Papers by Ming Zhu

Aligning VLM Assistants with Personalized Situated Cognition (2025.acl-long)

Challenge:	Experimental results show that the proposed cross-modal attention distillation is crucial to the success of our framework.
Approach:	They propose a framework that distills knowledge of fusion-encoder teacher into dual-encoding student model.
Outcome:	The proposed model is competitive with the fusion-encoder teacher model in performance, but suffers from a lack of deep cross-modal interactions.

Copied to clipboard

Yongqi Li, Shen Zhou, Xiaohu Li, Xin Miao, Jintao Wen, Mayi Xu, Jianhao Chen, Birong Pan, Hankun Kang, Yuanyuan Zhu, Ming Zhong, Tieyun Qian

Towards a Unified Multi-Dimensional Evaluator for Text Generation (2022.emnlp-main)

Challenge:	Existing studies on vision-language models aligned with general human objectives have not been successful because people with diversified backgrounds have different cognition even in the same situation.
Approach:	They propose to characterize individuals based on the sociological concept of Role-Set and then evaluate their actions to see whether personalized alignment is achieved.
Outcome:	The proposed framework constructs a cognition-aware and action-based reward model for personalized alignment.

Copied to clipboard

Ming Zhong, Yang Liu, Da Yin, Yuning Mao, Yizhu Jiao, Pengfei Liu, Chenguang Zhu, Heng Ji, Jiawei Han

Text Generation

Challenge:	Existing evaluation frameworks for natural language generation are dominated by similarity-based metrics.
Approach:	They propose a multi-dimensional evaluator for natural language generation that integrates multiple dimensions into one evaluer.
Outcome:	The proposed evaluator improves on three typical NLG tasks and improves with external knowledge.

Make Prompt-based Black-Box Tuning Colorful: Boosting Model Generalization from Three Orthogonal Perspectives (2024.lrec-main)

Copied to clipboard

Qiushi Sun, Chengcheng Han, Nuo Chen, Renyu Zhu, Jingyang Gong, Xiang Li, Ming Gao

ActionStudio: A Lightweight Framework for Data and Training of Large Action Models (2025.emnlp-main)

Challenge:	Large language models (LLMs) have shown increasing power on NLP tasks. however, tuning these models for downstream tasks usually requires exorbitant costs.
Approach:	They propose a black-box tuning technique that optimizes task-specific prompts without accessing gradients and hidden representations.
Outcome:	The proposed method improves performance under few-shot learning scenarios.

Copied to clipboard

Jianguo Zhang, Thai Quoc Hoang, Ming Zhu, Zuxin Liu, Shiyu Wang, Tulika Manoj Awalgaonkar, Akshara Prabhakar, Haolin Chen, Weiran Yao, Zhiwei Liu, Juntao Tan, Juan Carlos Niebles, Shelby Heinecke, Huan Wang, Silvio Savarese, Caiming Xiong

Challenge:	Existing infrastructure for efficient agentic data processing and model training remains underdeveloped.
Approach:	They propose a lightweight and extensible data and training framework for large action models . they propose to unify diverse agent trajectories using Unified Format 2.0 .
Outcome:	The proposed framework shows 9 higher throughput than existing frameworks and performs well across public and realistic agent benchmarks.

Generalization-Enhanced Code Vulnerability Detection via Multi-Task Instruction Fine-Tuning (2024.findings-acl)

Copied to clipboard

Xiaohu Du, Ming Wen, Jiahao Zhu, Zifan Xie, Bin Ji, Huijun Liu, Xuanhua Shi, Hai Jin

Pass off Fish Eyes for Pearls: Attacking Model Selection of Pre-trained Models (2022.acl-long)

Challenge:	Existing CodePre-trained models struggle to generalize due to superficial mapping from source code to labels instead of understanding the root causes of code vulnerabilities.
Approach:	They propose a framework that integrates multi-task learning with Large Language Models to effectively mine deep-seated vulnerability features.
Outcome:	The proposed framework surpasses seven state-of-the-art models in effectiveness, generalization, and robustness.

Copied to clipboard

Biru Zhu, Yujia Qin, Fanchao Qi, Yangdong Deng, Zhiyuan Liu, Maosong Sun, Ming Gu

Robustness in NLP

Challenge:	Existing feature-based model selection methods are vulnerable to fine-tuning and are not reliable indicators for the PTM’s transferability.
Approach:	They propose feature-based model selection methods which assess PTMs’ transferability to a specific task in a fast way without fine-tuning.
Outcome:	The proposed methods can make FMS mistakenly judge transferability of models and can be combined with the backdoor attack to misguide the FMS to select poisoned models.

PersonaBench: Evaluating AI Models on Understanding Personal Information through Accessing (Synthetic) Private User Data (2025.findings-acl)

Copied to clipboard

Juntao Tan, Liangwei Yang, Zuxin Liu, Zhiwei Liu, Rithesh R N, Tulika Manoj Awalgaonkar, Jianguo Zhang, Weiran Yao, Ming Zhu, Shirley Kokane, Silvio Savarese, Huan Wang, Caiming Xiong, Shelby Heinecke

Responsible & Trustworthy NLP

Challenge:	Existing research lacks direct access to such data, making benchmarking difficult due to privacy concerns.
Approach:	They propose a synthetic data pipeline that generates realistic user profiles and private documents and a benchmark to evaluate models' ability to understand personal information.
Outcome:	The proposed pipeline generates realistic user profiles and private documents, enabling PersonaBench, a benchmark for evaluating models’ ability to understand personal information.

Self-Error-Instruct: Generalizing from Errors for LLMs Mathematical Reasoning (2025.acl-long)

Copied to clipboard

Erxin Yu, Jing Li, Ming Liao, Qi Zhu, Boyang Xue, Minghui Xu, Baojun Wang, Lanqing Hong, Fei Mi, Lifeng Shang

Browse and Concentrate: Comprehending Multimodal Content via Prior-LLM Context Fusion (2024.acl-long)

Challenge:	Existing approaches to learning from errors synthesize training data by extrapolating from isolated bad cases, thereby failing to generalize the extensive patterns inherent within these cases.
Approach:	They propose a framework that synthesizes more generalized training data from isolated bad cases by extrapolating from isolated cases.
Outcome:	The proposed framework synthesizes more generalized training data to address these model weaknesses.

Copied to clipboard

Ziyue Wang, Chi Chen, Yiqi Zhu, Fuwen Luo, Peng Li, Ming Yan, Ji Zhang, Fei Huang, Maosong Sun, Yang Liu

The Shifted and The Overlooked: A Task-oriented Investigation of User-GPT Interactions (2023.emnlp-main)

Challenge:	Multimodal Large Language Models (MLLMs) lack understanding of multi-image and interleaved inputs due to the visual features encoded by frozen encoders before being fed into the LLM backbone.
Approach:	They propose a two phase paradigm to enable in-depth multimodal context fusion prior to feeding the features into LLMs.
Outcome:	The proposed paradigm boosts the performance on 7 multi-image scenarios, contributing to increments on average accuracy by 2.13% and 7.60% against strong MLLMs baselines with 3B and 11B LLMs, respectively.

Copied to clipboard

Siru Ouyang, Shuohang Wang, Yang Liu, Ming Zhong, Yizhu Jiao, Dan Iter, Reid Pryzant, Chenguang Zhu, Heng Ji, Jiawei Han

NAG-NER: a Unified Non-Autoregressive Generation Framework for Various NER Tasks (2023.acl-industry)

Challenge:	Recent advances in large language models (LLMs) have produced models that exhibit remarkable performance across a variety of NLP tasks.
Approach:	They analyze a large-scale collection of user-GPT conversations to identify a significant gap between academic research in NLP and the needs of real-world NLP applications.
Outcome:	The proposed model outperforms existing models in a large-scale collection of user-GPT conversations and identifies a significant gap between the tasks that users frequently request from LLMs and the tasks commonly studied in academic research.

Copied to clipboard

Xinpeng Zhang, Ming Tan, Jingfan Zhang, Wei Zhu

Information Extraction & Text Mining

Challenge:	Existing models for general NER tasks require entities to be generated in a predefined order, causing error propagation and inefficient decoding.
Approach:	They propose a non-autoregressive generation framework for general NER tasks that generates entities as a set instead of a sequence, avoiding error propagation and inefficient decoding.
Outcome:	The proposed model outperforms state-of-the-art models on three benchmark NER datasets and two of our proprietary NER tasks.

A Neural Network Architecture for Program Understanding Inspired by Human Behaviors (2022.acl-long)

Copied to clipboard

Renyu Zhu, Lei Yuan, Xiang Li, Ming Gao, Wenyuan Cai

Representation Learning

Challenge:	Existing studies for understanding programs do not take human behaviors as reference.
Approach:	They propose a graph neural network model that takes human behaviors as reference in understanding programs.
Outcome:	The proposed model performs better on code summarization and code clone detection tasks.

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

Intelligent Document Parsing: Towards End-to-end Document Parsing via Decoupled Content Parsing and Layout Grounding (2025.findings-emnlp)

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

Hangdi Xing, Feiyu Gao, Qi Zheng, Zhaoqing Zhu, Zirui Shao, Ming Yan

I²B-LPO: Latent Policy Optimization via Iterative Information Bottleneck (2026.acl-long)

Challenge:	Existing methods fragment document parsing into pipeline of separated subtasks, resulting in incomplete semantics and error propagation.
Approach:	They propose an end-to-end document parsing framework that leverages vision-language priors of MLLMs.
Outcome:	The proposed method surpasses existing methods significantly in document parsing . it leverages the vision-language priors of MLLMs to decouple parse and layout grounding based on visual information.

Copied to clipboard

Huilin Deng, Hongchen Luo, Yue Zhu, Long Li, Zhuoyue Chen, Xinghao Zhao, Ming LI, Chuyang Zhao, Jihai Zhang, MengChang Wang, Yang Cao, Yu Kang

SEEKR: Selective Attention-Guided Knowledge Retention for Continual Learning of Large Language Models (2024.emnlp-main)

Challenge:	Existing methods for large language model reasoning suffer from exploration collapse due to the semantic homogeneity of random rollouts.
Approach:	They propose to use latent policy optimization via iterative information bottleneck to optimize reasoning trajectories by diversifying reasoning .
Outcome:	Empirical results show that the proposed method achieves state-of-the-art performance with margins of up to 5.3% in accuracy and 7.4% in diversity metrics.

Copied to clipboard

Jinghan He, Haiyun Guo, Kuan Zhu, Zihan Zhao, Ming Tang, Jinqiao Wang

When Does Mixing Help? Analyzing Query Embedding Interpolation in Multilingual Dense Retrieval (2026.acl-long)

Challenge:	Existing methods fail to fully exploit the knowledge embedded in models from previous tasks . Existing techniques fail to exploit the information embedded in previous tasks, resulting in a large number of replay samples to achieve good results.
Approach:	They propose a method that uses attention weights to extract knowledge from previous tasks . they use a data replay strategy to extract the knowledge from the previous tasks.
Outcome:	The proposed method achieves comparable or even better performance with only 1/10 of replayed data used by other methods.

Copied to clipboard

Tongyao Zhu, Huang Chao Ming, Min-Yen Kan

Retrieval Enhanced Model for Commonsense Generation (2021.findings-acl)

Challenge:	Existing multilingual retrievers are largely untested for mixed language queries . sensitivity of dense retrievers to mixed language querying remains poorly understood .
Approach:	They propose to use mixed queries as an interpolation of monolingual embeddings to evaluate retrieval performance.
Outcome:	The proposed model outperforms the best monolingual endpoint in 88/105 cases.

Copied to clipboard

Han Wang, Yang Liu, Chenguang Zhu, Linjun Shou, Ming Gong, Yichong Xu, Michael Zeng

DISCO Balances the Scales: Adaptive Domain- and Difficulty-Aware Reinforcement Learning on Imbalanced Data (2025.findings-emnlp)

Challenge:	Existing frameworks for commonsense generation are lacking for pre-trained models.
Approach:	They propose a framework that uses concept matching to retrieve prototype sentences and trainable sentence retriever to enhance pre-training and fine-tuning.
Outcome:	The proposed framework achieves state-of-the-art on the large-scale Common-Gen benchmark.

Copied to clipboard

Yuhang Zhou, Jing Zhu, Shengyi Qian, Zhuokai Zhao, Xiyao Wang, Xiaoyu Liu, Ming Li, Paiheng Xu, Wei Ai, Furong Huang

A Survey on Training-free Alignment of Large Language Models (2025.findings-emnlp)

Challenge:	Large Language Models (LLMs) are increasingly aligned with human preferences through Reinforcement Learning from Human Feedback (RLHF).
Approach:	a new study proposes a domain-informed self-consistency policy optimization extension to GRPO that addresses inter-group imbalance.
Outcome:	a new extension of GRPO addresses inter-group imbalance with two key innovations . the proposed method outperforms existing GR PO variants by 5% on Qwen3 models .

Copied to clipboard

Birong Pan, Yongqi Li, Weiyu Zhang, Wenpeng Lu, Mayi Xu, Shen Zhou, Yuanyuan Zhu, Ming Zhong, Tieyun Qian

Visual Attention Reasoning via Hierarchical Search and Self-Verification (2026.acl-long)

Challenge:	a survey of large language models (LLMs) aims to ensure outputs adhere to human values, ethical standards, and legal norms.
Approach:	They present the first systematic review of TF alignment methods . they categorize them by stages of pre-decoding, in-decoder and post-decoration .
Outcome:	The proposed methods are based on training-free (TF) alignment techniques . they are able to be used in open-source and closed-source environments without retraining .

Copied to clipboard

Wei Cai, Jian Zhao, Yuchen Yuan, Tianle Zhang, Ming Zhu, Haichuan Tang, Xuelong Li

EMTIR-GRPO: Efficient Multi-Tool Augmented Large Language Models via Reinforcement Learning (2026.findings-acl)

Challenge:	Multimodal Large Language Models (MLLMs) often hallucinate due to fragile, linear reasoning and weak visual grounding.
Approach:	They propose a framework that reformulates reasoning as a hierarchical search with self-verification and replaces linear Chain-of-Thought with a tree-search policy capable of backtracking to correct logical errors.
Outcome:	The proposed framework outperforms state-of-the-art methods on hallucination and safety benchmarks.

Copied to clipboard

Shixin Jiang, Zhihao Zhu, Jiafeng Liang, Yang Wu, Ming Liu, Bing Qin

ARTIST: A Transformer-based Chinese Text-to-Image Synthesizer Digesting Linguistic and World Knowledge (2022.findings-emnlp)

Challenge:	Tool-integrated reasoning (TIR) enables large language models to invoke external tools for tasks beyond their internal capacity but often suffers from tool overuse.
Approach:	They propose an algorithm that uses a composite reward to model tool costs and tool efficiency.
Outcome:	The proposed algorithm models heterogeneous tool costs and encourages more cost-effective tool-use strategies.

Copied to clipboard

Tingting Liu, Chengyu Wang, Xiangru Zhu, Lei Li, Minghui Qiu, Jun Huang, Ming Gao, Yanghua Xiao

DoCIA: An Online Document-Level Context Incorporation Agent for Speech Translation (2025.findings-acl)

Challenge:	Text-to-Image Synthesis (TIS) is a popular task to convert natural language texts into realistic images.
Approach:	They propose a transformer-based Chinese text-to-image synthesizer for high-resolution image generation that incorporates linguistic and relational knowledge facts into the model to ensure better performance without the usage of ultra-large models.
Outcome:	The proposed model outperforms existing models in Chinese with linguistic and relational knowledge facts.

Copied to clipboard

Xinglin Lyu, Wei Tang, Yuang Li, Xiaofeng Zhao, Ming Zhu, Junhui Li, Yunfei Lu, Min Zhang, Daimeng Wei, Hao Yang, Min Zhang

Text Generation

Challenge:	Document-level context is crucial for speech translation due to noise from ASR . incorporating document-level contextual information into ST remains a challenge .
Approach:	They develop an online framework that integrates document-level context into machine translation . they use document-based modules to integrate document- level context into ST .
Outcome:	The proposed framework outperforms baselines in sentence and discourse metrics . it can correct ASR transcription errors and improve translation performance .

QueryLink: Leveraging Query-Memory Alignment for Long-Term Reasoning in LLM Agents (2026.findings-acl)

Copied to clipboard

Xuxian Hu, Zhu Teng, Wei Zhang, Ming He, Jianping Fan

Information Retrieval

Challenge:	Existing approaches to integrating external memory prioritize memory organization while overlooking a critical semantic gap between implicit, intent-driven queries and explicit, narrative-based memories.
Approach:	They propose a framework that leverages Query-Memory Alignment to project both queries and memories into a shared semantic space.
Outcome:	The proposed framework significantly outperforms SOTA methods on the LoCoMo and LongMemEval benchmarks and can be integrated as a plug-and-play component to boost existing vector-based systems like A-MEM.

LAM SIMULATOR: Advancing Data Generation for Large Action Model Training via Online Exploration and Trajectory Feedback (2025.findings-acl)

Copied to clipboard

Thai Quoc Hoang, Kung-Hsiang Huang, Shirley Kokane, Jianguo Zhang, Zuxin Liu, Ming Zhu, Jake Grigsby, Tian Lan, Michael S Ryoo, Chien-Sheng Wu, Shelby Heinecke, Huan Wang, Silvio Savarese, Caiming Xiong, Juan Carlos Niebles

Challenge:	Large Action Models (LAMs) face challenges due to the need for high-quality training data, especially for multi-steps tasks that involve planning, executing tool calls, and responding to feedback.
Approach:	They propose a framework for online exploration of agentic tasks with high-quality feedback . they use a dynamic task query generator and an extensive collection of tools to create a high-level feedback environment for LLM Agents.
Outcome:	The proposed framework achieves 49.3% performance improvement over baselines on toolbench and CRMArena.

SmartTrim: Adaptive Tokens and Attention Pruning for Efficient Vision-Language Models (2024.lrec-main)

Copied to clipboard

Zekun Wang, Jingchang Chen, Wangchunshu Zhou, Haichao Zhu, Jiafeng Liang, Liping Shan, Ming Liu, Dongliang Xu, Qing Yang, Bing Qin

TS-CLIP: Time Series Understanding by CLIP (2025.emnlp-main)

Challenge:	Experimental results show that SmartTrim accelerates the original model by 2-3 times with minimal performance degradation.
Approach:	They propose an adaptive acceleration framework which prunes redundant token representations and attention heads within each layer of the original model.
Outcome:	The proposed framework accelerates the original model by 2-3 times with minimal performance degradation across vision-language tasks.

Copied to clipboard

Ziwen Chen, Xiaoyuan Zhang, Ming Zhu

Learned Adapters Are Better Than Manually Designed Adapters (2023.findings-acl)

Challenge:	Contrastive Language–Image Pre-training (CLIP) has demonstrated remarkable success in aligning vision and language.
Approach:	They propose a synonym bank mechanism that generates synonym embeddings as alignment targets.
Outcome:	The proposed approach achieves state-of-the-art (SOTA) performance on 51 datasets.

Copied to clipboard

Yuming Zhang, Peng Wang, Ming Tan, Wei Zhu

Responsible & Trustworthy NLP

Challenge:	Existing approaches to improve adapter-based tuning are sub-optimal . a learning framework is proposed to learn the optimal adapter architectures .
Approach:	They propose a framework to automatically learn optimal adapter architectures for better task adaptation of pre-trained models.
Outcome:	The proposed framework outperforms the previous parameter-efficient tuning baselines while tuning comparable or fewer parameters.

SPT: Learning to Selectively Insert Prompts for Better Prompt Tuning (2023.emnlp-main)

Copied to clipboard

Wei Zhu, Ming Tan

Beat LLMs at Their Own Game: Zero-Shot LLM-Generated Text Detection via Querying ChatGPT (2023.emnlp-main)

Challenge:	Prompt tuning is a method of pre-trained models that optimizes the prompt to adapt to downstream tasks.
Approach:	They propose a framework that learns to select the proper prompt layers by inserting a probabilistic gate at each intermediate layer.
Outcome:	The proposed framework can perform better than the state-of-the-art prompt tuning frameworks on ten benchmark datasets.

Copied to clipboard

Biru Zhu, Lifan Yuan, Ganqu Cui, Yangyi Chen, Chong Fu, Bingxiang He, Yangdong Deng, Zhiyuan Liu, Maosong Sun, Ming Gu

EmoCaps: Emotion Capsule based Model for Conversational Emotion Recognition (2022.findings-acl)

Challenge:	Large language models (LLMs) are capable of performing tasks but are likely to be misused.
Approach:	They propose a zero-shot black-box method to detect LLM-generated texts . they revise the text to be detected using the ChatGPT model .
Outcome:	The proposed method can detect LLM-generated texts with a zero-shot black-box model . it is based on intuition that the model will make fewer revisions to LLMs than to human-written texts .

Copied to clipboard

Zaijing Li, Fengxiao Tang, Ming Zhao, Yusen Zhu

Dialogue Systems & Conversational Agents

Challenge:	Existing studies on ERC focus on context modeling but ignore representation of contextual emotional tendency.
Approach:	They propose to use Emoformer to extract multi-modal emotion vectors from different modalities and fuse them with sentence vector to be an emotion capsule.
Outcome:	The proposed model outperforms the state-of-the-art models on two benchmark datasets.

Less Is More: Domain Adaptation with Lottery Ticket for Reading Comprehension (2021.findings-emnlp)

Copied to clipboard

Haichao Zhu, Zekun Wang, Heng Zhang, Ming Liu, Sendong Zhao, Bing Qin

Question Answering with Long Multiple-Span Answers (2020.findings-emnlp)

Challenge:	Existing domain adaptation paradigms for reading comprehension require large amounts of annotation data to achieve the desired task performance.
Approach:	They propose a few-shot domain adaptation paradigm for reading comprehension . they introduce self-attention attribution to weigh parameters and refine the lottery subnetwork .
Outcome:	The proposed model outperforms the full model fine-tuning adaptation on four out of five domains with a small amount of data available for adaptation.

Copied to clipboard

Ming Zhu, Aman Ahuja, Da-Cheng Juan, Wei Wei, Chandan K. Reddy

Question Answering

Challenge:	Existing QA systems for question answering are limited by the availability of annotated datasets.
Approach:	They propose a dataset for question-answering that extracts information from multiple parts of text . they propose QA-based multi-span neural architecture that captures relevance among multiple answer spans .
Outcome:	The proposed model outperforms state-of-the-art QA models in this multi-span QA setting.

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

Copied to clipboard

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

MPBoCo: Multimodal Prompt-based Boundary-enhanced Continual Framework for Joint Entity and Relation Extraction (2026.acl-long)

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

Guanglu Sun, Xinyu Liu, Lili Liang, Yang Yu, Fei Lang, Suxia Zhu, Ming Liu

Low-Resource NLP

Challenge:	Existing methods struggle to balance real-time adaptability and computational efficiency in continual learning scenarios.
Approach:	They propose a Continual Multimodal Entity and Relation Joint Extraction task and a Multimodal Prompt-based Boundary-enhanced Continuum framework that stores task-specific knowledge via learnable multimodal prompts.
Outcome:	The proposed framework outperforms baseline methods in real-world scenarios by 5.5% and 7.2%.

Structure-aware Fine-tuning for Code Pre-trained Models (2024.lrec-main)

Copied to clipboard

Jiayi Wu, Renyu Zhu, Nuo Chen, Qiushi Sun, Xiang Li, Ming Gao

Is Cognition Consistent with Perception? Assessing and Mitigating Multimodal Knowledge Conflicts in Document Understanding (2025.emnlp-main)

Challenge:	Existing CodePTMs are mainly structure-free and structurebased, but how to fine-tune them remains a challenge.
Approach:	They propose a plug-and-play fine-tuning method that incorporates structural knowledge into pre-trained code models.
Outcome:	The proposed method can benefit CodePTMs more with limited training data.

Copied to clipboard

Zirui Shao, Feiyu Gao, Zhaoqing Zhu, Chuwei Luo, Hangdi Xing, Zhi Yu, Qi Zheng, Ming Yan, Jiajun Bu

CoLo: A Contrastive Learning Based Re-ranking Framework for One-Stage Summarization (2022.coling-1)

Challenge:	Multimodal large language models (MLLMs) have shown impressive capabilities in document understanding due to different types of annotation noise in training.
Approach:	They propose a method to reduce C&P knowledge conflicts across all tested MLLMs . they propose to use annotation noise to train models to understand document content .
Outcome:	The proposed method reduces C&P knowledge conflicts across all tested MLLMs and enhances their performance in both cognitive and perceptual tasks.

Copied to clipboard

Chenxin An, Ming Zhong, Zhiyong Wu, Qin Zhu, Xuanjing Huang, Xipeng Qiu

Revisiting Cross-Lingual Summarization: A Corpus-based Study and A New Benchmark with Improved Annotation (2023.acl-long)

Challenge:	Existing methods for extractive and abstractive summarization use token-level or sentence-level training objectives.
Approach:	They propose a Contrastive Learning based re-ranking framework for one-stage summarization called CoLo.
Outcome:	The proposed framework boosts extractive and abstractive results on CNN/DailyMail benchmarks while maintaining inference efficiency.

Copied to clipboard

Yulong Chen, Huajian Zhang, Yijie Zhou, Xuefeng Bai, Yueguan Wang, Ming Zhong, Jianhao Yan, Yafu Li, Judy Li, Xianchao Zhu, Yue Zhang

Text Generation

Challenge:	Existing work on cross-lingual summarization (CLS) does not consider crosslingual sources for summarizing.
Approach:	They propose a cross-lingual conversation summarization benchmark that explicitly considers source context.
Outcome:	The proposed method surpasses baselines on ConvSumX and 3 widely-used manual annotations.

Cracking the Code of Hallucination in LVLMs with Vision-aware Head Divergence (2025.acl-long)

Copied to clipboard

Jinghan He, Kuan Zhu, Haiyun Guo, Junfeng Fang, Zhenglin Hua, Yuheng Jia, Ming Tang, Tat-Seng Chua, Jinqiao Wang

CAT-probing: A Metric-based Approach to Interpret How Pre-trained Models for Programming Language Attend Code Structure (2022.findings-emnlp)

Challenge:	Existing methods focus on alignment training or decoding refinements but address symptoms at the generation stage without probing the underlying causes.
Approach:	They propose a training-free approach to mitigate hallucination by enhancing the role of vision-aware attention heads.
Outcome:	The proposed method achieves superior performance compared to state-of-the-art approaches in mitigating hallucinations while maintaining high efficiency with negligible additional time overhead.

Copied to clipboard

Nuo Chen, Qiushi Sun, Renyu Zhu, Xiang Li, Xuesong Lu, Ming Gao

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

Challenge:	Existing code pre-trained models fail to consider inherent characteristics of codes . Existing methods to interpret code pretrained model fail to take into account inherent characteristics .
Approach:	They propose a probing method to quantitatively interpret how CodePTMs attend code structure.
Outcome:	The proposed method denoises input code sequences and measures commonality between token-level attention scores and pair-wise distances between corresponding AST nodes.

Copied to clipboard

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

Synthetic Data Generation with Large Language Models for Text Classification: Potential and Limitations (2023.emnlp-main)

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

Zhuoyan Li, Hangxiao Zhu, Zhuoran Lu, Ming Yin

Information Retrieval

Challenge:	Recent studies have explored using large language models to generate synthetic datasets . however, the effectiveness of the LLM-generated synthetic data is inconsistent across different classification tasks.
Approach:	They propose to use large language models to generate synthetic datasets to better understand factors that moderate the effectiveness of LLM-generated synthetic data.
Outcome:	The results show that subjectivity is negatively associated with the performance of the model trained on synthetic data.

VRPO: Rethinking Value Modeling for Robust RL under Noisy Supervision in LLM Post-Training (2026.acl-long)

Copied to clipboard

Dingwei Zhu, Shihan Dou, Zhiheng Xi, Senjie Jin, Guoqiang Zhang, Jiazheng Zhang, Junjie Ye, Mingxu Chai, Enyu Zhou, Ming Zhang, Yuhui Wang, Caishuang Huang, Chenhao Huang, Yunke Zhang, Yuran Wang, Tao Gui, Qi Zhang, Xipeng Qiu, Xuanjing Huang

Robustness in NLP

Challenge:	Reinforcement Learning (RL) in real-world environments often suffers from ambiguous or incomplete supervision.
Approach:	They propose a framework that enhances value modeling for robust RL in LLM post-training by integrating auxiliary losses guided by entropy and perplexity from a frozen language model and variational information bottleneck.
Outcome:	The proposed framework outperforms baselines on multi-turn dialogue, math reasoning, and science QA with rule-based and model-based rewards.

xLAM: A Family of Large Action Models to Empower AI Agent Systems (2025.naacl-long)

Copied to clipboard

Jianguo Zhang, Tian Lan, Ming Zhu, Zuxin Liu, Thai Quoc Hoang, Shirley Kokane, Weiran Yao, Juntao Tan, Akshara Prabhakar, Haolin Chen, Zhiwei Liu, Yihao Feng, Tulika Manoj Awalgaonkar, Rithesh R N, Zeyuan Chen, Ran Xu, Juan Carlos Niebles, Shelby Heinecke, Huan Wang, Silvio Savarese, Caiming Xiong

Unsupervised Multi-Granularity Summarization (2022.findings-emnlp)

Challenge:	Autonomous agents powered by large language models (LLMs) have attracted significant research interest, but there are few standards for developing specialized models for agent tasks.
Approach:	They propose a series of large action models with dense and mixture-of-expert architectures that unifies, augments, and synthesizes diverse datasets to enhance agent generalizability and performance.
Outcome:	The proposed models outperform GPT-4, Claude-3, and many other models in terms of tool use and outperformed GPT-based models on multiple agent ability benchmarks.

Copied to clipboard

Ming Zhong, Yang Liu, Suyu Ge, Yuning Mao, Yizhu Jiao, Xingxing Zhang, Yichong Xu, Chenguang Zhu, Michael Zeng, Jiawei Han

Information Extraction & Text Mining

Challenge:	Experimental results confirm the substantial superiority of GranuSum on multi-granularity summarization over strong baselines.
Approach:	They propose to rank events by their salience and annotate a benchmark for GranuSum that contains multiple summaries at different granularities for each document cluster.
Outcome:	The proposed framework is capable of producing multi-granular summaries in unsupervised manner over strong 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

Conjoin after Decompose: Improving Few-Shot Performance of Named Entity Recognition (2024.lrec-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

Chengcheng Han, Renyu Zhu, Jun Kuang, Fengjiao Chen, Xiang Li, Ming Gao, Xuezhi Cao, Yunsen Xian

Information Extraction & Text Mining

Challenge:	Existing prompt-based NER models fail to detect entity boundaries, causing performance degradation.
Approach:	They propose a model which consists of a BART encoder and a parabiotic decoder and propose ' boundary expansion strategy' to enhance the model's capability in entity type classification.
Outcome:	The proposed model can achieve significant performance gains over state-of-the-art models.

BeamAggR: Beam Aggregation Reasoning over Multi-source Knowledge for Multi-hop Question Answering (2024.acl-long)

Copied to clipboard

Zheng Chu, Jingchang Chen, Qianglong Chen, Haotian Wang, Kun Zhu, Xiyuan Du, Weijiang Yu, Ming Liu, Bing Qin

Natural Language Interfaces

Challenge:	Large language models (LLMs) have demonstrated strong reasoning capabilities, but they still suffer from factual errors when tackling knowledge-intensive tasks.
Approach:	They propose a reasoning framework for knowledge-intensive multi-hop QA that prioritizes promising answers at each hop of question.
Outcome:	The proposed framework outperforms SOTA methods on four open-domain multi-hop reasoning datasets by 8.5%.

When Gradient Descent Meets Derivative-Free Optimization: A Match Made in Black-Box Scenario (2023.findings-acl)

Copied to clipboard

Chengcheng Han, Liqing Cui, Renyu Zhu, Jianing Wang, Nuo Chen, Qiushi Sun, Xiang Li, Ming Gao