Papers by Bo Zhu

MACS: Modality-Aware Capacity Scaling for Efficient Multimodal MoE Inference (2026.acl-long)

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

Bo Li, Chuan Wu, Shaolin Zhu

Syntax-guided Localized Self-attention by Constituency Syntactic Distance (2022.findings-emnlp)

Challenge:	Existing methods for expert parallelism inference suffer from a significant efficiency bottleneck . existing methods fail to address information heterogeneity and modality dynamics .
Approach:	They propose a training-free inference framework that scales experts without training . they propose an Entropy-Weighted Load mechanism to quantify the semantic value of visual tokens .
Outcome:	Experiments show that MACS outperforms existing methods on multimodal benchmarks.

Copied to clipboard

Shengyuan Hou, Jushi Kai, Haotian Xue, Bingyu Zhu, Bo Yuan, Longtao Huang, Xinbing Wang, Zhouhan Lin

Zero-shot Sharpness-Aware Quantization for Pre-trained Language Models (2023.emnlp-main)

Challenge:	Recent studies have shown that Transformers is implicitly learning syntactic information from data, albeit is highly dependent on the quality and scale of the training data.
Approach:	They propose a syntax-guided localized self-attention model that allows directly incorporating grammar structures from an external constituency parser.
Outcome:	The proposed model improves translation performance on a variety of datasets, from small to large datasets and with different source languages.

Copied to clipboard

Miaoxi Zhu, Qihuang Zhong, Li Shen, Liang Ding, Juhua Liu, Bo Du, Dacheng Tao

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

Challenge:	Existing zero-shot quantization methods are based on overfitting problem in adversarial learning process, leading to sub-optimal performance.
Approach:	They propose a zero-shot sharpness-aware quantization framework for the quantization of various PLMs by optimizing a minimax problem.
Outcome:	The proposed framework can achieve significant performance gains on discriminative and generative PLMs.

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

RWKV: Reinventing RNNs for the Transformer Era (2023.findings-emnlp)

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

Bo Peng, Eric Alcaide, Quentin Anthony, Alon Albalak, Samuel Arcadinho, Stella Biderman, Huanqi Cao, Xin Cheng, Michael Chung, Leon Derczynski, Xingjian Du, Matteo Grella, Kranthi Gv, Xuzheng He, Haowen Hou, Przemyslaw Kazienko, Jan Kocon, Jiaming Kong, Bartłomiej Koptyra, Hayden Lau, Jiaju Lin, Krishna Sri Ipsit Mantri, Ferdinand Mom, Atsushi Saito, Guangyu Song, Xiangru Tang, Johan Wind, Stanisław Woźniak, Zhenyuan Zhang, Qinghua Zhou, Jian Zhu, Rui-Jie Zhu

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

Challenge:	recurrent neural networks struggle to match the performance of Transformers due to limitations in parallelization and scalability.
Approach:	They propose a model architecture that combines the efficient parallelizable training of transformers with the efficient inference of RNNs.
Outcome:	The proposed model performs on par with similarly sized RNNs, suggesting future work can leverage this architecture to create more efficient models.

Copied to clipboard

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

IFlyEA: A Chinese Essay Assessment System with Automated Rating, Review Generation, and Recommendation (2021.acl-demo)

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

Jiefu Gong, Xiao Hu, Wei Song, Ruiji Fu, Zhichao Sheng, Bo Zhu, Shijin Wang, Ting Liu

GeoLaux: A Benchmark for Evaluating MLLMs’ Geometry Performance on Long-Step Problems Requiring Auxiliary Lines (2026.acl-long)

Challenge:	Automated Essay Assessment (AEA) aims to judge students’ writing proficiency in an automatic way.
Approach:	They propose to use Chinese AEA system IFlyEssayAssess to evaluate essays written by native Chinese students from primary and junior schools.
Outcome:	The proposed system provides application services for essay scoring, review generation, recommendation, and explainable analytical visualization.

Copied to clipboard

Yumeng Fu, Jiayin Zhu, Lingling Zhang, Wenjun Wu, Bo Zhao, Shaoxuan Ma, Yushun Zhang, Jun Liu

Reasoning

Challenge:	Existing benchmarks for Geometry problem solving lack fine-grained evaluation for long-step problems necessitating auxiliary line construction.
Approach:	They present a fine-grained annotated dataset with long-step reasoning and auxiliary line construction that provides a detailed evaluation of 23 leading MLLMs.
Outcome:	The proposed model performs significantly worse on long-step problems than short-step ones, with 18 models showing a performance drop of over 50%.

Beyond Instructional Videos: Probing for More Diverse Visual-Textual Grounding on YouTube (2020.emnlp-main)

Copied to clipboard

Jack Hessel, Zhenhai Zhu, Bo Pang, Radu Soricut

Re-ViLM: Retrieval-Augmented Visual Language Model for Zero and Few-Shot Image Captioning (2023.findings-emnlp)

Challenge:	a representative pretraining model is fit to a diverse YouTube8M dataset . a priori, this domain is relatively easy for instructional videos .
Approach:	They fit a representative pretraining model to a YouTube8M dataset and examine its success and failure cases.
Outcome:	The proposed model can be trained on more diverse video corpora and achieve high performance on many video understanding tasks.

Copied to clipboard

Zhuolin Yang, Wei Ping, Zihan Liu, Vijay Korthikanti, Weili Nie, De-An Huang, Linxi Fan, Zhiding Yu, Shiyi Lan, Bo Li, Mohammad Shoeybi, Ming-Yu Liu, Yuke Zhu, Bryan Catanzaro, Chaowei Xiao, Anima Anandkumar

FastMem: Fast Memorization of Prompt Improves Context Awareness of Large Language Models (2024.findings-emnlp)

Challenge:	Existing methods for image-to-text generation store all knowledge within parameters, thus requiring computational-expensive fine-tuning.
Approach:	They propose a Retrieval-augmented Visual Language Model that stores all the knowledge within parameters and can be used to retrieve it from the external database.
Outcome:	The proposed model significantly boosts performance for image-to-text generation tasks with 4x less parameters compared with baseline methods.

Copied to clipboard

Junyi Zhu, Shuochen Liu, Yu Yu, Bo Tang, Yibo Yan, Zhiyu Li, Feiyu Xiong, Tong Xu, Matthew Blaschko

End-to-end Dense Video Captioning as Sequence Generation (2022.coling-1)

Challenge:	Large language models struggle with context awareness, leading to inaccuracies in tasks requiring faithful adherence to provided information.
Approach:	They propose a method to enhance LLMs' context awareness by updating only the last Feed-Forward Network module to maximize the likelihood of the prompt before inference .
Outcome:	The proposed method improves the accuracy of Llama 3-8B-Inst on the NQ-SWAP dataset from 59.1% to 71.6% and reduces the output structure failure rate of Qwen 1.5-4B-Chat from 34.9% to 25.5%.

Copied to clipboard

Wanrong Zhu, Bo Pang, Ashish V. Thapliyal, William Yang Wang, Radu Soricut

Unifying Inference-Time Planning Language Generation (2026.findings-acl)

Challenge:	Existing methods for dense video captioning use a two-stage generative process . but, more complex tasks are not able to fully utilize this powerful paradigm .
Approach:	They propose to model two subtasks of dense video captioning as one sequence generation task and predict the events and the corresponding descriptions.
Outcome:	Experiments on YouCook2 and ViTT show that the proposed model can be used on any video platform.

Copied to clipboard

Prabhu Prakash Kagitha, Bo Sun, Ishan Desai, Andrew Zhu, Cassie Huang, Manling Li, Ziyang Li, Li Zhang

Text Generation

Challenge:	Large language models (LLMs) are used to generate a formal representation of a plan in a planning language.
Approach:	They propose a unifying organizational framework based on intermediate representations to unify the inference-time LLM-as-formalizer methodology for classical planning.
Outcome:	The proposed framework subsumes most existing work and proposes new ones that involve syntactically similar but high-resource intermediate languages.

Masks Can be Learned as an Alternative to Experts (2025.acl-long)

Copied to clipboard

Peiyu Liu, Tianwen Wei, Bo Zhu, Xin Zhao, Shuicheng Yan

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

Challenge:	a recent study shows that sparse activation techniques can reduce inference performance without sacrificing performance.
Approach:	They propose to sparsify a pre-trained dense large language model into a mixture-of-experts architecture for faster inference.
Outcome:	The proposed approach is more efficient than one-shot sparsification techniques . it achieves 97% performance retention on downstream tasks with only 50% of parameters activated .

Copied to clipboard

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

Reasoning

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.

MIT-10M: A Large Scale Parallel Corpus of Multilingual Image Translation (2025.coling-main)

Copied to clipboard

Bo Li, Shaolin Zhu, Lijie Wen

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

Challenge:	Existing datasets suffer from limitations in scale, diversity, and quality, hindering the development and evaluation of IT models.
Approach:	They propose a large-scale parallel corpus of multilingual image translation with over 10M image-text pairs derived from real-world data.
Outcome:	The proposed model performs better in tackling challenging and complex image translation tasks in the real world.

Copied to clipboard

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

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

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

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

Marco-Bench-MIF: On Multilingual Instruction-Following Capability of Large Language (2025.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

Bo Zeng, Chenyang Lyu, Sinuo Liu, Mingyan Zeng, Minghao Wu, Xuanfan Ni, Tianqi Shi, Yu Zhao, Yefeng Liu, Chenyu Zhu, Ruizhe Li, Jiahui Geng, Qing Li, Yu Tong, Longyue Wang, Weihua Luo, Kaifu Zhang

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

Challenge:	Existing datasets for instruction-following are monolingual and centered on English . existing data are unable to capture linguistic and cultural subtle differences .
Approach:	They propose an extension of IFEval to a localized multilingual version called Marco-Bench-MIF . their benchmark addresses linguistic constraints and cultural references via translation and verification .
Outcome:	The proposed extension of IFEval to a localized multilingual version covers 30 languages with varying levels of localization.

Copied to clipboard

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

M³GQA: A Multi-Entity Multi-Hop Multi-Setting Graph Question Answering Benchmark (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

Boci Peng, Yongchao Liu, Xiaohe Bo, Jiaxin Guo, Yun Zhu, Xuanbo Fan, Chuntao Hong, Yan Zhang

Responsible & Trustworthy NLP

Challenge:	GraphRAG systems have achieved remarkable progress in enhancing performance and reliability of large language models.
Approach:	They propose a GraphRAG benchmark focusing on multi-entity queries with six settings for comprehensive evaluation.
Outcome:	The proposed method can construct diverse data with semantically correct ground-truth reasoning paths.

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

Copied to clipboard

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

Attribution-Based Analysis and Optimization of Modular Agentic Workflows (2026.findings-acl)

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

Yingxuan Yang, Bo Huang, Siyuan Qi, Chao Feng, Haoyi Hu, Yuxuan Zhu, Jinbo Hu, Haoran Zhao, Ziyi He, Xiao Liu, ZongYu Wang, Muning Wen, Lin Qiu, Xuezhi Cao, Xunliang Cai, Yong Yu, Weinan Zhang

Challenge:	Large Language Models (LLMs) have driven the rise of agentic workflows . yet, how can we attribute performance gains to individual upgrades and their interactions?
Approach:	They propose a game-theoretic framework that models component upgrades as players and evaluates component coalitions to compute Shapley values.
Outcome:	The proposed framework provides interaction-aware attribution and recommendation for model allocation under a fixed workflow structure.

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

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

Conformalized Answer Set Prediction for Knowledge Graph Embedding (2025.naacl-long)

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

Yuqicheng Zhu, Nico Potyka, Jiarong Pan, Bo Xiong, Yunjie He, Evgeny Kharlamov, Steffen Staab

SCCS: Semantics-Consistent Cross-domain Summarization via Optimal Transport Alignment (2023.findings-acl)

Challenge:	Knowledge graph embeddings (KGE) map entities and predicates into numerical vectors, providing non-classical reasoning capabilities based on similarities and analogies between entities and relations.
Approach:	They propose to use knowledge graph embeddings to provide non-classical reasoning capabilities by exploiting similarities and analogies between entities and relations.
Outcome:	The proposed model can generate answer sets with probabilistic guarantees on four benchmark datasets and is scaled well with respect to the difficulty of the query.

Copied to clipboard

Jielin Qiu, Jiacheng Zhu, Mengdi Xu, Franck Dernoncourt, Trung Bui, Zhaowen Wang, Bo Li, Ding Zhao, Hailin Jin

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

Challenge:	Existing methods for multimodal summarization ignore the structure and semantics of the whole video and article.
Approach:	They propose a semantic-consistent cross-domain summarization model that extracts features from video and article and uses fusion methods to select representative one.
Outcome:	The proposed model produces high-quality multimodal summaries on three MSMO datasets.

Copied to clipboard

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

Intent Contrastive Learning Based on Multi-view Augmentation for Sequential Recommendation (2025.coling-main)

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

Bo Pei, Yingzheng Zhu, Guangjin Wang, Huajuan Duan, Wenya Wu, Fuyong Xu, Yizhao Zhu, Peiyu Liu, Ran Lu

AMA: Adaptive Memory via Multi-Agent Collaboration (2026.findings-acl)

Challenge:	Existing work on intent-related models fails to capture long-term dependencies in user behavior and fails to effectively utilize item relevance.
Approach:	They propose a sequential recommendation framework that combine temporal variability with position encoding that has extrapolation properties to encode sequences, thereby expanding the model’s view of user behavior.
Outcome:	The proposed model improves on three real datasets by 0.8% to 14.7% compared to baselines.

Copied to clipboard

Weiquan Huang, Zixuan Wang, Hehai Lin, Sudong Wang, Bo Xu, Qian Li, Beier Zhu, Linyi Yang, Chengwei Qin

Information Retrieval

Challenge:	Existing approaches to longterm memory rely on rigid retrieval granularity, accumulation-heavy maintenance strategies, and coarse-grained update mechanisms.
Approach:	They propose a framework that leverages coordinated agents to manage memory across multiple granularities.
Outcome:	The proposed framework outperforms state-of-the-art benchmarks while reducing token consumption by approximately 80%.

Multimodal Pretraining for Dense Video Captioning (2020.aacl-main)

Copied to clipboard

Gabriel Huang, Bo Pang, Zhenhai Zhu, Clara Rivera, Radu Soricut

LANDeRMT: Dectecting and Routing Language-Aware Neurons for Selectively Finetuning LLMs to Machine Translation (2024.acl-long)

Challenge:	a billion hours of videos are being watched on YouTube every day . videos are difficult to skim through, making it harder to quickly target the relevant part(s) of a video.
Approach:	They propose to use a video timeline tag dataset to generate time-stamped annotations for videos . they propose to pretrain and finetune captioning models using YouCook2 and ViTT .
Outcome:	The proposed model generalizes well and is robust over a wide variety of instructional videos.

Copied to clipboard

Shaolin Zhu, Leiyu Pan, Bo Li, Deyi Xiong

Text Detoxification: Data Efficiency, Semantic Preservation and Model Generalization (2025.emnlp-main)

Challenge:	Existing studies have shown promising results in multilingual translation with limited bilingual supervision.
Approach:	They propose a Language-Aware Neuron Detecting and Routing framework that fine tunes LLMs to Machine Translation with diverse translation training data.
Outcome:	The proposed framework selectively finetunes LLMs to MT tasks with diverse translation training data.

Copied to clipboard

Jing Yu, Yibo Zhao, Jiapeng Zhu, Wenming Shao, Bo Pang, Zhao Zhang, Xiang Li

Responsible & Trustworthy NLP

Challenge:	Existing methods for detoxification of text often rely on manually annotated data . xiangli: "detoxification of texts is a powerful way to remove toxic content"
Approach:	They propose a reinforcement learning framework that optimizes detoxification and semantic preservation without annotating large amounts of data.
Outcome:	The proposed method overcomes major limitations and surpasses humanannotated references across multiple benchmarks.

IGenBench: Benchmarking the Reliability of Text-to-Infographic Generation (2026.acl-long)

Copied to clipboard

Yinghao Tang, Xueding Liu, Boyuan Zhang, Tingfeng Lan, Yupeng Xie, Jiale Lao, Yiyao Wang, Haoxuan Li, Tingting Gao, Bo Pan, Luoxuan Weng, Xiuqi Huang, Minfeng Zhu, Yingchaojie Feng, Yuyu Luo, Wei Chen

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

Challenge:	Generated infographics may appear correct at first glance but contain easily overlooked issues, such as distorted data encoding or incorrect textual content.
Approach:	They propose to evaluate reliability of text-to-infographic generation using IGenBench . they employ multimodal large language models to verify each question .
Outcome:	The proposed framework decomposes reliability verification into atomic yes/no questions based on a taxonomy of 10 question types.

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

Reasoning

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.

Adversarial Preference Learning for Robust LLM Alignment (2025.findings-acl)

Copied to clipboard

Yuanfu Wang, Pengyu Wang, Chenyang Xi, Bo Tang, Junyi Zhu, Wenqiang Wei, Chen Chen, Chao Yang, Jingfeng Zhang, Chaochao Lu, Yijun Niu, Keming Mao, Zhiyu Li, Feiyu Xiong, Jie Hu, Mingchuan Yang

Responsible & Trustworthy NLP

Challenge:	Modern language models rely on Reinforcement Learning from Human Feedback (RLHF) to encourage safe behaviors, but they remain vulnerable to adversarial attacks due to three key limitations: (1) the inefficiency and high cost of human annotation; (2) the vast diversity of potential adversarials; and (3) the risk of feedback bias and reward hacking.
Approach:	They propose an iterative adversarial training method that incorporates three key innovations to address these challenges.
Outcome:	Experiments on Mistral-7B-Instruct-v0.3 show that the proposed method significantly enhances robustness and reduces harmful outputs from 5.88% to 0.43%.

Predictive Multiplicity of Knowledge Graph Embeddings in Link Prediction (2024.findings-emnlp)

Copied to clipboard

Yuqicheng Zhu, Nico Potyka, Mojtaba Nayyeri, Bo Xiong, Yunjie He, Evgeny Kharlamov, Steffen Staab

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

Challenge:	Knowledge graph embeddings (KGE) models are often used to predict missing links for knowledge graphs (KGs) however, multiple KG embedds can give conflicting predictions for unseen queries.
Approach:	They define predictive multiplicity in link prediction and introduce evaluation metrics to measure it using commonly used benchmark datasets.
Outcome:	The proposed methods significantly mitigat conflicts by 66% to 78% in link prediction.

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.

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

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

Knowledge Representation Learning with Contrastive Completion Coding (2021.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

Bo Ouyang, Wenbing Huang, Runfa Chen, Zhixing Tan, Yang Liu, Maosong Sun, Jihong Zhu

On Domain-Adaptive Post-Training for Multimodal Large Language Models (2025.findings-emnlp)

Challenge:	Existing knowledge representation learning methods suffer from immaturity on tackling potentially-imperfect knowledge graphs and highly-imbalanced positive-negative instances during training.
Approach:	They propose a framework for knowledge representation learning that incorporates two functional components to achieve robust embedding for each entity/relation.
Outcome:	The proposed framework achieves better convergence against state-of-the-art methods on several benchmarks.

Copied to clipboard

Daixuan Cheng, Shaohan Huang, Ziyu Zhu, Xintong Zhang, Xin Zhao, Zhongzhi Luan, Bo Dai, Zhenliang Zhang

Naive Bayes-based Context Extension for Large Language Models (2024.naacl-long)

Challenge:	Adapting general multimodal large language models to specific domains is important for practical applications.
Approach:	They investigate domain adaptation of multimodal large language models via post-training . they develop a generate-then-filter pipeline that curates diverse visual instruction tasks .
Outcome:	The proposed model outperforms existing models in domain adaptation by combining data from open-source models with training pipelines.

Copied to clipboard

Jianlin Su, Murtadha Ahmed, Bo Wen, Luo Ao, Mingren Zhu, Yunfeng Liu

Noise Learning for Text Classification: A Benchmark (2022.coling-1)

Challenge:	Large Language Models (LLMs) have shown promising in-context learning abilities, but are often impeded by length limitations of transformer architecture.
Approach:	They propose a framework to enable existing Large Language Models to perform ICL with an increased number of demonstration examples by significantly expanding their context size.
Outcome:	The proposed framework outperforms existing methods in in-context learning with an increased number of demonstration examples while preserving linear efficiency.

Copied to clipboard

Bo Liu, Wandi Xu, Yuejia Xiang, Xiaojun Wu, Lejian He, Bowen Zhang, Li Zhu

Information Extraction & Text Mining

Challenge:	Existing noise learning methods for text classification are underdeveloped . authors propose a noise learning benchmark for text classification .
Approach:	They propose to use four state-of-the-art methods of noise learning from the image domain to classify text.
Outcome:	The proposed benchmark of noise learning for text classification is based on four methods and five noise modes.

Copied to clipboard

Guangwei Zhang, Jianing Zhu, Cheng Qian, Neil Zhenqiang Gong, Rada Mihalcea, Zhaozhuo Xu, Jingrui He, Jiaqi W. Ma, Chaowei Xiao, Bo Li, Ahmed Abbasi, Dongwon Lee, Heng Ji, Denghui Zhang

Paraphrasing

Challenge:	Copyright Detective is the first interactive forensic system for detecting, analyzing, and visualizing potential copyright risks in LLM outputs.
Approach:	They propose a system that detects copyright infringements and visualizes them . they use content recall testing, paraphrase-level similarity analysis and persuasive jailbreak probing .
Outcome:	The proposed system detects, analyzes, and visualizes potential copyright risks in LLM outputs.

Point, Disambiguate and Copy: Incorporating Bilingual Dictionaries for Neural Machine Translation (2021.acl-long)

Copied to clipboard

Tong Zhang, Long Zhang, Wei Ye, Bo Li, Jinan Sun, Xiaoyu Zhu, Wen Zhao, Shikun Zhang

Predicate-Conditional Conformalized Answer Sets for Knowledge Graph Embeddings (2025.findings-acl)

Challenge:	Existing approaches to incorporate bilingual dictionaries into Neural Machine Translation (NMT) models have been criticized for lack of integration of bilingual lexical information into the neural architecture.
Approach:	They propose a neural architecture to incorporate bilingual dictionaries into Neural Machine Translation models by introducing three new components: Pointer, Disambiguator, and Copier.
Outcome:	The proposed method achieves the following merits inherently compared with previous efforts: (1) Pointer leverages the semantic information from bilingual dictionaries, for the first time, to better locate source words whose translation in dictionary can potentially be used; (2) Disambiguator synthesizes contextual information from source view and target view, both of which contribute to distinguishing translation of a specific source word from multiple candidates in dicaries; (3) Copier systematically connects Pointer and Disambiguators based on a hierarchical

Copied to clipboard

Yuqicheng Zhu, Daniel Hernández, Yuan He, Zifeng Ding, Bo Xiong, Evgeny Kharlamov, Steffen Staab

Intention Knowledge Graph Construction for User Intention Relation Modeling (2026.eacl-long)

Challenge:	Existing methods provide probabilistic guarantees over a reference set of queries and answers, but they fail to identify when the answers to a query are uncertain.
Approach:	They propose a method that approximates predicate-conditional coverage guarantees while maintaining compact prediction sets.
Outcome:	The proposed method provides predicate-conditional coverage guarantees while maintaining compact prediction sets.

Copied to clipboard

Jiaxin Bai, Zhaobo Wang, Junfei Cheng, Dan Yu, Zerui Huang, Weiqi Wang, Xin Liu, Chen Luo, Yanming Zhu, Bo Li, Yangqiu Song

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

Challenge:	Existing knowledge graphs focus on connecting intentions but lacks the ability to model the relationships between different intentions.
Approach:	They propose a framework to automatically generate an intention knowledge graph, capturing connections between user intentions.
Outcome:	The proposed model outperforms state-of-the-art methods and shows its utility.

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.

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

Can Brain Signals Reveal Inner Alignment with Human Languages? (2023.findings-emnlp)

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

Jielin Qiu, William Han, Jiacheng Zhu, Mengdi Xu, Douglas Weber, Bo Li, Ding Zhao

Sentiment Analysis

Challenge:	Brain Signals, such as Electroencephalography, and human languages have been explored independently for many downstream tasks, however, the connection between them has not been well explored.
Approach:	They introduce a multimodal transformer alignment model to observe coordinated representations between EEG and language.
Outcome:	The proposed method achieved an F1-score improvement of 1.7% on ZuCo and 9.3% on Zuco datasets for sentiment analysis, and 7.4% on ZuCO for relation detection.

MLAS-LoRA: Language-Aware Parameters Detection and LoRA-Based Knowledge Transfer for Multilingual Machine Translation (2025.acl-long)

Copied to clipboard

Tianyu Dong, Bo Li, Jinsong Liu, Shaolin Zhu, Deyi Xiong

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

Challenge:	Large language models (LLMs) have demonstrated strong performance even with limited parallel data.
Approach:	They propose a multiple language-aware LoRA knowledge transfer framework that selectively adapts LLMs to MT by transferring knowledge from a large teacher to a small student model.
Outcome:	The proposed framework outperforms baseline models on multilingual language pairs by +1.7 BLEU on average.

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