Papers by Yang Ni

Expanding before Inferring: Enhancing Factuality in Large Language Models through Premature Layers Interpolation (2025.emnlp-main)

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

Copied to clipboard

Dingwei Chen, Ziqiang Liu, Feiteng Fang, Chak Tou Leong, Shiwen Ni, Ahmadreza Argha, Hamid Alinejad-Rokny, Min Yang, Chengming Li

Continual Pretraining on Encrypted Synthetic Data for Privacy-Preserving LLMs (2026.findings-eacl)

Challenge:	Existing approaches to generating factually inconsistent outputs are resource-intensive.
Approach:	They propose a plug-and-play intervention designed to enhance factuality by inserting premature layers formed through mathematical interpolation with adjacent layers.
Outcome:	The proposed intervention reduces hallucinations while outperforming baselines on four datasets.

Copied to clipboard

Honghao Liu, Xuhui Jiang, Chengjin Xu, Cehao Yang, Yiran Cheng, Lionel Ni, Jian Guo

Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Models (2022.findings-acl)

Challenge:	Existing methods to protect PII from training on small corpora are difficult to implement in real-world applications.
Approach:	They propose an entity-based framework that synthesizes encrypted training data to protect PII.
Outcome:	The proposed framework outperforms base models and ensures PII security on limited-scale datasets while exhibiting a modest performance gap compared to models trained on unencrypted synthetic data.

Copied to clipboard

Jianmo Ni, Gustavo Hernandez Abrego, Noah Constant, Ji Ma, Keith Hall, Daniel Cer, Yinfei Yang

Layer-wise Regularized Dropout for Neural Language Models (2024.lrec-main)

Challenge:	Sentence embeddings are useful for language processing tasks, but it is unclear how to produce them from encoder-decoder models.
Approach:	They investigate the effects of scaling up sentence encoders to 11B parameters on sentence embeddings from text-to-text transformers (T5) .
Outcome:	The proposed models outperform the previous best models on both SentEval and SentGLUE transfer tasks.

Copied to clipboard

Shiwen Ni, Min Yang, Ruifeng Xu, Chengming Li, Xiping Xiping Hu

SrDetection: A Self-Referential Framework for Data Leakage Detection in Code Large Language Models (2026.findings-acl)

Challenge:	Existing methods to regularize dropout are consistency training and dropout is a problem in many pre-trained neural language models.
Approach:	They propose a layer-wise regularized dropout technique which regularizes dropout at the output layer using consistency training.
Outcome:	The proposed model can be regarded as a "self-distillation" framework, in which each sub-model generated by dropout is the other's "teacher" model and "student" model.

Copied to clipboard

Shuaimin Li, Liyang Fan, Zeyang li, Zhuoyue Wan, Yufang Lin, Shiwen Ni, Feiteng Fang, Hamid Alinejad-Rokny, Yuanfeng Song, Kun Jing, Chen Jason Zhang, Min Yang

Beyond Quantity: Trajectory Diversity Scaling for Code Agents (2026.findings-acl)

Challenge:	Existing methods for evaluating code large language models assume access to proprietary training corpora or use external reference sets with manually tuned, non-generalizable thresholds.
Approach:	They propose a framework for self-referential leakage detection for gray-box and black-box settings.
Outcome:	The proposed framework improves average F1 by 21.52 points in the gray-box setting and 14.46 points in black-box settings over strong baselines.

Copied to clipboard

Guhong Chen, Chenghao Sun, Cheng Fu, Qiyao Wang, Zhihong Huang, ChaoPeng Wei, Guangxu Chen, Feiteng Fang, Ahmadreza Argha, Bing Zhao, Xander Xu, Qi Han, Hamid Alinejad-Rokny, Qiang Qu, Binhua Li, Shiwen Ni, Min Yang, HU Wei, Yongbin Li

Green & Sustainable NLP

Challenge:	Code large language models (LLMs) are becoming tool-interactive agents . quantity-centric scaling exhibits an early bottleneck that underutilizes trajectory data . et al.: a new approach to scale trajectory diversity improves tool-use generalization .
Approach:	They propose a Trajectory Diversity Scaling-based data synthesis framework for code agents that scales performance through diversity rather than raw volume.
Outcome:	Experiments on general tool-use benchmarks and code agent tasks show that TDScaling improves tool-user generalization and inherent coding proficiency.

Forgetting before Learning: Utilizing Parametric Arithmetic for Knowledge Updating in Large Language Models (2024.acl-long)

Copied to clipboard

Shiwen Ni, Dingwei Chen, Chengming Li, Xiping Hu, Ruifeng Xu, Min Yang

Tree-of-Code: A Self-Growing Tree Framework for End-to-End Code Generation and Execution in Complex Tasks (2025.findings-acl)

Challenge:	Existing methods of model editing and knowledge updating add additional network parameters, knowledge bases, knowledge base, and model parameters.
Approach:	They propose a new paradigm for fine-tuning called F-Learning that employs parametric arithmetic to facilitate the forgetting of old knowledge and learning of new knowledge.
Outcome:	The proposed model outperforms existing models on two datasets and is comparable to full fine-tuning and LoRA fine-uning.

Copied to clipboard

Ziyi Ni, Yifan Li, Ning Yang, Dou Shen, Pin Lyu, Daxiang Dong

Programming Languages in NLP

Challenge:	Effectively and efficiently handling complex realworld problems has become a key focus across industry and academia.
Approach:	They propose a tree-of-code framework that generates nodes through self-supervision and combines prompt and model exploration in a GT-free setting.
Outcome:	Experiments on two datasets with ten popular zero-shot LLMs show that Tree-of-Code boosts accuracy by nearly 20% over CodeAct with fewer than 1/4 turns.

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

ResearchBench: Benchmarking LLMs in Scientific Discovery via Inspiration-Based Task Decomposition (2026.findings-acl)

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

Yujie Liu, Zonglin Yang, Tong Xie, Jinjie Ni, Ben Gao, Yuqiang Li, Shixiang Tang, Wanli Ouyang, Erik Cambria, Dongzhan Zhou

Knowledge Poisoning Attacks on Medical Multi-Modal Retrieval-Augmented Generation (2026.acl-long)

Challenge:	Large language models have shown potential in assisting scientific research, yet their ability to discover high-quality research hypotheses remains unexamined due to the lack of a dedicated benchmark.
Approach:	They propose a benchmark for evaluating large language models on a sufficient set of scientific discovery sub-tasks.
Outcome:	The proposed framework extracts critical components from papers across 12 disciplines with expert validation confirming its accuracy.

Copied to clipboard

Peiru Yang, Haoran Zheng, Tong Ju, Shiting Wang, Wanchun Ni, Jiajun Liu, Shangguang Wang, Yongfeng Huang, Tao Qi

Conflicts Make Large Reasoning Models Vulnerable to Attacks (2026.findings-acl)

Challenge:	Existing studies have investigated knowledge poisoning attacks in medical RAG systems . knowledge poison attacks can disrupt model outputs and undermine system reliability .
Approach:	They propose a knowledge poisoning framework that injects misinformation into textual data . they propose to use paired visual data as a query-agnostic trigger to promote retrieval .
Outcome:	The proposed framework produces clinically plausible but incorrect generations on five LLMs and datasets.

Copied to clipboard

Honghao Liu, Chengjin Xu, Xuhui Jiang, Cehao Yang, Shengming Yin, Zhengwu Ma, Lionel Ni, Jian Guo

LongT5: Efficient Text-To-Text Transformer for Long Sequences (2022.findings-naacl)

Challenge:	Large Reasoning Models have demonstrated outstanding capabilities in solving complex reasoning tasks by incorporating step-by-step chain-of-thought (CoT) reasoning.
Approach:	They evaluate three large reasoning models that perform explicit and coherent reasoning under conflicting objectives and use them to evaluate their performance.
Outcome:	The proposed models perform explicit and coherent reasoning before producing their outputs, improving problem-solving and multi-step decision making.

Copied to clipboard

Mandy Guo, Joshua Ainslie, David Uthus, Santiago Ontanon, Jianmo Ni, Yun-Hsuan Sung, Yinfei Yang

Can MLLMs Understand the Deep Implication Behind Chinese Images? (2025.acl-long)

Challenge:	Recent work has shown that increasing the input length or increasing model size can improve the performance of Transformer-based neural models.
Approach:	They propose a model that integrates attention ideas from long-input transformers and adopts pre-training strategies from summarization pre-train into the scalable T5 architecture.
Outcome:	The proposed model outperforms the original T5 models on several summarization and question answering tasks and achieves state-of-the-art results.

Copied to clipboard

Chenhao Zhang, Xi Feng, Yuelin Bai, Xeron Du, Jinchang Hou, Kaixin Deng, Guangzeng Han, Qinrui Li, Bingli Wang, Jiaheng Liu, Xingwei Qu, Yifei Zhang, Qixuan Zhao, Yiming Liang, Ziqiang Liu, Feiteng Fang, Min Yang, Wenhao Huang, Chenghua Lin, Ge Zhang, Shiwen Ni

DaMo: Data Mixing Optimizer in Fine-tuning Multimodal LLMs for Mobile Phone Agents (2026.findings-acl)

Challenge:	MLLMs perform poorly on traditional culture images, indicating limitations in understanding high-level semantics and lacking a deep knowledge base of Chinese traditional culture.
Approach:	They propose to use Chinese images to assess MLLMs' higher-order perception and understanding of Chinese visual content.
Outcome:	The proposed model incorporates images that represent Chinese traditional culture, such as famous Chinese traditional paintings, to ensure the authenticity of the Chinese context.

Copied to clipboard

Kai Shi, Jun Yang, Ni Yang, Binqiang Pan, Qingsong Xie, null Zhangchao, Zhenyu Yang, Tianhuang Su, Haonan Lu

E-EVAL: A Comprehensive Chinese K-12 Education Evaluation Benchmark for Large Language Models (2024.findings-acl)

Challenge:	Mobile Phone Agents (MPAs) have attracted huge attention due to their practicability in a multitude of scenarios.
Approach:	They propose a data mixture optimization solution that extrapolates optimal data mixtures from a trainable network.
Outcome:	The proposed model outperforms existing methods on open-source benchmarks and on open source benchmarks.

Copied to clipboard

Jinchang Hou, Chang Ao, Haihong Wu, Xiangtao Kong, Zhigang Zheng, Daijia Tang, Chengming Li, Xiping Hu, Ruifeng Xu, Shiwen Ni, Min Yang

Large Dual Encoders Are Generalizable Retrievers (2022.emnlp-main)

Challenge:	despite the rapid development of Large Language Models, there is no dedicated benchmark for evaluating LLMs in Chinese K-12 education.
Approach:	They propose to develop a benchmark specifically tailored for Chinese K-12 education.
Outcome:	EVAL is the first evaluation benchmark specifically tailored for Chinese K-12 education.

Copied to clipboard

Jianmo Ni, Chen Qu, Jing Lu, Zhuyun Dai, Gustavo Hernandez Abrego, Ji Ma, Vincent Zhao, Yi Luan, Keith Hall, Ming-Wei Chang, Yinfei Yang

E-ViC: Reasoning Beyond Text via Embodied Visual Chain for Spatial Intelligence (2026.acl-long)

Challenge:	Experimental results show that dual encoders outperform sparse and dense retrievers on the BEIR dataset significantly.
Approach:	They challenge belief that bottleneck layer is too limited for out-of-domain generalization . they scale up the model while keeping bottleneck as a single dot-product with a fixed size .
Outcome:	The proposed model outperforms sparse and dense retrievers on the BEIR dataset significantly.

Copied to clipboard

Junbo Qi, Yi Zhang, Hanchu Ni, Che Liu, Zhimin Yao, Ruilin Yang, Xiancong Ren, Liangjian Wen, Wei Ge, Yuya Ieiri, Osamu Yoshie, Yong Dai, Xiaozhu Ju

RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models (2024.findings-acl)

Challenge:	Existing Vision-Language Models (VLMs) lack spatial reasoning, despite text-based CoTs . e-ViC reframes spatial intelligence as a verifiable, tool-using capability, argues a new study.
Approach:	They propose a framework that moves reasoning beyond text into the visual domain . they ground reasoning in pixel-level interactions to enable human-like "look-and-confirm" strategies .
Outcome:	The proposed framework outperforms existing Vision-Language Models with an average gain of 10.1%.

Copied to clipboard

Noah Wang, Z.y. Peng, Haoran Que, Jiaheng Liu, Wangchunshu Zhou, Yuhan Wu, Hongcheng Guo, Ruitong Gan, Zehao Ni, Jian Yang, Man Zhang, Zhaoxiang Zhang, Wanli Ouyang, Ke Xu, Wenhao Huang, Jie Fu, Junran Peng

DenseLoRA: Dense Low-Rank Adaptation of Large Language Models (2025.acl-long)

Challenge:	Large Language Models (LLMs) have paved the way for complex tasks such as role-playing.
Approach:	They propose a framework to benchmark, elicit, and enhance role-playing abilities in Large Language Models.
Outcome:	The proposed framework improves role-playing abilities with 168,093 samples.

Copied to clipboard

Lin Mu, Xiaoyu Wang, Li Ni, Yang Li, Zhize Wu, Peiquan Jin, Yiwen Zhang

NUWA-XL: Diffusion over Diffusion for eXtremely Long Video Generation (2023.acl-long)

Challenge:	Low-rank adaptation (LoRA) is an efficient approach for adapting large language models (LLMs) but many of the weights in these matrices are redundant, leading to inefficiencies in parameter utilization.
Approach:	They propose a low-rank adaptation approach that fine-tunes two low-ranked matrices and adapts them through a dense low-Rank matrix, improving parameter utilization and adaptation efficiency.
Outcome:	The proposed approach achieves 83.8% accuracy with only 0.01% of trainable parameters compared to LoRA's 80.8% with 0.70% of trainability parameters on LLaMA3-8B.

Copied to clipboard

Shengming Yin, Chenfei Wu, Huan Yang, Jianfeng Wang, Xiaodong Wang, Minheng Ni, Zhengyuan Yang, Linjie Li, Shuguang Liu, Fan Yang, Jianlong Fu, Ming Gong, Lijuan Wang, Zicheng Liu, Houqiang Li, Nan Duan

Quantification of Large Language Model Distillation (2025.acl-long)

Challenge:	Existing work generates long videos segment by segment sequentially, which is inefficient.
Approach:	They propose a Diffusion over Difference architecture for eXtremely Long video generation.
Outcome:	The proposed architecture reduces the average inference time from 7.55min to 26s (94.26%) and generates high-quality long videos with both global and local coherence.

Copied to clipboard

Sunbowen Lee, Junting Zhou, Chang Ao, Kaige Li, Xeron Du, Sirui He, Haihong Wu, Tianci Liu, Jiaheng Liu, Hamid Alinejad-Rokny, Min Yang, Yitao Liang, Zhoufutu Wen, Shiwen Ni

P-QuASAR: A Unified Probabilistic Framework for Holistic Patent Quality Assessment and Refinement (2026.findings-acl)

Challenge:	Existing studies have revealed the robustness degra-dation caused by data distillation.
Approach:	They propose a framework to evaluate and quantify model distillation . they aim to identify identity cognition contradictions and analyse multi-granularity response similarities across models to measure the extent of homogenization.
Outcome:	The proposed framework addresses two key aspects: (1) Identifying identity cognition contradictions to assess discrepancies in how models perceive and represent identity-related information; (2) Analyzing multi-granularity response similarities across models to measure the extent of homogenization.

Copied to clipboard

Xinyuan Song, Ziyi Ni, Fred Yang, Bo Zhang, Yijin Wang, Jane Zhang

Structured Data in NLP

Challenge:	Existing methods for assessing patent quality rely on modular pipelines or generic detectors, resulting in fragmented decisions and limited integration across quality dimensions.
Approach:	They propose a probabilistic framework that represents patent specifications as Quality Graphs.
Outcome:	The proposed framework outperforms existing methods on 500 patents against seven baselines.

MoZIP: A Multilingual Benchmark to Evaluate Large Language Models in Intellectual Property (2024.lrec-main)

Copied to clipboard

Shiwen Ni, Minghuan Tan, Yuelin Bai, Fuqiang Niu, Min Yang, Bowen Zhang, Ruifeng Xu, Xiaojun Chen, Chengming Li, Xiping Hu

Natural Language Interfaces

Challenge:	Large language models (LLMs) have demonstrated impressive performance in various natural language processing tasks.
Approach:	They propose a benchmark for the evaluation of large language models in the IP domain . they also propose supervised multilingual large language model called MoZi .
Outcome:	The proposed model outperforms four well-known LLMs on the MoZIP benchmark . the most powerful ChatGPT does not reach the passing level .

Finding the Pillars of Strength for Multi-Head Attention (2023.acl-long)

Copied to clipboard

Jinjie Ni, Rui Mao, Zonglin Yang, Han Lei, Erik Cambria

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

Challenge:	Recent studies have revealed some issues of Multi-Head Attention (MHA) e.g., redundancy and over-parameterization.
Approach:	They propose to train attention heads with a self-supervised group constraint to focus on an essential but distinctive feature subset.
Outcome:	The proposed method achieves significant performance gains on three well-established tasks while significantly compressing parameters.

Copied to clipboard

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

CoTJudger: A Graph-Driven Framework for Automatic Evaluation of Chain-of-Thought Efficiency and Redundancy in LRMs (2026.findings-acl)

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

Copied to clipboard

Siyi Li, Jiajun Shi, Shiwen Ni, Ge Zhang, Shuaimin Li, Shijian Wang, Zhoufutu Wen, Yizhi LI, Hamid Alinejad-Rokny, Jiaheng Liu, Min Yang, Wenhao Huang

Green & Sustainable NLP

Challenge:	Existing evaluations emphasize final accuracy or coarse token counts, and lack automated tools to separate essential logic from structural redundancy.
Approach:	They propose a graph-driven framework that quantifies reasoning efficiency by converting free-form CoTs into directed dependency graphs and extracting the Shortest Effective Path needed to reach a correct solution.
Outcome:	Evaluating 21 LRMs, the proposed framework quantifies reasoning efficiency by converting free-form CoTs into directed dependency graphs and extracting the Shortest Effective Path (SEP) needed to reach a correct solution.

LIME: Less Is More for MLLM Evaluation (2025.findings-acl)

Copied to clipboard

King Zhu, Qianbo Zang, Shian Jia, Siwei Wu, Feiteng Fang, Yizhi Li, Shuyue Guo, Tianyu Zheng, Jiawei Guo, Bo Li, Haoning Wu, Xingwei Qu, Jian Yang, Ruibo Liu, Xiang Yue, Jiaheng Liu, Chenghua Lin, Hamid Alinejad-Rokny, Min Yang, Shiwen Ni, Wenhao Huang, Ge Zhang

Unveil: Unified Visual-Textual Integration and Distillation for Multi-modal Document Retrieval (2025.acl-long)

Challenge:	Existing MLLM benchmarks and unified evaluation frameworks cannot accurately and efficiently reflect the ability of MLMLs.
Approach:	They propose a semi-automated benchmark curated using a pipeline that filters out uninformative samples and eliminates answer leakage by focusing on tasks that require image-based understanding.
Outcome:	The proposed benchmark reduces the number of samples by 76% and evaluation time by 77% while it can more effectively distinguish different models’ abilities.

Copied to clipboard

Hao Sun, Yingyan Hou, Jiayan Guo, Bo Wang, Chunyu Yang, Jinsong Ni, Yan Zhang