Papers by Ying Wei

LightSeq: A High Performance Inference Library for Transformers (2021.naacl-industry)

Challenge:	composition of pre-training datasets for large language models remains undisclosed . current methods for evaluating data quality are limited by single-dimensional evaluation or redundancy-focused strategies.
Approach:	They propose a multi-dimensional data selection method that integrates dimensions with existing quality metrics through learned optimal weightings.
Outcome:	The proposed method doubles convergence speed for 1.3B model models and improves downstream task performance by 3.23%.

Copied to clipboard

Xiaohui Wang, Ying Xiong, Yang Wei, Mingxuan Wang, Lei Li

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

Challenge:	Existing inference frameworks for natural language processing are not the best choice for online service of sequence processing problems.
Approach:	They propose a highly efficient inference library for Transformer models that includes GPU optimization techniques to streamline computation and reduce memory footprint.
Outcome:	The proposed library achieves 14x speedup compared with TensorFlow and 1.4x speed up compared to a concurrent CUDA implementation.

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

Title2Event: Benchmarking Open Event Extraction with a Large-scale Chinese Title Dataset (2022.emnlp-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

Haolin Deng, Yanan Zhang, Yangfan Zhang, Wangyang Ying, Changlong Yu, Jun Gao, Wei Wang, Xiaoling Bai, Nan Yang, Jin Ma, Xiang Chen, Tianhua Zhou

Improving Alignment in LVLMs with Debiased Self-Judgment (2025.findings-emnlp)

Challenge:	Existing EE datasets define fixed event types and design specific schemas for each of them, failing to cover diverse events emerging from the online text.
Approach:	They propose to use a sentence-level dataset to benchmark Open Event Extraction without restricting event types.
Outcome:	The proposed dataset contains more than 42,000 news titles in 34 topics collected from Chinese web pages.

Copied to clipboard

Sihan Yang, Chenhang Cui, Zihao Zhao, Yiyang Zhou, Weilong Yan, Ying Wei, Huaxiu Yao

Automatic Expert Discovery in LLM Upcycling via Sparse Interpolated Mixture-of-Experts (2025.acl-long)

Challenge:	Existing methods for aligning LVLMs rely on external datasets, human annotations or complex post-processing.
Approach:	They propose a method that generates a debiased self-judgment score for LVLMs . this self-evaluation metric is created internally by the model without external resources .
Outcome:	The proposed approach outperforms existing methods in reducing hallucinations and safety concerns.

Copied to clipboard

Shengzhuang Chen, Ying Wei, Jonathan Richard Schwarz

Language Scaling for Universal Suggested Replies Model (2021.naacl-industry)

Challenge:	Sparse Interpolated Mixture-of-Experts (SIMoE) instruction-tuning is an end-to-end algorithm designed to fine-tune a dense pre-trained Large Language Model (LLM) into a MoE-style model that possesses capabilities in multiple specialized domains.
Approach:	They propose an algorithm to fine-tune a dense pre-trained Large Language Model into a MoE-style model that possesses capabilities in multiple specialized domains.
Outcome:	The proposed algorithm achieves state-of-the-art on common instruction-tuning benchmarks while maintaining an optimal performance-compute trade-off compared to baselines.

Copied to clipboard

Qianlan Ying, Payal Bajaj, Budhaditya Deb, Yu Yang, Wei Wang, Bojia Lin, Milad Shokouhi, Xia Song, Yang Yang, Daxin Jiang

Multilinguality

Challenge:	We consider scaling automated suggested replies (SR) to multiple languages for a commercial email application.
Approach:	They propose a multi-lingual multi-task continual learning framework with auxiliary tasks and language adapters to train universal language representation across regions.
Outcome:	The proposed model reduces catastrophic forgetting and improves cross-lingual transfer across languages while reducing training costs.

Text-to-TrajVis: Enabling Trajectory Data Visualizations from Natural Language Questions (2026.findings-acl)

Copied to clipboard

Tian Bai, Huiyan Ying, Kailong Suo, Victor Junqiu Wei, Tao Fan, Yuanfeng Song

Challenge:	Existing datasets for this task are limited and there is no suitable one available.
Approach:	They propose a new visualization language called Trajectory Visualization Language (TVL) to facilitate querying trajectory data and generating visualizations.
Outcome:	The proposed language can be used to query and generate trajectory data and generate visualizations with large language models.

Mitigating the Language Mismatch and Repetition Issues in LLM-based Machine Translation via Model Editing (2024.emnlp-main)

Copied to clipboard

Weichuan Wang, Zhaoyi Li, Defu Lian, Chen Ma, Linqi Song, Ying Wei

Machine Translation

Challenge:	Existing studies have focused on using Large Language Models to improve translation quality . language mismatch and repetition are two of the main problems with LLMs .
Approach:	They propose to leverage model editing methods to reduce language mismatch and repetition . they propose to fetch intersections of locating results under different language settings .
Outcome:	The proposed methods reduce language mismatch and repetition ratios and enhance translation quality in most cases.

Neural Response Generation with Meta-words (P19-1)

Copied to clipboard

Can Xu, Wei Wu, Chongyang Tao, Huang Hu, Matt Schuerman, Ying Wang

Dialogue Systems & Conversational Agents

Challenge:	Experimental results show that meta-words can be used to generate open domain dialogues . human-machine conversation is a fundamental problem in NLP .
Approach:	They propose a goal-tracking memory network that formalizes meta-word expression as a target in response generation and manages the generation process with a state memory panel and a controller.
Outcome:	The proposed model outperforms state-of-the-art generation models in response relevance, response diversity, and accuracy.

Disentangling Language and Culture for Evaluating Multilingual Large Language Models (2025.acl-long)

Copied to clipboard

Jiahao Ying, Wei Tang, Yiran Zhao, Yixin Cao, Yu Rong, Wenxuan Zhang

LLMs-as-Instructors: Learning from Errors Toward Automating Model Improvement (2024.findings-emnlp)

Challenge:	Extensive evaluations of large language models (LLMs) are conducted on a wide range of models, revealing a notable cultural-linguistic synergy phenomenon, where models exhibit better performance when questions are culturally aligned with the language.
Approach:	They propose a Dual Evaluation Framework to comprehensively assess the multilingual capabilities of large language models by decomposing evaluation along dimensions of linguistic medium and cultural context.
Outcome:	The proposed framework allows for a nuanced analysis of LLMs’ ability to process questions within both native and cross-cultural contexts cross-lingually.

Copied to clipboard

Jiahao Ying, Mingbao Lin, Yixin Cao, Wei Tang, Bo Wang, Qianru Sun, Xuanjing Huang, Shuicheng Yan

Challenge:	Using advanced Large Language Models, instructors can improve training of smaller models by analyzing their own model's errors.
Approach:	They propose a framework that leverages advanced Large Language Models to enhance training of smaller target models.
Outcome:	The proposed framework outperforms ChatGPT on multiple benchmarks and shows that it improves on both in-domain and out-of-domain benchmarks.

Towards Anytime Fine-tuning: Continually Pre-trained Language Models with Hypernetwork Prompts (2023.findings-emnlp)

Copied to clipboard

Gangwei Jiang, Caigao Jiang, Siqiao Xue, James Zhang, Jun Zhou, Defu Lian, Ying Wei

MMLU-CF: A Contamination-free Multi-task Language Understanding Benchmark (2025.acl-long)

Challenge:	Continual pre-training has been used for a multitude of domains and tasks . a continually pre-trained model can show a non-decreasing performance on unseen domains .
Approach:	They propose a method that generates domain-specific prompts by agreement and disagreement losses.
Outcome:	The proposed method achieves improvements of 3.57% and 3.4% on two real-world datasets.

Copied to clipboard

Qihao Zhao, Yangyu Huang, Tengchao Lv, Lei Cui, Qinzheng Sun, Shaoguang Mao, Xin Zhang, Ying Xin, Qiufeng Yin, Scarlett Li, Furu Wei

MetaTS: Meta Teacher-Student Network for Multilingual Sequence Labeling with Minimal Supervision (2021.emnlp-main)

Challenge:	Multiple-choice question datasets like Massive Multitask Language Understanding (MMLU) have inevitably led to benchmark contamination, resulting in unreliable evaluation.
Approach:	They propose a contamination-free MCQ benchmark called MMLU-CF which reassesses LLMs’ understanding of world knowledge by averting both unintentional and malicious data contamination.
Outcome:	The proposed MMLU-CF reassesses LLMs’ understanding of world knowledge by averting both unintentional and malicious data contamination.

Copied to clipboard

Zheng Li, Danqing Zhang, Tianyu Cao, Ying Wei, Yiwei Song, Bing Yin

Multilinguality

Challenge:	Sequence labeling aims to predict fine-grained sequences of labels for text, but lack of token-level annotated data hinders the effectiveness of supervised methods.
Approach:	They propose a Meta Teacher-Student (MetaTS) Network to alleviate data scarcity by leveraging large multilingual unlabeled data.
Outcome:	The proposed meta learning method alleviates data scarcity by leveraging large multilingual unlabeled data.

DMN: A Compositional Framework for Jailbreaking Multimodal LLMs with Multi-Image Inputs (2026.acl-long)

Copied to clipboard

Wenzhuo Xu, Zhipeng Wei, Zonghao Ying, Deyue Zhang, Dongdong Yang, Xiangzheng Zhang, Quanchen Zou

Learning to Substitute Spans towards Improving Compositional Generalization (2023.acl-long)

Challenge:	Existing jailbreak methods only use a single image, restricting the attack space . Existing frameworks only use single image to distribute harmful requests across multiple images .
Approach:	They propose a compositional jailbreak framework that leverages Distributed instruction, Multimodal evidence and a Number chain task to fully enhance the jailbreak performance.
Outcome:	The proposed framework achieves attack success rates of over 90% on GPT-4o, Gemini-2.5-pro and Claude Sonnet 4 .

Copied to clipboard

Zhaoyi Li, Ying Wei, Defu Lian

Knowledge as A Bridge: Improving Cross-domain Answer Selection with External Knowledge (C18-1)

Challenge:	despite the rising prevalence of neural sequence models, there is a deficiency in compositional generalization.
Approach:	They propose a compositional augmentation strategy that enables multi-grained composition of substructures in the whole training set.
Outcome:	The proposed strategy outperforms existing strategies on three compositional generalization benchmarks.

Copied to clipboard

Yang Deng, Ying Shen, Min Yang, Yaliang Li, Nan Du, Wei Fan, Kai Lei

Question Answering

Challenge:	Existing approaches to answer selection are limited in domains with limited labeled data.
Approach:	They propose a Knowledge-aware Attentive Network framework for cross-domain answer selection that uses the knowledge base as a bridge to enable knowledge transfer from the source domain to the target domain.
Outcome:	The proposed model outperforms strong competitors by a noticeable margin in cross-domain answer selection.

Understanding and Patching Compositional Reasoning in LLMs (2024.findings-acl)

Copied to clipboard

Zhaoyi Li, Gangwei Jiang, Hong Xie, Linqi Song, Defu Lian, Ying Wei

Reasoning

Challenge:	LLMs have marked a revolutonary shift, yet they falter when faced with compositional reasoning tasks.
Approach:	They propose a lightweight method to patch compositional reasoning errors via editing the located MHSA modules in LLMs.
Outcome:	The proposed method can be used to patch compositional reasoning errors using MHSA modules located within the layers of the LLMs.

Aspect and Sentiment Aware Abstractive Review Summarization (C18-1)

Copied to clipboard

Min Yang, Qiang Qu, Ying Shen, Qiao Liu, Wei Zhao, Jia Zhu

Summarization

Challenge:	Abstractive summarization is a task that generates short and concise summaries of user generated reviews.
Approach:	They propose an interactive attention mechanism to learn the representations of context and aspect words within reviews, acted as an encoder.
Outcome:	The proposed model achieves impressive results compared to other strong competitors on a real-life dataset.

Enabling Agents to Communicate Entirely in Latent Space (2026.acl-long)

Copied to clipboard

Zhuoyun Du, Runze Wang, Huiyu Bai, Zouying Cao, Xiaoyong Zhu, Yu Cheng, Bo Zheng, Wei Chen, Haochao Ying

Challenge:	Natural language is the de facto communication medium for LLM-based agents, but it presents a fundamental constraint . natural language downsampling limits the depth and nuance of information that can be transmitted . et al.: inter-agent latent space communication is a promising paradigm for solving complex tasks .
Approach:	They propose a paradigm that leverages the last hidden states of an LLM as a representation of its thought for direct communication.
Outcome:	The proposed paradigm outperforms fine-tuned chain-of-thought prompting and single-agent baselines even across heterogeneous models.

Cross-modal Contrastive Attention Model for Medical Report Generation (2022.coling-1)

Copied to clipboard

Xiao Song, Xiaodan Zhang, Junzhong Ji, Ying Liu, Pengxu Wei

Cooperative Denoising for Distantly Supervised Relation Extraction (C18-1)

Challenge:	Existing methods for medical report generation are unable to capture useful information from historical cases.
Approach:	They propose a model that captures both visual and semantic information from similar cases.
Outcome:	The proposed model outperforms the state-of-the-art models on almost all metrics on IU X-Ray and MIMIC-CXR benchmarks.

Copied to clipboard

Kai Lei, Daoyuan Chen, Yaliang Li, Nan Du, Min Yang, Wei Fan, Ying Shen

XGLUE: A New Benchmark Dataset for Cross-lingual Pre-training, Understanding and Generation (2020.emnlp-main)

Challenge:	Existing methods for distantly supervised relation extraction suffer from noisy labeling problem, which can severely degrade its performance.
Approach:	They propose a framework for distantly supervised relation extraction that leverages text corpus and knowledge graph and a cooperative module involving their mutual learning.
Outcome:	The proposed method reduces the noisy labels and achieves substantial improvement over the state-of-the-art methods.

Copied to clipboard

Yaobo Liang, Nan Duan, Yeyun Gong, Ning Wu, Fenfei Guo, Weizhen Qi, Ming Gong, Linjun Shou, Daxin Jiang, Guihong Cao, Xiaodong Fan, Ruofei Zhang, Rahul Agrawal, Edward Cui, Sining Wei, Taroon Bharti, Ying Qiao, Jiun-Hung Chen, Winnie Wu, Shuguang Liu, Fan Yang, Daniel Campos, Rangan Majumder, Ming Zhou

Multilinguality

Challenge:	XGLUE provides a benchmark dataset to train large-scale cross-lingual pre-trained models . XCLUE provides 11 diversified tasks that cover both understanding and generation scenarios .
Approach:	They introduce a new benchmark dataset to train large-scale cross-lingual pre-trained models using multilingual and bilingual corpora.
Outcome:	The proposed dataset is labeled in English and includes only natural language understanding tasks.

Attention Basin: Why Contextual Position Matters in Large Language Models (2026.acl-long)

Copied to clipboard

Zihao Yi, Zhenqing Ling, Delong Zeng, Haohao Luo, Zhe Xu, Wei Liu, Jian Luan, Wanxia Cao, Ying Shen

Think and Recall: Layer-Level Prompting for Lifelong Model Editing (2025.emnlp-main)

Challenge:	Large Language Models (LLMs) are sensitive to the contextual position of information in input.
Approach:	They introduce Attention-Driven Reranking (AttnRank) which estimates a model’s intrinsic positional attention preferences using a small calibration set and reorders retrieved documents or few-shot examples to align the most salient content with these high-attention positions.
Outcome:	Experiments on multi-hop QA and few-shot in-context learning tasks show that AttnRank achieves substantial improvements across 10 large language models of varying architectures and scales, without modifying model parameters or training procedures.

Copied to clipboard

Jinke Wang, Zenan Ying, Qi Liu, Wei Chen, Tong Xu, Huijun Hou, Zhi Zheng

Low-Resource NLP

Challenge:	Existing methods for lifelong model editing suffer from limitations in usability, such as requiring additional training corpora or lacking support for reversible and detachable edits.
Approach:	They propose a plug-and-play method for knowledge retrieval and storage, i.e., Layer-Level Prompting, which enables seamless and efficient lifelong model editing.
Outcome:	The proposed method outperforms existing methods on question answering and hallucination benchmarks across different LLMs.

Keep it Consistent: Topic-Aware Storytelling from an Image Stream via Iterative Multi-agent Communication (2020.coling-main)

Copied to clipboard

Ruize Wang, Zhongyu Wei, Ying Cheng, Piji Li, Haijun Shan, Ji Zhang, Qi Zhang, Xuanjing Huang

Benchmarking and Improving Compositional Generalization of Multi-aspect Controllable Text Generation (2024.acl-long)

Challenge:	Existing methods for visual storytelling construct text description independently for each image and roughly concatenate them as a story, which leads to the problem of generating semantically incoherent content.
Approach:	They propose a topic description task to detect the global semantic context of an image stream and a story is then constructed with the guidance of the topic description.
Outcome:	The proposed framework can generate stories with higher quality compared to state-of-the-art methods on a VIST dataset.

Copied to clipboard

Tianqi Zhong, Zhaoyi Li, Quan Wang, Linqi Song, Ying Wei, Defu Lian, Zhendong Mao

Text Generation

Challenge:	Existing MCTG methods face a noticeable performance drop in compositional testing.
Approach:	They propose a benchmark to evaluate compositional generalization of MCTG methods by combining multi-aspect labeled datasets and a crafted three-dimensional evaluation protocol.
Outcome:	The proposed framework improves compositional generalization performance by 3.64% and 94.4% in compositional testing.

PAFT: Prompt-Agnostic Fine-Tuning (2025.emnlp-main)

Copied to clipboard

Chenxing Wei, Yao Shu, Mingwen Ou, Ying He, Fei Yu

A + B: A General Generator-Reader Framework for Optimizing LLMs to Unleash Synergy Potential (2024.findings-acl)

Challenge:	Prompt-agnostic fine-tuning (PAFT) improves performance by reducing overfitting to specific prompts.
Approach:	They propose a method that enhances robustness through dynamic prompt variation during training.
Outcome:	The proposed method achieves higher generalization accuracy on unseen prompts than standard methods with similar training efficiency.

Copied to clipboard

Wei Tang, Yixin Cao, Jiahao Ying, Bo Wang, Yuyue Zhao, Yong Liao, Peng Zhou

Information Retrieval

Challenge:	Retrieval-Augmented Generation (RAG) is an effective solution to supplement necessary knowledge to large language models.
Approach:	They propose a "generate-then-read" pipeline to replace retrieval stage with generation from the LLM itself.
Outcome:	The proposed framework outperforms single models in the base and chat versions and addresses safety and helpfulness post-adaptation challenges.

LLMs Can Simulate Standardized Patients via Agent Coevolution (2025.acl-long)

Copied to clipboard

Zhuoyun Du, LujieZheng LujieZheng, Renjun Hu, Yuyang Xu, Xiawei Li, Ying Sun, Wei Chen, Jian Wu, Haolei Cai, Haochao Ying

Challenge:	Training medical personnel using standardized patients (SPs) remains a complex challenge, necessitating extensive domain expertise and role-specific practice.
Approach:	They propose a simulated patient framework that allows patient agents to simulate diagnostic process through multi-turn dialogues.
Outcome:	The proposed framework improves over existing reasoning methods by more than 10% in requirement alignment and better human preference after evolving over 200 cases for 10 hours with excellent generalizability.

Multi-Agent Procedural Graph Extraction with Structural and Logical Refinement (2026.findings-eacl)

Copied to clipboard

Wangyang Ying, Yanchi Liu, Xujiang Zhao, Wei Cheng, Zhengzhang Chen, Wenchao Yu, Yanjie Fu, Haifeng Chen

Structured Data in NLP

Challenge:	Recent advances in large language models (LLMs) show potential for graph extraction, but often yield ill-formed structures or misinterpret logical constructs such as gateways.
Approach:	They propose a framework that treats procedural graph extraction as a multi-round reasoning process with structural and logical refinement agents.
Outcome:	The proposed framework achieves significant improvements in structural correctness and logical consistency over strong baselines.

Transferable End-to-End Aspect-based Sentiment Analysis with Selective Adversarial Learning (D19-1)

Copied to clipboard

Zheng Li, Xin Li, Ying Wei, Lidong Bing, Yu Zhang, Qiang Yang

Sentiment Analysis

Challenge:	Existing methods to extract aspects and sentiments are limited due to lack of annotated sequence data.
Approach:	They propose a Selective Adversarial Learning method to align latent correlation vectors . they propose tagging a set of aspect boundary tags and sentiment tags to create a joint label space .
Outcome:	The proposed method can learn weights for words to achieve fine-grained adaptation.

PASUM: A Pre-training Architecture for Social Media User Modeling Based on Text Graph (2024.lrec-main)

Copied to clipboard

Kun Wu, Xinyi Mou, Lanqing Xue, Zhenzhe Ying, Weiqiang Wang, Qi Zhang, Xuanjing Huang, Zhongyu Wei

Agent-based Substructure Counting under Local Differential Privacy (2026.acl-long)

Challenge:	Existing studies have incorporated different digital traces to better learn the representations of social media users, limited by overloaded text information and hard-to-collect social network information.
Approach:	They propose a Pre-training Architecture for Social Media User Modeling based on Text Graph and combine microblogs to represent social media users based upon the text graph model.
Outcome:	The proposed framework can represent users based on text even without social network information on microblogs.

Copied to clipboard

Yuting Zhang, Kai Wang, Wei Ni, Ying Zhang, Wenjie Zhang

Disentangling Task Relations for Few-shot Text Classification via Self-Supervised Hierarchical Task Clustering (2022.findings-emnlp)

Challenge:	Recent studies have demonstrated the ability of Large Language Models (LLMs) to process graph problems.
Approach:	They propose to decompose substructure counting into node-level tasks distributed among node agents and embed the knowledge of distributed algorithms and DP frameworks in the curator agent and privacy controller.
Outcome:	Extensive experiments on 6 real-world datasets validate the effectiveness of the proposed framework for substructure counting tasks under edge local differential privacy (LDP).

Copied to clipboard

Juan Zha, Zheng Li, Ying Wei, Yu Zhang

Safety Guardrails of Large Language Models Are Vulnerable to Value-Driven Adversarial Prompting (2026.findings-acl)

Challenge:	Existing methods for Few-Shot Text Classification are limited by their global knowledge-shared mechanisms.
Approach:	They propose a self-supervised hierarchical task clustering method to address task heterogeneity . they use prior knowledge from historical tasks to leverage prior knowledge .
Outcome:	The proposed method can learn a classifier efficiently with few examples . it disentangles the underlying relations between tasks to improve interpretability .

Copied to clipboard

Xiaohao Luo, Ying Wei, Zhijun Li

WebCoderBench: Benchmarking Web Application Generation with Comprehensive and Interpretable Evaluation Metrics (2026.acl-long)

Challenge:	Existing jailbreak attacks against large language models (LLMs) can be divided into white-box attacks and black-box attack.
Approach:	They propose a value-driven jailbreak attack that exploits the phenomenon that large language models agree with humans to induce LLMs to affirm the moral value of harmful tasks.
Outcome:	Extensive experiments on five state-of-the-art (SOTA) LLMs show the value-driven jailbreak attack achieves an average attack success rate (ASR) of 91.8% on JailbreakBench and 95.2% on the AdvBench subset.

Copied to clipboard

Chenxu Liu, Yingjie Fu, Wei Yang, Ying Zhang, Tao Xie

Explainability & Interpretability in NLP

Challenge:	Web applications (web apps) are a key arena for large language models to demonstrate their code generation capabilities and commercial potential.
Approach:	a new benchmark for large language models (LLMs) is designed to provide real-world user requirements and generalizable evaluation metrics.
Outcome:	a new benchmark for large language models (LLMs) provides a real-world, generalizable, and interpretable evaluation score . the benchmark measures user requirements, expression styles and human-preference-aligned weights . a web application can be used to demonstrate its commercial potential, authors say .

Language-Informed Synthesis of Rational Agent Models for Grounded Theory-of-Mind Reasoning On-the-fly (2025.findings-emnlp)

Copied to clipboard

Lance Ying, Ryan Truong, Katherine M. Collins, Cedegao E. Zhang, Megan Wei, Tyler BrookeWilson, Tan Zhi-Xuan, Lionel Wong, Joshua B. Tenenbaum

ScdNER: Span-Based Consistency-Aware Document-Level Named Entity Recognition (2023.emnlp-main)

Challenge:	Language is a powerful source of information in social settings, especially in novel situations where language can provide both abstract information about the environment dynamics and concrete specifics about an agent that cannot be easily visually observed.
Approach:	They propose a language-informed rational agent synthesis framework that integrates linguistic and visual inputs to draw context-specific social inferences.
Outcome:	The proposed framework outperforms ablations and state-of-the-art models on a range of social reasoning tasks derived from cognitive science experiments.

Copied to clipboard

Ying Wei, Qi Li

CompTab: A Comprehensive Benchmark for Real-World TableQA with Complex Reasoning and Irregular Tables (2026.acl-long)

Challenge:	Named entity recognition (NER) is an important task for many natural language processing applications.
Approach:	They propose to fuse global features of tokens via word-based key-value memory to produce documentlevel encoding for token label prediction.
Outcome:	The proposed model can produce consistent and consistent predictions on word level with reduced impact of non-entity sequences and adaptive global feature fusion.

Copied to clipboard

Zhen Yang, Wei Du, Jie Wang, Wenze Zhou, Xiangfeng Meng, Zhengyang Wang, Suping Sun, Ziwei Du, Haodong Zou, Jie Chen, Yongbin Liu, Shicheng Tan, Jiahao Ying, Shu Zhao

CFinBench: A Comprehensive Chinese Financial Benchmark for Large Language Models (2025.naacl-long)

Challenge:	Existing benchmarks focus on well-structured tables and fail to reflect irregular structures and complex reasoning commonly encountered in real-world scenarios.
Approach:	They propose a benchmark to evaluate TableQA under complex reasoning and irregular table conditions.
Outcome:	The proposed framework improves generalization and realism of large language models under complex and irregular table conditions.

Copied to clipboard

Ying Nie, Binwei Yan, Tianyu Guo, Hao Liu, Haoyu Wang, Wei He, Binfan Zheng, Weihao Wang, Qiang Li, Weijian Sun, Yunhe Wang, Dacheng Tao

Improving Zero-Shot Entity Linking Candidate Generation with Ultra-Fine Entity Type Information (2022.coling-1)

Challenge:	Large language models (LLMs) have achieved remarkable performance on various NLP tasks, yet their potential in more challenging task like finance, has not been fully explored.
Approach:	They propose a benchmark to assess the financial knowledge of large language models (LLMs) in China.
Outcome:	The proposed benchmark is the most comprehensive evaluation benchmark to date for LLMs in finance.

Copied to clipboard

Xuhui Sui, Ying Zhang, Kehui Song, Baohang Zhou, Guoqing Zhao, Xin Wei, Xiaojie Yuan

QRMeM: Unleash the Length Limitation through Question then Reflection Memory Mechanism (2024.findings-emnlp)

Challenge:	Entity linking is a task of assigning entity mentions to referent entities in a knowledge base.
Approach:	They propose to use ultra-fine-grained type information to improve the generalization ability of EL models by utilizing a low-level task to extract ultra-finish entity type information.
Outcome:	The proposed model achieves state-of-the-art in the zero-shot entity linking task .

Copied to clipboard

Bo Wang, Heyan Huang, Yixin Cao, Jiahao Ying, Wei Tang, Chong Feng

Question Answering

Challenge:	Existing methods for processing large textual content face insufficient adaptation to task-specific needs and missing multi-segmentation relationships.
Approach:	They propose a question then reflection memory mechanism which integrates a dual-structured memory pool and a structured graph guidance to facilitate a reflective trial-and-error approach for navigating and identifying relevant segments.
Outcome:	The proposed model achieves superior performance on multiple-choice questions and multi-doc QA.

PIPER: Benchmarking and Prompting Event Reasoning Boundary of LLMs via Debiasing-Distillation Enhanced Tuning (2025.acl-long)

Copied to clipboard

Zhicong Lu, Changyuan Tian, PeiguangLi PeiguangLi, Li Jin, Sirui Wang, Wei Jia, Ying Shen, Guangluan Xu

EvoWiki: Evaluating LLMs on Evolving Knowledge (2025.acl-long)

Challenge:	Existing studies on Large Language Models (LLMs) have failed to evaluate their performance in event reasoning with a single event relational type or reasoning format.
Approach:	They propose a benchmark to evaluate LLMs' event reasoning capability using a single event relational type or reasoning format.
Outcome:	The proposed model improves on 10K diverse instruction-tuning demonstrations to alleviate event reasoning-oriented data scarcity.

Copied to clipboard

Wei Tang, Yixin Cao, Yang Deng, Jiahao Ying, Bo Wang, Yizhe Yang, Yuyue Zhao, Qi Zhang, Xuanjing Huang, Yu-Gang Jiang, Yong Liao

Challenge:	Existing knowledge evolution benchmarks are static and fail to capture the evolving nature of LLMs and knowledge.
Approach:	They propose an evolving dataset that categorizes information into stable, evolved, and uncharted states.
Outcome:	The proposed dataset is auto-updatable and enables evaluation of continuously changing knowledge and newly released LLMs.

DSRM: Boost Textual Adversarial Training with Distribution Shift Risk Minimization (2023.acl-long)

Copied to clipboard

SongYang Gao, Shihan Dou, Yan Liu, Xiao Wang, Qi Zhang, Zhongyu Wei, Jin Ma, Ying Shan

Robustness in NLP

Challenge:	Existing adversarial training methods require multi-step gradient ascents or word substitutions to obtain adversarials, which impairs the effectiveness of adversariarial training.
Approach:	They propose a procedure for instead adversarial training with only clean data that estimates the adversarials loss by perturbing the input data’s probability distribution rather than their embeddings.
Outcome:	The proposed procedure reduces time consumption by up to 70% compared to current best-performing adversarial training methods.

Learn to Cross-lingual Transfer with Meta Graph Learning Across Heterogeneous Languages (2020.emnlp-main)

Copied to clipboard

Zheng Li, Mukul Kumar, William Headden, Bing Yin, Ying Wei, Yu Zhang, Qiang Yang

Detecting What Queries Seek: Steering LLM Safety with FFN Output Activation Monitoring (2026.acl-long)

Challenge:	Existing mPLM-based methods focus on designing costly model pre-training while ignoring equally crucial downstream adaptation.
Approach:	They propose a meta graph learning method that extracts meta-knowledge from historical CLT experiences to learn to cross-lingual transfer.
Outcome:	The proposed method can learn to cross-lingual transfer by extracting meta-knowledge from historical CLT experiences (tasks) it can also capture intrinsic language relationships to explicitly guide cross-linguistic transfer.

Copied to clipboard

Xiaohao Luo, Ying Wei, Rui Zhao

Browsing Like Human: A Multimodal Web Agent with Experiential Fast-and-Slow Thinking (2025.acl-long)

Challenge:	Existing methods for detecting malicious queries rely on residual stream activations, resulting in limited discriminative power and unreliable interventions.
Approach:	They propose to use feed-forward networks (FFNs) to generate more discriminative signals for intervention, since these activations more explicitly reflect the intent of a query.
Outcome:	Experiments show that the proposed approach achieves state-of-the-art defense performance against various jailbreak attacks while maintaining the model's original performance on benign tasks.

Copied to clipboard

Haohao Luo, Jiayi Kuang, Wei Liu, Ying Shen, Jian Luan, Yang Deng