Papers by Lei Zhu

FuxiTranyu: A Multilingual Large Language Model Trained with Balanced Data (2024.emnlp-industry)

Challenge:	Large Audio Language Models (LALMs) exhibit a degradation in knowledge and reasoning capabilities . empirical results show that CORD significantly bridges the audio–text performance gap .
Approach:	They propose a framework that performs online cross-modal self-distillation to bridge the acoustic-semantic gap between LALMs and text-based models.
Outcome:	The proposed framework bridges the acoustic-semantic gap between LALMs and text-based models . it employs on-policy reverse KL divergence with importance-aware weighting .

Copied to clipboard

Haoran Sun, Renren Jin, Shaoyang Xu, Leiyu Pan, null Supryadi, Menglong Cui, Jiangcun Du, Yikun Lei, Lei Yang, Ling Shi, Juesi Xiao, Shaolin Zhu, Deyi Xiong

TWAG: A Topic-Guided Wikipedia Abstract Generator (2021.acl-long)

Challenge:	Large language models exhibit significant performance discrepancies between high- and low-resource languages.
Approach:	They present an open-source multilingual LLM with 8 billion parameters and a multilingual instruction dataset.
Outcome:	The proposed model achieves consistent multilingual representations across languages.

Copied to clipboard

Fangwei Zhu, Shangqing Tu, Jiaxin Shi, Juanzi Li, Lei Hou, Tong Cui

Reasoning-to-Defend: Safety-Aware Reasoning Can Defend Large Language Models from Jailbreaking (2025.emnlp-main)

Challenge:	Existing models view Wikipedia abstract as plain text, ignoring that it is a description of a certain entity and can be decomposed into different topics.
Approach:	They propose a model that guides Wikipedia abstract generation with topical information.
Outcome:	The proposed model outperforms baselines and is capable of generating comprehensive abstracts.

Copied to clipboard

Junda Zhu, Lingyong Yan, Shuaiqiang Wang, Dawei Yin, Lei Sha

Robustness in NLP

Challenge:	Large Reasoning Models (LLMs) have demonstrated impressive performances across diverse domains, but how their safety benefits from enhanced reasoning capabilities against jailbreak queries remains unexplored.
Approach:	They propose a safety-aware reasoning paradigm that integrates a pivot token-based safety-based reasoning mechanism into LLMs’ generation process.
Outcome:	The proposed model improves the safety of large language models against jailbreak queries while minimizing attacks and maintaining the original performance.

Large Language Models are not Fair Evaluators (2024.acl-long)

Copied to clipboard

Peiyi Wang, Lei Li, Liang Chen, Zefan Cai, Dawei Zhu, Binghuai Lin, Yunbo Cao, Lingpeng Kong, Qi Liu, Tianyu Liu, Zhifang Sui

CCSRD: Content-Centric Speech Representation Disentanglement Learning for End-to-End Speech Translation (2023.findings-emnlp)

Challenge:	Existing evaluation frameworks that use large language models as referees are insufficient for accurately assessing their alignment with human intent.
Approach:	They propose a calibration framework to address positional bias in large language models as evaluators by manually annotating the “win/tie/lose” outcomes of responses from ChatGPT and Vicuna-13B in the Vicun A Benchmark’s question prompt.
Outcome:	The proposed framework alleviates evaluation bias, resulting in closer alignment with human judgments.

Copied to clipboard

Xiaohu Zhao, Haoran Sun, Yikun Lei, Shaolin Zhu, Deyi Xiong

MentalSeek-Dx: Towards Progressive Hypothetico-Deductive Reasoning for Real-world Psychiatric Diagnosis (2026.acl-long)

Challenge:	Existing speech-to-text translation models can extract features from speech inputs, but they may include non-linguistic speech factors such as pitch, timbre and speaker identity.
Approach:	They propose a content-centric speech representation disentanglement learning framework for speech translation that decomposes speech representations into content representations and non-linguistic representations via representation disentanglement learning.
Outcome:	The proposed framework outperforms state-of-the-art speech translation models and cascaded models on five translation directions.

Copied to clipboard

Xiao Sun, null Ymyang, Xinyi Jiang, Yu Tian, Junnan Zhu, Jiang Zhong, Qin Lei, Jingwang Huang, Haoyang Zeng, Xinyu Zhou, Xin Xiao, Kaiwen Wei

Learning Personalized Alignment for Evaluating Open-ended Text Generation (2024.emnlp-main)

Challenge:	Mental health disorders represent a burgeoning global public health challenge . lack of ecological validity and fine-grained diagnostic supervision limits their utility .
Approach:	They propose a medical-specialized LLM trained to internalize clinical reasoning process through supervised trajectory construction and curriculum-based reinforcement learning.
Outcome:	The proposed model achieves state-of-the-art with only 14B parameters, establishing a clinically grounded framework for reliable psychiatric diagnosis.

Copied to clipboard

Danqing Wang, Kevin Yang, Hanlin Zhu, Xiaomeng Yang, Andrew Cohen, Lei Li, Yuandong Tian

Explainability & Interpretability in NLP

Challenge:	Traditional evaluation metrics rely heavily on lexical similarity with human-written references, showing poor correlation with human judgments and failing to account for alignment with the diversity of human preferences.
Approach:	They propose an interpretable evaluation framework that evaluates alignment with specific human preferences by providing detailed comments and fine-grained scoring.
Outcome:	The proposed framework outperforms GPT-4 in Kendall correlation and accuracy with zero-shot reviewers.

Learning When to Translate for Streaming Speech (2022.acl-long)

Copied to clipboard

Qian Dong, Yaoming Zhu, Mingxuan Wang, Lei Li

OmniEvent: A Comprehensive, Fair, and Easy-to-Use Toolkit for Event Understanding (2023.emnlp-demo)

Challenge:	Existing methods waiting-and-translating for a fixed duration break speech acoustic units . Existing models waiting-for a set duration and generating partial sentences are not effective .
Approach:	They propose a monotonic segmentation module inside an encoder-decoder model to detect proper speech unit boundaries for a streaming speech input.
Outcome:	The proposed method outperforms existing methods on a speech translation dataset and achieves the best trade-off between translation quality and latency.

Copied to clipboard

Hao Peng, Xiaozhi Wang, Feng Yao, Zimu Wang, Chuzhao Zhu, Kaisheng Zeng, Lei Hou, Juanzi Li

Perplexity-Aware Data Scaling Law: Perplexity Landscapes Predict Performance for Continual Pre-training (2026.acl-long)

Challenge:	Event understanding is fundamental for humans to understand the world.
Approach:	They propose an event understanding toolkit called OmniEvent that is comprehensive and fair . it supports mainstream modeling paradigms and the processing of 15 widely-used datasets .
Outcome:	The toolkit supports mainstream modeling paradigms and the processing of 15 widely-used English and Chinese datasets.

Copied to clipboard

Lei Liu, Hao Zhu, Xiaoyan Yang, Yue Shen, Zhixuan Chu, Jian Wang, Jinjie Gu, Kui Ren

Hence, Socrates is mortal: A Benchmark for Natural Language Syllogistic Reasoning (2023.findings-acl)

Challenge:	Large language models (LLMs) have impressive capabilities across a wide range of domains, but their generalpurpose pre-training objectives often leave them illsuited for specialized applications such as healthcare.
Approach:	They propose a perplexity-aware data scaling law that establishes a predictive relationship between the perplexities of domain-specific data and the test loss.
Outcome:	Experiments on medical and general-domain benchmarks show that the proposed scaling law consistently identifies near-optimal training subsets with significantly reduced data consumption.

Copied to clipboard

Yongkang Wu, Meng Han, Yutao Zhu, Lei Li, Xinyu Zhang, Ruofei Lai, Xiaoguang Li, Yuanhang Ren, Zhicheng Dou, Zhao Cao

BTC-LLM: Efficient Sub-1-Bit LLM Quantization via Learnable Transformation and Binary Codebook (2026.acl-long)

Challenge:	SylloBase is a benchmark for syllogistic reasoning, a critical capability widely required in natural language understanding tasks, such as text entailment and question answering.
Approach:	They propose to use a benchmark to learn syllogistic reasoning on a set of templates and to use them to generate and understand slogisms.
Outcome:	The proposed benchmark covers a complete taxonomy of syllogism reasoning patterns, and contains both automatically and manually constructed samples.

Copied to clipboard

Hao Gu, Lujun Li, Hao Wang, Lei Wang, Zheyu Wang, Bei Liu, Jiacheng Liu, Qiyuan Zhu, Sirui Han, Yike Guo

Text Clustering

Challenge:	Recent sparsity-aware binarization approaches can achieve sub-1-bit compression, but they face performance degradation, mask-management overhead, and limited hardware compatibility.
Approach:	They propose a binary quantization framework that leverages binary pattern clustering and weight transformation to overcome performance degradation and mask-management overhead.
Outcome:	The proposed framework achieves state-of-the-art compression (1.11–0.7 bits) it maintains high performance with only a 3.1% accuracy drop in zero-shot benchmarks while delivering a 1.6 speedup over FP16.

Towards a Deep Understanding of Multilingual End-to-End Speech Translation (2023.findings-emnlp)

Copied to clipboard

Haoran Sun, Xiaohu Zhao, Yikun Lei, Shaolin Zhu, Deyi Xiong

LIRE: listwise reward enhancement for preference alignment (2024.findings-acl)

Challenge:	Recent years have witnessed the rapid development of end-to-end speech-totext translation (ST) which has demonstrated remarkable performance and outperformed conventional cascaded systems.
Approach:	They employ Singular Value Canonical Correlation Analysis to analyze representations learnt in a multilingual end-to-end speech translation model trained over 22 languages.
Outcome:	The proposed approach outperforms existing cascaded systems in predicting phonetic features and improves translation quality.

Copied to clipboard

Mingye Zhu, Yi Liu, Lei Zhang, Junbo Guo, Zhendong Mao

Challenge:	prevailing approaches to preference alignment focus on pairwise comparisons, with limited exploration into multi-response scenarios.
Approach:	They propose a listwise reward enhancement approach that integrates offline rewards of multiple responses into a streamlined listwise framework.
Outcome:	The proposed approach outperforms existing methods on dialogue and summarization tasks with good transferability to out-of-distribution data.

TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Finance (2021.acl-long)

Copied to clipboard

Fengbin Zhu, Wenqiang Lei, Youcheng Huang, Chao Wang, Shuo Zhang, Jiancheng Lv, Fuli Feng, Tat-Seng Chua

Structured Data in NLP

Challenge:	Existing QA systems focus on unstructured text, structured knowledge base, or semi-structured tables.
Approach:	They propose a large-scale question answering model based on financial reports . numerical reasoning is usually required to infer the answer .
Outcome:	The proposed model achieves 58.0% inF1, an 11.1% increase over the baseline model, but still lags behind the best human model.

TinyScientist: An Interactive, Extensible, and Controllable Framework for Building Research Agents (2025.emnlp-demos)

Copied to clipboard

Haofei Yu, Keyang Xuan, Fenghai Li, Kunlun Zhu, Zijie Lei, Jiaxun Zhang, Ziheng Qi, Kyle Richardson, Jiaxuan You

SMARTCAL: An Approach to Self-Aware Tool-Use Evaluation and Calibration (2024.emnlp-industry)

Challenge:	Existing research systems often design and use agentic workflows to perform research tasks such as ideation, scientific coding, review writing, and tree-based search.
Approach:	They propose an open-source codebase, an interactive web demonstration, and a PyPI Python package to make state-of-the-art auto-research pipelines broadly accessible to every researcher and developer.
Outcome:	The proposed framework adapts easily to new tools and supports iterative growth.

Copied to clipboard

Yuanhao Shen, Xiaodan Zhu, Lei Chen

Large-Scale Multimodal Knowledge Graph about Classical Chinese Poetry: Fine-grained Method and Comprehensive Evaluation (2026.findings-acl)

Challenge:	Large Language Models (LLMs) have a profound impact on a wide range of applications.
Approach:	They propose a framework to mitigate the tool-abuse behavior of Large Language Models and propose SMARTCAL to mitigate this issue.
Outcome:	The proposed framework improves the performance of LLMs on three datasets with two mainstream tool-use frameworks and shows an 8.6% increase in QA performance and 21.6 percent lower expected calibration error (ECE) than existing methods.

Copied to clipboard

Shuo Wang, Qing Zhu, Yang Xiao, Minglong Lei

Detoxification for LLM: From Dataset Itself (2026.acl-long)

Challenge:	Existing studies on classical Chinese poetry are limited by modality constraints, dataset size, or the level of refinement.
Approach:	They propose to construct a large-scale and fine-grained multimodal knowledge graph of classical Chinese poetry using an informative ontology graph and a text-image alignment method.
Outcome:	The proposed method collects knowledge about classical Chinese poetry from ontology graphs and performs four tasks that demonstrate its comprehensiveness and high quality.

Copied to clipboard

Wei Shao, Yihang Wang, Gao yu Zhu, Ziqiang Cheng, Lei Yu, Jiafeng Guo, Xueqi Cheng

Alignment for Efficient Tool Calling of Large Language Models (2025.emnlp-main)

Challenge:	Existing methods for large language models focus on post-training stage or inference time, while few tackle the source of toxicity, namely, the dataset itself.
Approach:	They propose to localize and rewrite toxic spans in raw corpora with SoCD, which guides an LLM to localized and preserving semantics while preserving toxicity.
Outcome:	The proposed method reduces TP from 0.42 to 0.18 and Expected Maximum Toxicity (EMT) from 0.43 to 0.20 on three LLMs.

Copied to clipboard

Hongshen Xu, Zihan Wang, Zichen Zhu, Lei Pan, Xingyu Chen, Shuai Fan, Lu Chen, Kai Yu

A Neural Network Architecture for Program Understanding Inspired by Human Behaviors (2022.acl-long)

Challenge:	Recent advances in tool learning have enabled large language models to integrate external tools, enhancing their task performance by expanding their knowledge boundaries.
Approach:	They propose a framework that combines probabilistic knowledge boundary estimation with dynamic decision-making to allow LLMs to better assess when to invoke tools based on their confidence.
Outcome:	The proposed framework shows significant improvements in tool efficiency by reducing unnecessary tool usage.

Copied to clipboard

Renyu Zhu, Lei Yuan, Xiang Li, Ming Gao, Wenyuan Cai

Representation Learning

Challenge:	Existing studies for understanding programs do not take human behaviors as reference.
Approach:	They propose a graph neural network model that takes human behaviors as reference in understanding programs.
Outcome:	The proposed model performs better on code summarization and code clone detection tasks.

SAPGraph: Structure-aware Extractive Summarization for Scientific Papers with Heterogeneous Graph (2022.aacl-main)

Copied to clipboard

Siya Qi, Lei Li, Yiyang Li, Jin Jiang, Dingxin Hu, Yuze Li, Yingqi Zhu, Yanquan Zhou, Marina Litvak, Natalia Vanetik

Think-Search-Patch: A Retrieval-Augmented Reasoning Framework for Repository-Level Code Repair (2025.emnlp-industry)

Challenge:	Abstractive and extractive methods are used to condense long text into concise summaries while retaining essential information.
Approach:	They propose to use paper structure to extract paper summaries from long text . they provide a large-scale dataset of COVID-19-related papers .
Outcome:	The proposed framework generates more comprehensive and valuable summaries compared to previous work on COVID-19-related papers.

Copied to clipboard

Bojian Xiong, Yikun Lei, Xikai Liu, Shaowei Zhang, Pengyun Zhu, Yan Liu, Yongqi Leng, Ling Shi, Meizhi Zhong, Yurong Zhang, Yan Gao, null Yiwu, Yao Hu, Deyi Xiong

Information Retrieval

Challenge:	Large language models suffer from multiple-file coding scenarios with strong inter-file dependencies . experimental results show that large language models exhibit inadequate performance in multi-file scenarios .
Approach:	They propose a retrieval-augmented reasoning framework for repository-level code repair . they use a dataset to generate standardized patches based on the key snippets .
Outcome:	The proposed framework improves retrieval accuracy and repair success on SWE-bench Lite . it surpasses models with larger size in managing extensive code contexts and fixing bugs spanning across multiple files.

LLaMAX: Scaling Linguistic Horizons of LLM by Enhancing Translation Capabilities Beyond 100 Languages (2024.findings-emnlp)

Copied to clipboard

Yinquan Lu, Wenhao Zhu, Lei Li, Yu Qiao, Fei Yuan

Learning to Describe for Predicting Zero-shot Drug-Drug Interactions (2023.emnlp-main)

Challenge:	Large Language Models (LLMs) exhibit exceptional translation capabilities in high-resource language tasks, yet their effectiveness in low-resourced languages is suboptimal.
Approach:	They conduct extensive multilingual continual pre-training on the LLaMA series models and develop LLiMAX for translation support across more than 100 languages.
Outcome:	The proposed model achieves higher translation performance than existing open-source models and performs on-par with specialized translation model on the Flores-101 benchmark.

Copied to clipboard

Fangqi Zhu, Yongqi Zhang, Lei Chen, Bing Qin, Ruifeng Xu

CRAFTQA: A Code-Driven Adaptive Framework for Complex Structured Data Reasoning (2026.findings-acl)

Challenge:	Existing computational methods for DDI prediction fail to capture interactions for new drugs due to the lack of knowledge.
Approach:	They propose a problem setup as zero-shot DDI prediction that deals with the case of new drugs by using textual information from online databases.
Outcome:	The proposed method improves on several settings including zero-shot and few-shot DDI prediction and the selected texts are semantically relevant.

Copied to clipboard

Chengtao Gan, Zhiqiang Liu, Long Jin, Yushan Zhu, Lei Liang, Wen Zhang

DVMap: Fine-Grained Pluralistic Value Alignment via High-Consensus Demographic-Value Mapping (2026.acl-long)

Challenge:	Existing unified structured data question answering methods rely on a set of predefined functions, which restricts their ability to perform complex reasoning beyond these predefined operations.
Approach:	They propose a novel adaptive code-driven framework that generates code-based reasoning operations based on a question.
Outcome:	The proposed framework improves on multiple structured datasets on real-world scenarios.

Copied to clipboard

Pengyun Zhu, Yuqi Ren, Zhen Wang, Lei Yang, Deyi Xiong

Challenge:	Current Large Language Models (LLMs) rely on coarse-grained national labels for pluralistic value alignment.
Approach:	They propose a framework for fine-grained pluralistic value alignment using demographic constraints.
Outcome:	The proposed framework can identify groups with predictable, high-consensus value preference . it achieves 48.6% accuracy, surpassing open-source LLM DeepSeek-v3.2 .

Towards IP Intelligence: Benchmarking Large Language Models on Intellectual Property Knowledge and Practice (2026.findings-acl)

Copied to clipboard

Qiyao Wang, Guhong Chen, Hongbo Wang, Huaren Liu, Minghui Zhu, Zhifei Qin, Li Linwei, Yilin Yue, Shiqiang Wang, Jiayan Li, Wu Yihang, Ziqiang Liu, Longze Chen, Run Luo, Liyang Fan, Jiaming Li, Lei Zhang, Kan Xu, Hamid Alinejad-Rokny, Chengming Li, Shiwen Ni, Yuan Lin, Min Yang

Context-Aware Hierarchical Taxonomy Generation for Scientific Papers via LLM-Guided Multi-Aspect Clustering (2025.emnlp-main)

Challenge:	Existing datasets and benchmarks focus only on patents or cover limited aspects of the IP field, lacking alignment with real-world scenarios.
Approach:	They propose a bilingual IP task taxonomy and a large-scale bilingual benchmark to evaluate LLMs in real-world IP practice.
Outcome:	The proposed model achieves only 75.8% accuracy, indicating room for improvement . open-source IP and law-oriented models lag behind closed-source general-purpose models .

Copied to clipboard

Kun Zhu, Lizi Liao, Yuxuan Gu, Lei Huang, Xiaocheng Feng, Bing Qin

Text Clustering

Challenge:	Existing taxonomy construction methods lack coherence and granularity . Existing approaches rely on manual or narrowly defined schemes .
Approach:	They propose a context-aware hierarchical taxonomy generation framework that integrates LLMs with dynamic clustering.
Outcome:	The proposed method outperforms existing methods in taxonomy coherence, granularity, and interpretability.

Towards an On-device Agent for Text Rewriting (2024.findings-naacl)

Copied to clipboard

Yun Zhu, Yinxiao Liu, Felix Stahlberg, Shankar Kumar, Yu-Hui Chen, Liangchen Luo, Lei Shu, Renjie Liu, Jindong Chen, Lei Meng

Can Large Language Models Effectively Support Decision-Making in Sudden Emergencies? (2026.findings-acl)

Challenge:	Large Language Models (LLMs) have demonstrated impressive capabilities for text rewriting, however creating a smaller yet potent language model presents two formidable challenges: costly data collection and absence of emergent capabilities.
Approach:	They propose a new instruction tuning method to develop a mo-bile text rewriting model that leverages LLM-generated data and heuristic reinforcement learning, eliminating the need for human data collection.
Outcome:	The proposed model surpasses the current state-of-the-art LLMs in text rewriting while maintaining a significantly reduced model size using public benchmark EditEval and our new benchmark.

Copied to clipboard

Mengna Zhu, Jibing Wu, Lihua Liu, Yuran Gong, Yang Hao, Fu Yachao, Mao Wang, Lei Hou, Juanzi Li

ClinAlign: Scaling Healthcare Alignment from Clinician Preference (2026.findings-acl)

Challenge:	Existing research has focused on the earlier stages of emergency response . lack of suitable datasets for reliable and compliance-aware decision-oriented modeling and evaluation is limiting current research .
Approach:	They propose a first real-world emergency decision-making dataset EDM-Bench . they propose 'rule-enhanced reasoning framework' that integrates external regulatory knowledge with constrained inference mechanisms to improve both decision safety and interpretability.
Outcome:	The proposed framework improves decision safety and interpretability by integrating regulatory knowledge with constrained inference mechanisms.

Copied to clipboard

Shiwei Lyu, Xidong Wang, Hao Zhu, Lei Liu, Chaohe Zhang, Jian Wang, Jinjie Gu, Benyou Wang, Yue Shen

Challenge:	Existing methods for aligning open-ended outputs with fine-grained clinician preferences are weakly grounded in professional guidelines.
Approach:	They propose a framework to align large language models' outputs with fine-grained clinician preferences . they propose 119 broadly reusable, clinically grounded principles organized by clinical dimensions .
Outcome:	The proposed framework outperforms existing models on HealthBench-Hard and Deepseek-R1 and o3.

SLAM: Towards Efficient Multilingual Reasoning via Selective Language Alignment (2025.coling-main)

Copied to clipboard

Yuchun Fan, Yongyu Mu, YiLin Wang, Lei Huang, Junhao Ruan, Bei Li, Tong Xiao, Shujian Huang, Xiaocheng Feng, Jingbo Zhu

Developing Prefix-Tuning Models for Hierarchical Text Classification (2022.emnlp-industry)

Challenge:	Large language models (LLMs) have demonstrated significant improvements in reasoning abilities, but these improvements are primarily focused on English, leading to inferior performance in non-English scenarios.
Approach:	They propose a multilingual reasoning alignment approach that fine-tunes the layers responsible for multilingual comprehension in one stage.
Outcome:	The proposed method fine-tunes 6 of the 9 layers responsible for multilingual comprehension, while reducing training time by 4.1-11.9 compared to the two-stage method.

Copied to clipboard

Lei Chen, Houwei Chou, Xiaodan Zhu

BCL: Bayesian In-Context Learning Framework for Information Extraction (2026.findings-acl)

Challenge:	Hierarchical text classification (HTC) is a key task in many industrial applications. Pre-trained Language Models (PLMs) have become dominant for most natural language processing (NLP) tasks.
Approach:	They investigate how prefix tuning can improve hierarchical text classification . prefix-tuning model only needs less than 1% of parameters to achieve performance .
Outcome:	The proposed model can achieve comparable performance to regular full fine-tuning.

Copied to clipboard

Haoliang Liu, Chengkun Cai, Xu Zhao, Han Zhu, Shizhou Huang, Xinglin Zhang, Tao Chen, Jenq-Neng Hwang, Zhang Huaping, Lei Li

Low-Resource NLP

Challenge:	Existing information extraction (IE) tasks rely on in-context learning with large language models.
Approach:	They propose a Bayesian-based in-context learning framework that refines label representations across IE tasks using particle filtering and Bayes updates.
Outcome:	The proposed framework improves performance over existing methods (up to 30%) it underperforms one-shot prompting by a substantial margin on NER tasks and CodeIE fails on RE tasks with near-zero micro-F1.

Lego-MT: Learning Detachable Models for Massively Multilingual Machine Translation (2023.findings-acl)

Copied to clipboard

Fei Yuan, Yinquan Lu, Wenhao Zhu, Lingpeng Kong, Lei Li, Yu Qiao, Jingjing Xu

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

Challenge:	Existing monolithic models for multilingual neural machine translation encounter parameter interference and inefficient inference for large models.
Approach:	They propose a detachable multi-way model that assigns each language to an individual branch . they use data from OPUS to build a translation benchmark covering 433 languages .
Outcome:	The proposed model outperforms existing models in OPUS and is faster than existing models.

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

Retrieval-Enhanced Adversarial Training for Neural Response Generation (P19-1)

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

Qingfu Zhu, Lei Cui, Wei-Nan Zhang, Furu Wei, Ting Liu

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

Challenge:	Existing approaches to dialogue systems are labor-intensive and difficult to scale up.
Approach:	They propose a Retrieval-Enhanced Adversarial Training method for neural response generation that leverages an adversarial training paradigm while taking advantage of N-best response candidates from a retrieval-based system to construct the discriminator.
Outcome:	The proposed method outperforms the vanilla Seq2Seq model and conventional adversarial training approach on a large scale dataset.

Copied to clipboard

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

A Simple and Effective Framework for Strict Zero-Shot Hierarchical Classification (2023.acl-short)

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

Copied to clipboard

Rohan Bhambhoria, Lei Chen, Xiaodan Zhu

Learning from Diverse Reasoning Paths with Routing and Collaboration (2025.emnlp-main)

Challenge:	Large language models have been able to perform well on benchmarks, but they are often not able address real-world challenges.
Approach:	They propose to refactor hierarchical tasks into a more indicative long-tail prediction task.
Outcome:	The proposed method does not require parameter updates and achieves strong performance across multiple datasets.

Copied to clipboard

Zhenyu Lei, Zhen Tan, Song Wang, Yaochen Zhu, Zihan Chen, Yushun Dong, Jundong Li

ARTIST: A Transformer-based Chinese Text-to-Image Synthesizer Digesting Linguistic and World Knowledge (2022.findings-emnlp)

Challenge:	Recent studies suggest that the reasoning abilities of large language models (LLMs) grows with model size and pre-training data.
Approach:	They propose to combine quality filtering, conditional routing, and cooperative peer teaching to transfer knowledge from powerful teacher models to compact and transparent students.
Outcome:	Experiments show that QR-Distill is superior to traditional methods.

Copied to clipboard

Tingting Liu, Chengyu Wang, Xiangru Zhu, Lei Li, Minghui Qiu, Jun Huang, Ming Gao, Yanghua Xiao

Benchmarking Long-Context Language Models on Long Code Understanding (2025.acl-long)

Challenge:	Text-to-Image Synthesis (TIS) is a popular task to convert natural language texts into realistic images.
Approach:	They propose a transformer-based Chinese text-to-image synthesizer for high-resolution image generation that incorporates linguistic and relational knowledge facts into the model to ensure better performance without the usage of ultra-large models.
Outcome:	The proposed model outperforms existing models in Chinese with linguistic and relational knowledge facts.

Copied to clipboard

Jia Li, Xuyuan Guo, Lei Li, Kechi Zhang, Ge Li, Jia Li, Zhengwei Tao, Fang Liu, Chongyang Tao, Yuqi Zhu, Zhi Jin

Few-Shot Table Understanding: A Benchmark Dataset and Pre-Training Baseline (2022.coling-1)

Challenge:	Currently, long-context language models are limited by the lack of a rigorous evaluation framework for long code understanding.
Approach:	They propose to use a long code understanding benchmark LongCodeU to evaluate LCLMs' long code comprehension ability for practical applications.
Outcome:	The proposed benchmarks show that current LCLMs are limited in their long code understanding ability, particularly when the long code length is greater than 32K, falling far short of their claimed 128K to 1M context windows.

Copied to clipboard

Ruixue Liu, Shaozu Yuan, Aijun Dai, Lei Shen, Tiangang Zhu, Meng Chen, Xiaodong He

R3 Prompting: Review, Rephrase and Resolve for Chain-of-Thought Reasoning in Large Language Models under Noisy Context (2023.findings-emnlp)

Challenge:	Pre-trained language models have demonstrated their effectiveness for few-shot table understanding, but few-shoot table understanding is rarely explored due to the deficiency of public table pre-training corpus and well-defined downstream benchmark tasks.
Approach:	They establish a benchmark dataset and use it to explore few-shot table understanding in Chinese.
Outcome:	The proposed model improves the few-shot table understanding in Chinese.

Copied to clipboard

Qingyuan Tian, Hanlun Zhu, Lei Wang, Yang Li, Yunshi Lan

CLeVeR: Multi-modal Contrastive Learning for Vulnerability Code Representation (2025.findings-acl)

Challenge:	Existing studies have evaluated LLMs under noise-free context but the dilemma for LLM to produce inaccurate results under noisy context has not been fully investigated.
Approach:	They propose a new method for CoT reasoning using Chain-of-Thought prompting that interacts with LLMs to perform key sentence extraction, variable declaration and answer prediction.
Outcome:	The proposed method outperforms existing CoT prompting methods on five reasoning tasks under noisy context.

Copied to clipboard

Jiayuan Li, Lei Cui, Sen Zhao, Yun Yang, Lun Li, Hongsong Zhu

Text2Sql: Pure Fine-Tuning and Pure Knowledge Distillation (2025.naacl-industry)

Challenge:	Existing methods for detecting code capture the overall semantics of the code rather than its intrinsic vulnerability-specific semantics.
Approach:	They propose an approach that leverages contrastive learning to generate precise vulnerability code representations under the supervision of vulnerability descriptions.
Outcome:	The proposed approach outperforms state-of-the-art methods in vulnerability detection tasks by 11.85% and 13.61%.

Copied to clipboard

Gao yu Zhu, Wei Shao, Xichou Zhu, Lei Yu, Jiafeng Guo, Xueqi Cheng

Question Tells You Where the Answer Is: Intention-aware Long-Context KV Cache Compression (2026.acl-long)

Challenge:	Text2Sql is a task that translates natural language questions and database schemas into SQL queries.
Approach:	They employ pure fine-tuning strategy to reduce redundancy by using only 53% of the baseline prompt length to fine- tune the model.
Outcome:	The model outperforms the baseline model by 8.2% and 8.6% in Test-suite accuracy (TS) and exact-set-match accuracy (EM) under the most refined Spider dev set of prompts, the model achieves 73.5% and 75.4%, respectively, approaching state-of-the-art (SOTA) levels.

Copied to clipboard

Liang Zhao, Xiaocheng Feng, Weihong Zhong, Lei Huang, Kun Zhu, Baoxin Wang, Dayong Wu, Guoping Hu, Ting Liu, Bing Qin

Challenge:	Recent methods to reduce the KV cache size fail to identify crucial KVs for generation while excluding others accurately, resulting in severe information loss.
Approach:	They propose an intention-aware KV cache eviction method that identifies and retains crucial KVs according to the attention distribution of intention, which semantically reflects the user’s goal and determines which part of the context is relevant.
Outcome:	The proposed method can maintain the model performance while reducing the KV cache size from 128K to 2K, leading to a 6.3x increase in decoding speed and 7.8x enhancement in memory efficiency compared to the default setting.

Beyond Prompt: Fine-grained Simulation of Cognitively Impaired Standardized Patients via Stochastic Steering (2026.findings-acl)

Copied to clipboard

Weikang Zhang, Zimo Zhu, Zhichuan Yang, Chen Huang, Wenqiang Lei, See-Kiong Ng

GLTW: Joint Improved Graph Transformer and LLM via Three-Word Language for Knowledge Graph Completion (2025.findings-acl)

Challenge:	Existing methods for training patients with cognitive impairment rely on discrete prompt engineering and fail to capture the heterogeneity of deficits across domains and severity levels.
Approach:	They propose to use steering vectors from contrastive pairs of instructions and responses to capture domain-specific features and introduce a Stochastic Token Modulation mechanism to regulate the intervention probability.
Outcome:	The proposed model outperforms baselines in clinical authenticity and severity controllability while remaining open-source.

Copied to clipboard

Kangyang Luo, Yuzhuo Bai, Cheng Gao, Shuzheng Si, Zhu Liu, Yingli Shen, Zhitong Wang, Cunliang Kong, Wenhao Li, Yufei Huang, Ye Tian, Xuantang Xiong, Lei Han, Maosong Sun

MoE Adapter for Large Audio Language Models: Sparsity, Disentanglement, and Gradient-Conflict-Free (2026.findings-acl)

Challenge:	Existing knowledge graphs lack the ability to integrate structural information into LLMs and output predictions deterministically.
Approach:	They propose a method which encodes structural information of KGs and merges it with LLMs to enhance KGC performance.
Outcome:	The proposed method improves the performance of KG Completion datasets on KGs by integrating structural information with LLMs.

Copied to clipboard

Yishu Lei, Shuwei He, Hu Jing, Dan Zhang, Xianlong Luo, Danxiang Zhu, Shikun Feng, Rui Liu, Jingzhou HE, Yu Sun, Hua Wu, Haifeng Wang

Language-Specific Layer Matters: Efficient Multilingual Enhancement for Large Vision-Language Models (2025.findings-emnlp)

Challenge:	Existing research on Large Language Models (LLMs) limited to textual input modality . acoustic information is intrinsically heterogeneous, entangling attributes such as speech, music, and environmental context.
Approach:	They propose a sparse Mixture-of-Experts architecture to decouple acoustic information by routing audio tokens to specialized experts.
Outcome:	The proposed architecture outperforms existing models on audio semantic and paralinguistic tasks while retaining shared experts for global context.

Copied to clipboard

Yuchun Fan, Yilin Wang, Yongyu Mu, Lei Huang, Bei Li, Xiaocheng Feng, Tong Xiao, JingBo Zhu

Fusion-Eval: Integrating Assistant Evaluators with LLMs (2024.emnlp-industry)

Challenge:	Large vision-language models exhibit an imbalance in multilingual capabilities .
Approach:	They propose a training recipe that achieves efficient multilingual enhancement for LVLMs by Precise Language Specific layers fine-tuning.
Outcome:	The proposed training recipe achieves efficient multilingual enhancement for LVLMs by fine-tuning language specific layers.

Copied to clipboard

Lei Shu, Nevan Wichers, Liangchen Luo, Yun Zhu, Yinxiao Liu, Jindong Chen, Lei Meng

Learning from the Irrecoverable: Error-Localized Policy Optimization for Tool-Integrated LLM Reasoning (2026.acl-long)

Challenge:	Recent studies have employed large language models (LLMs) as reference-free metrics for NLG evaluation, enhancing adaptability to new tasks tasks.
Approach:	They propose a method that leverages large language models to integrate insights from various assistant evaluators.
Outcome:	The proposed approach achieves a 0.962 system-level Kendall-Tau correlation with humans on SummEval and a 0.7444 turn-level Spearman correlation on TopicalChat, which is significantly higher than baseline methods.

Copied to clipboard

Qiao Liang, Yuke Zhu, Chao Ge, Lei Yang, Ying Shen, Bo Zheng, Sheng Guo

MTR-DuplexBench: Towards a Comprehensive Evaluation of Multi-Round Conversations for Full-Duplex Speech Language Models (2026.findings-acl)

Challenge:	Tool-integrated reasoning (TIR) enables LLM agents to solve tasks through planning, tool use, and iterative revision, but outcome-only reinforcement learning suffers from sparse, delayed rewards and weak step-level credit assignment.
Approach:	They propose a tool-integrated reasoning approach that localizes the first irrecoverable step and leverages it for fine-grained credit assignment.
Outcome:	The proposed algorithm outperforms strong Agentic RL benchmarks in math, science QA, and code execution with additional gains in Pass@K and Major@K scaling, rollout ranking quality, and tool-call efficiency.

Copied to clipboard

Zhang He, Wenqian Cui, Haoning Xu, Xiao-Hui Li, Lei Zhu, Haoli Bai, Ma Shaohua, Irwin King

Dialogue Systems & Conversational Agents

Challenge:	Existing benchmarks focus on evaluating single-round interactions, neglecting other critical aspects.
Approach:	They propose a benchmark to evaluate full-duplex speech language models in multi-round settings . they segment continuous full-dual dialogues into discrete turns for evaluation .
Outcome:	The proposed benchmark compared full-duplex speech language models with full-dual speech models . the results show that the models perform better in multi-round settings than standard models compared to benchmarks .

DocEE: A Large-Scale and Fine-grained Benchmark for Document-level Event Extraction (2022.naacl-main)

Copied to clipboard

MeiHan Tong, Bin Xu, Shuai Wang, Meihuan Han, Yixin Cao, Jiangqi Zhu, Siyu Chen, Lei Hou, Juanzi Li

DCIS: Efficient Length Extrapolation of LLMs via Divide-and-Conquer Scaling Factor Search (2025.emnlp-main)

Challenge:	Existing datasets focus on sentence-level event extraction, but document-level EE is limited due to the lack of large-scale and practical training and evaluation datasets.
Approach:	They propose a document-level event extraction dataset with 27,000+ events and 180,000+ arguments.
Outcome:	The proposed dataset includes 27,000+ events, 180,000+ arguments and large-scale manual annotations, fine-grained argument types and application-oriented settings.

Copied to clipboard

Lei Yang, Shaoyang Xu, Jianxiang Peng, Shaolin Zhu, Deyi Xiong

Multilingual Machine Translation with Large Language Models: Empirical Results and Analysis (2024.findings-naacl)

Challenge:	Existing frameworks for large language models with context length limitations are suboptimal for initialization and fine-tuning.
Approach:	They propose a RoPE-based fine-tuning framework that strategically determines the best scaling factors for LLMs by a Divide-and-Conquer Incremental Search algorithm.
Outcome:	The proposed framework mitigates performance decay at extended target lengths and can perform effectively without fine-tuning.

Copied to clipboard

Wenhao Zhu, Hongyi Liu, Qingxiu Dong, Jingjing Xu, Shujian Huang, Lingpeng Kong, Jiajun Chen, Lei Li

Length Controlled Generation for Black-box LLMs (2025.acl-long)

Challenge:	Existing studies show that large language models (LLMs) can handle multilingual machine translation (MMT) However, the multilingual translation ability of LLMs remains under-explored.
Approach:	They evaluate eight popular LLMs including ChatGPT and GPT-4 to determine their performance in multilingual machine translation.
Outcome:	The proposed model can generate moderate translation even on zero-resource languages and cross-lingual exemplars can provide better task guidance for low-resourced translation than exemplar in the same language pairs.

Copied to clipboard

Yuxuan Gu, Wenjie Wang, Xiaocheng Feng, Weihong Zhong, Kun Zhu, Lei Huang, Ting Liu, Bing Qin, Tat-Seng Chua

Prompting Large Language Models with Chain-of-Thought for Few-Shot Knowledge Base Question Generation (2023.emnlp-main)

Challenge:	Existing length control methods involve fine-tuning the parameters of LLMs, which is inefficient and suboptimal for practical use.
Approach:	They propose an iterative sampling framework that regulates LLMs to generate length-constrained text without modifying the underlying parameters.
Outcome:	The proposed method achieves 100% success rates on Llama3.1 tasks with minimal additional computational overhead.

Copied to clipboard

Yuanyuan Liang, Jianing Wang, Hanlun Zhu, Lei Wang, Weining Qian, Yunshi Lan

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

Challenge:	Existing methods for question generation over knowledge bases rely on annotated data for fine-tuning . emergence of Large Language Models (LLMs) has shown impressive generalization ability in few-shot tasks.
Approach:	They propose to use a logical form to generate a question in a reasoning problem . they propose to extend the prompting method into a method that can generate questions in logical forms .
Outcome:	The proposed method outperforms baselines on three public KBQG datasets.

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

An Efficient Conversational Smart Compose System (2023.acl-demo)

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

Yun Zhu, Xiayu Chen, Lei Shu, Bowen Tan, Xinying Song, Lijuan Liu, Maria Wang, Jindong Chen, Ning Ruan

Dialogue Systems & Conversational Agents

Challenge:	a cloud-based smart compose system is designed to improve human-to-human conversation efficiency.
Approach:	They propose a cloud-based smart compose system to improve conversation efficiency . they propose heuristics to achieve the best trade-off between quality and latency .
Outcome:	The proposed system reduces latency without losing composing quality further.

Weighted Contrastive Learning With False Negative Control to Help Long-tailed Product Classification (2023.acl-industry)

Copied to clipboard

Tianqi Wang, Lei Chen, Xiaodan Zhu, Younghun Lee, Jing Gao

DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak (2025.emnlp-main)

Challenge:	Item categorization (IC) aims to classify a product into leaf nodes in a categorical taxonomy due to scarce supervision.
Approach:	They propose to use K-positive contrastive loss (KCL) to address IC task’s long-tail issue by re-weighting positive pairs in the KCL loss with a regularization that the sum of weights should be constrained to K+1 as close as possible.
Outcome:	The proposed method improves on the long-tail issue in the image classification task and when using text-based contrastive learning, it can be applied on the IC task.

Copied to clipboard

Hao Wang, Hao Li, Junda Zhu, Xinyuan Wang, Chengwei Pan, Minlie Huang, Lei Sha

LLaSE-G1: Incentivizing Generalization Capability for LLaMA-based Speech Enhancement (2025.acl-long)

Challenge:	Large Language Models (LLMs) are susceptible to generating harmful content when prompted with carefully crafted inputs, a vulnerability known as LLM jailbreaking.
Approach:	They propose an end-to-end generative approach for jailbreak rewriting inspired by diffusion models that uses a sequence-tosequence (seq2sequ) diffusion model as a generator, conditioning on the original prompt and guiding the denoising process with a novel attack loss.
Outcome:	Experiments on Advbench and Harmbench show that the proposed method outperforms autoregressive jailbreak models across evaluation metrics including ASR, fluency, diversity and diversity.

Copied to clipboard

Boyi Kang, Xinfa Zhu, Zihan Zhang, Zhen Ye, Mingshuai Liu, Ziqian Wang, Yike Zhu, Guobin Ma, Jun Chen, Longshuai Xiao, Chao Weng, Wei Xue, Lei Xie

QaRL: Rollout-Aligned Quantization-Aware RL for Fast and Stable Training under Training–Inference Mismatch (2026.findings-acl)

Challenge:	Recent advances in language models have demonstrated strong capabilities in semantic understanding and contextual modeling.
Approach:	They propose a LLaMA-based language model that incentivizes generalization capabilities for speech enhancement.
Outcome:	The proposed language model outperforms prior task-specific discriminative and generative models in acoustic enhancement tasks.

Copied to clipboard

Hao Gu, Hao Wang, Jiacheng Liu, Lujun Li, Qiyuan Zhu, Bei Liu, Binxing Xu, Lei Wang, Xintong Yang, Sida Lin, Sirui Han, Yike Guo

Challenge:	Recent work has shown that reinforcement learning with simple rule-based reward functions (RLVR) can induce emergent reasoning behaviors and yield gains in challenging domains such as math problem solving.
Approach:	They propose a rollout-alignment-quantization-aware RL which aligns training-side forward with the quantized rollout to minimize mismatch.
Outcome:	The proposed approach outperforms quantized-rollout training by +5.5 on Qwen3-30B-A3B MoE for math problems while maintaining low-bit throughput.

FoldMoE: Efficient Long Sequence MoE Training via Attention-MoE Pipelining (2025.acl-long)

Copied to clipboard

Guichao Zhu, Lintian Lei, Yuhao Qing, Yichao Fu, Fanxin Li, Dong Huang, Zekai Sun, Heming Cui

Green & Sustainable NLP

Challenge:	Existing approaches to training LLMs with Mixture-of-Experts (MoE) architecture on long sequences are limited by the insufficient computation.
Approach:	They propose a MoE training system that enables token-level overlapping across entire Transformer blocks through novel attention-MoE pipelining.
Outcome:	The proposed system achieves 1.49x and 2.72x speedup over state-of-the-art token-level overlapping and non-overlapping baselines on GPT-MoE models with sequences up to 32K tokens.

Dynamic PMI-Guided Contrastive Decoding Reduces Hallucination in Large Language Models: A Unified Framework of Fine-Grained Input Transformations (2026.findings-acl)

Copied to clipboard

Dongsheng Chen, Yingqi Zhu, Xingyue Zhang, Wenqing Zhou, Lei Li

PoLLMgraph: Unraveling Hallucinations in Large Language Models via State Transition Dynamics (2024.findings-naacl)

Challenge:	Despite the remarkable generation capabilities of large language models, the issue of hallucination remains a critical challenge.
Approach:	They propose a contrastive decoding framework based on dynamic pointwise mutual information that disentangles spurious dependencies induced by context priors, lexical co-occurrences, and syntactic structures and prioritizes causal logic.
Outcome:	The proposed framework significantly improves the model’s factuality and reasoning robustness while maintaining high computational efficiency.

Copied to clipboard

Derui Zhu, Dingfan Chen, Qing Li, Zongxiong Chen, Lei Ma, Jens Grossklags, Mario Fritz

ChartMind: A Comprehensive Benchmark for Complex Real-world Multimodal Chart Question Answering (2025.emnlp-main)

Challenge:	Existing studies have recognized hallucination as a notable concern in large autoregressive language models (LLMs).
Approach:	They propose a polygraph for large language models that detects "hallucination" they demonstrate that hallucination can be detected by tractable probabilistic models .
Outcome:	The proposed model outperforms state-of-the-art methods on open-source LLMs by 20% on TruthfulQA benchmarks.

Copied to clipboard

Jingxuan Wei, Nan Xu, Junnan Zhu, null Haoyanni, Gaowei Wu, Qi Chen, Bihui Yu, Lei Wang

Natural Language Interfaces

Challenge:	Chart question answering (CQA) is a multimodal task for evaluating the reasoning capabilities of vision-language models.
Approach:	They propose a chart question answering benchmark that incorporates multilingual contexts and supports open-domain textual outputs.
Outcome:	The proposed framework outperforms the previous three common CQA paradigms: instruction-following, OCR-enhanced, and chain-of-thought.

RecBase: Generative Foundation Model Pretraining for Zero-Shot Recommendation (2025.emnlp-main)

Copied to clipboard

Sashuai Zhou, Weinan Gan, Qijiong Liu, Ke Lei, Jieming Zhu, Hai Huang, Yan Xia, Ruiming Tang, Zhenhua Dong, Zhou Zhao

CKDST: Comprehensively and Effectively Distill Knowledge from Machine Translation to End-to-End Speech Translation (2023.findings-acl)

Challenge:	Existing methods for addressing item-level user interests are lacking in cross-domain generalization . RecBase model is domain-agnostic and can be used to enhance recommender systems' effectiveness .
Approach:	They propose a domain-agnostic foundational model pretrained with a recommendation-oriented objective that leverages a large-scale, heterogeneous, cross-domain corpus with unified textual representations and feature mappings to enhance cross- domain generalization.
Outcome:	The proposed model matches or surpasses baselines in zero-shot and cross-domain recommendation tasks on eight real-world datasets.

Copied to clipboard

Yikun Lei, Zhengshan Xue, Xiaohu Zhao, Haoran Sun, Shaolin Zhu, Xiaodong Lin, Deyi Xiong

Improving Factual Consistency in Abstractive Summarization with Sentence Structure Pruning (2024.lrec-main)

Challenge:	End-to-end speech-totext translation (ST) data are limited due to the limited resources.
Approach:	They propose a knowledge distillation framework for speech translation that integrates knowledge from machine translation and decouples knowledge from non-target class knowledge.
Outcome:	The proposed framework outperforms state-of-the-art models on a benchmark dataset.

Copied to clipboard

Dingxin Hu, Xuanyu Zhang, Xingyue Zhang, Yiyang Li, Dongsheng Chen, Marina Litvak, Natalia Vanetik, Qing Yang, Dongliang Xu, Yanquan Zhou, Lei Li, Yuze Li, Yingqi Zhu

UPER: Boosting Multi-Document Summarization with an Unsupervised Prompt-based Extractor (2022.coling-1)

Challenge:	Abstractive summarization models suffer from factual inconsistency problem . post-editing methods focus on replacing suspicious entities, failing to modify incorrect content hidden in sentence structures.
Approach:	They propose to use sentence pruning operation to correct possible errors . they propose to apply sentence pruning operations to the syntactic dependency tree .
Outcome:	The proposed method improves factual consistency on the FRANK dataset compared with baselines . it is model-independent and can serve as the final step in ensuring factual consistentness.

Copied to clipboard

Shangqing Tu, Jifan Yu, Fangwei Zhu, Juanzi Li, Lei Hou, Jian-Yun Nie

Low-Resource NLP

Challenge:	Multi-Document Summarization (MDS) uses the extract-then-abstract paradigm, which extracts a relatively short meta-document and then feeds it into the deep neural networks to generate an abstract.
Approach:	They propose to use pre-trained language models to calculate document and keyword’s perplexity to boost other metrics for evaluating a document’s salience.
Outcome:	The proposed method can be applied as a plug-in to boost other metrics for evaluating a document’s salience, thus improving the subsequent abstract generation.

WenetSpeech-Wu: Datasets, Benchmarks, and Models for a Unified Chinese Wu Dialect Speech Processing Ecosystem (2026.findings-acl)

Copied to clipboard

Chengyou Wang, Mingchen Shao, Jingbin Hu, Zeyu Zhu, Hongfei Xue, Bingshen Mu, Xin Xu, Xingyi Duan, Binbin Zhang, Zhu Pengcheng, Chuang Ding, Xiaojun Zhang, Hui Bu, Lei Xie

Croppable Knowledge Graph Embedding (2025.acl-long)

Challenge:	despite its linguistic significance, the Wu dialect of Chinese has long been hindered by the lack of large-scale speech data, standardized evaluation benchmarks, and publicly available models.
Approach:	They propose to use WenetSpeech-Wu as a large-scale, multi-dimensionally annotated open-source speech corpus for the Wu dialect of Chinese.
Outcome:	The proposed dataset includes 8,000 hours of speech data and strong open-source models . the proposed dataset is competitive and empirically validated .

Copied to clipboard

Yushan Zhu, Wen Zhang, Zhiqiang Liu, Mingyang Chen, Lei Liang, Huajun Chen

TableEval: A Real-World Benchmark for Complex, Multilingual, and Multi-Structured Table Question Answering (2025.emnlp-main)

Challenge:	Knowledge Graph Embedding (KGE) is a common approach for Knowledge Grasse (KGs) in AI tasks.
Approach:	They propose a new KGE training framework MED that allows one training to obtain a croppable KGE model for multiple scenarios with different dimensional needs.
Outcome:	The proposed framework improves low-dimensional sub-models and makes high-dimensional models retain the low-dimension sub-modells’ capacity.

Copied to clipboard

Junnan Zhu, Jingyi Wang, Bohan Yu, Xiaoyu Wu, Junbo Li, Lei Wang, Nan Xu

Structured Data in NLP

Challenge:	Existing TableQA benchmarks focus on simple flat tables and suffer from data leakage . current benchmarks are monolingual and fail to capture cross-lingual variability .
Approach:	They propose a table-based TableQA benchmark to evaluate LLMs on real-world tasks.
Outcome:	The proposed benchmarks show that they achieve high agreement with human judgment . the proposed framework improves on the alignment between model responses and reference answers .

ATM: Adversarial Tuning Multi-agent System Makes a Robust Retrieval-Augmented Generator (2024.emnlp-main)

Copied to clipboard

Junda Zhu, Lingyong Yan, Haibo Shi, Dawei Yin, Lei Sha

Robustness in NLP

Challenge:	Large language models (LLMs) are proven to benefit a lot from retrieval-augmented generation (RAG) due to noisy and fabricating content, it is inevitable that RAG systems are vulnerable to these noises and prone to respond incorrectly.
Approach:	They propose to optimize retrieval-augmented generation (RGG) with an Adversarial Tuning Multi-agent system (ATM) ATM steers the Generator to have a robust perspective of useful documents for question answering with the help of an auxiliary Attacker agent.
Outcome:	The proposed system improves the retrieval-augmented generator with an auxiliary Attacker agent and can discriminate useful documents amongst fabrications.

Faster and Better LLMs via Latency-Aware Test-Time Scaling (2025.findings-emnlp)

Copied to clipboard

Zili Wang, Tianyu Zhang, Haoli Bai, Lu Hou, Xianzhi Yu, Wulong Liu, Shiming Xiang, Lei Zhu

Challenge:	Existing research has overlooked the efficiency of TTS from a latency-sensitive perspective.
Approach:	They propose two approaches to achieve latency-optimal TTS by branch-wise parallelism and sequence-wise parallelism.
Outcome:	The proposed approach achieves latency-optimal TTS for large models . branch-wise parallelism and sequence-wise parallelism are key approaches .

PEIT: Bridging the Modality Gap with Pre-trained Models for End-to-End Image Translation (2023.acl-long)

Copied to clipboard

Shaolin Zhu, Shangjie Li, Yikun Lei, Deyi Xiong

Sheaf Discovery with Joint Computation Graph Pruning and Flexible Granularity (2025.emnlp-main)

Challenge:	Image translation is a task that translates an image containing text in the source language to the target language.
Approach:	They propose an end-to-end image translation framework that bridges the modality gap between visual inputs and textual inputs/outputs of machine translation (MT).
Outcome:	The proposed framework outperforms existing models on a large-scale image translation corpus . it significantly outperformed both cascaded and strong models on the e-commerce domain .

Copied to clipboard

Lei Yu, Jingcheng Niu, Zining Zhu, Xi Chen, Gerald Penn

Establishing Trustworthy LLM Evaluation via Shortcut Neuron Analysis (2025.acl-long)

Challenge:	Experimental results show that DiscoGP extracts sheaves that preserve 93-100% of a model’s performance while comprising only 1-7% of the original weights and connections.
Approach:	They propose a framework for extracting self-contained modular units within neural language models (LMs) they use a gradient-based pruning algorithm to prune the original LM to a sparse skeleton .
Outcome:	The proposed framework preserves 93-100% of the original model's performance while preserving only 1-7% of the model''s original weights and connections.

Copied to clipboard

Kejian Zhu, Shangqing Tu, Zhuoran Jin, Lei Hou, Juanzi Li, Jun Zhao

BenchMAX: A Comprehensive Multilingual Evaluation Suite for Large Language Models (2025.findings-emnlp)

Challenge:	Recent studies have focused on building dynamic benchmarks to address data contamination issues.
Approach:	They propose a method for identifying shortcut neurons through comparative and causal analysis to suppress shortcut neurons.
Outcome:	The proposed method overestimates contaminated models and is highly generalizable across benchmarks and hyperparameter settings.

Copied to clipboard

Xu Huang, Wenhao Zhu, Hanxu Hu, Conghui He, Lei Li, Shujian Huang, Fei Yuan

Neeko: Leveraging Dynamic LoRA for Efficient Multi-Character Role-Playing Agent (2024.emnlp-main)

Challenge:	Existing multilingual benchmarks focus primarily on language understanding tasks.
Approach:	They develop a multi-way multilingual benchmark that measures critical capabilities of large language models across languages.
Outcome:	Extensive experiments on BenchMAX reveal uneven utilization of core capabilities across languages, emphasizing the performance gaps that scaling model size alone does not resolve.

Copied to clipboard

Xiaoyan Yu, Tongxu Luo, Yifan Wei, Fangyu Lei, Yiming Huang, Hao Peng, Liehuang Zhu

Green & Sustainable NLP

Challenge:	Large Language Models (LLMs) have revolutionized open-domain dialogue agents but face challenges in multi-character role-playing (MCRP) scenarios.
Approach:	They propose a framework for efficient multi-character role-playing that employs a dynamic low-rank adapter strategy and distinct LoRA blocks for each character.
Outcome:	Neeko employs a dynamic low-rank adapter (LoRA) strategy, enabling it to adapt seamlessly to diverse characters.

Enhancing Reinforcement Learning with Dense Rewards from Language Model Critic (2024.emnlp-main)

Copied to clipboard

Meng Cao, Lei Shu, Lei Yu, Yun Zhu, Nevan Wichers, Yinxiao Liu, Lei Meng

Counter-Interference Adapter for Multilingual Machine Translation (2021.findings-emnlp)

Challenge:	Reinforcement learning (RL) can align language models with non-differentiable reward signals, such as human preferences, but the sparsity of these signals can lead to inefficient and unstable learning.
Approach:	They propose a framework that utilizes the critique capability of Large Language Models to produce intermediate-step rewards during RL training.
Outcome:	The proposed framework improves sample efficiency and the overall performance of the policy model, supported by both automatic and human evaluation.

Copied to clipboard

Yaoming Zhu, Jiangtao Feng, Chengqi Zhao, Mingxuan Wang, Lei Li

KnowAgent: Knowledge-Augmented Planning for LLM-Based Agents (2025.findings-naacl)

Challenge:	Existing approaches to multilingual machine translation suffer from performance degradation, resulting in a single model being inferior to separately trained bilingual models on resource-rich languages.
Approach:	They propose a transformer-based model with a small parameter overhead for multilingual machine translation that outperforms strong multilingual baselines on 64 of 66 language directions.
Outcome:	The proposed model outperforms strong multilingual baselines on 64 of 66 language directions, 42 of which have above 0.5 BLEU improvement.

Copied to clipboard

Yuqi Zhu, Shuofei Qiao, Yixin Ou, Shumin Deng, Shiwei Lyu, Yue Shen, Lei Liang, Jinjie Gu, Huajun Chen, Ningyu Zhang

RelayAttention for Efficient Large Language Model Serving with Long System Prompts (2024.acl-long)

Challenge:	Large Language Models (LLMs) fail to effectively guide the planning trajectories during task solving and result in planning hallucinations.
Approach:	They propose a novel approach to enhance the planning capabilities of large language models by incorporating explicit action knowledge.
Outcome:	The proposed approach can achieve comparable or superior performance to existing baselines on HotpotQA and ALFWorld.

Copied to clipboard

Lei Zhu, Xinjiang Wang, Wayne Zhang, Rynson Lau

Beyond Layout Embedding: Layout Attention with Gaussian Biases for Structured Document Understanding (2023.findings-emnlp)

Challenge:	a long system prompt causes throughput/latency bottlenecks as the cost of generating the next token increases w.r.t the sequence length.
Approach:	They propose an attention algorithm that reads hidden state from DRAM exactly once for a batch of input tokens.
Outcome:	The proposed algorithm reduces the need for redundant memory accesses in existing algorithms.

Copied to clipboard

Xi Zhu, Xue Han, Shuyuan Peng, Shuo Lei, Chao Deng, Junlan Feng

Representation Learning

Challenge:	Existing methods for encoding layout information rely on millions of learnable parameters . polar coordinates provide superior choice for layout modeling, study finds .
Approach:	They propose to model layout attention with Gaussian biases by feeding polar coordinates into 2-D Gausssian kernels.
Outcome:	The proposed model improves on three widely used benchmarks.

LC4EE: LLMs as Good Corrector for Event Extraction (2024.findings-acl)

Copied to clipboard

Mengna Zhu, Kaisheng Zeng, JibingWu JibingWu, Lihua Liu, Hongbin Huang, Lei Hou, Juanzi Li

Learn to Not Link: Exploring NIL Prediction in Entity Linking (2023.findings-acl)

Challenge:	Event extraction (EE) is a critical task in natural language processing, yet deploying a practical EE system remains challenging.
Approach:	They propose to leverage the superior extraction capability of LLMs and instruction-following ability of LRMs to construct a robust and highly available EE system.
Outcome:	The proposed method can identify and correct errors in SLMs predictions based on automatically generated feedback information and improve performance.

Copied to clipboard

Fangwei Zhu, Jifan Yu, Hailong Jin, Lei Hou, Juanzi Li, Zhifang Sui

Proofread: Fixes All Errors with One Tap (2024.acl-demos)

Challenge:	Entity linking models have been successful in capturing semantic features, but the NIL prediction problem has not been addressed.
Approach:	They propose an entity linking dataset that categorizes mentions linking to NIL into Missing Entity and Non-Entity Phrases.
Outcome:	The proposed dataset categorizes mentions linking to NIL into Missing Entity and Non-Entity Phrase categories and ensures the presence of mentions by human annotation and entity masking.

Copied to clipboard

Renjie Liu, Yanxiang Zhang, Yun Zhu, Haicheng Sun, Yuanbo Zhang, Michael Huang, Shanqing Cai, Lei Meng, Shumin Zhai