Papers by Xiao Zeng

Improving End-to-End Speech Processing by Efficient Text Data Utilization with Latent Synthesis (2023.findings-emnlp)

Challenge:	mainstream event argument extraction methods process each event in isolation, resulting in inefficient inference and ignoring correlations among multiple events.
Approach:	They propose a multi-event argument argument extraction model which extracts arguments from all events simultaneously.
Outcome:	The proposed model performs better on four public datasets while saving time.

Copied to clipboard

Jianqiao Lu, Wenyong Huang, Nianzu Zheng, Xingshan Zeng, Yu Yeung, Xiao Chen

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

Challenge:	Latent Synthesis is an efficient textual data utilization framework for end-to-end speech processing models . labeled speech data are scarcer and more expensive for collection compared to textual ones .
Approach:	They propose a textual data utilization framework for E2E speech processing models . they train a latent synthesizer to convert textual information into an intermediate latent representation .
Outcome:	The proposed framework improves on low-resource speech recognition and spoken language understanding tasks.

Copied to clipboard

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

The Confidence Dichotomy: Analyzing and Mitigating Miscalibration in Tool-Use Agents (2026.acl-long)

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

Copied to clipboard

Weihao Xuan, Qingcheng Zeng, Heli Qi, Yunze Xiao, Junjue Wang, Naoto Yokoya

Robustness in NLP

Challenge:	a fundamental pillar of trustworthiness is calibration, which refers to an agent’s ability to express confidence that reliably reflects its actual performance.
Approach:	They propose a reinforcement learning framework that jointly optimizes task accuracy and calibration, supported by a holistic benchmark of reward designs.
Outcome:	The proposed framework improves calibration across tool types and shows that trained agents achieve superior calibration and exhibit robust generalization from local training environments to noisy web settings and to distinct domains such as mathematical reasoning.

Cross-layer Attention Sharing for Pre-trained Large Language Models (2026.tacl-1)

Copied to clipboard

Yongyu Mu, Yuzhang Wu, Yuchun Fan, Chenglong Wang, Hengyu Li, Jiali Zeng, Qiaozhi He, Murun Yang, Fandong Meng, Jie Zhou, Tong Xiao, Jingbo Zhu

Fine-grained Video Dubbing Duration Alignment with Segment Supervised Preference Optimization (2025.acl-long)

Challenge:	Existing studies focus on compressing the Key-Value cache or grouping attention heads, while overlooking redundancy between layers.
Approach:	They propose a lightweight substitute for self-attention in well-trained LLMs that uses feed-forward networks to align attention heads between adjacent layers and low-rank matrices to approximate differences in layer-wise attention weights.
Outcome:	The proposed model reduces redundancy by sharing weights across layers while maintaining high response quality while reducing redundant calculations within 53% 84% of the total layers.

Copied to clipboard

Chaoqun Cui, Liangbin Huang, Shijing Wang, Zhe Tong, Zhaolong Huang, Xiao Zeng, Xiaofeng Liu

Revisiting Parallel Context Windows: A Frustratingly Simple Alternative and Chain-of-Thought Deterioration (2024.findings-acl)

Challenge:	Video dubbing systems use neural machine translation and text-to-speech technologies to translate original speech into visual media programs.
Approach:	They propose a preference optimization method to optimize video dubbing duration alignment . they propose combining segment-wise sampling and fine-grained loss to mitigate duration mismatches .
Outcome:	The proposed method achieves superior performance in duration alignment tasks.

Copied to clipboard

Kejuan Yang, Xiao Liu, Kaiwen Men, Aohan Zeng, Yuxiao Dong, Jie Tang

i-Code V2: An Autoregressive Generation Framework over Vision, Language, and Speech Data (2024.findings-naacl)

Challenge:	Existing methods for extending the maximum context lengths of language models are lacking a strong baseline for in-context few-shot classification and on more challenging Chain-of-Thought reasoning, such as HotpotQA, deteriorate question miscomprehension and false inference.
Approach:	They propose to harness window-wise attention and positional embedding techniques to extend the maximum context lengths of language models.
Outcome:	The proposed method is able to extend the maximum context lengths of language models, e.g., 2048 for LLaMA, by harnessing window-wise attention and positional embedding techniques.

Copied to clipboard

Ziyi Yang, Mahmoud Khademi, Yichong Xu, Reid Pryzant, Yuwei Fang, Chenguang Zhu, Dongdong Chen, Yao Qian, Xuemei Gao, Yi-Ling Chen, Robert Gmyr, Naoyuki Kanda, Noel Codella, Bin Xiao, Yu Shi, Lu Yuan, Takuya Yoshioka, Michael Zeng, Xuedong Huang

ProductResearch: Training E-Commerce Deep Research Agents via Multi-Agent Synthetic Trajectory Distillation (2026.acl-industry)

Challenge:	i-Code V2 is one of the first models capable of generating natural language from any combination of Vision, Language, and Speech data.
Approach:	They propose to create a model that can generate natural language from any combination of Vision, Language, and Speech data.
Outcome:	i-Code V2 matches or outperforms state-of-the-art single- and dual-modality baselines on 7 multimodal tasks.

Copied to clipboard

Jiangyuan Wang, Kejun Xiao, Huaipeng Zhao, Tao Luo, Xiaoyi Zeng

OctoBench: Benchmarking Scaffold-Aware Instruction Following in Repository-Grounded Agentic Coding (2026.acl-long)

Challenge:	Existing LLM-based agents lack the interaction depth and contextual breadth required for complex product research.
Approach:	They propose a multi-agent framework that synthesizes high-fidelity tool-use trajectories for training robust e-commerce shopping agents.
Outcome:	The proposed framework synthesizes high-fidelity, long-horizon tool-use trajectories for training robust e-commerce shopping agents.

Copied to clipboard

Deming Ding, Shichun Liu, Enhui Yang, Jiahang Lin, Ziying Chen, Shihan Dou, Honglin Guo, Weiyu Cheng, Pengyu Zhao, Chengjun Xiao, Qunhong Zeng, Qi Zhang, Xuanjing Huang, Qidi Xu, Tao Gui

Programming Languages in NLP

Challenge:	coding scaffolds that follow heterogeneous instructions remain under-examined in software engineering . coding models are capable software agents, but their ability to follow constraints remains under-explored .
Approach:	They introduce OctoBench, which benchmarks scaffold-aware instruction following in agentic coding.
Outcome:	The proposed benchmark aims to accelerate the development of more scaffold-aware agents.

Bridging the Granularity Gap for Acoustic Modeling (2023.findings-acl)

Copied to clipboard

Chen Xu, Yuhao Zhang, Chengbo Jiao, Xiaoqian Liu, Chi Hu, Xin Zeng, Tong Xiao, Anxiang Ma, Huizhen Wang, Jingbo Zhu

NUMINA: A Natural Understanding Benchmark for Multi-dimensional Intelligence and Numerical Reasoning Abilities (2025.findings-emnlp)

Challenge:	Despite the success of speech recognition, how to encode the speech features effectively remains an open problem.
Approach:	They propose a Progressive Down-Sampling technique which compresses acoustic features into coarser-grained units containing more complete semantic information, like text-level representation.
Outcome:	The proposed method yields comparable or better results on the speech recognition task and inference speedups ranging from 1.20x to 1.47x.

Copied to clipboard

Changyu Zeng, Yifan Wang, Zimu Wang, Wei Wang, Zhengni Yang, Muyi Bao, Jimin Xiao, Anh Nguyen, Yutao Yue

Tool Zero: Training Tool-Augmented LLMs via Pure RL from Scratch (2025.findings-emnlp)

Challenge:	Existing 3D benchmarks lack fine-grained numerical reasoning task annotations, limiting MLLMs’ ability to perform precise spatial measurements and complex numerical reasoning.
Approach:	They propose a 3D-based benchmark to enhance indoor perceptual understanding by using multi-scale annotations and question-answer pairs.
Outcome:	The proposed benchmark improves indoor perceptual understanding by incorporating multi-scale annotations and question-answer pairs.

Copied to clipboard

Yirong Zeng, Xiao Ding, Yutai Hou, Yuxian Wang, Li Du, Juyi Dai, Qiuyang Ding, Duyu Tang, Dandan Tu, Weiwen Liu, Bing Qin, Ting Liu

Zero-shot Event Detection Using a Textual Entailment Model as an Enhanced Annotator (2024.lrec-main)

Challenge:	Experimental results demonstrate that our models achieve over 7% performance improvement compared to both SFT and RL-with-SFT models under the same experimental settings.
Approach:	They propose a dynamic generalization-guided reward design for rule-based RL that shifts rewards from exploratory to exploitative tool-use patterns.
Outcome:	The proposed model achieves over 7% performance improvement compared to SFT and RL-with-SFT models under the same experimental settings.

Copied to clipboard

Ziqian Zeng, Runyu Wu, Yuxiang Xiao, Xiaoda Zhong, Hanlin Wang, Zhengdong Lu, Huiping Zhuang

AgentTuning: Enabling Generalized Agent Abilities for LLMs (2024.findings-acl)

Challenge:	Recent work proposed to use a pre-trained textual entailment model for event detection . but, those methods treated the TE model as a frozen annotator .
Approach:	They propose to use TE models to annotate large-scale unlabeled text and annotated data to fine-tune the TE model.
Outcome:	The proposed method outperforms baseline methods by 15% on the ACE05 dataset.

Copied to clipboard

Aohan Zeng, Mingdao Liu, Rui Lu, Bowen Wang, Xiao Liu, Yuxiao Dong, Jie Tang

Harnessing Consistency for Robust Test-Time LLM Ensemble (2026.findings-eacl)

Challenge:	Open large language models (LLMs) with great performance in various tasks are far inferior to commercial models such as ChatGPT and GPT-4 when acting as agents to tackle complex tasks in the real world.
Approach:	They propose a method to enhance the agent capabilities of LLMs while maintaining their general abilities.
Outcome:	The AgentLM-70B is comparable to GPT-3.5-turbo on unseen agent tasks, demonstrating generalized agent capabilities.

Copied to clipboard

Zhichen Zeng, Qi Yu, Xiao Lin, Ruizhong Qiu, Xuying Ning, Tianxin Wei, Yuchen Yan, Jingrui He, Hanghang Tong

Robustness in NLP

Challenge:	Existing efforts to improve LLM ensemble quality have focused on model consistency, but failures are often due to heterogeneous tokenization schemes and varying model expertise.
Approach:	They propose a plug-and-play technique that harnesses model consistency for robust LLM ensemble.
Outcome:	The proposed technique improves ensemble performance and robustness against erroneous signals.

Emergent Modularity in Pre-trained Transformers (2023.findings-acl)

Copied to clipboard

Zhengyan Zhang, Zhiyuan Zeng, Yankai Lin, Chaojun Xiao, Xiaozhi Wang, Xu Han, Zhiyuan Liu, Ruobing Xie, Maosong Sun, Jie Zhou

ChatGLM-Math: Improving Math Problem-Solving in Large Language Models with a Self-Critique Pipeline (2024.findings-emnlp)

Challenge:	Existing studies on pre-trained Transformers show that they learn fine-grained neuron functions.
Approach:	They examine the presence of modularity in pre-trained Transformers . they focus on Mixture-of-Experts, a promising candidate for modularity .
Outcome:	The proposed structure stabilizes at the early stage, which is faster than neuron stabilization.

Copied to clipboard

Yifan Xu, Xiao Liu, Xinghan Liu, Zhenyu Hou, Yueyan Li, Xiaohan Zhang, Zihan Wang, Aohan Zeng, Zhengxiao Du, Zhao Wenyi, Jie Tang, Yuxiao Dong

Numerical Reasoning

Challenge:	Large language models (LLMs) have shown excellent mastering of human language but struggle in real-world applications that require mathematical problem-solving.
Approach:	They propose a pipeline to train a general Math-Critique model from the LLM itself to provide feedback signals and employ rejective fine-tuning and direct preference optimization over the Llm's own generations for data collection.
Outcome:	The proposed pipeline outperforms existing LLMs that could be two times larger.

ODE Transformer: An Ordinary Differential Equation-Inspired Model for Sequence Generation (2022.acl-long)

Copied to clipboard

Bei Li, Quan Du, Tao Zhou, Yi Jing, Shuhan Zhou, Xin Zeng, Tong Xiao, JingBo Zhu, Xuebo Liu, Min Zhang

From Long Videos to Engaging Clips: A Human-Inspired Video Editing Framework with Multimodal Narrative Understanding (2025.emnlp-industry)

Challenge:	Residual networks are an Euler discretization of solutions to Ordinary Differential Equations (ODE).
Approach:	They propose a residual block of layers in Transformer that can be described as a higher-order solution to ODE.
Outcome:	The proposed architecture can gain large improvements over strong baselines at a slight cost in inference efficiency.

Copied to clipboard

Xiangfeng Wang, Xiao Li, Yadong Wei, null Songxueyu, Yang Song, null Xiaxiaoqiang, Fangrui Zeng, Zaiyi Chen, null Liuliu, Gu Xu, Tong Xu

ThinkNote: Enhancing Knowledge Integration and Utilization of Large Language Models via Constructivist Cognition Modeling (2026.findings-eacl)

Challenge:	Existing methods for video editing rely on textual cues from ASR transcripts and segment selection, often neglecting rich visual context.
Approach:	They propose a human-inspired automatic video editing framework that leverages multimodal narrative understanding to address these limitations.
Outcome:	The proposed framework outperforms existing baselines across general and advertisement-oriented editing tasks.

Copied to clipboard

Zhipeng Xu, Zhenghao Liu, Yukun Yan, Shuo Wang, Shi Yu, Zheni Zeng, Chaojun Xiao, Zhiyuan Liu, Ge Yu, Chenyan Xiong

RU22Fact: Optimizing Evidence for Multilingual Explainable Fact-Checking on Russia-Ukraine Conflict (2024.lrec-main)

Challenge:	Large Language Models (LLMs) exhibit suboptimal behaviors and inconsistencies when exposed to unfamiliar external information, underscoring their limitations in effectively leveraging such knowledge.
Approach:	They propose a framework that enhances the external knowledge utilization of Large Language Models through a two-stage constructivist cognitive modeling process.
Outcome:	The proposed framework achieves a 10% improvement over baseline methods on various question-answering benchmarks.

Copied to clipboard

Yirong Zeng, Xiao Ding, Yi Zhao, Xiangyu Li, Jie Zhang, Chao Yao, Ting Liu, Bing Qin

FaStFact: Faster, Stronger Long-Form Factuality Evaluations in LLMs (2025.findings-emnlp)

Challenge:	Existing methods to verify factuality of claims do not provide sufficient evidence for explainable fact-checking systems.
Approach:	They propose a method to automatically retrieve and summarize evidence from the Web and a novel multilingual explainable fact-checking dataset on the Russia-Ukraine conflict in 2022.
Outcome:	The proposed method can retrieve and summarize evidence from the Web and generate explanations in 16 languages.

Copied to clipboard

Yingjia Wan, Haochen Tan, Xiao Zhu, Xinyu Zhou, Zhiwei Li, Qingsong Lv, Changxuan Sun, Jiaqi Zeng, Yi Xu, Jianqiao Lu, Yinhong Liu, Zhijiang Guo

Multi-Modal Entities Matter: Benchmarking Multi-Modal Entity Alignment (2025.coling-main)

Challenge:	Prior evaluation pipelines fail to evaluate factuality of long-form LLMs due to inefficiency and costly human assessment.
Approach:	They propose a fast and strong evaluation pipeline that can evaluate factuality of long-form LLMs . they propose 'faStFact' to reduce cost of web searching and inference calling .
Outcome:	The proposed evaluation pipeline achieves highest alignment with human evaluation and efficiency among existing baselines.

Copied to clipboard

GuanChen Xiao, WeiXin Zeng, ShiQi Zhang, MingRui Lao, Xiang Zhao

From Complex to Simple: Enhancing Multi-Constraint Complex Instruction Following Ability of Large Language Models (2024.findings-emnlp)

Challenge:	Existing MMEA datasets consider multi-modal data as attributes of textual entities, neglecting correlations between the multi-modal data.
Approach:	They propose a multi-modal entity alignment dataset that models multi-dimensional data as textual entities in the MMKG.
Outcome:	The proposed dataset can learn the structural information of entities by considering both intra-modal and cross-modal relations and infer the similarity of different types of entity pairs.

Copied to clipboard

Qianyu He, Jie Zeng, Qianxi He, Jiaqing Liang, Yanghua Xiao

Plug-and-Play Knowledge Injection for Pre-trained Language Models (2023.acl-long)

Challenge:	Large language models (LLMs) follow instructions with elaborate requirements, yet it remains under-explored how to enhance their ability to follow complex instructions with multiple constraints.
Approach:	They propose a method to obtain and utilize effective training data to enhance LLMs' ability to follow complex instructions with multiple constraints.
Outcome:	The proposed framework improves models' ability to follow instructions generally and generalize effectively across out-of-domain, in domain, and adversarial settings while maintaining general capabilities.

Copied to clipboard

Zhengyan Zhang, Zhiyuan Zeng, Yankai Lin, Huadong Wang, Deming Ye, Chaojun Xiao, Xu Han, Zhiyuan Liu, Peng Li, Maosong Sun, Jie Zhou

Step-by-Step Mastery: Enhancing Soft Constraint Following Ability of Large Language Models (2025.findings-acl)

Challenge:	Existing knowledge injection methods are not suitable for enhancing pre-trained language models with external knowledge bases.
Approach:	They propose a plug-and-play knowledge injection method where knowledge bases are injected into frozen existing downstream models by a knowledge plugin.
Outcome:	The proposed method improves the performance of knowledge injection on knowledge-driven tasks while keeping model parameters frozen.

Copied to clipboard

Qingyu Ren, Jie Zeng, Qianyu He, Jiaqing Liang, Yanghua Xiao, Weikang Zhou, Zeye Sun, Fei Yu

EfficientLLM: Unified Pruning-Aware Pretraining for Auto-Designed Compact Language Models (2026.acl-long)

Challenge:	In real-world scenarios, user instructions often contain soft constraints, which are semantically related and cannot be rule-based verified, posing challenges for large language models.
Approach:	They propose a pipeline to construct datasets with high-quality outputs for instructions containing soft constraints automatically and use Direct Preference Optimization (DPO) as the training method.
Outcome:	The proposed model improves the LLMs' soft constraint following ability by using direct preference optimization (DPO) and constraint quantity.

Copied to clipboard

Xingrun Xing, Zheng Liu, Shitao Xiao, Boyan Gao, Yiming Liang, Haokun Lin, Xianlin Zeng, Guoqi Li, Jiajun Zhang

Exploring Large Language Models for Effective Rumor Detection on Social Media (2025.naacl-long)

Challenge:	Large language models (LLMs) driven by scaling laws can be developed in large model sizes.
Approach:	They propose a pruning-aware pretraining approach that decouples LLM pruning from direct pretraining.
Outcome:	The proposed model outperforms pretraining models with 100M 1B parameters in commen sense benchmarks.

Copied to clipboard

Yirong Zeng, Xiao Ding, Bibo Cai, Ting Liu, Bing Qin

PromptARA: Improving Deep Representation in Hybrid Automatic Readability Assessment with Prompt and Orthogonal Projection (2023.findings-emnlp)

Challenge:	Large-scale contexts hinder LLMs’ reasoning abilities while moderate contexts perform better for LLM.
Approach:	They propose a semantic-propagation collaboration-base framework that integrates small language models with LLMs for effective rumor detection.
Outcome:	The proposed framework bridges the gap between LLMs and LLM in facing long, structured data and offers a novel solution for rumor detection on social media.

Copied to clipboard

Jinshan Zeng, Xianglong Yu, Xianchao Tong, Wenyan Xiao

HighMATH: Evaluating Math Reasoning of Large Language Models in Breadth and Depth (2025.findings-emnlp)

Challenge:	Readability assessment aims to automatically classify texts based on readers’ reading levels.
Approach:	They propose a hybrid automatic readability assessment model using prompts to improve deep feature representations and an orthogonal projection layer to fuse both deep and linguistic features.
Outcome:	The proposed model outperforms state-of-the-art models over four English and two Chinese corpora and demonstrates that it is more efficient than existing models.

Copied to clipboard

Yan Liu, Minghui Zhang, Bojian Xiong, Yifan Xiao, Yinong Sun, Yating Mei, Longyu Zeng, Jingchao Yang, Yang Wang, Deyi Xiong

MMLU-ProX: A Multilingual Benchmark for Advanced Large Language Model Evaluation (2025.emnlp-main)

Challenge:	a gap in math models' accuracy has been widened with the development of large language models (LLMs) . a new study aims to bridge this gap by evaluating a set of high-level math reasoning models .
Approach:	They propose to evaluate large language models on existing math benchmarks to bridge this gap . they collect 5,293 problems from Chinese senior high school mathematics exams .
Outcome:	The proposed model is based on o1-like models and a high-level model.

Copied to clipboard

Weihao Xuan, Rui Yang, Heli Qi, Qingcheng Zeng, Yunze Xiao, Aosong Feng, Dairui Liu, Yun Xing, Junjue Wang, Fan Gao, Jinghui Lu, Yuang Jiang, Huitao Li, Xin Li, Kunyu Yu, Ruihai Dong, Shangding Gu, Yuekang Li, Xiaofei Xie, Felix Juefei-Xu, Foutse Khomh, Osamu Yoshie, Qingyu Chen, Douglas Teodoro, Nan Liu, Randy Goebel, Lei Ma, Edison Marrese-Taylor, Shijian Lu, Yusuke Iwasawa, Yutaka Matsuo, Irene Li

Multilinguality

Challenge:	Existing large language model evaluation benchmarks focus on English, while current multilingual tasks lack parallel questions that specifically assess cross-lingual reasoning abilities.
Approach:	They propose a comprehensive benchmark covering 29 languages, built on an English benchmark.
Outcome:	The MMLU-ProX is a comprehensive benchmark covering 29 languages, built on an English benchmark.

Neighbors Are Not Strangers: Improving Non-Autoregressive Translation under Low-Frequency Lexical Constraints (2022.naacl-main)

Copied to clipboard

Chun Zeng, Jiangjie Chen, Tianyi Zhuang, Rui Xu, Hao Yang, Qin Ying, Shimin Tao, Yanghua Xiao

Machine Translation

Challenge:	Existing approaches to lexically constrained neural machine translation suffer from high latency.
Approach:	They propose a plug-in algorithm for non-autoregressive translation for this problem . they propose ACT to familiarize the model with the source-side context of constraints .
Outcome:	The proposed model improves over the backbone constrained NAT model in constraint preservation and translation quality, especially for rare constraints.

Instructions are all you need: Self-supervised Reinforcement Learning for Instruction Following (2026.acl-long)

Copied to clipboard

Qingyu Ren, Qianyu He, Powei Chang, Jie Zeng, Zeye Sun, Fei Yu, Jiaqing Liang, Yanghua Xiao

Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention (2025.acl-long)

Challenge:	Existing reinforcement learning approaches suffer from dependency on external supervision and sparse reward signals from multi-constraint tasks.
Approach:	They propose a self-supervised reinforcement learning framework that eliminates dependency on external supervision by deriving reward signals directly from instructions and generating pseudo-labels for reward model training.
Outcome:	The proposed framework achieves strong improvements across 3 in-domain and 5 out-of-domain datasets while maintaining computational efficiency.

Copied to clipboard

Jingyang Yuan, Huazuo Gao, Damai Dai, Junyu Luo, Liang Zhao, Zhengyan Zhang, Zhenda Xie, Yuxing Wei, Lean Wang, Zhiping Xiao, Yuqing Wang, Chong Ruan, Ming Zhang, Wenfeng Liang, Wangding Zeng

Green & Sustainable NLP

Challenge:	Long-context modeling is crucial for next-generation language models, but high computational cost of standard attention mechanisms poses significant computational challenges.
Approach:	They propose a natively trained Sparse Attention mechanism that integrates algorithms with hardware-aligned optimizations to achieve efficient long-context modeling.
Outcome:	The proposed model maintains or exceeds Full Attention models across general benchmarks, long-context tasks, and instruction-based reasoning.

Efficient Hyperparameter Optimization for LLM Reinforcement Learning (2026.acl-long)

Copied to clipboard

Minping Chen, Bowen Xiao, Du Liang, Chuxuan Zeng, Zeyi Wen

Green & Sustainable NLP

Challenge:	Existing hyperparameter optimization methods are inefficient in reinforcement learning due to model scale and resource-intensive training cycles.
Approach:	They propose a hyperparameter optimization method that adapts both model size and training budget as fidelity.
Outcome:	The proposed method significantly improves the computational efficiency of each trial (up to 14.9) over existing HPO methods.

LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding (2024.acl-long)

Copied to clipboard

Yushi Bai, Xin Lv, Jiajie Zhang, Hongchang Lyu, Jiankai Tang, Zhidian Huang, Zhengxiao Du, Xiao Liu, Aohan Zeng, Lei Hou, Yuxiao Dong, Jie Tang, Juanzi Li

Multilinguality

Challenge:	Large language models (LLMs) can only handle texts a few thousand tokens long, limiting their applications on longer sequence inputs, such as books, reports, and codebases.
Approach:	They propose a bilingual, multi-task benchmark for long context understanding that extends context windows and more sophisticated memory mechanisms to improve models' long context capabilities.
Outcome:	The proposed model outperforms open-source models but struggles on longer contexts.

MirageBackdoor: A Stealthy Attack that Induces Think-Well-Answer-Wrong Reasoning (2026.acl-long)

Copied to clipboard

Yizhe Zeng, Wei Zhang, Yunpeng Li, Juxin Xiao, Xiao Wang, Yuling Liu

Robustness in NLP

Challenge:	Existing CoT backdoor attacks manipulate intermediate reasoning steps to steer the model toward incorrect answers, but these corrupted reasoning traces are readily detected by prevalent process-monitoring defenses.
Approach:	They propose a backdoor attack that exploits the model's post-output space to preserve clean CoTs while selectively steering the final answer toward a specific target.
Outcome:	Experiments show that MirageBD achieves over 90% success rate across four datasets and five models with a poison ratio of only 5%.

CritiqueLLM: Towards an Informative Critique Generation Model for Evaluation of Large Language Model Generation (2024.acl-long)

Copied to clipboard

Pei Ke, Bosi Wen, Andrew Feng, Xiao Liu, Xuanyu Lei, Jiale Cheng, Shengyuan Wang, Aohan Zeng, Yuxiao Dong, Hongning Wang, Jie Tang, Minlie Huang

SEMIROUTER: Sparse-Data Enhanced Routing for Adaptive Multi-LLM System (2026.eacl-long)

Challenge:	Existing models for NLP evaluations lack the ability to generate informative critiques in pointwise grading and pairwise comparison especially without references.
Approach:	They propose a method which can acquire pointwise grading critiques with pseudo references and revise these critiques via multi-path prompting to obtain informative evaluation data in different tasks and settings.
Outcome:	The proposed method outperforms all open-source models and even GPT-4 in system-level correlations of pointwise grading.

Copied to clipboard

Zijie Wang, Xinyu Yan, Che Wang, Zeng Zihao, Lei Xiao, Wei Yang Bryan Lim

Green & Sustainable NLP

Challenge:	Existing routing methods suffer from poor scalability and dependence on datasets for training . energy footprint is also considered in the decision to implement our new LLM routing framework .
Approach:	They propose a new LLM routing framework that dynamically allocates queries to the most appropriate LLM.
Outcome:	The proposed method improves data efficiency, adaptability, and routing accuracy compared to existing methods.

OS Agents: A Survey on MLLM-based Agents for Computer, Phone and Browser Use (2025.acl-long)

Copied to clipboard

Xueyu Hu, Tao Xiong, Biao Yi, Zishu Wei, Ruixuan Xiao, Yurun Chen, Jiasheng Ye, Meiling Tao, Xiangxin Zhou, Ziyu Zhao, Yuhuai Li, Shengze Xu, Shenzhi Wang, Xinchen Xu, Shuofei Qiao, Zhaokai Wang, Kun Kuang, Tieyong Zeng, Liang Wang, Jiwei Li, Yuchen Eleanor Jiang, Wangchunshu Zhou, Guoyin Wang, Keting Yin, Zhou Zhao, Hongxia Yang, Fan Wu, Shengyu Zhang, Fei Wu

Order Matters: Investigate the Position Bias in Multi-constraint Instruction Following (2025.findings-acl)

Challenge:	a new generation of (M)LLMs is enabling the creation of superintelligent AI assistants . OS Agents can complete tasks autonomously and have the potential to significantly enhance the lives of billions of users worldwide.
Approach:	They propose to build OS Agents that operate within operating systems' GUIs and GUIs . they examine evaluation metrics and benchmarks to identify promising directions .
Outcome:	The proposed agents are based on operating systems (OS) and operating systems frameworks.

Copied to clipboard

Jie Zeng, Qianyu He, Qingyu Ren, Jiaqing Liang, Weikang Zhou, Zeye Sun, Fei Yu, Yanghua Xiao

Challenge:	Existing large language models struggle to follow multi-constraint instructions in real-world applications.
Approach:	They propose to quantify the difficulty distribution of constraints by a novel Difficulty Distribution Index (CDDI) they find that LLMs are more performant when presented with constraints in a “hard-to-easy” order.
Outcome:	The proposed model is more performant when presented with constraints in a “hard-to-easy” order, compared with existing models with different architectures and sizes of parameters.

iTool: Reinforced Fine-Tuning with Dynamic Deficiency Calibration for Advanced Tool Use (2025.emnlp-main)

Copied to clipboard

Yirong Zeng, Xiao Ding, Yuxian Wang, Weiwen Liu, Yutai Hou, Wu Ning, Xu Huang, Duyu Tang, Dandan Tu, Bing Qin, Ting Liu

CMNEE:A Large-Scale Document-Level Event Extraction Dataset Based on Open-Source Chinese Military News (2024.lrec-main)

Challenge:	Synthesizing tool-use data through real-world simulations is effective for enhancing large language models (LLMs) however, training gains decay as synthetic data increases, and the model struggles to benefit from more synthetic data.
Approach:	They propose an iterative reinforced fine-tuning strategy to improve LLMs with external tools to augment their capabilities.
Outcome:	The proposed method achieves 13.11% better performance than the same-size base model and outperforms larger open-source and closed-source models.

Copied to clipboard

Mengna Zhu, Zijie Xu, Kaisheng Zeng, Kaiming Xiao, Mao Wang, Wenjun Ke, Hongbin Huang

Information Extraction & Text Mining

Challenge:	Current research focuses on the general news or financial domains, with relatively few studies for military domain.
Approach:	They propose to annotate Chinese military news events from documents using a schema for the military domain.
Outcome:	The proposed dataset is large-scale, document-level open-source for the military domain . it contains 17,000 documents and 29,223 events, which are all manually annotated .

SOLAR-RL: Semi-Online Long-horizon Assignment Reinforcement Learning (2026.findings-acl)

Copied to clipboard

Jichao Wang, Liuyang Bian, Yufeng Zhou, Han Xiao, Yue Pan, Guozhi Wang, Hao Wang, Zhaoxiong Wang, Yafei Wen, Xiaoxin Chen, Shuai Ren, Lingfang Zeng