Papers by Lu Yan

TrInk: Ink Generation with Transformer Network (2025.emnlp-main)

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

Zezhong Jin, Shubhang Desai, Xu Chen, Biyi Fang, Zhuoyi Huang, Zhe Li, Chong-Xin Gan, Xiao Tu, Man-Wai Mak, Yan Lu, Shujie Liu

Experience-driven Multi-turn Reinforcement Learning for GUI Agents (2026.acl-long)

Challenge:	Existing methods for handwriting generation capture global dependencies and can generate high-quality handwritten samples.
Approach:	They propose a Transformer-based model for ink generation, TrInk, which captures global dependencies.
Outcome:	The proposed model reduces character error rate and word error rate by 35.56% on the IAM-OnDB dataset compared to previous models.

Copied to clipboard

Zhengxi Lu, Jiabo Ye, Fei Tang, Yongliang Shen, Haiyang Xu, Ziwei Zheng, Weiming Lu, Ming Yan, Fei Huang, Jun Xiao, Yueting Zhuang

Challenge:	GUI agents have demonstrated remarkable progress in automating complex user interface interactions . training such agents for long-horizon tasks remains challenging due to limited rewards and prohibitive costs.
Approach:	They propose a method that leverages expert trajectories as environment experiences for on-policy multi-turn training.
Outcome:	The proposed method achieves significant gains over the base model with 1K public trajectories as RL experiences . it achieves competitive performance against strong baselines such as UI-TARS-7B and GPT-4o .

From Off-Policy to On-Policy: Enhancing GUI Agents via Bi-level Expert-to-Policy Assimilation (2026.acl-long)

Copied to clipboard

Zezhou Wang, Ziyun Zhang, Xiaoyi Zhang, Zhuzhong Qian, Yan Lu

Challenge:	Vision-language models are increasingly deployed as computer-use agents that operate desktops and browsers.
Approach:	They propose a method that turns static expert traces into policy-aligned guidance . they propose RLVR with a per-task, dynamically updated cache to decompose planning and execution .
Outcome:	The proposed model improves UITARS1.5-7B success from 22.87% to 32.13% on OSWorld-Verified and raises a held-out split from 5.74% to 10.30% on MMBench-GUI and Online-Mind2Web.

Lightweight, Dynamic Graph Convolutional Networks for AMR-to-Text Generation (2020.emnlp-main)

Copied to clipboard

Yan Zhang, Zhijiang Guo, Zhiyang Teng, Wei Lu, Shay B. Cohen, Zuozhu Liu, Lidong Bing

SPARD: Self-Paced Curriculum for RL Alignment via Integrating Reward Dynamics and Data Utility (2026.acl-long)

Challenge:	AMR-to-text generation is used to transduce Abstract Meaning Representation structures (AMRs) Graph Convolution Networks (GCNs) are not able to capture non-local information and follow a local (first-order) information aggregation scheme.
Approach:	They propose a dynamic fusion mechanism that captures richer non-local interactions . they propose weight tied convolutions and group graph convolution to reduce memory usage .
Outcome:	The proposed model outperforms state-of-the-art models on two benchmark datasets with significantly fewer parameters while maintaining the model capacity.

Copied to clipboard

Xuyang Zhi, Peilun Zhou, Chengqiang Lu, Hang Lv, Yiwei Liang, Rongyang Zhang, Yan Gao, null Yiwu, Yao Hu, Hongchao Gu, Defu Lian, Hao Wang, Enhong Chen

Challenge:	Large Language Models (LLMs) are shifting the focus from single verifiable tasks toward complex, open-ended real-world scenarios.
Approach:	They propose a framework that automatically adjusts reward weights and data importance to synchronize learning intent with data utility for optimal performance.
Outcome:	The proposed framework improves model capabilities across all domains and scales.

DeepPresenter: Environment-Grounded Reflection for Agentic Presentation Generation (2026.findings-acl)

Copied to clipboard

Hao Zheng, Guozhao Mo, Xinru Yan, Qianhao Yuan, Wenkai Zhang, Xuanang Chen, Yaojie Lu, Hongyu Lin, Xianpei Han, Le Sun

Challenge:	Existing presentation agents rely on predefined workflows and fixed templates to generate presentations.
Approach:	They propose an agentic framework that adapts to diverse user intents and iterative refinement based on observation.
Outcome:	The proposed framework can be used to generate presentations with environmental observations.

Quantifying and Mitigating Unimodal Biases in Multimodal Large Language Models: A Causal Perspective (2024.findings-emnlp)

Copied to clipboard

Meiqi Chen, Yixin Cao, Yan Zhang, Chaochao Lu

Pause or Fabricate? Training Language Models for Grounded Reasoning (2026.findings-acl)

Challenge:	Recent advances in Large Language Models have facilitated the development of Multimodal LLMs.
Approach:	They propose a causal framework to interpret unimodal biases in visual question answering problems and a framework to integrate information from different modalities and mitigate biase.
Outcome:	The proposed framework analyzes visual question answering (VQA) problems to assess their impact on predictions.

Copied to clipboard

Yiwen Qiu, Linjuan Wu, Yizhou Liu, Yuchen Yan, Jin Ma, Xu Tan, Yao Hu, Daoxin Zhang, Wenqi Zhang, Weiming Lu, Jun Xiao, Yongliang Shen

A Systematic Survey of Automatic Prompt Optimization Techniques (2025.emnlp-main)

Challenge:	Large language models implicitly fabricate information when inputs are incomplete, causing confidence but unreliable conclusions.
Approach:	They propose a framework for grounded reasoning under incomplete information that decomposes reasoning into two stages . they propose stage-specific rewards to penalize hallucinations, enabling models to detect gaps, stop proactively, and resume reasoning after clarification.
Outcome:	The proposed framework improves premise detection and task success by 30% . it also reduces average response length by over 20% .

Copied to clipboard

Kiran Ramnath, Kang Zhou, Sheng Guan, Soumya Smruti Mishra, Xuan Qi, Zhengyuan Shen, Shuai Wang, Sangmin Woo, Sullam Jeoung, Yawei Wang, Haozhu Wang, Han Ding, Yuzhe Lu, Zhichao Xu, Yun Zhou, Balasubramaniam Srinivasan, Qiaojing Yan, Yueyan Chen, Haibo Ding, Panpan Xu, Lin Lee Cheong

CELLO: Causal Evaluation of Large Vision-Language Models (2024.emnlp-main)

Challenge:	Recent advances in prompt engineering have created impediments for end users to adopt . however, prompt engineering remains an impedance due to rapid advances in models, tasks, and associated best practices.
Approach:	They propose to define APO as a 5-part unifying framework and categorize all relevant works based on their salient features.
Outcome:	The proposed framework aims to improve the performance of large language models on various tasks.

Copied to clipboard

Meiqi Chen, Bo Peng, Yan Zhang, Chaochao Lu

RealBench: A Chinese Multi-image Understanding Benchmark Close to Real-world Scenarios (2025.findings-emnlp)

Challenge:	Recent advances in large vision-language models have improved causal reasoning abilities . however, current models struggle with tasks like causal reasoning .
Approach:	They propose a fine-grained and unified definition of causality involving interactions between humans and objects.
Outcome:	The proposed model surpasses traditional commonsense causality by including explicit causal graphs . it also shows that current LVLMs can benefit from a causally inspired prompting strategy .

Copied to clipboard

Fei Zhao, Chengqiang Lu, Yufan Shen, Qimeng Wang, Yicheng Qian, Haoxin Zhang, Yan Gao, null Yiwu, Yao Hu, Zhen Wu, Shangyu Xing, Xinyu Dai

STORM-BORN: A Challenging Mathematical Derivations Dataset Curated via a Human-in-the-Loop Multi-Agent Framework (2025.findings-acl)

Challenge:	RealBench is the first Chinese multimodal multi-image dataset . the dataset contains 9393 samples and 69910 images .
Approach:	They propose to create a Chinese multimodal multi-image dataset using 21 models . they use closed-source models that support multi-inputs as well as open-source visual and video models a .
Outcome:	The first Chinese multimodal multi-image dataset contains 9393 samples and 69910 images.

Copied to clipboard

Wenhao Liu, Zhenyi Lu, Xinyu Hu, Jerry Zhang, Dailin Li, Jiacheng Cen, Huilin Cao, Haiteng Wang, Yuhan Li, Xie Kun, Dandan Li, Pei Zhang, Chengbo Zhang, Yuxiang Ren, Xiaohong Huang, Yan Ma

QaDialMoE: Question-answering Dialogue based Fact Verification with Mixture of Experts (2022.findings-emnlp)

Challenge:	Existing datasets suffer from outdated and insufficient challenging content, neglecting human-like reasoning, and limited reliability due to single-LLM generation.
Approach:	They propose a human-in-the-loop, multi-agent data generation framework that integrates reasoning-dense filters, multiagent collaboration, and human mathematicians’ evaluations to ensure the reliability and quality of the dataset.
Outcome:	The proposed framework improves accuracy and quality of the 2,000-synthesized datasets by integrating reasoning-dense filters, multi-agent collaboration, and human mathematicians’ evaluations.

Copied to clipboard

Longzheng Wang, Peng Zhang, Xiaoyu Lu, Lei Zhang, Chaoyang Yan, Chuang Zhang

Natural Language Interfaces

Challenge:	Existing research on fact verification focuses on news, tables and Wikipedia passages.
Approach:	They propose a question-answering dialogue based fact verification with mixture of experts that exploits questions and evidence effectively in the verification process.
Outcome:	The proposed approach outperforms previous approaches on three benchmark datasets and achieves state-of-the-art results.

SLAM-Omni: Timbre-Controllable Voice Interaction System with Single-Stage Training (2025.findings-acl)

Copied to clipboard

Wenxi Chen, Ziyang Ma, Ruiqi Yan, Yuzhe Liang, Xiquan Li, Ruiyang Xu, Zhikang Niu, Yanqiao Zhu, Yifan Yang, Zhanxun Liu, Kai Yu, Yuxuan Hu, Jinyu Li, Yan Lu, Shujie Liu, Xie Chen

Speech & Audio in NLP

Challenge:	a new spoken dialogue system with single-stage training is demonstrating its low latency and high quality . SLAM-Omni achieves zero-shot timbre control by modeling spoken language with semantic tokens .
Approach:	They propose a timbre-controllable, end-to-end voice interaction system with single-stage training.
Outcome:	The proposed system outperforms previous models on 4 GPUs with limited data.

AskToAct: Enhancing LLMs Tool Use via Self-Correcting Clarification (2025.emnlp-main)

Copied to clipboard

Xuan Zhang, Yongliang Shen, Zhe Zheng, Linjuan Wu, Wenqi Zhang, Yuchen Yan, Qiuying Peng, Jun Wang, Weiming Lu

CoVerRL: Breaking the Consensus Trap in Label-Free Reasoning via Generator-Verifier Co-Evolution (2026.acl-long)

Challenge:	Existing tools for ambiguous and incomplete queries are limited by manual construction and lack of error correction mechanisms during multi-turn clarification.
Approach:	They propose a framework that exploits the mapping between queries and their tool invocation solutions by removing key parameters from queries while retaining them as ground truth.
Outcome:	The proposed framework outperforms existing methods while maintaining high accuracy in tool invocation.

Copied to clipboard

Teng Pan, Yuchen Yan, Zixuan Wang, Ruiqing Zhang, Guiyang Hou, Wenqi Zhang, Weiming Lu, Jun Xiao, Yongliang Shen

Anti-Length Shift: Dynamic Outlier Truncation for Training Efficient Reasoning Models (2026.acl-long)

Challenge:	Label-free reinforcement learning enables large language models to improve reasoning capabilities . but as training maximizes self-consistency, output diversity collapses, authors say . authors propose a framework where a single model alternates between generator and verifier roles .
Approach:	They propose a framework where a model alternates between generator and verifier roles, bootstrapping each other.
Outcome:	Experiments show that CoVerRL outperforms label-free baselines on reasoning benchmarks . the framework can be used to improve reasoning abilities without ground-truth supervision .

Copied to clipboard

Wei Wu, Liyi Chen, Congxi Xiao, Tianfu Wang, Qimeng Wang, Chengqiang Lu, Yan Gao, null Yiwu, Yao Hu, Hui Xiong

System Prompt Hijacking via Permutation Triggers in LLM Supply Chains (2025.findings-acl)

Challenge:	Existing efficient reasoning methods rely on explicit length penalties for excessive verbosity on simple queries.
Approach:	They propose a training-time intervention that selectively suppresses redundant tokens . they find length shift occurs when models generate unnecessary reasoning on trivial inputs - a phenomenon that is often unexplored .
Outcome:	The proposed method reduces inference token usage by 78% while increasing accuracy compared to the initial policy and surpasses state-of-the-art efficient reasoning methods.

Copied to clipboard

Lu Yan, Siyuan Cheng, Xuan Chen, Kaiyuan Zhang, Guangyu Shen, Xiangyu Zhang

CSPO: Alleviating Reward Ambiguity for Structured Table-to-LaTeX Generation (2026.acl-long)

Challenge:	Large language models (LLMs) are rapidly transforming the landscape of artificial intelligence due to the substantial resources required for training.
Approach:	They propose a post-deployment attack that bypasses system prompts to compromise models . they introduce Precise Activation Guarding and Unit Deviation Sampling to protect against attack .
Outcome:	The proposed attack bypasses system prompts, enabling unrestricted model outputs and safety violations.

Copied to clipboard

Yunfan Yang, Cuiling Lan, Jitao Sang, Yan Lu

Unknown Intent Detection Using Gaussian Mixture Model with an Application to Zero-shot Intent Classification (2020.acl-main)

Challenge:	Tables contain rich structured information, but when stored as images their contents remain "locked" within pixels.
Approach:	They propose a framework that disentangles optimization across LaTeX tables components . CSPO assigns component-specific rewards and backpropagates each signal through tokens .
Outcome:	The proposed framework disentangles optimization across LaTeX tables components—structure, style, and content.

Copied to clipboard

Guangfeng Yan, Lu Fan, Qimai Li, Han Liu, Xiaotong Zhang, Xiao-Ming Wu, Albert Y.S. Lam

A Knowledge-driven Generative Model for Multi-implication Chinese Medical Procedure Entity Normalization (2020.emnlp-main)

Challenge:	Existing methods for unknown intent detection are limited by prior knowledge of class labels.
Approach:	They propose to use a Gaussian mixture model to model utterance embeddings with a distribution and inject dynamic class semantic information into Gausssian means.
Outcome:	The proposed model performs well on three real task-oriented dialogue datasets in two languages.

Copied to clipboard

Jinghui Yan, Yining Wang, Lu Xiang, Yu Zhou, Chengqing Zong

Challenge:	Medical entity normalization (NEN) is a task that links medical mentions to entities in knowledge bases.
Approach:	They propose a sequence generative framework to generate Chinese medical procedure entity normalization by constraint decoding and category-based model refining.
Outcome:	The proposed model improves on baselines especially in the case of multi-implication Chinese medical procedures.

SelfAug: Mitigating Catastrophic Forgetting in Retrieval-Augmented Generation via Distribution Self-Alignment (2025.findings-emnlp)

Copied to clipboard

Yuqing Huang, Rongyang Zhang, Qimeng Wang, Chengqiang Lu, Yan Gao, null Yiwu, Yao Hu, Xuyang Zhi, Guiquan Liu, Xin Li, Hao Wang, Enhong Chen

What If Consensus Lies? Selective-Complementary Reinforcement Learning at Test Time (2026.acl-long)

Challenge:	Existing solutions for supervised fine-tuning often lead to catastrophic forgetting, where models lose their previously acquired knowledge and general capabilities.
Approach:	They propose a self-distribution alignment method that aligns input sequence logits to preserve the model’s semantic distribution, thereby mitigating catastrophic forgetting and improving downstream performance.
Outcome:	The proposed method achieves a superior balance between downstream learning and general capability retention.

Copied to clipboard

Dong Yan, Jian Liang, Yanbo Wang, Shuo Lu, Ran He, Tieniu Tan

Object-oriented Neural Programming (OONP) for Document Understanding (P18-1)

Challenge:	Existing TTRL methods rely on positive pseudo-labeling strategies to enhance reasoning capabilities.
Approach:	They propose a test-time reinforcement learning framework that mitigates label noise amplification by deriving pseudo-rewards from majority voting consensus.
Outcome:	The proposed framework mitigates label noise amplification by implementing selective positive pseudo-labeling and entropy-gated negative p-labeled pruning.

Copied to clipboard

Zhengdong Lu, Xianggen Liu, Haotian Cui, Yukun Yan, Daqi Zheng

Noisy Positive-Unlabeled Learning with Self-Training for Speculative Knowledge Graph Reasoning (2023.findings-acl)

Challenge:	Object-oriented Neural Programming (OONP) is a framework for semantically parsing documents in domains.
Approach:	They propose a framework for semantically parsing documents in specific domains using OONP . OOPN parsers use a rich family of operations to represent the semantics of the document .
Outcome:	The proposed framework can learn to handle fairly complicated ontology with training data of modest sizes.

Copied to clipboard

Ruijie Wang, Baoyu Li, Yichen Lu, Dachun Sun, Jinning Li, Yuchen Yan, Shengzhong Liu, Hanghang Tong, Tarek Abdelzaher

Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models (2024.acl-long)

Challenge:	State-of-the-art methods fail in speculative reasoning task on knowledge graphs . state-of the-art approaches assume correctness of fact is determined by its presence in KG .
Approach:	They propose a speculative reasoning task on real-world knowledge graphs . they propose nPUGraph that estimates correctness of both collected and uncollected facts .
Outcome:	The proposed framework improves the robustness of a label posterior-aware graph encoder against false positive links and identifies missing facts to provide high-quality grounds of reasoning.

Copied to clipboard

Xudong Lu, Qi Liu, Yuhui Xu, Aojun Zhou, Siyuan Huang, Bo Zhang, Junchi Yan, Hongsheng Li

CNNSum: Exploring Long-Context Summarization with Large Language Models in Chinese Novels (2025.findings-acl)

Challenge:	Mixture-of-Experts (MoE) LLMs achieve higher performance with fewer active parameters, but are still difficult to deploy due to their immense parameter sizes.
Approach:	They propose expert-level sparsification techniques to enhance the deployment efficiency of large language models by introducing plug-and-play expert pruning and skipping techniques.
Outcome:	The proposed methods reduce model sizes and increase inference speed while maintaining satisfactory performance across a wide range of tasks.

Copied to clipboard

Lingxiao Wei, He Yan, Lu Xiangju, Junmin Zhu, Jun Wang, Wei Zhang

Information Extraction & Text Mining

Challenge:	Currently, long-context summarization mainly relies on memory ability.
Approach:	They propose a multi-scale long-context summarization benchmark based on Chinese novels . they use human-driven annotations to analyze long-constituency models .
Outcome:	The proposed benchmark features human-driven annotations across four subsets with lengths ranging from 16k to 128k.

Can LLM Agents Simulate Multi-Turn Human Behavior? Evidence from Real Online Customer Behavior Data (2026.acl-long)

Copied to clipboard

Yuxuan Lu, Jing Huang, Yan Han, Bingsheng Yao, Sisong Bei, Yaochen Xie, Yisi Sang, Qi He, Dakuo Wang

Reward Modeling Requires Automatic Adjustment Based on Data Quality (2024.findings-emnlp)

Challenge:	Recent research shows that LLM Agents can generate “believable” human behaviors via prompt-only methods, leaving open questions of whether they can accurately generate step-by-step actions in multi-turn interaction tasks.
Approach:	They propose to use shopping data to evaluate LLMs' ability to accurately generate step-by-step actions in a multi-turn interaction task.
Outcome:	The proposed model achieves 17.26% action generation accuracy and 33.86% F1 score on final purchase prediction, representing improvements of 5.4% and 13.85% over baselines.

Copied to clipboard

Binghai Wang, Rui Zheng, Lu Chen, Zhiheng Xi, Wei Shen, Yuhao Zhou, Dong Yan, Tao Gui, Qi Zhang, Xuanjing Huang

Challenge:	Reinforcement Learning from Human Feedback (RLHF) is a method for aligning language models with human values.
Approach:	They propose a method that automatically adjusts reward modeling based on data quality . they use preference data to train a reward model that is more aligned with human values .
Outcome:	The proposed method stabilizes reward model training and significantly improves alignment performance on human preference datasets.

Learning Like Humans: Advancing LLM Reasoning Capabilities via Adaptive Difficulty Curriculum Learning and Expert-Guided Self-Reformulation (2025.emnlp-main)

Copied to clipboard

Enci Zhang, Xingang Yan, Wei Lin, Tianxiang. Zhang, Lu Qianchun

MoDification: Mixture of Depths Made Easy (2025.naacl-long)

Challenge:	Extensive experiments on challenging mathematical reasoning benchmarks demonstrate that these human-inspired strategies synergistically and significantly enhance performance.
Approach:	They propose to use Adaptive Difficulty Curriculum Learning and Expert-Guided Self-Reformulation to improve model performance.
Outcome:	Extensive experiments on mathematical reasoning benchmarks show that the proposed strategies synergistically and significantly improve performance over the baseline model.

Copied to clipboard

Chen Zhang, Meizhi Zhong, Qimeng Wang, Xuantao Lu, Zheyu Ye, Chengqiang Lu, Yan Gao, Yao Hu, Kehai Chen, Min Zhang, Dawei Song

Green & Sustainable NLP

Challenge:	Long-context efficiency is a trending topic in large language model (LLM) serving.
Approach:	They propose a method to combine long-context efficiency and mixture of depths to bring down both latency and memory.
Outcome:	The proposed method achieves 1.2 speedup in latency and 1.8 reduction in memory compared to original LLMs especially in long-context applications.

AgentRM: Enhancing Agent Generalization with Reward Modeling (2025.acl-long)

Copied to clipboard

Yu Xia, Jingru Fan, Weize Chen, Siyu Yan, Xin Cong, Zhong Zhang, Yaxi Lu, Yankai Lin, Zhiyuan Liu, Maosong Sun

Do Large Language Models Truly Grasp Addition? A Rule-Focused Diagnostic Using Two-Integer Arithmetic (2025.emnlp-main)

Challenge:	Existing LLM-based agents have strong performance on held-in tasks, but their generalizability to unseen tasks remains poor.
Approach:	They propose a reward-based generalizable reward model to guide the policy model for effective test-time search.
Outcome:	The proposed agentRM outperforms existing agents on held-in tasks by 8.8 points on average.

Copied to clipboard

Yang Yan, Yu Lu, Renjun Xu, Zhenzhong Lan

SeqAR: Jailbreak LLMs with Sequential Auto-Generated Characters (2025.naacl-long)

Challenge:	Large language models (LLMs) excel at complex math but fail on basic addition, raising the question of whether they grasp rules or are merely reproducing patterns.
Approach:	They systematically probe LLMs’ understanding of two-integer addition by testing three crucial properties: commutativity (A+B=B+A), representation invariance via symbolic remapping and consistent accuracy scaling with operand length.
Outcome:	The proposed models achieve high numeric accuracy but fail basic addition tasks.

Copied to clipboard

Yan Yang, Zeguan Xiao, Xin Lu, Hongru Wang, Xuetao Wei, Hailiang Huang, Guanhua Chen, Yun Chen

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

Challenge:	Existing studies have focused on the potential misuse of large language models (LLMs) however, the ability to align LLMs with human values is still vulnerable to malicious attacks.
Approach:	They propose a red-teaming strategy to enhance LLM safety by using a framework to design jailbreak prompts automatically.
Outcome:	The proposed framework achieves attack success rates of 88% and 60% in cold-start scenarios.

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

Beyond Cross-Modal Alignment: Measuring and Leveraging Modality Gap in Vision-Language Models (2026.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

Hanqi Yan, Xiangxiang Cui, Lu Yin, Jindong Gu, Paul Pu Liang, Yulan He, Yifei Wang

Negating Negatives: Alignment with Human Negative Samples via Distributional Dispreference Optimization (2024.findings-emnlp)

Challenge:	a recent study shows that vision-language models have modality gaps that persist even in well-aligned models.
Approach:	They propose a modality-dominance score to measure and leverage modality gaps . they propose automatic interpretability metrics to evaluate these features in a scalable manner .
Outcome:	The proposed framework allows for training-free probing and editing methods for understanding model perception across genders and generating adversarial examples.

Copied to clipboard

Shitong Duan, Xiaoyuan Yi, Peng Zhang, Yan Liu, Zheng Liu, Tun Lu, Xing Xie, Ning Gu

Weakly Supervised Contrastive Learning for Chest X-Ray Report Generation (2021.findings-emnlp)

Challenge:	Existing methods to steer LLMs towards human preference suffer from noisy positive-negative training pairs.
Approach:	They propose a distributional preference optimization method which maximizes discrepancy between dispreferred responses and generated non-negative ones.
Outcome:	The proposed method achieves comparable generation quality and surpasses the latest strong baselines in producing less harmful and more informative responses with better training stability and faster convergence.

Copied to clipboard

An Yan, Zexue He, Xing Lu, Jiang Du, Eric Chang, Amilcare Gentili, Julian McAuley, Chun-Nan Hsu

Wenqiang Wang, Peng Chen, Yan Xiao, Yangshijie Zhang, Xiaoyue Lu, Jianjie Huang, Xiaochun Cao

Challenge:	Radiology report generation aims at generating descriptive text from radiology images automatically.
Approach:	They propose a weakly supervised contrastive loss method that generates descriptive text from radiology images automatically.
Outcome:	The proposed method outperforms previous work on correctness and text generation metrics for two public benchmarks.

Copied to clipboard

Information Retrieval

Challenge:	Standard in-context learning assumes identical output spaces between test and retrieval datasets . however, in practice, these datasets can be fully aligned, partially alignes, or fully disjoint in label space .
Approach:	They propose a framework for in-context learning under output-space mismatch . they identify demonstrations relevant to the test label space via a Bayesian probabilistic criterion .
Outcome:	The proposed framework achieves state-of-the-art results across three LLMs, three task types, and four datasets.

LLMs know their vulnerabilities: Uncover Safety Gaps through Natural Distribution Shifts (2025.acl-long)

Copied to clipboard

Qibing Ren, Hao Li, Dongrui Liu, Zhanxu Xie, Xiaoya Lu, Yu Qiao, Lei Sha, Junchi Yan, Lizhuang Ma, Jing Shao

AscendKernelGen: LLM-Driven Kernel Generation for NPUs (2026.findings-acl)

Challenge:	Current safety training focuses on teaching models to reject harmful queries, but recent research shows that adversarial attacks or jailbreak methods bypass these safety mechanisms.
Approach:	They propose to use a new attack method to craft multi-turn toxic prompts that gradually lead LLMs to reveal unsafe content.
Outcome:	The proposed method outperforms existing methods in diversity, effectiveness, and efficiency across aligned LLMs.

Copied to clipboard

Xinzi Cao, Jianyang Zhai, Pengfei Li, Zhiheng Hu, Cen Yan, null Mubingxu, Guanghuan Fang, Bin She, Jiayu Li, Yihan Su, Dongyang Tao, Feidiao Yang, Chang-Dong Wang, Yutong Lu, Weicheng Xue, Bin Zhou, Yonghong Tian

Challenge:	Neural Processing Units (NPUs) are critical for AI infrastructure, but their development remains a bottleneck due to vendor-specific Domain-Specific Languages (DSLs).
Approach:	They propose a framework for NPU kernel development that bridges the gap in hardware-specific coding . compiler success on complex Level-2 kernels improves from 0% to 95.5%, they say .
Outcome:	The proposed framework bridges the gap in hardware-specific coding, showing a near-zero success rate on complex kernels.

BrainLoc: Brain Signal-Based Object Detection with Multi-modal Alignment (2025.findings-emnlp)

Copied to clipboard

Jiaqi Duan, Xiaoda Yang, Kaixuan Luan, Hongshun Qiu, Weicai Yan, Xueyi Zhang, Youliang Zhang, Zhaoyang Li, Donglin Huang, JunYu Lu, Ziyue Jiang, Xifeng Yang

Improving Autoformalization Using Direct Dependency Retrieval (2026.acl-long)

Challenge:	BrainLoc is a lightweight object detection model guided by fMRI signals.
Approach:	They propose a brain-based object detection model guided by fMRI signals . they employ a multi-modal alignment strategy that enhances fmr feature extraction .
Outcome:	The proposed model improves fMRI-based object detection accuracy and convenience.

Copied to clipboard

Shaoqi Wang, Lu Yu, Siwei Lou, Feng Yan, Chunjie Yang, Qing Cui, Jun Zhou

Finch: Benchmarking Finance & Accounting across Spreadsheet-Centric Enterprise Workflows (2026.findings-acl)

Challenge:	Existing methods for hallucinate formal dependencies lack scalability and precision to leverage ever-growing public datasets.
Approach:	They propose a retrieval-augmented framework based on Direct Dependency Retrieval to generate formal dependencies from natural-language mathematical descriptions and verify their existence via an efficient Suffix Array Check (SAC).
Outcome:	The proposed framework outperforms state-of-the-art methods in retrieval precision and recall and can be used to validate formal representations in a public dataset.

Copied to clipboard

Haoyu Dong, Pengkun Zhang, Yan Gao, Xuanyu Dong, Yilin Cheng, Mingzhe Lu, Adina Yakefu, Shuxin Zheng

Visualize Before You Write: Imagination-Guided Open-Ended Text Generation (2023.findings-eacl)

Challenge:	FinWorkBench evaluates real-world enterprise-grade finance and accounting workflows . a human evaluation of GPT 5.1 Pro passes only 38.4% of workflows, a study finds .
Approach:	They propose a workflow construction process that combines LLM-assisted mining and expert annotation to build 172 composite workflows.
Outcome:	The proposed process combines expert annotation with LLM-assisted mining of workflows from authentic enterprise environments.

Copied to clipboard

Wanrong Zhu, An Yan, Yujie Lu, Wenda Xu, Xin Wang, Miguel Eckstein, William Yang Wang

UI-E2I-Synth: Advancing GUI Grounding with Large-Scale Instruction Synthesis (2025.findings-acl)

Challenge:	Existing tools for text-to-image synthesis can visualize machine imaginations for a given context.
Approach:	They propose a framework that uses machine-generated images to guide language models in open-ended text generation.
Outcome:	The proposed framework is effective on open-ended text generation tasks while showing minor degeneration.

Copied to clipboard

Xinyi Liu, Xiaoyi Zhang, Ziyun Zhang, Yan Lu

Closing the Modality Reasoning Gap for Speech Large Language Models (2026.acl-long)

Challenge:	Graphical User Interface (GUI) agents that utilize human-like vision perception capabilities are gaining a wider applicability compared to GUI metadata-based approaches.
Approach:	They propose a large-scale data synthesis pipeline for generating varying complex instruction datasets using GPT-4o instead of human annotators.
Outcome:	The proposed model achieves superior performance in GUI instruction grounding, demonstrating the advancements of proposed data synthesis pipeline.

Copied to clipboard

Chaoren Wang, Heng Lu, Xueyao Zhang, Shujie Liu, Yan Lu, Jinyu Li, Zhizheng Wu

Triad: A Framework Leveraging a Multi-Role LLM-based Agent to Solve Knowledge Base Question Answering (2024.emnlp-main)

Challenge:	Recent advances in Speech Large Language Models have a modality reasoning gap that is not addressed by prior work.
Approach:	They propose a reinforcement-learning framework that aligns text-conditioned and speech-conditioned trajectories through an asymmetric reward design.
Outcome:	Experiments on MMSU and OBQA show that the proposed framework narrows the modality reasoning gap and achieves state-of-the-art performance among 7B-scale Speech LLMs.

Copied to clipboard

Chang Zong, Yuchen Yan, Weiming Lu, Jian Shao, Yongfeng Huang, Heng Chang, Yueting Zhuang

Natural Language Interfaces

Challenge:	Recent advances with LLMs have shown promising results across various tasks, but their use in answering questions from knowledge bases remains largely unexplored.
Approach:	They propose a framework that utilizes an LLM-based agent with multiple roles for KBQA tasks.
Outcome:	The proposed framework outperforms state-of-the-art systems on the LC-QuAD and YAGO-QA benchmarks yielding F1 scores of 11.8% and 20.7%, respectively.

Goal-oriented Vision-and-Dialog Navigation via Reinforcement Learning (2022.findings-emnlp)

Copied to clipboard

Yan Cao, Keting Lu, David DeFazio, Shiqi Zhang

Visual Data in NLP

Challenge:	Existing methods for vision-and-dialog navigation are limited and do not adapt to domain changes.
Approach:	They propose a problem where an agent computes dialog-navigation policies from trial and error.
Outcome:	The proposed agent outperforms baselines in success rate in photo-realistic simulations.

CC-Tuning: A Cross-Lingual Connection Mechanism for Improving Joint Multilingual Supervised Fine-Tuning (2025.acl-long)

Copied to clipboard

Yangfan Ye, Xiaocheng Feng, Zekun Yuan, Xiachong Feng, Libo Qin, Lei Huang, Weitao Ma, Yichong Huang, Zhirui Zhang, Yunfei Lu, Xiaohui Yan, Duyu Tang, Dandan Tu, Bing Qin

Multilinguality

Challenge:	Existing fine-tuning approaches that focus on English-centric training corpora often introduce implicit cross-lingual alignment, overlooking the potential for more profound, latent-level cross-linguistic interactions.
Approach:	They propose a multilingual fine-tuning paradigm that explicitly establishes a cross-lingual connection mechanism at the latent level.
Outcome:	The proposed model outperforms vanilla SFT and offers a strong latent-level alternative to data-level augmentation methods.

LIFBench: Evaluating the Instruction Following Performance and Stability of Large Language Models in Long-Context Scenarios (2025.acl-long)

Copied to clipboard

Xiaodong Wu, Minhao Wang, Yichen Liu, Xiaoming Shi, He Yan, Lu Xiangju, Junmin Zhu, Wei Zhang

Attention Guided Graph Convolutional Networks for Relation Extraction (P19-1)

Challenge:	Existing benchmarks rarely focus on instruction-following in long-context scenarios or stability on different inputs.
Approach:	They propose a scalable dataset to evaluate LLMs’ instruction-following capabilities and stability across long contexts.
Outcome:	The proposed method evaluates LLMs’ instruction-following capabilities and stability across long contexts.

Copied to clipboard

Zhijiang Guo, Yan Zhang, Wei Lu

Information Extraction & Text Mining

Challenge:	Existing approaches for selecting relevant partial dependency structures may not yield optimal results.
Approach:	They propose a model which directly takes full dependency trees as inputs and uses them to selectively attend to relevant sub-structures.
Outcome:	The proposed model can be understood as a soft-pruning approach that automatically learns how to selectively attend to the relevant sub-structures useful for the relation extraction task.

TrendFact: A Benchmark Towards Hotspot Perception in Automatic Fact-Checking (2026.acl-long)

Copied to clipboard

Xiaocheng Zhang, Xi Wang, Yifei Lu, Jianing Wang, Zhuangzhuang Ye, Mengjiao Bao, Peng Yan, Xiaohong Su

ENT-DESC: Entity Description Generation by Exploring Knowledge Graph (2020.emnlp-main)

Challenge:	Existing benchmarks lack social metadata and evaluation framework to meet this urgent evaluation needs.
Approach:	They propose a benchmark capable of evaluating HPA and three fact-checking tasks.
Outcome:	The proposed framework improves HPA and computational efficiency for RLM-driven systems.

Copied to clipboard

Liying Cheng, Dekun Wu, Lidong Bing, Yan Zhang, Zhanming Jie, Wei Lu, Luo Si

Structured Data in NLP

Challenge:	Existing models for knowledge-to-text generation use RDF triples or key-value pairs to generate a natural language description.
Approach:	They propose a large-scale dataset to facilitate the study of KG-to-text . they propose MGCN model architecture that incorporates aggregation methods to extract the rich graph information.
Outcome:	The proposed model can represent the original graph information more comprehensively and integrates multiple aggregation methods to extract the rich graph information.

Inverting the Shield: Systematically Generating Safety Tests from Policy Specifications (2026.acl-long)

Copied to clipboard

Xiaoyue Lu, Xianglin Yang, Haijun Liu, Jiahao Liu, Kuntai Cai, Yan Xiao, Jin Song Dong

Structured Data in NLP

Challenge:	Existing safety evaluation paradigms rely on constructed benchmarks or dynamic red-teaming to probe potential vulnerabilities.
Approach:	They propose a framework that integrates specification-based software testing with AI safety.
Outcome:	The proposed framework achieves higher coverage and attack success counts compared to baselines.

RevCore: Review-Augmented Conversational Recommendation (2021.findings-acl)

Copied to clipboard

Yu Lu, Junwei Bao, Yan Song, Zichen Ma, Shuguang Cui, Youzheng Wu, Xiaodong He

Dialogue Systems & Conversational Agents

Challenge:	Existing conversational recommendation systems lack item information when conducted on short dialogue history and unfamiliar items.
Approach:	They propose a framework where reviews are seamlessly incorporated into conversational recommendation systems.
Outcome:	The proposed framework yields better performance on recommendation and conversation responding.

Enhancing Open-Domain Task-Solving Capability of LLMs via Autonomous Tool Integration from GitHub (2025.acl-long)

Copied to clipboard

Bohan Lyu, Xin Cong, Heyang Yu, Pan Yang, Cheng Qian, Zihe Wang, Yujia Qin, Yining Ye, Yaxi Lu, Chen Qian, Zhong Zhang, Yukun Yan, Yankai Lin, Zhiyuan Liu, Maosong Sun

Route to Rome Attack: Directing LLM Routers to Expensive Models via Adversarial Suffix Optimization (2026.acl-long)

Challenge:	Existing approaches lack flexibility to address diverse and ever-evolving user queries in open domains.
Approach:	They propose to evaluate LLMs on open-domain knowledge that requires tools to solve diverse and ever-evolving user queries.
Outcome:	The proposed system outperforms baselines in the open domain task-solving benchmark.

Copied to clipboard

Haochun Tang, Yuliang Yan, Jiahua Lu, Huaxiao Liu, Enyan Dai

SpeechLLM-as-Judges: Towards General and Interpretable Speech Quality Evaluation (2026.acl-long)

Challenge:	Existing routing attacks depend on white-box access or heuristic prompts, rendering them ineffective in real-world black-box scenarios.
Approach:	They propose a cost-aware routing strategy that routes queries to the least-cost model . they propose heuristic prompts that are ineffective in real-world black-box scenarios .
Outcome:	The proposed approach significantly increases the routing rate to expensive models on queries of different distributions.

Copied to clipboard

Hui Wang, Jinghua Zhao, Yifan Yang, Shujie Liu, Junyang Chen, Yanzhe Zhang, Shiwan Zhao, Jinyu Li, Jiaming Zhou, Haoqin Sun, Yan Lu, Yong Qin