Papers by Bo Zheng

GeoGPT4V: Towards Geometric Multi-modal Large Language Models with Geometric Image Generation (2024.emnlp-main)

Challenge:	Large language models have created significant safety concerns . factuality ability is crucial in determining whether they can be deployed and applied safely and compliantly within specific regions.
Approach:	They propose a benchmark to evaluate the factuality of large language models in China . they evaluate the models' ability to provide accurate and reliable information .
Outcome:	The proposed benchmark evaluates the factuality abilities of existing LLMs and compares them to LLM abilities.

Copied to clipboard

Shihao Cai, Keqin Bao, Hangyu Guo, Jizhi Zhang, Jun Song, Bo Zheng

E2-LLM: Efficient and Extreme Length Extension of Large Language Models (2024.findings-acl)

Challenge:	Existing datasets are too challenging for direct model learning or suffer from misalignment between text and images.
Approach:	They propose a pipeline that leverages GPT-4 and GPT4V to generate geometry problems with aligned text and images, facilitating model learning.
Outcome:	The proposed pipeline generates 4.9K geometry problems with aligned text and images, facilitating model learning.

Copied to clipboard

Jiaheng Liu, ZhiqiBai ZhiqiBai, Yuanxing Zhang, Chenchen Zhang, YuangZh YuangZh, Ge Zhang, JiakaiWang JiakaiWang, Haoran Que, Yukang Chen, Wenbo Su, Tiezheng Ge, Jie Fu, Wenhu Chen, Bo Zheng

All Languages Matter: Understanding and Mitigating Language Bias in Multilingual RAG (2026.acl-long)

Challenge:	Existing techniques for extending context capabilities in LLMs require additional training procedures and access to datasets with long context (e.g., sequences of 32K tokens).
Approach:	They propose a solution to extend context capabilities in Large Language Models by training a single process over a sequence of 4K tokens.
Outcome:	The proposed solution significantly reduces the cost of continual-pretraining or fine-tuning over short sequences and improves robustness to diverse relative positions.

Copied to clipboard

Dan Wang, Guozhao Mo, Yafei Shi, Cheng Zhang, Bo Zheng, Boxi Cao, Xuanang Chen, Yaojie Lu, Hongyu Lin, Ben He, Xianpei Han, Le Sun

Multilinguality

Challenge:	Existing mRAG systems suffer from a language bias during reranking, systematically favoring English and the query’s native language.
Approach:	They propose a language-agnostic utility-driven reranker alignment technique to mitigate language bias during re-ranking.
Outcome:	The proposed approach mitigates language bias and consistently improves mRAG performance across languages.

Unified Thinker: A General Reasoning Core for Image Generation (2026.acl-long)

Copied to clipboard

Sashuai Zhou, Qiang Zhou, Jijin Hu, Hanqing Yang, Yue Cao, Junpeng Ma, Yinchao Ma, Jun Song, Tiezheng Ge, Cheng Yu, Bo Zheng, Zhou Zhao

USB: A COMPREHENSIVE AND UNIFIED SAFETY EVALUATION BENCHMARK FOR MULTIMODAL LARGE LANGUAGE MODELS (2026.acl-long)

Challenge:	generative models struggle with logic-intensive instruction following, exposing a persistent reasoning–execution gap.
Approach:	They propose a task-agnostic reasoning architecture for general image generation . they propose pixel-level feedback to ground the Thinker's policy in pixel feedback .
Outcome:	The proposed system significantly improves image reasoning and generation quality.

Copied to clipboard

Baolin Zheng, Guanlin Chen, Qingyang Teng, Hongqiong Zhong, Yingshui Tan, Zhendong Liu, Weixun Wang, Jiaheng Liu, Jian Yang, Huiyun Jing, Jincheng Wei, Wenbo Su, Xiaoyong Zhu, Bo Zheng, Kaifu Zhang

v-HUB: A Benchmark for Video Humor Understanding from Vision and Sound (2026.acl-long)

Challenge:	Existing safety benchmarks fail to provide reliable assessments due to limited risk coverage, insufficient scale and the oversight of complex modality combinations.
Approach:	They propose a framework that covers 61 risk categories across four modality interactions to address this gap.
Outcome:	The proposed framework covers 61 risk categories across four distinct modality interactions.

Copied to clipboard

Zhengpeng Shi, Yanpeng Zhao, Jianqun Zhou, Yuxuan Wang, Qinrong Cui, Wei Bi, Song-Chun Zhu, Bo Zhao, Zilong Zheng

XLM-E: Cross-lingual Language Model Pre-training via ELECTRA (2022.acl-long)

Challenge:	Humor enriches our daily lives and appears in many forms, from jokes and cartoons to comedies and viral videos.
Approach:	They introduce a video humor understanding benchmark to test their ability to understand humor from visual cues.
Outcome:	The proposed video humor understanding benchmark is based on a collection of short videos . it features rich annotations and a study of environmental sound that can enhance humor .

Copied to clipboard

Zewen Chi, Shaohan Huang, Li Dong, Shuming Ma, Bo Zheng, Saksham Singhal, Payal Bajaj, Xia Song, Xian-Ling Mao, Heyan Huang, Furu Wei

SEGMENT+: Long Text Processing with Short-Context Language Models (2024.emnlp-main)

Challenge:	ELECTRA-style tasks are used to pretrain cross-lingual models for NLP tasks . masked language modeling tasks require massive computation resources, rendering such models quite expensive .
Approach:	They propose to use ELECTRA-style tasks to pre-train a cross-lingual language model . they propose to pretrain the model on multilingual and parallel corpora .
Outcome:	The proposed model outperforms baseline models on cross-lingual understanding tasks with much less computation cost.

Copied to clipboard

Wei Shi, Shuang Li, Kerun Yu, Jinglei Chen, Zujie Liang, Xinhui Wu, Yuxi Qian, Feng Wei, Bo Zheng, Jiaqing Liang, Jiangjie Chen, Yanghua Xiao

CREATER: CTR-driven Advertising Text Generation with Controlled Pre-Training and Contrastive Fine-Tuning (2022.naacl-industry)

Challenge:	Existing frameworks that increase context window do not guarantee robust performance across long input tasks.
Approach:	They propose a framework that enables language models to handle extended inputs within limited context windows efficiently.
Outcome:	The framework improves performance on long-document question-answering and Needle-in-a-Haystack tasks.

Copied to clipboard

Penghui Wei, Xuanhua Yang, ShaoGuo Liu, Liang Wang, Bo Zheng

Allocating Large Vocabulary Capacity for Cross-Lingual Language Model Pre-Training (2021.emnlp-main)

Challenge:	a paper focuses on automatically generating the text of an ad to capture user interest for achieving higher click-through rate.
Approach:	They propose a CTR-driven advertising text generation approach to generate ad texts based on user reviews.
Outcome:	The proposed approach outperforms existing approaches on industrial datasets and on large-scale unpaired reviews.

Copied to clipboard

Bo Zheng, Li Dong, Shaohan Huang, Saksham Singhal, Wanxiang Che, Ting Liu, Xia Song, Furu Wei

MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing (2026.acl-industry)

Challenge:	Existing models require a more expressive vocabulary to represent all languages . however, increasing the vocabulary size significantly slows down the pre-training speed .
Approach:	They propose an algorithm VoCap to determine the desired vocabulary capacity of each language.
Outcome:	The proposed algorithm improves cross-lingual model pre-training while reducing side effects of increasing vocabulary size.

Copied to clipboard

Junbo Niu, Zheng Liu, Zhuangcheng Gu, Bin Wang, Linke Ouyang, Zhiyuan Zhao, Tao Chu, Tianyao He, Fan Wu, Qintong Zhang, Zhenjiang Jin, Guang Liang, Rui Zhang, Wenzheng Zhang, Yuan Qu, Zhifei Ren, Yuefeng Sun, Zirui Tang, Boyu Niu, Yuanhong Zheng, Dongsheng Ma, Ziyang Miao, Hejun Dong, Siyi Qian, Junyuan Zhang, Fangdong Wang, Jingzhou Chen, Xiaomeng Zhao, Liqun Wei, Wei Li, Shasha Wang, RuiLiang Xu, Yuanyuan Cao, Lu Chen, Qianqian Wu, Huaiyu Gu, Lindong Lu, Dechen Lin, null Shenguanlin, Xuanhe Zhou, Linfeng Zhang, Yuhang Zang, Xiaoyi Dong, Jiaqi Wang, Bo Zhang, Lei Bai, Pei Chu, Weijia Li, Jiang Wu, Lijun Wu, Zhenxiang Li, Guangyu Wang, Zhongying Tu, Chao Xu, Kai Chen, Bowen Zhou, Dahua Lin, Wentao Zhang, Conghui He

Green & Sustainable NLP

Challenge:	Document images are characterized by higher resolutions, denser content, and more complex structural layouts.
Approach:	They propose a 1.2B-parameter document parsing vision-language model that decouples layout analysis from local content recognition.
Outcome:	The proposed model surpasses general-purpose and domain-specific models on multiple benchmarks while maintaining significantly lower computational overhead.

SELECting over Tokens: Curating Pre-training Data at Scale via Token Classification (2026.acl-long)

Copied to clipboard

Xin Tong, Weidong Zhang, Jiaang Li, Haibin Chen, Shilei Liu, Langming Liu, Kangtao Lv, Yujin Yuan, Wenbo Su, Bo Zheng

From Pseudo-Balancing to True Specialization: Memory-Aware Routing for Mixture-of-Experts (2026.findings-acl)

Challenge:	Existing pipelines rely on expert-crafted heuristic rules, which lack content-aware, fine-grained noise detection.
Approach:	They propose a framework that reframes data refinement as a highly efficient token classification task.
Outcome:	The proposed framework outperforms existing pipelines on benchmarks and is 2.5x faster at inference.

Copied to clipboard

Peixuan Hou, Yunbo Hou, Bin Chen, LI He, Jian Xu, Weiping Li, Bo Zheng, Guojie Song

Green & Sustainable NLP

Challenge:	Existing methods to optimize expert-centered load balancing fail to account for pseudo-balance phenomenon . severe knowledge overlap among experts leads to redundant representations and inefficient parameter utilization .
Approach:	They propose a method that prioritizes expert utilization over semantic alignment . they use memory-aware routing to ensure expert load balancing is consistent .
Outcome:	Experimental results show that MAR improves expert specialization by 35% and accuracy by 2%-25% . MAR matches baseline performance with only half the experts .

KCAT: A Knowledge-Constraint Typing Annotation Tool (P19-3)

Copied to clipboard

Sheng Lin, Luye Zheng, Bo Chen, Siliang Tang, Zhigang Chen, Guoping Hu, Yueting Zhuang, Fei Wu, Xiang Ren

Named Entity Recognition

Challenge:	Recent years Natural Language Processing community has seen a surge of interest in fine-grained entity typing (FET) given an entity mention (i.e. a sequence of token spans representing an entity), FET aims at uncovering its contextdependent type.
Approach:	They propose an efficient Knowledge Constraint Fine-grained Entity Typing Annotation Tool which further improves the entity typing process through entity linking together with some practical functions.
Outcome:	The proposed tool improves the entity typing process by linking the candidate types with some practical functions.

Beyond Black-Box Interventions: Latent Probing for Faithful Retrieval-Augmented Generation (2026.findings-acl)

Copied to clipboard

Linfeng Gao, Qinggang Zhang, Baolong Bi, Bo Zeng, Zheng Yuan, Zerui Chen, Zhimin Wei, Shenghua Liu, Linlong Xu, Longyue Wang, Weihua Luo, Jinsong Su

Navigating the Infinite Dynamic Web Space: Effective In-Context Exploration via Cognitive Multi-Agent Collaboration (2026.eacl-long)

Challenge:	Existing approaches to improve contextual faithfulness treat the LLM as a black box, generating responses that are inconsistent with the provided context.
Approach:	They propose a framework for faithful RAG that operates in three stages: (i) fine-grained knowledge pruning to filter irrelevant context, (ii) latent conflict probing to identify hard conflicts in the model’s latent space, and (iv) conflict-aware attention to modulate attention heads toward faithful context integration.
Outcome:	Experiments show that ProbeRAG significantly improves both accuracy and contextual faithfulness.

Copied to clipboard

Guozhao Mo, Yanjiang Liu, Yafei Shi, Jiawei Chen, Yang Li, Yaojie Lu, Hongyu Lin, Ben He, Le Sun, Bo Zheng, Xianpei Han

Linguistics & Cognitive NLP

Challenge:	Existing methods for dynamic web navigation rely on greedy strategies or value estimation, struggle to achieve effective backtracking and are heavily dependent on proprietary models.
Approach:	They propose a cognitive multi-agent collaboration framework that enhances cyberspace exploration capability through In-Context Exploration.
Outcome:	The proposed framework surpasses the proprietary model Claude-3.5 Sonnet on the WebArena benchmark.

PGPO: Enhancing Agent Reasoning via Pseudocode-style Planning Guided Preference Optimization (2025.findings-acl)

Copied to clipboard

Zouying Cao, Runze Wang, Yifei Yang, Xinbei Ma, Xiaoyong Zhu, Bo Zheng, Hai Zhao

Can Public Large Language Models Help Private Cross-device Federated Learning? (2024.findings-naacl)

Challenge:	Existing LLM agents generate verbose and inefficient natural language plans to guide reasoning, which restricts agents’ ability to generalize across similar tasks.
Approach:	They propose a pseudocode-style planning guide optimization method that captures the structural logic of reasoning and uses two planning-oriented rewards to enhance agent learning.
Outcome:	The proposed method outperforms existing LLM agents on representative agent benchmarks and outperformed the current leading baselines.

Copied to clipboard

Boxin Wang, Yibo Zhang, Yuan Cao, Bo Li, Hugh McMahan, Sewoong Oh, Zheng Xu, Manzil Zaheer

GSID: Generative Semantic Indexing for E-Commerce Product Understanding (2025.emnlp-industry)

Challenge:	Recent studies have shown that public data can be used to improve privacy-utility trade-offs for large and small language models.
Approach:	They propose to use large-scale public data to help differentially private FL training . they propose a distribution matching algorithm with theoretical grounding to sample public data close to private data distribution .
Outcome:	The proposed method is efficient and effective for training private models by taking advantage of public data.

Copied to clipboard

Haiyang Yang, Qinye Xie, Qingheng Zhang, Chen Li Yu, Huike Zou, Chengbao Lian, Shuguang Han, Fei Huang, Jufeng Chen, Bo Zheng

MaskTab: Scalable Masked Tabular Pretraining with Scaling Laws and Distillation for Industrial Classification (2026.findings-acl)

Challenge:	Structured product information is a major bottleneck for the efficiency of e-commerce platforms.
Approach:	They propose a data-driven approach to generate product structured representations using product metadata.
Outcome:	Extensive experiments show that GSID can generate better product representations on real-world e-commerce platforms.

Copied to clipboard

Bo Zheng, Yudong Chen, Zihua Xiong, Shuai Fang, Peidong He, Yang Yang, Sheng Guo

An Industry Evaluation of Embedding-based Entity Alignment (2020.coling-industry)

Challenge:	Tabular data is high-dimensional, riddled with missing entries, and rarely labeled at scale.
Approach:	They propose a unified pre-training framework for industrial-scale tabular data . MaskTab encodes missing values via dedicated learnable tokens .
Outcome:	The proposed framework outperforms XGBoost and MaskTab-L on industrial-scale . it achieves +5.04% AUC and +8.28% KS over prior art under rigorous scaling .

Copied to clipboard

Ziheng Zhang, Hualuo Liu, Jiaoyan Chen, Xi Chen, Bo Liu, YueJia Xiang, Yefeng Zheng

Token Preference Optimization with Self-Calibrated Visual-Anchored Rewards for Hallucination Mitigation (2025.findings-emnlp)

Challenge:	Knowledge graphs (KGs) are increasingly important in various applications such as question answering and search engines.
Approach:	They propose to use a supervised learning environment with unbiased seed mappings for training and validation to evaluate alignment methods in an industrial context.
Outcome:	The proposed methods are evaluated in an industrial context and are compared with DBpedia and Wikidata benchmarks.

Copied to clipboard

Jihao Gu, Yingyao Wang, Meng Cao, Pi Bu, Jun Song, Bo Zheng, Yancheng He, Shilong Li

ShopSimulator: Evaluating and Exploring RL-Driven LLM Agent for Shopping Assistants (2026.acl-long)

Challenge:	Existing methods for predicting hallucinations suffer from two drawbacks: Lack of scalable token-level rewards and Neglect of visual-anchored tokens.
Approach:	They propose a Token Preference Optimization model with self-calibrated rewards . they propose based on visual-anchored tokens and visual-aware training objective .
Outcome:	The proposed model improves hallucination performance by focusing on visual-anchored tokens without fine-grained annotations.

Copied to clipboard

Pei Wang, Yanan Wu, Xiaoshuai Song, Weixun Wang, Gengru Chen, Zhongwen Li, Kezhong Yan, Qi Liu, Ken Deng, Shuaibing Zhao, Shaopan Xiong, Xuepeng Liu, Xuefeng Chen, Wanxi Deng, Wenbo Su, Bo Zheng

Challenge:	Existing studies on large language model-based agents focus on evaluation benchmarks without training support.
Approach:	They propose a large-scale Chinese shopping simulation environment that uses large language models to train agents.
Outcome:	The proposed model performs poorly in a large-scale and challenging shopping environment in China.

AFMRL: Attribute-Enhanced Fine-Grained Multi-Modal Representation Learning in E-commerce (2026.findings-acl)

Copied to clipboard

Biao Zhang, Lixin Chen, Bin Zhang, Wang Zongwei, Tong Liu, Bo Zheng

DualRAG: A Dual-Process Approach to Integrate Reasoning and Retrieval for Multi-Hop Question Answering (2025.acl-long)

Challenge:	Multimodal representation is crucial for E-commerce tasks such as identical product retrieval.
Approach:	They propose an approach which leverages the generative power of Multimodal Large Language Models to extract key attributes from product images and text and enhances representation learning through a two-stage training framework.
Outcome:	The proposed model achieves state-of-the-art on multiple downstream retrieval tasks, validating the effectiveness of harnessing generative models to advance fine-grained representation learning.

Copied to clipboard

Rong Cheng, Jinyi Liu, Yan Zheng, Fei Ni, Jiazhen Du, Hangyu Mao, Fuzheng Zhang, Bo Wang, Jianye Hao

Natural Language Interfaces

Challenge:	Existing approaches to multi-hop question answering struggle to identify and organize dynamic knowledge . et al., 2023; Liu e.t. al. 2023) suggest a dual-process framework for multi-step reasoning .
Approach:	They propose a synergistic dual-process framework that integrates reasoning and retrieval.
Outcome:	The proposed framework improves answer accuracy and coherence even in smaller-scale models.

HiddenDetect: Detecting Jailbreak Attacks against Multimodal Large Language Models via Monitoring Hidden States (2025.acl-long)

Copied to clipboard

Yilei Jiang, Xinyan Gao, Tianshuo Peng, Yingshui Tan, Xiaoyong Zhu, Bo Zheng, Xiangyu Yue

Read As Human: Compressing Context via Parallelizable Close Reading and Skimming (2026.acl-long)

Challenge:	Existing studies focus on posthoc alignment techniques, but the underlying safety mechanisms within LVLMs remain unexplored.
Approach:	They propose a tuning-free framework that leverages internal activations to enhance safety.
Outcome:	The proposed framework outperforms state-of-the-art methods in detecting jailbreak attacks against large vision-language models.

Copied to clipboard

Jiwei Tang, Shilei Liu, Zhicheng Zhang, Qingsong Lv, Runsong Zhao, Tingwei Lu, Langming Liu, Haibin Chen, Yujin Yuan, Hai-Tao Zheng, Wenbo Su, Bo Zheng

Challenge:	Existing task-aware methods require loading the entire input sequence at once for compression, which suffer from computational inefficiency.
Approach:	They propose a framework that adopts an adaptive hybrid reading strategy to reduce computational inefficiency and redundant information in long-context scenarios.
Outcome:	Experiments show that RAM outperforms baselines on multiple question answering and summarization benchmarks while delivering up to a 12x speedup on long inputs.

See the World, Discover Knowledge: A Chinese Factuality Evaluation for Large Vision Language Models (2025.findings-acl)

Copied to clipboard

Jihao Gu, Yingyao Wang, Pi Bu, Chen Wang, Ziming Wang, Tengtao Song, Donglai Wei, Jiale Yuan, Yingxiu Zhao, Yancheng He, Shilong Li, Jiaheng Liu, Meng Cao, Jun Song, Yingshui Tan, Xiang Li, Wenbo Su, Xiaoyong Zhu, Bo Zheng

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

Challenge:	Existing models for large vision language models do not fully reflect their knowledge capacity and reliability, resulting in erroneous outputs that do not align with the image content or provide answers lacking knowledge evidence.
Approach:	They propose a Chinese-based benchmark for visual factuality across 8 major topics and 56 subtopics and a multi-hop question construction.
Outcome:	The proposed model decouples visual factuality into two parts: seeing the world and discovering knowledge.

Copied to clipboard

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

MegaPairs: Massive Data Synthesis for Universal Multimodal Retrieval (2025.acl-long)

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

Copied to clipboard

Junjie Zhou, Yongping Xiong, Zheng Liu, Ze Liu, Shitao Xiao, Yueze Wang, Bo Zhao, Chen Jason Zhang, Defu Lian

VISTA: Visualized Text Embedding For Universal Multi-Modal Retrieval (2024.acl-long)

Challenge:	despite the growing demand for multimodal retrieval, there is a lack of training data.
Approach:	They propose a data synthesis method that leverages vision language models and open-domain images to generate high-quality data.
Outcome:	The proposed method outperforms baseline models on 70 more datasets and can scale up.

Copied to clipboard

Junjie Zhou, Zheng Liu, Shitao Xiao, Bo Zhao, Yongping Xiong

A Self-training Framework for Automated Medical Report Generation (2023.emnlp-main)

Challenge:	Existing methods for multimodal retrieval are mostly text-oriented, which lack the capability to process visual information.
Approach:	They propose a multi-modal multi-text embedding model VISTA which extends a powerful text encoder with the image understanding capability by introducing visual token embedds.
Outcome:	The proposed model achieves superior performance across a variety of multi-modal retrieval tasks in zero-shot and supervised settings.

Copied to clipboard

Siyuan Wang, Zheng Liu, Bo Peng

PILOT: Planning via Internalized Latent Optimization Trajectories for Large Language Models (2026.acl-long)

Challenge:	Medical report generation is an important medical artificial intelligence task.
Approach:	They propose a framework for medical report generation that exploits unlabeled medical images and a reference-free evaluation metric.
Outcome:	The proposed framework performs better than previous fully-supervised models trained on entire training data.

Copied to clipboard

Haoyu Zheng, Yun Zhu, Yuqian Yuan, Bo Yuan, Wenqiao Zhang, Siliang Tang, Jun Xiao

Reinforcement Learning on Pre-Training Data (2026.acl-long)

Challenge:	Large Language Models lack the capacity to formulate global strategies due to latency and availability constraints.
Approach:	They propose a framework to internalize the strategic oversight of large models into intrinsic Latent Guidance by synthesizing a query-conditioned Latent Guide.
Outcome:	The proposed framework outperforms strong baselines on mathematical and coding benchmarks with negligible inference latency.

Copied to clipboard

Siheng Li, Kejiao Li, Zenan Xu, Guanhua Huang, Kun Li, Haoyuan Wu, null Wujiajia, Zihao Zheng, Chenchen Zhang, Kun Shi, Xue Gong, Qi Yi, Ruibin Xiong, Tingqiang Xu, Yuhao Jiang, Jianfeng Yan, Yuyuan Zeng, Guanghui Xu, Jinbao Xue, Zhijiang xu, Zheng Fang, Shuai LI, Qibin Liu, Xiaoxue Li, Zhuoyu Li, Yangyu Tao, Fei Gao, Cheng Jiang, Bochao Wang, Kai Liu, Jianchen Zhu, Wai Lam, Bo Zhou, Di Wang

How to inject knowledge efficiently? Knowledge Infusion Scaling Law for Pre-training Large Language Models (2025.emnlp-main)

Challenge:	Recent progress in large language models is driven by scaling of training compute through pre-training with nexttoken prediction (NTP) or post-training (RL) Pre-training using NTP enables models to acquire extensive knowledge and skills from general data, but it suffers from data inefficiency and catastrophic forgetting in continual learning settings.
Approach:	They propose to scale training compute through pre-training with next-token prediction (NTP) or post-training by scaling reinforcement learning (RL) to improve learning from general data.
Outcome:	Experiments on multiple benchmarks and models show that the proposed approach improves continual pre-training and provides a strong foundation for post-training on Qwen3-8B-Base.

Copied to clipboard

Kangtao Lv, Haibin Chen, Yujin Yuan, Langming Liu, Shilei Liu, Yongwei Wang, Wenbo Su, Bo Zheng

Demons in the Detail: On Implementing Load Balancing Loss for Training Specialized Mixture-of-Expert Models (2025.acl-long)

Challenge:	Recent studies show that strategically infusing domain knowledge during pretraining can substantially improve downstream performance.
Approach:	They propose a knowledge infusion scaling law that predicts the optimal amount of domain knowledge to inject into large LLMs by analyzing their smaller counterparts.
Outcome:	The proposed model predicts the optimal amount of domain knowledge to inject into large LLMs by analyzing their smaller counterparts.

Copied to clipboard

Zihan Qiu, Zeyu Huang, Bo Zheng, Kaiyue Wen, Zekun Wang, Rui Men, Ivan Titov, Dayiheng Liu, Jingren Zhou, Junyang Lin

Programming Languages in NLP

Challenge:	Existing Mixture-of-Experts training frameworks use a micro-batch to calculate LBL . micro-batches are restricted to a single sequence, preventing expert specialization .
Approach:	They propose to use a global-batch to loosen the load balance constraint for MoEs models . they propose to synchronize fi across micro-batches and then use it to calculate the LBL .
Outcome:	The proposed global-batch LBL improves the domain specialization of experts . the micro-battery LBL is almost at the sequence level, and the router is pushed to distribute the token evenly .

MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scale (2025.acl-long)

Copied to clipboard

Jiawei Guo, Tianyu Zheng, Yizhi Li, Yuelin Bai, Bo Li, Yubo Wang, King Zhu, Graham Neubig, Wenhu Chen, Xiang Yue

Synchronized Video Storytelling: Generating Video Narrations with Structured Storyline (2024.acl-long)

Challenge:	Current instruction-tuning datasets focus on simplistic visual question answering tasks, and provide phrase-level answers without any intermediate rationales.
Approach:	They propose to use open-source multimodal large language models to train MLLMs on a dataset with 12M instruction-response pairs to elicit CoT reasoning.
Outcome:	The proposed model achieves state-of-the-art performance on benchmarks such as MathVerse, MMMU-Pro, and MuirBench, and gains improvements of up to 4% on non-reasoning-based benchmarks.

Copied to clipboard

Dingyi Yang, Chunru Zhan, Ziheng Wang, Biao Wang, Tiezheng Ge, Bo Zheng, Qin Jin

DeepGeneMD: A Joint Deep Learning Model for Extracting Gene Mutation-Disease Knowledge from PubMed Literature (D19-57)

Challenge:	Existing studies on dense video captioning and video story generation have made some progress, but in practical applications, we typically require synchronized narrations for ongoing visual scenes.
Approach:	They propose a task of Synchronized Video Storytelling to generate synchronized narrations for videos using a benchmark dataset with rich annotations.
Outcome:	The proposed framework can generate narrations with the guidance of the generated or predefined storyline and human evaluations validate the effectiveness.

Copied to clipboard

Feifan Liu, Xiaoyu Zheng, Bo Wang, Catarina Kiefe

Low-Resource NLP

Challenge:	Identifying and understanding the pathogenesis of genetic diseases is an essential task.
Approach:	They propose a joint deep learning model for gene mutation-disease knowledge extraction that adapts the state-of-the-art hierarchical multi-task learning framework for joint inference on named entity recognition and relation extraction.
Outcome:	The proposed model achieves the average score of 0.45 on recognizing gene activities and disease entities and the average F1 score of 0.3 on extracting relations, ranking 1st in the AGAC RE task.

AIGuard: A Benchmark and Lightweight Detection for E-commerce AIGC Risks (2025.findings-acl)

Copied to clipboard

Wenhua Zhang, Weicheng Li, Xuanrong Rao, Lixin Zou, Xiangyang Luo, Chubin Zhuang, Yongjie Hong, Zhen Qin, Hengyu Chang, Chenliang Li, Bo Zheng

Eureka: Neural Insight Learning for Knowledge Graph Reasoning (2022.coling-1)

Challenge:	Existing detection methods lack real-world scenarios and corresponding risk datasets . current MLLMs lack knowledge and have limited capability to detect the risk of AIGC content.
Approach:	They propose a benchmark for AIGC risk detection in real-world e-commerce . it includes 253,420 image-text pairs across four critical categories .
Outcome:	The proposed method achieves 9.68% higher recall than leading multimodal models while using only 25% of training resources.

Copied to clipboard

Alex X. Zhang, Xun Liang, Bo Wu, Xiangping Zheng, Sensen Zhang, Yuhui Guo, Jun Wang, Xinyao Liu

CASE: Aligning Coarse-to-Fine Cognition and Affection for Empathetic Response Generation (2023.acl-long)

Challenge:	Existing knowledge embedding methods have limited performance on knowledge graph reasoning tasks . eureka is empowered to learn seen relations with sufficient training triples .
Approach:	They propose a neural insight learning framework called Eureka to bridge the “seen” to “unsea” gap . Eureca is empowered to learn seen relations with sufficient training triples while providing flexibility to learn unseen relations given only one trigger .
Outcome:	The proposed framework outperforms state-of-the-art models on seen and unseen relations . it can learn seen and unseen relationships with sufficient training triples .

Copied to clipboard

Jinfeng Zhou, Chujie Zheng, Bo Wang, Zheng Zhang, Minlie Huang

Dialogue Systems & Conversational Agents

Challenge:	Existing empathetic dialogue models only consider the affective aspect of empathy, which limits the capability of emotional response generation.
Approach:	They propose a model that aligns the user's cognition and affection at both the coarse-grained and fine-grounded levels and then automatically and manually evaluates the model.
Outcome:	The proposed model outperforms state-of-the-art models and generates more empathetic and informative responses.

SMEC:Rethinking Matryoshka Representation Learning for Retrieval Embedding Compression (2025.emnlp-main)

Copied to clipboard

Biao Zhang, Lixin Chen, Tong Liu, Bo Zheng

2D-DPO: Scaling Direct Preference Optimization with 2-Dimensional Supervision (2025.findings-naacl)

Challenge:	Large language models generate high-dimensional embeddings that capture rich semantic and syntactic information.
Approach:	They propose a training framework to reduce dimensionality and complexity of large language models.
Outcome:	Experiments on image, text, and multimodal datasets show that the proposed training framework reduces dimensionality while maintaining performance.

Copied to clipboard

Shilong Li, Yancheng He, Hui Huang, Xingyuan Bu, Jiaheng Liu, Hangyu Guo, Weixun Wang, Jihao Gu, Wenbo Su, Bo Zheng

Challenge:	Existing methods that optimize for scalar scores or ranking reward ignore multi-dimensional nature of human preferences.
Approach:	They propose to extend the preference of Direct Preference Optimization to two dimensions: segments and aspects.
Outcome:	The proposed framework decomposes the overall objective into multi-segment and multi-aspect objectives.

Geoparsing: Diagram Parsing for Plane and Solid Geometry with a Unified Formal Language (2026.findings-acl)

Copied to clipboard

Peijie Wang, Ming-Liang Zhang, Jun Cao, Chao Deng, Dekang Ran, Pi Bu, Hongda Sun, Xuan Zhang, Yingyao Wang, Jun Song, Bo Zheng, Fei Yin, Cheng-Lin Liu

LoRE: Enhancing Search Relevance with Progressive Chain-of-Thought and Preference Alignment (2026.findings-acl)

Challenge:	Recent advances in Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities across various vision reasoning tasks.
Approach:	They propose a unified formal language that integrates plane and solid geometry, comprehensively covering geometric structures and semantic relations.
Outcome:	The proposed language achieves state-of-the-art parsing performance and significantly boosts MLLMs’ capabilities for downstream geometry reasoning tasks.

Copied to clipboard

Chenji Lu, Zhuo Chen, Hui Zhao, Zhiyuan Zeng, Gang Zhao, Junjie Ren, null Lihaoran, Songyan Liu, Pengjie Wang, Chuan Yu, Jian Xu, Bo Zheng

AIR: Complex Instruction Generation via Automatic Iterative Refinement (2025.emnlp-main)

Challenge:	E-commerce search relevance is a critical component of retrieval systems.
Approach:	They propose a large-generative model for search relevance that trains reasoning knowledge, multi-modal understanding and rule awareness into three core competencies.
Outcome:	The proposed model outperforms GPT-5 in Macro-F1 and achieves 27% online gain.

Copied to clipboard

Wei Liu, Yancheng He, Yu Li, Hui Huang, Chengwei Hu, Jiaheng Liu, Shilong Li, Wenbo Su, Bo Zheng

Text Generation

Challenge:	Existing methods for generating complex instructions are resource-intensive and lack diversity.
Approach:	They propose a framework to generate complex instructions with constraints using a document-generated initial instruction and an iterative refinement framework to incorporate LLM-as-judge guidance.
Outcome:	The proposed framework significantly outperforms existing methods for generating complex instructions, and outperformed existing methods.

An AMR Aligner Tuned by Transition-based Parser (D18-1)

Copied to clipboard

Yijia Liu, Wanxiang Che, Bo Zheng, Bing Qin, Ting Liu

Learning to Evolve: A Self-Improving Framework for Multi-Agent Systems via Textual Parameter Graph Optimization (2026.findings-acl)

Challenge:	Experimental results show that our AMR aligner outperforms the rule-based aligner by achieving higher alignment F1 score and consistently improving two open-source AMR parsers.
Approach:	They propose a rich resource enhanced AMR aligner which produces multiple alignments and a new transition system for AMR parsing along with its oracle parser.
Outcome:	The proposed AMR aligner outperforms the current state-of-the-art parser by achieving higher alignment F1 score and consistently improving two open-source AMR parsers.

Copied to clipboard

Shan He, Runze Wang, Zhuoyun Du, Huiyu Bai, Zouying Cao, Yu Cheng, Bo Zheng

MPPO: Multi Pair-wise Preference Optimization for LLMs with Arbitrary Negative Samples (2025.coling-main)

Challenge:	Existing methods for designing and optimizing multi-agent systems are static and do not learn from experience.
Approach:	They propose a framework that enables a multi-agent system to learn to evolve . they use "textual gradients" to pinpoint failures and suggest granular modifications .
Outcome:	a new framework enables a multi-agent system to learn to evolve . it learns from historical optimization experiences to improve its performance .

Copied to clipboard

Shuo Xie, Fangzhi Zhu, Jiahui Wang, Lulu Wen, Wei Dai, Xiaowei Chen, Junxiong Zhu, Kai Zhou, Bo Zheng

Challenge:	Existing preference optimization methods such as DPO and KTO are inherently derived from PPO, requiring a reference model that adds GPU memory resources and relies heavily on abundant preference data.
Approach:	They propose an algorithm that leverages the average likelihood of model responses to fit the reward function and maximizes the utilization of preference data.
Outcome:	The proposed algorithm outperforms DPO, ORPO, and SimPO on MT-Bench and Arena-Hard.

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

Copied to clipboard

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

GRAPHIA: Harnessing Social Graph Data to Enhance LLM-Based Social Simulation (2026.acl-long)

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

Jiarui Ji, Zehua Zhang, Zhewei Wei, Bin Tong, Guan Wang, Bo Zheng

StableMoE: Stable Routing Strategy for Mixture of Experts (2022.acl-long)

Challenge:	Social graphs provide high-quality supervision signals that encode local interactions and global network structure, yet they remain underutilized for LLM training.
Approach:	They propose a general LLM-based social graph simulation framework that leverages graph data as supervision for LLM training.
Outcome:	The proposed framework improves micro-level alignment by 6.1% on three real-world networks compared to the strongest baseline.

Copied to clipboard

Damai Dai, Li Dong, Shuming Ma, Bo Zheng, Zhifang Sui, Baobao Chang, Furu Wei

Challenge:	Existing learning-to-route methods suffer from the routing fluctuation issue . with the model scale growing, training speed will go slower and memory requirements are heavy .
Approach:	They propose a Mixture-of-Experts technique that can scale up the model size of Transformers with an affordable computational overhead.
Outcome:	The proposed method outperforms existing learning-to-route methods on language modeling and multilingual machine translation.

Good Arguments Against the People Pleasers: How Reasoning Mitigates (Yet Masks) LLM Sycophancy (2026.acl-long)

Copied to clipboard

Zhaoxin Feng, Zheng Chen, Jianfei Ma, Yip Tin Po, Emmanuele Chersoni, Bo Li

Skill-Based Few-Shot Selection for In-Context Learning (2023.emnlp-main)

Challenge:	Recent studies have identified a critical drawback of aligning models with human judgments and outputs that are flawed or incorrect.
Approach:	They evaluate a range of LLMs to examine whether CoT reasoning mitigates sycophancy . they find that reasoning masks a tendency to scophage in some cases .
Outcome:	The proposed model models show that CoT reasoning reduces sycophancy but masks it in some cases.

Copied to clipboard

Shengnan An, Bo Zhou, Zeqi Lin, Qiang Fu, Bei Chen, Nanning Zheng, Weizhu Chen, Jian-Guang Lou

RAVR: Reference-Answer-guided Variational Reasoning for Large Language Models (2026.findings-acl)

Challenge:	Existing methods based on pre-trained embeddings can be easily biased by surface features that are not important for the target task.
Approach:	They propose a skill-based few-shot selection method for in-context learning . it generates skill-specific descriptions for each test case and candidate example .
Outcome:	The proposed method significantly outperforms existing methods in five cross-domain semantic parsing datasets and six backbone models.

Copied to clipboard

Tianqianjin Lin, Xi Zhao, Xingyao Zhang, Rujiao Long, Yi Xu, Zhuoren Jiang, Wenbo Su, Bo Zheng

R3-RAG: Learning Step-by-Step Reasoning and Retrieval for LLMs via Reinforcement Learning (2025.findings-emnlp)

Challenge:	Experiments show that reinforcement learning (RL) can refine the reasoning abilities of large language models (LLMs) but requires a key prerequisite: the model must already be able to generate high-utility reasoning paths with non-negligible probability.
Approach:	They propose a framework that uses answer-conditioned reasoning as a variational surrogate for question-only reasoning.
Outcome:	Experiments on 11 benchmarks and 3 models show that RAVR reduces hesitation, strengthens conclusion consolidation, and promotes problem-specific strategies in reasoning.

Copied to clipboard

Yuan Li, Qi Luo, Xiaonan Li, Bufan Li, Qinyuan Cheng, Bo Wang, Yining Zheng, Yuxin Wang, Zhangyue Yin, Xipeng Qiu

AIR-Bench: Automated Heterogeneous Information Retrieval Benchmark (2025.acl-long)

Challenge:	RAG systems that integrate external knowledge with Large Language Models often become bottlenecks due to their limited parameters compared to LLMs and their inability to perform step-by-step reasoning.
Approach:	They propose a model that integrates external knowledge with Large Language Models to enhance factual correctness and mitigate hallucination.
Outcome:	The proposed model outperforms baselines and can transfer well to different retrievers.

Copied to clipboard

Jianlyu Chen, Nan Wang, Chaofan Li, Bo Wang, Shitao Xiao, Han Xiao, Hao Liao, Defu Lian, Zheng Liu

FinMRAGBench: A Realistic and Complex Benchmark for Multi-Modal RAG in Financial Document Analysis (2026.findings-acl)

Challenge:	Evaluation benchmarks based on predefined domains and human-labeled data face limitations in addressing evaluation needs for emerging domains.
Approach:	They propose an automated information retrieval benchmark based on predefined domains and human-labeled data . AIR-Bench is automated and Heterogeneous with three key features .
Outcome:	The proposed benchmarks are based on predefined domains and human-labeled data.

Copied to clipboard

Shouqing Yang, Qi Zhang, Yuhang Yang, Ruikang Xu, Yuwei Hou, Zhulin Jia, Lirong Gao, Haobo Wang, Jinglei Chen, Jiexiang Wang, Sheng Guo, Bo Zheng, Gang Chen

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

Challenge:	Existing benchmarks for realistic financial analysis fail to capture realistic financial situations involving cross-document retrieval, multi-page evidence integration, and diverse analytical tasks.
Approach:	They propose a multi-modal financial RAG benchmark that evaluates large language models in realistic financial analysis settings.
Outcome:	The proposed framework achieves the strongest overall performance across all models.

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.

GRAG: Graph Retrieval-Augmented Generation (2025.findings-naacl)

Copied to clipboard

Yuntong Hu, Zhihan Lei, Zheng Zhang, Bo Pan, Chen Ling, Liang Zhao

CoMeT: Collaborative Memory Transformer for Efficient Long Context Modeling (2026.acl-long)

Challenge:	Naive Retrieval-Augmented Generation (RAG) focuses on individual documents during retrieval and is not suitable for networked documents.
Approach:	They propose a novel divide-and-conquer strategy that retrieves optimal subgraph structure in linear time.
Outcome:	The proposed approach outperforms current state-of-the-art methods on graph reasoning benchmarks.

Copied to clipboard

Runsong Zhao, Shilei Liu, Jiwei Tang, Langming Liu, Haibin Chen, Weidong Zhang, Yujin Yuan, Tong Xiao, JingBo Zhu, Wenbo Su, Bo Zheng

DCMKC: A Dual Consistency Matching Approach for Multi-hop Question Answering in LLMs (2025.findings-emnlp)

Challenge:	a novel architecture that enables LLMs to handle arbitrarily long sequences with constant memory usage and linear time complexity is a major barrier to long-context processing.
Approach:	They propose a novel architecture that enables LLMs to handle arbitrarily long sequences with constant memory usage and linear time complexity.
Outcome:	The proposed architecture can handle arbitrarily long sequences with constant memory usage and linear time complexity.

Copied to clipboard

Xinyi Wang, Yiping Song, Chang Liu, Tingjin Luo, Bo Liu, Zheng Xie, Minlie Huang

Synergizing Multimodal Temporal Knowledge Graphs and Large Language Models for Social Relation Recognition (2025.emnlp-main)

Challenge:	Existing reasoning based on chains of thought (CoTs) fails to find logical connections between reasoning steps .
Approach:	They propose a method to match KG reasoning chains with CoTs based on semantic similarity . they use a knowledge graph to find relevant information "within" each reasoning step .
Outcome:	The proposed method outperforms baselines on multi-answer questions with 5.1% improvement over baselines.

Copied to clipboard

Haorui Wang, Zheng Wang, Yuxuan Zhang, Bo Wang, Bin Wu

A Survey of Reinforcement Learning for Large Language Models under Data Scarcity: Challenges and Solutions (2026.acl-long)

Challenge:	Recent advances in Large Language Models (LLMs) have limited capacity to model complex graph-structured relationships.
Approach:	They propose a low-coupling method synergizing multimodal temporal Knowledge Graphs and Large Language Models for social relation reasoning.
Outcome:	The proposed method exhibits state-of-the-art performance in social relation recognition . it bridges the gap between KGs and LLMs and will be released after acceptance .

Copied to clipboard

Zhiyin Yu, Yuchen Mou, Juncheng Yan, Junyu Luo, Chunchun Chen, Xing Wei, Yunhui Liu, Hongru Sun, Yuxing Zhang, Jun Xu, Yatao Bian, Ming Zhang, Wei Ye, Tieke He, Jie Yang, Guanjie Zheng, Zhonghai Wu, Bo Zhang, Lei Bai, Xiao Luo

PretrainRL: Alleviating Factuality Hallucination of Large Language Models at the Beginning (2026.findings-acl)

Challenge:	Existing research on reinforcement learning for LLMs under data scarcity has not been unified.
Approach:	They propose a top-up hierarchical framework built around three complementary perspectives: data-centric, training-centric and framework-centric.
Outcome:	The proposed framework provides a clear conceptual foundation for understanding the design space of data-efficient RL for large language models and to guide researchers working in this emerging area.

Copied to clipboard

Langming Liu, Kangtao Lv, Haibin Chen, Weidong Zhang, Yejing Wang, Shilei Liu, Xin Tong, Yujin Yuan, Yongwei Wang, Wenbo Su, Bo Zheng

LongDocURL: a Comprehensive Multimodal Long Document Benchmark Integrating Understanding, Reasoning, and Locating (2025.acl-long)

Challenge:	Large language models suffer from factual hallucinations where they generate verifiable falsehoods.
Approach:	They propose a framework that integrates reinforcement learning into the pretraining phase to consolidate factual knowledge.
Outcome:	The proposed framework significantly alleviates factual hallucinations and outperforms state-of-the-art methods.

Copied to clipboard

Chao Deng, Jiale Yuan, Pi Bu, Peijie Wang, Zhong-Zhi Li, Jian Xu, Xiao-Hui Li, Yuan Gao, Jun Song, Bo Zheng, Cheng-Lin Liu

ABC-Bench: Benchmarking Agentic Backend Coding in Real-World Development (2026.findings-acl)

Challenge:	Existing document understanding benchmarks only handle a small number of pages . existing models are limited to handling only a limited number of documents .
Approach:	They propose a long document understanding benchmark that integrates three primary tasks and 20 sub-tasks based on different primary tasks.
Outcome:	The proposed model outperforms existing benchmarks on open-source and closed-source models . the model outpersforms other models on more than 33,000 pages of documents .

Copied to clipboard

Jie Yang, Honglin Guo, Li Ji, Jiazheng Zhou, Rui Zheng, Zhikai Lei, Shuo Zhang, Zhiheng Xi, Shichun Liu, Yuxin Wang, Bo Wang, Yining Zheng, Tao Gui, Xipeng Qiu

Do not Abstain! Identify and Solve the Uncertainty (2025.acl-long)

Challenge:	Large Language Models (LLMs) have redefined the role of AI in software engineering . current benchmarks focus on localized code generation, but neglect dynamic, full-process requirements of real-world engineering.
Approach:	They propose a benchmark to evaluate agentic backend coding within a realistic, executable workflow.
Outcome:	The ABC-Bench benchmark evaluates agentic backend coding within a realistic, executable workflow.

Copied to clipboard

Jingyu Liu, JingquanPeng JingquanPeng, Xiaopeng Wu, Xubin Li, Tiezheng Ge, Bo Zheng, Yong Liu

Challenge:	Existing solutions rely on evasive responses when confronting uncertain scenarios.
Approach:	They propose a benchmark to assess LLMs' ability to recognize and address uncertainty . they generate context-aware inquiries that highlight the confusing aspect of the original query .
Outcome:	Experiments with ConfuseBench show that LLMs struggle to identify root cause of uncertainty and solve it.

Massive End-to-end Speech Recognition Models with Time Reduction (2024.naacl-long)

Copied to clipboard

Weiran Wang, Rohit Prabhavalkar, Haozhe Shan, Zhong Meng, Dongseong Hwang, Qiujia Li, Khe Chai Sim, Bo Li, James Qin, Xingyu Cai, Adam Stooke, Chengjian Zheng, Yanzhang He, Tara Sainath, Pedro Moreno Mengibar

Chinese SimpleQA: A Chinese Factuality Evaluation for Large Language Models (2025.acl-long)

Challenge:	Using the neural architecture of Google’s universal speech model, we reduce the frame rate and speed up training and inference.
Approach:	They propose to use the neural architecture of Google’s universal speech model with additional funnel pooling layers to significantly reduce the frame rate and speed up training and inference.
Outcome:	The proposed methods work with both connectionist temporal classification (CTC) and RNN-Transducer (RNN-T) and over two domains.

Copied to clipboard

Yancheng He, Shilong Li, Jiaheng Liu, Yingshui Tan, Weixun Wang, Hui Huang, Xingyuan Bu, Hangyu Guo, Chengwei Hu, Boren Zheng, Zhuoran Lin, Dekai Sun, Zhicheng Zheng, Wenbo Su, Bo Zheng

mABC: Multi-Agent Blockchain-inspired Collaboration for Root Cause Analysis in Micro-Services Architecture (2024.findings-emnlp)

Challenge:	Current frontier models sometimes generate false outputs or answers that are not substantiated by evidence.
Approach:	They propose Chinese SimpleQA, a Chinese benchmark to evaluate LLMs' factuality . they focus on Chinese language over 6 major topics with 99 diverse subtopics .
Outcome:	The Chinese SimpleQA benchmark evaluates the factuality ability of LLMs . the questions and answers are short and easy-to-evaluate .

Copied to clipboard

Wei Zhang, Hongcheng Guo, Jian Yang, Zhoujin Tian, Yi Zhang, Yan Chaoran, Zhoujun Li, Tongliang Li, Xu Shi, Liangfan Zheng, Bo Zhang

Consistency Regularization for Cross-Lingual Fine-Tuning (2021.acl-long)

Challenge:	Root cause analysis (RCA) in Micro-services architectures with escalating complexity is challenging due to fault propagation and circular dependencies among nodes.
Approach:	They propose a framework where multiple agents follow Agent Workflow and collaborate in blockchain-inspired voting to ensure the reliability of root cause analysis.
Outcome:	The proposed framework reduces the number of steps and standardizes task processing through Agent Workflow.

Copied to clipboard

Bo Zheng, Li Dong, Shaohan Huang, Wenhui Wang, Zewen Chi, Saksham Singhal, Wanxiang Che, Ting Liu, Xia Song, Furu Wei

Multilinguality

Challenge:	Experimental results show that consistency regularization improves cross-lingual fine-tuning . pre-trained cross-linguistic models can transfer task-specific supervision from one language to the other .
Approach:	They propose to improve cross-lingual fine-tuning with consistency regularization . they use example consistency regularized to penalize prediction sensitivity to four types of data augmentations .
Outcome:	The proposed method improves cross-lingual fine-tuning across tasks . it can be generalized to other target languages without additional training .

GuessArena: Guess Who I Am? A Self-Adaptive Framework for Evaluating LLMs in Domain-Specific Knowledge and Reasoning (2025.acl-long)

Copied to clipboard

Qingchen Yu, Zifan Zheng, Ding Chen, Simin Niu, Bo Tang, Feiyu Xiong, Zhiyu Li

Document Modeling with Graph Attention Networks for Multi-grained Machine Reading Comprehension (2020.acl-main)

Challenge:	Existing evaluation methods for large language models rely on static benchmarks and standardized evaluation protocols.
Approach:	They propose an adaptive evaluation framework that integrates dynamic domain knowledge modeling with progressive reasoning assessment to improve evaluation fidelity.
Outcome:	Empirical results show that the framework distinguishes LLMs in terms of domain knowledge coverage and reasoning chain completeness.

Copied to clipboard

Bo Zheng, Haoyang Wen, Yaobo Liang, Nan Duan, Wanxiang Che, Daxin Jiang, Ming Zhou, Ting Liu

Improving Pretrained Cross-Lingual Language Models via Self-Labeled Word Alignment (2021.acl-long)

Challenge:	Existing approaches to machine reading comprehension treat documents at their hierarchical nature, ignoring their dependencies.
Approach:	They propose a machine reading comprehension benchmark with two-grained answers . they use graph attention networks to model documents at their hierarchical nature .
Outcome:	The proposed framework outperforms existing systems at long and short answer criteria.

Copied to clipboard

Zewen Chi, Li Dong, Bo Zheng, Shaohan Huang, Xian-Ling Mao, Heyan Huang, Furu Wei

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

Challenge:	Experimental results show that denoising word alignment improves cross-lingual transferability . most applications and resources are still English-centric, making non-English users hard to access.
Approach:	They propose to denoise word alignment as a cross-lingual pre-training task . they first self-label word alignments for parallel sentences and then mask tokens .
Outcome:	The proposed model improves cross-lingual transferability on token-level tasks, especially on question answering, and structured prediction.

Copied to clipboard

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

ConceptMath: A Bilingual Concept-wise Benchmark for Measuring Mathematical Reasoning of Large Language Models (2024.findings-acl)

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

Copied to clipboard

Yanan Wu, Jie Liu, Xingyuan Bu, Jiaheng Liu, Zhanhui Zhou, Yuanxing Zhang, Chenchen Zhang, ZhiqiBai ZhiqiBai, Haibin Chen, Tiezheng Ge, Wanli Ouyang, Wenbo Su, Bo Zheng

CORN: Co-Reasoning Network for Commonsense Question Answering (2022.coling-1)

Challenge:	ConceptMath evaluates concept-wise mathematical reasoning of Large Language Models (LLMs) Existing benchmarks that evaluate general mathematical reasoning with an average accuracy fail to probe the fine-grained failure modes of mathematical reasoning on specific datasets.
Approach:	They introduce a bilingual, fine-grained benchmark that evaluates concept-wise mathematical reasoning of Large Language Models.
Outcome:	The proposed benchmarks evaluate concept-wise mathematical reasoning of Large Language Models with concept-based accuracies.

Copied to clipboard

Xin Guan, Biwei Cao, Qingqing Gao, Zheng Yin, Bo Liu, Jiuxin Cao

M2RC-EVAL: Massively Multilingual Repository-level Code Completion Evaluation (2025.acl-long)

Challenge:	Existing work uses two independent modules to model QA content and external commonsense knowledge graph (KG) Existing research uses two separate modules to create QA contextual text representations and relationships between QA entities.
Approach:	They propose a commonsense question answering (QA) model that uses two independent modules to model QA contextual text representation and relationships between QA entities in KG.
Outcome:	The proposed model achieves state-of-the-art on QA benchmarks in the CommonsenseQA and OpenBookQA datasets.

Copied to clipboard

Jiaheng Liu, Ken Deng, Congnan Liu, Jian Yang, Shukai Liu, He Zhu, Peng Zhao, Linzheng Chai, Yanan Wu, JinKe JinKe, Ge Zhang, Zekun Moore Wang, Guoan Zhang, Yingshui Tan, Bangyu Xiang, Zhaoxiang Zhang, Wenbo Su, Bo Zheng

Programming Languages in NLP

Challenge:	Existing repository-level code completion benchmarks focus on a limited number of languages . existing benchmarks report overall average scores of different languages ignoring fine-grained abilities .
Approach:	They propose to use repository-level code completion benchmarks to evaluate general code intelligence abilities across languages for existing code Large Language Models.
Outcome:	The proposed benchmarks improve the code completion abilities of existing LLMs by using two types of annotations on the parsed syntax tree.

MT-Bench-101: A Fine-Grained Benchmark for Evaluating Large Language Models in Multi-Turn Dialogues (2024.acl-long)

Copied to clipboard

Ge Bai, Jie Liu, Xingyuan Bu, Yancheng He, Jiaheng Liu, Zhanhui Zhou, Zhuoran Lin, Wenbo Su, Tiezheng Ge, Bo Zheng, Wanli Ouyang

Natural Language Interfaces

Challenge:	Large Language Models (LLMs) have greatly enhanced dialogue systems, but evaluation of their capabilities remains a challenge.
Approach:	They propose a model to evaluate the fine-grained abilities of Large Language Models in multi-turn dialogues.
Outcome:	The proposed model evaluates 21 popular chatbots based on MT-Bench-101 . it includes 3 overarching abilities and 13 distinct tasks within multi-turn dialogue scenarios.

GraphReader: Building Graph-based Agent to Enhance Long-Context Abilities of Large Language Models (2024.findings-emnlp)

Copied to clipboard

Shilong Li, Yancheng He, Hangyu Guo, Xingyuan Bu, Ge Bai, Jie Liu, Jiaheng Liu, Xingwei Qu, Yangguang Li, Wanli Ouyang, Wenbo Su, Bo Zheng

GraphNarrator: Generating Textual Explanations for Graph Neural Networks (2025.acl-long)

Challenge:	Existing models for long contexts struggle to handle long inputs due to limited context window and memory usage.
Approach:	They propose a graph-based agent system that analyzes long texts into a graphical graph . GraphReader consistently outperforms GPT-4-128k across context lengths from 16k to 256k .
Outcome:	The proposed model outperforms existing models on four challenging benchmarks.

Copied to clipboard

Bo Pan, Zhen Xiong, Guanchen Wu, Zheng Zhang, Yifei Zhang, Yuntong Hu, Liang Zhao

VC4VG: Optimizing Video Captions for Text-to-Video Generation (2025.emnlp-main)

Challenge:	Graph representation learning has garnered significant attention due to its broad applications in various domains, such as recommendation systems and social network analysis.
Approach:	They propose to use a generative language model to map input-output pairs to explanations reflecting the model’s decision-making process to generate a model that generates pseudo-labels that capture the model's decisions from saliency-based explanations.
Outcome:	Extensive experiments show that GraphNarrator produces human-preferred explanations that are faithful, concise, and human-like.

Copied to clipboard

Yang Du, Zhuoran Lin, Kaiqiang Song, Biao Wang, Zhicheng Zheng, Tiezheng Ge, Bo Zheng, Qin Jin

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

Challenge:	Recent advances in text-to-video generation highlight the critical role of high-quality video-text pairs in training models capable of producing coherent and instruction-aligned videos.
Approach:	They propose a caption optimization framework tailored to the needs of T2V models.
Outcome:	The proposed framework improves video caption quality and video generation performance.

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

Cache-of-Thought: Master-Apprentice Framework for Cost-Effective Vision Language Model Reasoning (2025.emnlp-main)

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

Mingyuan Wu, Jize Jiang, Haozhen Zheng, Meitang Li, Zhaoheng Li, Beitong Tian, Bo Chen, Yongjoo Park, Minjia Zhang, ChengXiang Zhai, Klara Nahrstedt

ProgCo: Program Helps Self-Correction of Large Language Models (2025.acl-short)

Challenge:	Recent Vision Language Models (VLMs) have shown tremendous promise in a wide range of realworld applications, but their size has made at-scale deployment and operation challenging due to high consumption of cloud computing resource, high latency, and expensive API calls.
Approach:	They propose a master–apprentice framework for collaborative inference between large and small vision language models.
Outcome:	The proposed framework improves reasoning performance on widely-recognized and challenging general reasoning benchmarks and specifically boosts reasoning of apprentice VLMs by 36.6%.

Copied to clipboard

Xiaoshuai Song, Yanan Wu, Weixun Wang, Jiaheng Liu, Wenbo Su, Bo Zheng

Improving Robustness of GNN-based Anomaly Detection by Graph Adversarial Training (2024.lrec-main)

Challenge:	Existing LLMs fail to self-correct and generate correct feedback, leading to misleading refinement and failure of self-refinement.
Approach:	They propose a program-driven self-correction approach that uses program-based verification to self-refine initial responses without external feedback.
Outcome:	The proposed model achieves self-correction and can be further enhanced when combined with real program tools.

Copied to clipboard

Xiangping Zheng, Bo Wu, Alex X. Zhang, Wei Li

Hypergraph-Based Session Modeling: A Multi-Collaborative Self-Supervised Approach for Enhanced Recommender Systems (2024.lrec-main)

Challenge:	Graph neural networks excel at anomaly detection, but exhibit vulnerability to attacks . novel mechanism for graph adversarial training designed to bolster anomaly detectors .
Approach:	They propose a mechanism for graph adversarial training to bolster anomaly detection systems against potential poisoning attacks.
Outcome:	The proposed method bolsters GNN-based anomaly detection systems against poisoning attacks.

Copied to clipboard

Xiangping Zheng, Bo Wu, Alex X. Zhang, Wei Li

Can Large Language Models Detect Errors in Long Chain-of-Thought Reasoning? (2025.acl-long)

Challenge:	Presently, graph-based recommendations are limited by session dependencies and data sparsity in real-world scenarios.
Approach:	They propose a method which uses multi-collaborative self-supervised learning in hypergraph neural networks to model item transitions and to mitigate the challenges of data sparsity.
Outcome:	The proposed method outperforms existing methods in a number of domains and consistently outperformed existing methods.

Copied to clipboard

Yancheng He, Shilong Li, Jiaheng Liu, Weixun Wang, Xingyuan Bu, Ge Zhang, Z.y. Peng, Zhaoxiang Zhang, Zhicheng Zheng, Wenbo Su, Bo Zheng

Profanity-Avoiding Training Framework for Seq2seq Models with Certified Robustness (2021.emnlp-main)

Challenge:	Recent advances in o1-like models have generated long Chain-of-Thought reasoning steps to improve the reasoning abilities of existing Large Language Models (LLMs).
Approach:	They propose a DeltaBench to analyze the quality and effectiveness of o1-like models and measure their ability to detect errors in long COT reasoning.
Outcome:	The proposed model can detect errors in long COT reasoning.

Copied to clipboard

Hengtong Zhang, Tianhang Zheng, Yaliang Li, Jing Gao, Lu Su, Bo Li

Robustness in NLP

Challenge:	a recent study shows that inappropriate language can cause models to output profanity . authors propose a training framework to prevent such outputs from hurting the usability of models .
Approach:	proposed training framework eliminates the causes that trigger the generation of profanity . authors propose a framework that leverages a short list of profans to prevent this .
Outcome:	a proposed training framework can prevent models from generating profanity . the proposed framework leverages a short list of profanities examples .

Mobile-R1: Towards Interactive Capability for VLM-Based Mobile Agent via Systematic Training (2026.acl-long)

Copied to clipboard

Jihao Gu, Qihang Ai, Yingyao Wang, Pi Bu, Jingxuan Xing, Yue Cao, Zekun Zhu, Wei Jiang, Ziming Wang, Yingxiu Zhao, Ming-Liang Zhang, Jun Song, Yuning Jiang, Bo Zheng