli Xu, Sijie Teng, Ruoyu Zhao, Junliang Guo, Chi Xiao, Deqiang Jiang, Bo Ren

Information Extraction & Text Mining

Challenge:	Existing approaches to hierarchical multi-label text classification ignore vertical category correlations or exploit dependencies across levels without considering horizontal correlations .
Approach:	They propose a hierarchical multi-label text classification framework that considers both vertical and horizontal category correlations.
Outcome:	The proposed framework improves on real-world HMTC datasets with significant improvements over baselines.

A.S.E: A Repository-Level Benchmark for Evaluating Security in AI-Generated Code (2026.findings-acl)

Copied to clipboard

Keke Lian, Wang Bin, Lei Zhang, Libo Chen, Junjie Wang, Ziming Zhao, Yujiu Yang, Miaoqian Lin, Haotong Duan, Haoran Zhao, Shuang Liao, Mingda Guo, Quan Jiazheng, Yilu Zhong, Chenhao He, Chen Zichuan, Jie Wu, Haoling Li, Zhaoxuan Li, Jiongchi Yu, Hui LI, Dong Zhang

E3-TIR: Enhanced Experience Exploitation for Tool-Integrated Reasoning (2026.findings-acl)

Challenge:	Existing security evaluation benchmarks lack relevance to real-world AI programming tasks . current LLMs struggle with secure coding, research shows .
Approach:	They propose a repository-level evaluation benchmark to assess security of AI-generated code.
Outcome:	The proposed framework mirrors real-world AI programming tasks and offers valuable insights into the state of AI code generation.

Copied to clipboard

Weiyang Guo, Zesheng Shi, Liye Zhao, Jiayuan Ma, Zeen Zhu, Junxian He, Min Zhang, Jing Li

Learning Diverse Responses with Prefix-Conditioned Supervised Fine-Tuning (2026.acl-long)

Challenge:	Existing training paradigms for Large Language Models (LLMs) suffer from inefficient exploration and mode degradation due to a lack of prior guidance, while SFT-then-RL is limited by high data costs and capability plateaus caused by low-entropy collapse.
Approach:	They propose an Enhanced Experience Exploitation paradigm that integrates expert prefixes, expert guided, and self-exploration to improve agent training.
Outcome:	The proposed model achieves a 6% performance improvement over traditional paradigms on tool-use tasks while requiring less than 10% of the synthetic data.

Copied to clipboard

Zhiyuan Fan, Guanqiao Chen, Yanyi Huang, Mingkuan Zhao, Dadi Guo, Yi R. Fung