Papers by Wei Tian

FanLoRA: Fantastic LoRAs and Where to Find Them in Large Language Model Fine-tuning (2024.emnlp-industry)

Challenge:	Large Language Models lack specialized priors for subtle grammatical distinctions, and Supervised Fine-Tuning fails to optimize for precision-focused metrics.
Approach:	They propose a framework that builds correction capability through Continual Pre-training on 5.9M balanced samples to internalize domain knowledge.
Outcome:	The proposed framework outperforms existing models on the NACGEC benchmark with 50.99 F0.5 and 57.17 precision while mitigating over-correction bias.

Copied to clipboard

Aaron Tian, Yi Zhao, Congrui Yin, Wei Zhu, Xing Tian, Yi Ge

Learning from Mistakes: Negative Reasoning Samples Enhance Out-of-Domain Generalization (2026.acl-long)

Challenge:	Lowrank adaptation and its variants introduce significant latency in multi-tenant settings, hindering their applications in the industry.
Approach:	They propose a framework to fine-tune LoRA modules on a large-scale instruction tuning dataset.
Outcome:	The proposed framework outperforms existing PEFT methods and significantly reduces inference latency.

Copied to clipboard

Tian Xueyun, MingHua Ma, Bingbing Xu, Nuoyan Lyu, Wei Li, Heng Dong, Zheng Chu, Yuanzhuo Wang, Huawei Shen

Detoxifying Large Language Models via the Diversity of Toxic Samples (2025.emnlp-main)

Challenge:	Recent studies show that supervised fine-tuning (SFT) is a common approach for reasoning in large language models.
Approach:	They propose to use supervised fine-tuning (SFT) on chain-of-thought trajectories demonstrations . they find that incorporating negative traxories yields substantial OOD generalization gains .
Outcome:	The proposed scheme yields 5.51% OOD gain over positive-only training.

Copied to clipboard

Ying Zhao, Yuanzhao Guo, Xuemeng Weng, Yuan Tian, Wei Wang, Yi Chang

Cross-Lingual Phrase Retrieval (2022.acl-long)

Challenge:	Existing methods for analyzing and utilizing toxic samples are limited . current methods fail to fully harness their potential .
Approach:	They propose a diverse detoxification framework that leverages toxic samples' diversity . they propose MPSG strategy and SC-DPO approach to elicit personalized toxic responses .
Outcome:	The proposed framework could be used to optimize large language models for user safety . it incorporates two components: MPSG strategy and SC-DPO approach .

Copied to clipboard

Heqi Zheng, Xiao Zhang, Zewen Chi, Heyan Huang, Yan Tan, Tian Lan, Wei Wei, Xian-Ling Mao

Cross-Lingual Transfer

Challenge:	Existing approaches to cross-lingual phrase retrieval learn word or sentence representations in word or sentences.
Approach:	They propose a cross-lingual phrase retrieval model that extracts phrase representations from unlabeled example sentences.
Outcome:	The proposed model outperforms state-of-the-art methods on a large-scale cross-lingual phrase retrieval dataset, showing it can perform in an unseen language pair during training.

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

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

SafeSteer: A Decoding-level Defense Mechanism for Multimodal Large Language Models (2026.findings-acl)

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

Xinyi Zeng, Xue Yang, Jingyuan Zhang, Huanqian Yan, Xiang Chen, Kaiwen Wei, Hankun Kang, Yu Tian

Interpretable Composition Attribution Enhancement for Visio-linguistic Compositional Understanding (2024.emnlp-main)

Challenge:	Existing defense methods rely on fine-tuning or inefficient post-hoc interventions, limiting their ability to address novel attacks.
Approach:	They propose a decoding-level defense mechanism that employs a lightweight discriminator to iteratively steer the decoding process toward safety.
Outcome:	The proposed method improves safety performance by up to 33.40% without fine-tuning on multiple MLLMs.

Copied to clipboard

Wei Li, Zhen Huang, Xinmei Tian, Le Lu, Houqiang Li, Xu Shen, Jieping Ye

Explainability & Interpretability in NLP

Challenge:	Despite promising progress, vision-language models still exhibit significant challenges in understanding visio-linguistic concepts beyond object terms.
Approach:	They propose a framework that encourages the model to pay greater attention to composition words denoting relationships and attributes within the text.
Outcome:	The proposed framework improves the ability to discern intricate details and construct more sophisticated interpretations of combined visual and linguistic elements.

Learning a Multi-Domain Curriculum for Neural Machine Translation (2020.acl-main)

Copied to clipboard

Wei Wang, Ye Tian, Jiquan Ngiam, Yinfei Yang, Isaac Caswell, Zarana Parekh

Multilinguality

Challenge:	Existing data selection methods do not work well for multiple domains . multiple aspects need to be considered for training a multi-domain model .
Approach:	They propose a dynamic data selection method to multi-domain NMT that incorporates instance-level domain-relevance features and a curriculum to gradually focus on multi- domain relevant data batches.
Outcome:	The proposed model outperforms no-curriculum training on multiple domains and reaches or outperformed individual performance.

Visual Evidence Prompting Mitigates Hallucinations in Large Vision-Language Models (2025.acl-long)

Copied to clipboard

Wei Li, Zhen Huang, Houqiang Li, Le Lu, Yang Lu, Xinmei Tian, Xu Shen, Jieping Ye

MiLoRA: Efficient Mixture of Low-Rank Adaptation for Large Language Models Fine-tuning (2024.findings-emnlp)

Challenge:	LVLMs have shown impressive progress by integrating visual perception with linguistic understanding to produce contextually grounded outputs.
Approach:	They propose a visual evidence prompting method to mitigate hallucinations in large vision-language models by using small visual models to complement them.
Outcome:	The proposed method reduces hallucinations by reducing false activation and enhancing correct ones.

Copied to clipboard

Jingfan Zhang, Yi Zhao, Dan Chen, Xing Tian, Huanran Zheng, Wei Zhu

AgentCPM-GUI: Building Mobile-Use Agents with Reinforcement Fine-Tuning (2025.emnlp-demos)

Challenge:	Low-rank adaptation and its mixture-of-experts (MOE) methods are highly effective but introduce significant latency in multi-tenant settings due to the LoRA modules and MOE routers added to multiple linear modules.
Approach:	They propose a low-rank adaptation variant that considers each LoRA module as an expert and employs a prompt-aware routing mechanism.
Outcome:	Extensive analysis on commonsense reasoning tasks and math reasoning tasks show that MiLoRA outperforms strong PEFT baselines with comparable tunable parameter budgets.

Copied to clipboard

Zhong Zhang, Yaxi Lu, Yikun Fu, Yupeng Huo, Shenzhi Yang, Yesai Wu, Han Si, Xin Cong, Haotian Chen, Yankai Lin, Xie Xie, Wei Zhou, Wang Xu, Zhou Su, Zhongwu Zhai, Xiaoming Liu, null Meiyudong, Jianming Xu, Hongyan Tian, Chongyi Wang, Chi Chen, Yuan Yao, Zhiyuan Liu, Maosong Sun

Multi-Agent Collaboration via Cross-Team Orchestration (2025.findings-acl)

Challenge:	Large language model agents have enabled GUI-based automation, but their deployment is limited by noisy data, poor generalization, and lack of support for non-English GUIs.
Approach:	They propose an 8B-parameter GUI agent built for robust and efficient on-device GUI interaction.
Outcome:	The proposed GUI agent achieves promising performance on five public benchmarks and proposed Chinese benchmark CAGUI.

Copied to clipboard

Zhuoyun Du, Chen Qian, Wei Liu, Zihao Xie, YiFei Wang, Rennai Qiu, Yufan Dang, Weize Chen, Cheng Yang, Ye Tian, Xuantang Xiong, Lei Han

Challenge:	Large Language Models (LLMs) have significantly impacted various domains, especially through organized LLM-driven autonomous agents.
Approach:	They propose a framework that enables orchestrated teams to jointly propose various task-oriented solutions and interact with their insights in a self-independence while cross-team collaboration environment for superior solutions generation.
Outcome:	Experiments show that the framework can generate better software quality compared to state-of-the-art frameworks.

TabularMath: Understanding Math Reasoning over Tables with Large Language Models (2026.findings-acl)

Copied to clipboard

Shi-Yu Tian, Zhi Zhou, Wei Dong, Kun-Yang Yu, Ming Yang, Zi-Jian Cheng, Lan-Zhe Guo, Yu-Feng Li

Mitigating Boundary Ambiguity and Inherent Bias for Text Classification in the Era of Large Language Models (2024.findings-acl)

Challenge:	Mathematical reasoning has long been a key benchmark for evaluating large language models.
Approach:	They propose a framework that transforms math word problems into scalable tabular reasoning tasks.
Outcome:	The proposed framework transforms math word problems into scalable and verified tabular reasoning tasks.

Copied to clipboard

Zhenyi Lu, Jie Tian, Wei Wei, Xiaoye Qu, Yu Cheng, Wenfeng Xie, Dangyang Chen

Text Classification

Challenge:	a new text classification framework for large language models addresses the problem of boundary ambiguity and inherent biases in LLMs.
Approach:	They propose a two-stage classification framework for large language models to mitigate bottlenecks . their approach uses pairwise comparisons to efficiently narrow down options .
Outcome:	The proposed framework reduces the number of options and improves on four datasets.

MMAC: A Multilingual, Multimodal Alignment Framework for Cultural Grounding Evaluation (2026.acl-long)

Copied to clipboard

Weihua Zheng, Zhengyuan Liu, Tanmoy Chakraborty, Weiwen Xu, Xiaoxue Gao, Bryan Chen Zhengyu Tan, Bowei Zou, Chang Liu, Yujia Hu, Xing Xie, Xiaoyuan Yi, Jing Yao, Chaojun Wang, Long Li, Rui Liu, Huiyao Liu, Koji Inoue, Ryuichi Sumida, Tatsuya Kawahara, Fan Xu, Lingyu Ye, Wei Tian, Dongjun Kim, Jimin Jung, Jaehyung Seo, Nadya Yuki Wangsajaya, Pham Minh Duc, Ojasva Saxena, Palash Nandi, Xiyan Tao, Wiwik Karlina, Tuan Luong, Keertana Arun Vasan, Roy Ka-Wei Lee, Nancy F. Chen

Text-to-TrajVis: Enabling Trajectory Data Visualizations from Natural Language Questions (2026.findings-acl)

Challenge:	Existing models lack cultural alignment across modalities and languages . a new framework to assess cultural awareness across linguistics and languages is needed .
Approach:	They propose a framework that integrates tri-modally aligned cultural benchmarks and a five-dimensional evaluation protocol to assess cross-country awareness disparities.
Outcome:	The proposed framework assesses cultural awareness disparities across modalities and languages . it is the first dataset aligned at the input level across text, image, and speech .

Copied to clipboard

Tian Bai, Huiyan Ying, Kailong Suo, Victor Junqiu Wei, Tao Fan, Yuanfeng Song

Challenge:	Existing datasets for this task are limited and there is no suitable one available.
Approach:	They propose a new visualization language called Trajectory Visualization Language (TVL) to facilitate querying trajectory data and generating visualizations.
Outcome:	The proposed language can be used to query and generate trajectory data and generate visualizations with large language models.

PlanGenLLMs: A Modern Survey of LLM Planning Capabilities (2025.acl-long)

Copied to clipboard

Hui Wei, Zihao Zhang, Shenghua He, Tian Xia, Shijia Pan, Fei Liu

Challenge:	Existing studies have focused on developing LLMs to automate complex planning tasks.
Approach:	They propose to provide a comprehensive overview of current LLM planners to fill this gap . they examine performance criteria including completeness, executability, optimality, representation, generalization, and efficiency .
Outcome:	The proposed survey examines performance criteria for LLM planners and highlights their strengths and weaknesses.

CARL: Constraint-Aware Reinforcement Learning for Planning with LLMs (2026.findings-acl)

Copied to clipboard

Qiuyi Qi, Jinjian Zhang, Mutian Bao, Tian Liang, Guocong Li, Dongnan Liu, Wei Zhou, Jie Liu, Ming Kong, Linjian Mo, Feng Zhang, Qiang Zhu

Facilitating Long Context Understanding via Supervised Chain-of-Thought Reasoning (2025.emnlp-main)

Challenge:	Existing approaches to constraint-aware planning fail to enhance the model’s intrinsic focus on constraints.
Approach:	They propose a constraint-aware reinforcement learning framework that encourages constraint focus and penalizes neglect of LLMs.
Outcome:	The proposed framework outperforms existing frameworks and state-of-the-art reasoning models in a number of real-world applications.

Copied to clipboard

Jingyang Lin, Andy Wong, Tian Xia, Shenghua He, Hui Wei, Mei Han, Jiebo Luo

Cross-Modal Masked Compositional Concept Modeling for Enhancing Visio-Linguistic Compositionality (2026.acl-long)

Challenge:	Recent advances in Large Language Models (LLMs) have enabled them to process increasingly longer sequences, ranging from 2K to 2M tokens and even beyond.
Approach:	They propose a synthetic dataset in the financial domain that integrates Chain-of-Thought reasoning into LLMs in a supervised manner to facilitate effective long-context understanding.
Outcome:	The proposed model outperforms standard GPT-4o-mini on the Loong benchmark and fine tunes LLaMA-3.1-8B-Instruct on the model, achieving a 28.0% gain on the financial subset.

Copied to clipboard

Wei Li, Zhen Huang, Xinmei Tian

Exploring the Capability Boundaries of LLMs in Mastering of Chinese Chouxiang Language (2026.findings-acl)

Challenge:	a contrastive learning approach for vision-language models is needed to capture compositional information.
Approach:	They propose a framework that masks compositional concepts in one modality and reconstructs them conditioned on full contextual information from the other .
Outcome:	The proposed framework enhances compositionality in visual language models and improves their ability to capture syntactic structure and linguistic information.

Copied to clipboard

Dianqing Lin, Tian Lan, Jiali Zhu, Jiang Li, Wei Chen, Xu Liu, null Aruukhan, Xiangdong Su, Hongxu Hou, Guanglai Gao

Machine Translation

Challenge:	Current state-of-the-art LLMs exhibit clear limitations on multiple tasks, while performing well on tasks that involve contextual semantic understanding.
Approach:	They propose a mouse-based benchmark to evaluate LLMs' performance on NLP tasks involving Chouxiang Language.
Outcome:	The proposed benchmark evaluates the performance of LLMs on six NLP tasks involving Chouxiang Language.

Confidence-Calibrated Small-Large Language Model Collaboration for Cost-Efficient Reasoning (2026.eacl-long)

Copied to clipboard

Chuang Zhang, Zizhen Zhu, Yihao Wei, Bing Tian, Junyi Liu, Henan Wang, Wang Xavier, Yaxiao Liu

ChatMusician: Understanding and Generating Music Intrinsically with LLM (2024.findings-acl)

Challenge:	Large language models (LLMs) have superior reasoning capabilities compared to small language models, but incur substantially higher inference costs.
Approach:	They propose a system that cascades an LLM with an SLM to achieve a balance between accuracy and cost in complex reasoning tasks.
Outcome:	The proposed system improves the SLM’s reasoning ability and confidence calibration across diverse datasets and model backbones.

Copied to clipboard

Ruibin Yuan, Hanfeng Lin, Yi Wang, Zeyue Tian, Shangda Wu, Tianhao Shen, Ge Zhang, Yuhang Wu, Cong Liu, Ziya Zhou, Liumeng Xue, Ziyang Ma, Qin Liu, Tianyu Zheng, Yizhi Li, Yinghao Ma, Yiming Liang, Xiaowei Chi, Ruibo Liu, Zili Wang, Chenghua Lin, Qifeng Liu, Tao Jiang, Wenhao Huang, Wenhu Chen, Jie Fu, Emmanouil Benetos, Gus Xia, Roger Dannenberg, Wei Xue, Shiyin Kang, Yike Guo

Task-oriented Word Embedding for Text Classification (C18-1)

Challenge:	Despite LLMs' impressive capabilities in musical knowledge, music reasoning remains an unsolved task.
Approach:	They propose an open-source large language model (LLM) that integrates intrinsic musical abilities into LLaMA2 and GPT-3.5.
Outcome:	The proposed model can understand and generate music with a pure text tokenizer without external multi-modal neural structures or tokenizers.

Copied to clipboard

Qian Liu, Heyan Huang, Yang Gao, Xiaochi Wei, Yuxin Tian, Luyang Liu

Information Retrieval

Challenge:	Existing word embeddings only consider contextual information, which is suboptimal when used in various tasks due to a lack of task-specific features.
Approach:	They propose a task-oriented word embedding method that regularizes the distribution of words to enable a clear classification boundary.
Outcome:	The proposed method outperforms the state-of-the-art methods on a text classification task.

Premise-based Multimodal Reasoning: Conditional Inference on Joint Textual and Visual Clues (2022.acl-long)

Copied to clipboard

Qingxiu Dong, Ziwei Qin, Heming Xia, Tian Feng, Shoujie Tong, Haoran Meng, Lin Xu, Zhongyu Wei, Weidong Zhan, Baobao Chang, Sujian Li, Tianyu Liu, Zhifang Sui

Shorten After You’re Right: Lazy Length Penalties for Reasoning RL (2026.findings-acl)

Challenge:	Existing work in vision language cross-modal reasoning uses binary or multi-choice classification based on source image and textual query.
Approach:	They propose a task where a textual premise is the background presumption on each source image.
Outcome:	The proposed task is based on a dataset of 15,360 movie screenshots and human-curated premise templates from 6 pre-defined categories.

Copied to clipboard

Danlong Yuan, Tian Xie, Shaohan Huang, Huishuai Zhang, Zhuocheng Gong, Chong Luo, Furu Wei, Dongyan Zhao

Me-Agent: A Personalized Mobile Agent with Two-Level User Habit Learning for Enhanced Interaction (2026.findings-acl)

Challenge:	Existing shortening methods for long reasoning models rely on additional supervision or multi-stage post-training.
Approach:	They propose a lazy length penalty that imposes length pressure on models without extra training stages.
Outcome:	The proposed method significantly reduces response length without extra training stages while maintaining or improving performance.

Copied to clipboard

Shuoxin Wang, Chang Liu, Gowen Loo, Lifan Zheng, Kaiwen Wei, Huanqian Yan, Xinyi Zeng, Jingyuan Zhang, Yu Tian

KG-Adapter: Enabling Knowledge Graph Integration in Large Language Models through Parameter-Efficient Fine-Tuning (2024.findings-acl)

Challenge:	Existing Large Language Model (LLM)-based mobile agents follow explicit user instructions without personalized needs.
Approach:	They propose a user preference learning strategy enhanced with a Personal Reward Model to improve personalization performance.
Outcome:	The proposed agent achieves state-of-the-art performance while maintaining competitive instruction execution performance.

Copied to clipboard

Shiyu Tian, Yangyang Luo, Tianze Xu, Caixia Yuan, Huixing Jiang, Chen Wei, Xiaojie Wang

League of LLMs: A Benchmark-Free Paradigm for Mutual Evaluation of Large Language Models (2026.acl-long)

Challenge:	Large language models (LLMs) are criticized for lack of expertise and knowledge conflict . KG-Adapter is a parameter-level KG integration method for decoder-only LLMs .
Approach:	They propose a parameter-level KG integration method based on parameter-efficient fine-tuning . they use KG-Adapter to integrate knowledge graphs with LLMs and perform joint reasoning .
Outcome:	The proposed method outperforms the current state-of-the-art method on four datasets for two different tasks.

Copied to clipboard

Qianhong Guo, Wei Xie, Xiaofang Cai, Enze Wang, Shuoyoucheng Ma, Xiaobing Sun, Tian Xia, Kai Chen, Xiaofeng Wang, Baosheng Wang

Re-examining the Role of Schema Linking in Text-to-SQL (2020.emnlp-main)

Challenge:	Large language models (LLMs) have shown exceptional capabilities across a wide range of tasks, but reliable evaluation remains a challenge due to data contamination, opaque operation, and subjective preferences.
Approach:	They propose a benchmark-free evaluation paradigm that organizes multiple LLMs into a self-governed league for multi-round mutual evaluation.
Outcome:	Experiments on eight mainstream LLMs in mathematics and programming show that the proposed model can distinguish capabilities while maintaining high internal ranking stability.

Copied to clipboard

Wenqiang Lei, Weixin Wang, Zhixin Ma, Tian Gan, Wei Lu, Min-Yen Kan, Tat-Seng Chua

Programming Languages in NLP

Challenge:	Existing text-to-SQL models treat schema linking as a minor component . Existing solutions treat schema as merely a string component based on string matching .
Approach:	They build a schema linking corpus based on a Spider text-to-SQL dataset . they find schema linking is the crux for the current text- to-Sql task .
Outcome:	The proposed model performs well on the Spider text-to-SQL dataset despite its simplicity.

StyleFlow: Disentangle Latent Representations via Normalizing Flow for Unsupervised Text Style Transfer (2024.lrec-main)

Copied to clipboard

Kangchen Zhu, Zhiliang Tian, Jingyu Wei, Ruifeng Luo, Yiping Song, Xiaoguang Mao

PARA: Parameter-Efficient Fine-tuning with Prompt-Aware Representation Adjustment (2024.emnlp-industry)

Challenge:	Existing methods to separate content from style but some words contain both content and style information.
Approach:	They propose a method which uses a reversible encoder to improve content disentanglement.
Outcome:	The proposed method outperforms baselines on sentiment transfer and formality transfer tasks.

Copied to clipboard

Zequan Liu, Yi Zhao, Ming Tan, Wei Zhu, Aaron Tian

ROMA: Real-time Omni-Multimodal Assistant with Interactive Streaming Understanding (2026.findings-acl)

Challenge:	Existing methods for parameter-efficient fine-tuning excel in the context of single-backbone multi-tenant applications.
Approach:	They propose to integrate a lightweight vector generator within each Transformer layer to improve prompt-aware representation adjustment.
Outcome:	The proposed method surpasses current benchmarks in terms of performance despite having a similar number of adjustable parameters.

Copied to clipboard

Tian Xueyun, Wei Li, Bingbing Xu, Heng Dong, Yuanzhuo Wang, Huawei Shen

IAPT: Instance-Aware Prompt Tuning for Large Language Models (2024.acl-long)

Challenge:	Existing omni-multimodal large language models lack incomplete modality support or lack autonomous proactive monitoring.
Approach:	They propose a real-time omni-multimodal assistant for unified reactive and proactive interaction that decouples response initiation from generation to ensure precise triggering without task conflict.
Outcome:	The proposed model achieves state-of-the-art performance on proactive tasks while competing in reactive settings.

Copied to clipboard

Wei Zhu, Aaron Tian, Congrui Yin, Yuan Ni, Xiaoling Wang, Guotong Xie

Learning to Instruct: Fine-Tuning a Task-Aware Instruction Optimizer for Black-Box LLMs (2025.findings-emnlp)

Challenge:	Existing methods for prompt tuning require many soft tokens to guarantee performance . large language models still require a large amount of GPU memory and computations to fine-tune .
Approach:	They propose to use a parameter-efficient soft prompt generator to generate idiosyncratic soft prompts for each input instruction.
Outcome:	The proposed method outperforms the baselines with comparable tunable parameters and is more efficient than LoRA under the single-backbone multi-tenant setting.

Copied to clipboard

Yunzhe Qi, Jinjin Tian, Tianci Liu, Ruirui Li, Tianxin Wei, Hui Liu, Xianfeng Tang, Monica Xiao Cheng, Jingrui He

MathAgent: Adversarial Evolution of Constraint Graphs for Mathematical Reasoning Data Synthesis (2026.findings-acl)

Challenge:	Learning to Instruct is a new paradigm for black-box LLMs with inaccessible internal states.
Approach:	They propose a new paradigm that formulates instruction optimization as an LLM fine-tuning objective for a white-box “instruction engineer” LLM.
Outcome:	The proposed framework outperforms strong baselines in performance and efficiency.

Copied to clipboard

Zixiong Yu, Jun Rao, Guhan Chen, Songtao Tian, Bohan Li, Jiansheng Wei, Min Zhang, Xiaojun Meng

Alloc-MoE: Budget-Aware Expert Activation Allocation for Efficient Mixture-of-Experts Inference (2026.acl-long)

Challenge:	Current approaches to synthesising high-quality mathematical reasoning data without human priors suffer from mode collapse and limited logical complexity.
Approach:	They propose a hierarchical synthesis framework that formulates data synthesis as an unsupervised optimization problem over a constraint graph followed by semantic instantiation rather than a direct text generation task.
Outcome:	The proposed framework outperforms widely-used datasets on eight mathematical benchmarks.

Copied to clipboard

Baihui Liu, Kaiyuan Tian, Wei Wang, Zhaoning Zhang, Linbo Qiao, Dongsheng Li

Green & Sustainable NLP

Challenge:	Existing approaches that reduce expert activations lead to severe model performance degradation.
Approach:	They propose a framework that optimizes budget allocation coordinately at layer and token levels to minimize model performance degradation.
Outcome:	The proposed framework achieves 1.15 prefill and 1.34 decode speedups on DeepSeek-V2-Lite at half of the original budget.

mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections (2022.emnlp-main)

Copied to clipboard

Chenliang Li, Haiyang Xu, Junfeng Tian, Wei Wang, Ming Yan, Bin Bi, Jiabo Ye, He Chen, Guohai Xu, Zheng Cao, Ji Zhang, Songfang Huang, Fei Huang, Jingren Zhou, Luo Si

Visual Data in NLP

Challenge:	Existing pre-trained vision-language models suffer from inefficiency and linguistic signal overwhelmed by long visual sequences in cross-modal alignment.
Approach:	They propose a vision-language foundation model with cross-modal skip-connections that can be pre-trained end-to-end on large-scale image-text pairs with both discriminative and generative objectives.
Outcome:	The proposed model achieves state-of-the-art results on a wide range of vision-language downstream tasks, including image captioning, image-text retrieval, visual grounding and visual question answering.

GROVE: A Retrieval-augmented Complex Story Generation Framework with A Forest of Evidence (2023.findings-emnlp)

Copied to clipboard

Zhihua Wen, Zhiliang Tian, Wei Wu, Yuxin Yang, Yanqi Shi, Zhen Huang, Dongsheng Li

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

Challenge:	Existing methods for generating stories with complex plots rely on detailed prompts, which inadvertently limit the creative potential of the generated stories.
Approach:	They propose a retrieval-auGmented stoRy generation framework with a fOrest of eVidEnce to enhance stories’ complexity.
Outcome:	The proposed framework enables generating more diverse plotlines from human-written stories.

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

PRISM-MCTS: Learning from Reasoning Trajectories with Metacognitive Reflection (2026.findings-acl)

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

Siyuan Cheng, Bozhong Tian, Yanchao Hao, Zheng Wei

ALoRA: Allocating Low-Rank Adaptation for Fine-tuning Large Language Models (2024.naacl-long)

Challenge:	Existing reasoning models are limited by inefficiency and computational redundancy . PRISM-MCTS integrates a process reward model with a dynamic shared memory .
Approach:	They propose a reasoning framework that integrates a process reward model with a dynamic shared memory.
Outcome:	PRISM-MCTS integrates a process reward model with a dynamic shared memory . it halves trajectory requirements on GPQA while surpassing MCTS-RAG and Search-o1 .

Copied to clipboard

Zequan Liu, Jiawen Lyn, Wei Zhu, Xing Tian

UrbanGeoEval: A City-Scale Benchmark for Evaluating Large Language Models in Geospatial Reasoning (2026.acl-long)

Challenge:	Low-rank adaptation (LoRA) has demonstrated commendable performance as a popular method . however, it is implemented with a fixed intrinsic rank that might not be ideal for downstream tasks.
Approach:	They propose a method that estimates the importance score of each LoRA rank and prunes abundant LoRA ranks to improve performance.
Outcome:	The proposed method outperforms baselines on a variety of tasks with comparable parameters.

Copied to clipboard

Mutian Bao, Qiuyi Qi, Tian Liang, Jinjian Zhang, Wei Zhou, Ming Kong, Linjian Mo, Qiang Zhu

DiffER: Diffusion Entity-Relation Modeling for Reversal Curse in Diffusion Large Language Models (2026.findings-acl)

Challenge:	Extensive experiments on 18 widely used LLMs uncover critical insights: (1) models exhibit severe geographic biases and resolution gaps; (2) failures in complex multi-hop tasks stem from brittle foundational spatial skills rather than high-level logic deficits.
Approach:	They propose a dual-module framework that disentangles factual recall and spatial logic from the model's real capabilities in urban environments.
Outcome:	Extensive tests on 18 widely used LLMs reveal that models exhibit severe geographic biases and resolution gaps, and failures in complex multi-hop tasks often stem from brittle foundational spatial skills rather than high-level logic deficits.

Copied to clipboard

Shaokai He, Kaiwen Wei, Xinyi Zeng, Xiang Chen, Xue Yang, Zhenyang Li, Jiang Zhong, Yu Tian

Learning to Abstract for Memory-augmented Conversational Response Generation (P19-1)

Challenge:	Existing large language models exhibit unidirectional behavior when processing bidirectional relationships . authors propose a solution to alleviate the reversal curse in Diffusion LLMs .
Approach:	They propose a model that addresses the "reversal curse" of bidirectional behavior in large language models . they propose 'entity-aware training' and balanced data construction to alleviate asymmetry and missing relations .
Outcome:	The proposed model alleviates the "reversal curse" in Diffusion LLMs . the proposed model employs whole-entity masking to mitigate entity fragmentation .

Copied to clipboard

Zhiliang Tian, Wei Bi, Xiaopeng Li, Nevin L. Zhang

Dialogue Systems & Conversational Agents

Challenge:	Existing generative models for open-domain chit-chat conversations lack informativeness and diversity.
Approach:	They propose a retrieval-augmented generative model that learns to abstract from the training corpus and saves useful information to the memory to assist the response generation.
Outcome:	The proposed model outperforms other baselines in query-response clustering and learning to utilize these characteristics for response generation.

An LLM-Enabled Knowledge Elicitation and Retrieval Framework for Zero-Shot Cross-Lingual Stance Identification (2024.findings-emnlp)

Copied to clipboard

Ruike Zhang, Yuan Tian, Penghui Wei, Daniel Zeng, Wenji Mao

Low-Resource NLP

Challenge:	Existing research is conducted in monolingual setting on English datasets, whereas in other low-resource languages, it lacks sufficient data for training quality stance detection models.
Approach:	They propose a knowledge elicitation and retrieval framework that leverages the capability of large language models for stance knowledge acquisition and matches the target language input to the most relevant stance information.
Outcome:	The proposed framework improves on multilingual datasets and competitive baselines.

STAPO: Selective Trajectory-Aware Policy Optimization for LLM Agent Training (2026.acl-long)

Copied to clipboard

Qiuyi Qi, Tian Liang, Mutian Bao, Jinjian Zhang, Dongnan Liu, Wei Zhou, Linjian Mo, Ming Kong, Jie Liu, Feng Zhang, Qiang Zhu

A Novel Cascade Binary Tagging Framework for Relational Triple Extraction (2020.acl-main)

Challenge:	Prior work has explored step-level supervision using Shannon-entropy-based uncertainty signals, which conflate inherent state complexity with agent confidence.
Approach:	They propose a hierarchical group-based RL framework that leverages normalized entropy to locate outlier steps associated with trajectory neglect and optimizes them via a mechanism of trajectory-aware reward and trajectory-independent penalty.
Outcome:	Experiments on ALFWorld, WebShop, and Search-Augmented QA show that STAPO achieves state-of-the-art performance while substantially alleviating trajectory neglect.

Copied to clipboard

Zhepei Wei, Jianlin Su, Yue Wang, Yuan Tian, Yi Chang

Information Extraction & Text Mining

Challenge:	Existing approaches to extract relational triples from unstructured text are inadequate to solve the overlapping triple problem.
Approach:	They propose a cascade binary tagging framework that models relations as functions that map subjects to objects in a sentence.
Outcome:	The proposed framework outperforms state-of-the-art methods on two datasets . it outperformed baseline methods by 17.5 and 30.2 absolute gains .

Response-Anticipated Memory for On-Demand Knowledge Integration in Response Generation (2020.acl-main)

Copied to clipboard

Zhiliang Tian, Wei Bi, Dongkyu Lee, Lanqing Xue, Yiping Song, Xiaojiang Liu, Nevin L. Zhang

Text Generation

Challenge:	Neural conversation models generate appropriate but non-informative responses in general.
Approach:	They propose to construct a document memory with anticipated responses in mind using a teacher-student framework and a student's input.
Outcome:	The proposed model outperforms the state-of-the-art for the Conversing by Reading task.

AgentMark: Utility-Preserving Behavioral Watermarking for Agents (2026.acl-long)

Copied to clipboard

Kaibo Huang, Jin Tan, Yukun Wei, Wanling Li, Zipei Zhang, Hui Tian, Zhongliang Yang, Linna Zhou

Challenge:	Recent advances in large language models (LLMs) have improved text generation and reasoning.
Approach:	They propose a behavioral watermarking framework that embeds multi-bit identifiers into planning decisions while preserving utility.
Outcome:	The proposed framework embeds multi-bit provenance into planning decisions while preserving utility.

PIPER: Benchmarking and Prompting Event Reasoning Boundary of LLMs via Debiasing-Distillation Enhanced Tuning (2025.acl-long)

Copied to clipboard

Zhicong Lu, Changyuan Tian, PeiguangLi PeiguangLi, Li Jin, Sirui Wang, Wei Jia, Ying Shen, Guangluan Xu

DiningBench: A Hierarchical Multi-view Benchmark for Perception and Reasoning in the Dietary Domain (2026.acl-long)

Challenge:	Existing studies on Large Language Models (LLMs) have failed to evaluate their performance in event reasoning with a single event relational type or reasoning format.
Approach:	They propose a benchmark to evaluate LLMs' event reasoning capability using a single event relational type or reasoning format.
Outcome:	The proposed model improves on 10K diverse instruction-tuning demonstrations to alleviate event reasoning-oriented data scarcity.

Copied to clipboard

Song Jin, Juntian Zhang, Xun Zhang, Zeying Tian, Fei Jiang, Guojun Yin, Wei Lin, Yong Liu, Rui Yan

LAiW: A Chinese Legal Large Language Models Benchmark (2025.coling-main)

Challenge:	Existing vision-language models lack fine-grained classification, single-view imagery, and inaccurate metadata.
Approach:	They propose a hierarchical, multi-view benchmark to evaluate VLMs across three levels of cognitive complexity.
Outcome:	The proposed benchmark evaluates vision-language models across three levels of complexity . it systematically identifies five primary failure modes . the proposed benchmarks are available on https://github.com/meituan/DiningBench.

Copied to clipboard

Yongfu Dai, Duanyu Feng, Jimin Huang, Haochen Jia, Qianqian Xie, Yifang Zhang, Weiguang Han, Wei Tian, Hao Wang

Towards Unified Representations of Knowledge Graph and Expert Rules for Machine Learning and Reasoning (2022.aacl-main)

Challenge:	Xie et al., 2023) show that large language models (LLMs) can generate legal text, but lack the legal syllogism . legal experts are cautious about their practical application due to the opaque nature of the LLMs.
Approach:	They propose a Chinese legal LLM benchmark structured around the legal syllogism . they evaluate LLMs across three levels of capability, each reflecting a more complex stage of legal .
Outcome:	The proposed benchmark identifies that LLMs lack the legal syllogism, which hinders trust and understanding from legal experts.

Copied to clipboard

Zhepei Wei, Yue Wang, Jinnan Li, Zhining Liu, Erxin Yu, Yuan Tian, Xin Wang, Yi Chang

TANet: Thread-Aware Pretraining for Abstractive Conversational Summarization (2022.findings-naacl)

Challenge:	Empirical study shows superiority of proposed method over time-tested knowledge-driven and data-driven methods.
Approach:	They propose a cognitive knowledge graph that unifies expert rules and relational facts as the substrate of machine learning and reasoning models.
Outcome:	Empirical results show the proposed method superior to time-tested methods . the proposed model can perform both learning and reasoning with labeled data .

Copied to clipboard

Ze Yang, Christian Wang, Zhoujin Tian, Wei Wu, Zhoujun Li