Papers by Meng Luo

Search Augmented Instruction Learning (2023.findings-emnlp)

Challenge:	Existing work on integrating audio encoders with large language models (LLMs) has focused on semantic understanding tasks, but different tasks may require distinct features that emphasize either semantic or acoustic aspects.
Approach:	They propose to use a prompt-aware mixture to enhance the Speech LLM that uses multiple audio encoders to extract different features based on the prompt.
Outcome:	The proposed approach outperforms all single-encoder Speech LLMs on ASR, speaker number verification, and AC tasks.

Copied to clipboard

Hongyin Luo, Tianhua Zhang, Yung-Sung Chuang, Yuan Gong, Yoon Kim, Xixin Wu, Helen Meng, James Glass

Beyond Single Frames: Can LMMs Comprehend Implicit Narratives in Comic Strip? (2025.findings-emnlp)

Challenge:	Large language models (LLMs) have been significantly improved by instruction fine-tuning, but still lack transparency and the ability to utilize up-to-date knowledge and information.
Approach:	They propose a search-augmented instruction learning model which grounds the language generation and instruction following abilities on complex search results generated by in-house and external search engines.
Outcome:	The proposed model outperforms plain LLMs on zero-shot language tasks and can generate both natural and programming languages following natural language guidance and requests.

Copied to clipboard

Xiaochen Wang, Heming Xia, Jialin Song, Longyu Guan, Qingxiu Dong, Rui Li, Yixin Yang, Yifan Pu, Weiyao Luo, Yiru Wang, Xiangdi Meng, Wenjie Li, Zhifang Sui

Wukong-Reader: Multi-modal Pre-training for Fine-grained Visual Document Understanding (2023.acl-long)

Challenge:	Large Multimodal Models have demonstrated strong performance on vision-language benchmarks, yet current evaluations focus on single-image reasoning.
Approach:	STRIPCIPHER is a benchmark designed to evaluate model ability on understanding implicit narratives in silent comics.
Outcome:	STRIPCIPHER is a high-quality, human-annotated dataset featuring fine-grained annotations and comprehensive coverage of varying difficulty levels.

Copied to clipboard

Haoli Bai, Zhiguang Liu, Xiaojun Meng, Li Wentao, Shuang Liu, Yifeng Luo, Nian Xie, Rongfu Zheng, Liangwei Wang, Lu Hou, Jiansheng Wei, Xin Jiang, Qun Liu

Aristotle: Mastering Logical Reasoning with A Logic-Complete Decompose-Search-Resolve Framework (2025.acl-long)

Challenge:	Existing solutions for visual document understanding lack granularity of document textlines.
Approach:	They propose a supervised pre-training program to leverage structural knowledge nested in document textlines to achieve fine-grained alignment between visual regions and texts.
Outcome:	The proposed system performs better on various VDU tasks in English and Chinese.

Copied to clipboard

Jundong Xu, Hao Fei, Meng Luo, Qian Liu, Liangming Pan, William Yang Wang, Preslav Nakov, Mong-Li Lee, Wynne Hsu

Towards an On-device Agent for Text Rewriting (2024.findings-naacl)

Challenge:	Existing systems fail to fully leverage the structure of logical tasks throughout the reasoning process, causing bottlenecks in efficiency and efficacy.
Approach:	They propose a logic-complete reasoning framework, Aristotle, which integrates symbolic expressions and logical rules into the entire reasoning process.
Outcome:	The proposed framework outperforms state-of-the-art reasoning frameworks in accuracy and efficiency.

Copied to clipboard

Yun Zhu, Yinxiao Liu, Felix Stahlberg, Shankar Kumar, Yu-Hui Chen, Liangchen Luo, Lei Shu, Renjie Liu, Jindong Chen, Lei Meng

Text Generation

Challenge:	Large Language Models (LLMs) have demonstrated impressive capabilities for text rewriting, however creating a smaller yet potent language model presents two formidable challenges: costly data collection and absence of emergent capabilities.
Approach:	They propose a new instruction tuning method to develop a mo-bile text rewriting model that leverages LLM-generated data and heuristic reinforcement learning, eliminating the need for human data collection.
Outcome:	The proposed model surpasses the current state-of-the-art LLMs in text rewriting while maintaining a significantly reduced model size using public benchmark EditEval and our new benchmark.

Enhancing Argument Structure Extraction with Efficient Leverage of Contextual Information (2023.findings-emnlp)

Copied to clipboard

Yun Luo, Zhen Yang, Fandong Meng, Yingjie Li, Jie Zhou, Yue Zhang

Self Question-answering: Aspect-based Sentiment Analysis by Role Flipped Machine Reading Comprehension (2021.findings-emnlp)

Challenge:	Argument structure extraction (ASE) aims to identify the discourse structure of arguments within documents.
Approach:	They propose an Efficient Context-aware ASE model that fully exploits contextual information by augmenting modeling capacity and augmenting training data.
Outcome:	The proposed model can extract argumentative discourse structure from documents and reduce reliance on specific words or less informative sentences.

Copied to clipboard

Guoxin Yu, Jiwei Li, Ling Luo, Yuxian Meng, Xiang Ao, Qing He

Information Extraction & Text Mining

Challenge:	unified Aspect-based Sentiment Analysis (ABSA) aims to couple aspect terms with their corresponding opinion terms, which might make it easier to predict sentiment polarities.
Approach:	They propose a new paradigm to pair aspect terms with their corresponding opinion terms . they propose to use a machine learning paradigm to solve the unified ABSA task .
Outcome:	The proposed framework can solve the ABSA task without any additional data annotation or transformation.

Generate, Discriminate, Evolve: Enhancing Context Faithfulness via Fine-Grained Sentence-Level Self-Evolution (2025.findings-acl)

Copied to clipboard

Kun Li, Tianhua Zhang, Yunxiang Li, Hongyin Luo, Abdalla Mohamed Salama Sayed Moustafa, Xixin Wu, James R. Glass, Helen M. Meng

Challenge:	Existing methods to improve context faithfulness in large language models are either inadequate or overlook the potential for self-improvement.
Approach:	They propose a framework that enhances context faithfulness through fine-grained sentence-level optimization.
Outcome:	Experiments on ASQA and ConFiQA datasets show that GenDiE surpasses baselines in faithfulness and correctness and exhibits robust performance for domain adaptation.

Adaptive Graph Convolutional Network for Knowledge Graph Entity Alignment (2022.findings-emnlp)

Copied to clipboard

Renbo Zhu, Xukun Luo, Meng Ma, Ping Wang

From Mimesis to Metamorphosis: Evolving VLM Judges via In-Context Comparing and Knowledge Internalization (2026.findings-acl)

Challenge:	Entity alignment (EA) aims to identify equivalent entities from different Knowledge Graphs (KGs) noisy neighbors of entities transfer invalid information, drown out equivalent information, and ultimately reduce the performance of EA.
Approach:	They propose a method to deal with neighbor noises to reduce the performance of EA by capturing the differences and complementarities of multiple KGs.
Outcome:	The proposed framework outperforms the state-of-the-art methods in supervised and unsupervised settings.

Copied to clipboard

Juntuo Wang, Yuming Qiao, Yifan Yang, Lunxi Yuan, Liang Luo, Dan Meng

Information Retrieval

Challenge:	Existing approaches to subjective assessment are inconsistent and inconsistent due to inconsistent scales and inherent preference biases.
Approach:	They propose a framework that operationalizes subjective assessment as comparative analysis and internalizes it via Language Buttons.
Outcome:	The proposed framework achieves state-of-the-art performance across multiple benchmarks and is scale-steerable.

XAL: EXplainable Active Learning Makes Classifiers Better Low-resource Learners (2024.naacl-long)

Copied to clipboard

Yun Luo, Zhen Yang, Fandong Meng, Yingjie Li, Fang Guo, Qinglin Qi, Jie Zhou, Yue Zhang

RAG-Zeval: Enhancing RAG Responses Evaluator through End-to-End Reasoning and Ranking-Based Reinforcement Learning (2025.emnlp-main)

Challenge:	Existing methods for active learning rely on model uncertainty or disagreement to pick unlabeled data, leading to over-confidence in superficial patterns and lack of exploration.
Approach:	They propose to use a bi-directional encoder and a uni-directional decoder to generate and score an explanation for low-resource text classification.
Outcome:	The proposed model improves on 9 strong baselines on six datasets and can generate explanations for its predictions.

Copied to clipboard

Kun Li, Yunxiang Li, Tianhua Zhang, Hongyin Luo, Xixin Wu, James R. Glass, Helen M. Meng

Low-Resource NLP

Challenge:	Existing evaluation frameworks rely on direct prompting of resource-intensive models with complex multi-stage prompts, introducing significant computational cost and underutilizing models’ reasoning capabilities.
Approach:	They propose a framework that trains evaluators with reinforcement learning to generate comprehensive and sound assessments with detailed explanation in one-pass.
Outcome:	The proposed framework outperforms baseline evaluation frameworks that rely on LLMs with 10-100 more parameters and achieves the strongest correlation with human judgments.

Natural Language Embedded Programs for Hybrid Language Symbolic Reasoning (2024.findings-naacl)

Copied to clipboard

Tianhua Zhang, Jiaxin Ge, Hongyin Luo, Yung-Sung Chuang, Mingye Gao, Yuan Gong, Yoon Kim, Xixin Wu, Helen Meng, James Glass

Interpretable Research Replication Prediction via Variational Contextual Consistency Sentence Masking (2022.findings-acl)

Challenge:	Existing methods for surfacing symbolic reasoning capabilities are limited to narrow tasks . arithmetic computations are unnatural to perform in pure language space, and hence present difficulties for LLMs.
Approach:	They propose a natural language embedded program framework for solving symbolic reasoning tasks.
Outcome:	The proposed framework improves on strong baselines across math and symbolic reasoning, text classification, question answering, and instruction following tasks.

Copied to clipboard

Tianyi Luo, Rui Meng, Xin Wang, Yang Liu

Let’s Be Self-generated via Step by Step: A Curriculum Learning Approach to Automated Reasoning with Large Language Models (2025.findings-acl)

Challenge:	Existing methods for predicting research replication are insufficient especially for long research papers.
Approach:	They propose to build an interpretable neural model which can provide sentence-level explanations and apply weakly supervised approach to leverage large corpus of unlabeled datasets.
Outcome:	The proposed model can provide sentence-level explanations and leverage large unlabeled datasets to boost interpretability and improve prediction performance.

Copied to clipboard

Kangyang Luo, Zichen Ding, Zhenmin Weng, Lingfeng Qiao, Meng Zhao, Xiang Li, Di Yin, Jinlong Shu

Language Models

Challenge:	Existing efforts to improve CoT prompting have limitations that require extensive human effort or performance needs to be improved.
Approach:	They propose a prompt approach for automatic reasoning called LBS3 inspired by curriculum learning which better reflects human learning habits.
Outcome:	The proposed approach achieves strongly competitive performance compared to baselines in reasoning-intensive tasks with varying open- and closed-source LLMs.

Overcome Noise and Bias: Segmentation-Aided Multi-Granularity Denoising and Debiasing for Enhanced Quarduples Extraction in Dialogue (2024.emnlp-main)

Copied to clipboard

Xianlong Luo, Meng Yang, Yihao Wang

Robustness in NLP

Challenge:	Existing methods for generating sentiment quadruples in dialogues face heightened noise and order bias challenges, leading to decreased robustness and accuracy.
Approach:	They propose a Segmentation-Aided multi-grained denoising and debiasing method to address noise and order bias challenges in ABSA.
Outcome:	The proposed method achieves word-level denoising and utterance-level demoising via topic-aware dialogue segmentation.

Decoding on Graphs: Faithful and Sound Reasoning on Knowledge Graphs through Generation of Well-Formed Chains (2025.acl-long)

Copied to clipboard

Kun Li, Tianhua Zhang, Xixin Wu, Hongyin Luo, James R. Glass, Helen M. Meng

Structured Data in NLP

Challenge:	Existing research on the utilization of Knowledge Graphs (KGs) for large language models (LLMs) relies on subgraph retriever or iterative prompting, overlooking the potential synergy of LLMs’ step-wise reasoning capabilities and KGs’ structural nature.
Approach:	They propose a graph-aware constrained decoding framework that facilitates a deep synergy between LLMs and KGs by constraint derived from the topology of the KG.
Outcome:	The proposed framework can provide faithful and sound reasoning for KGQA.

A Novel Graph-based Multi-modal Fusion Encoder for Neural Machine Translation (2020.acl-main)

Copied to clipboard

Yongjing Yin, Fandong Meng, Jinsong Su, Chulun Zhou, Zhengyuan Yang, Jie Zhou, Jiebo Luo

Tagging-Assisted Generation Model with Encoder and Decoder Supervision for Aspect Sentiment Triplet Extraction (2023.emnlp-main)

Challenge:	Existing multi-modal neural machine translation models do not fully exploit fine-grained semantic correspondences between semantic units of different modalities.
Approach:	They propose a graph-based multi-modal fusion encoder that exploits fine-grained semantic correspondences between different modalities.
Outcome:	The proposed encoder significantly extends the conventional text-based translation by taking images as additional inputs.

Copied to clipboard

Luo Xianlong, Meng Yang, Yihao Wang

Fusion-Eval: Integrating Assistant Evaluators with LLMs (2024.emnlp-industry)

Challenge:	Recent advances in the ASTE task have been driven by Natural Language Generation-based approaches, but most NLG methods overlook the supervision of the encoder-decoder hidden representations and fail to fully utilize the semantic information provided by the labels.
Approach:	They propose a tagging-assisted generation model with encoder and decoder supervision that enhances the supervision of the encoder-decoder through multiple-perspective tabbing assistance and label semantic representations.
Outcome:	The proposed model enhances the supervision of the encoder and decoder through multiple-perspective tagging assistance and label semantic representations.

Copied to clipboard

Lei Shu, Nevan Wichers, Liangchen Luo, Yun Zhu, Yinxiao Liu, Jindong Chen, Lei Meng

Text Generation

Challenge:	Recent studies have employed large language models (LLMs) as reference-free metrics for NLG evaluation, enhancing adaptability to new tasks tasks.
Approach:	They propose a method that leverages large language models to integrate insights from various assistant evaluators.
Outcome:	The proposed approach achieves a 0.962 system-level Kendall-Tau correlation with humans on SummEval and a 0.7444 turn-level Spearman correlation on TopicalChat, which is significantly higher than baseline methods.

TurnBack: A Geospatial Route Cognition Benchmark for Large Language Models through Reverse Route (2025.emnlp-main)

Copied to clipboard

Hongyi Luo, Qing Cheng, Daniel Matos, Hari Krishna Gadi, Yanfeng Zhang, Lu Liu, Yongliang Wang, Niclas Zeller, Daniel Cremers, Liqiu Meng

Language Models

Challenge:	Existing studies on large language models have limited evaluation of their geospatial cognition . a unified framework for evaluating geospcial cognition in LLMs remains absent .
Approach:	They propose a benchmark to evaluate the geospatial route cognition of Large Language Models . they propose 'pathbuilder' tool for converting natural language instructions into navigation routes .
Outcome:	The proposed framework and metrics evaluate 9 state-of-the-art LLMs on route reversal task.

GATE: Graph-based Adaptive Tool Evolution Across Diverse Tasks (2026.acl-long)

Copied to clipboard

Jianwen Luo, Yiming Huang, Jinxiang Meng, Fangyu Lei, Shizhu He, Xiao Liu, Shanshan Jiang, Bin Dong, Jun Zhao, Kang Liu

CAP: Controllable Alignment Prompting for Unlearning in LLMs (2026.acl-long)

Challenge:	Existing toolsets that use large language models are limited to single-task settings.
Approach:	They propose a framework that dynamically constructs and evolves a hierarchical graph of reusable tools across multiple scenarios.
Outcome:	The proposed framework achieves up to 4.3 faster milestone completion in Minecraft compared to the previous state-of-the-art method and provides an average improvement of 9.23% over existing tool-making methods in code generation tasks and 10.03% in agent tasks.

Copied to clipboard

Zhaokun Wang, Jinyu Guo, Jingwen Pu, Hongli Pu, Meng Yang, Xunlei Chen, Jie Ou, Wenyi Li, Guangchun Luo, Wenhong Tian

ChartAssistant: A Universal Chart Multimodal Language Model via Chart-to-Table Pre-training and Multitask Instruction Tuning (2024.findings-acl)

Challenge:	Existing methods for modifying parameters are unsystematic and rely on empirical experience.
Approach:	They propose a controllable alignment prompting for unlearning framework that decouples unlearning into a learnable prompt optimization process via reinforcement learning.
Outcome:	The proposed framework achieves precise, controllable unlearning without updating model parameters.

Copied to clipboard

Fanqing Meng, Wenqi Shao, Quanfeng Lu, Peng Gao, Kaipeng Zhang, Yu Qiao, Ping Luo

ARCQuant: Boosting NVFP4 Quantization with Augmented Residual Channels for LLMs (2026.acl-long)

Challenge:	Charts are an effective tool for understanding data patterns, but their combination of graphical elements and textual components poses challenges for general-purpose multimodal models.
Approach:	They propose a chart-based vision-language model for universal chart comprehension and reasoning that leverages a dataset of chart-related tasks.
Outcome:	The proposed model outperforms the state-of-the-art charts with zero-shot setting on various chart tasks.

Copied to clipboard

Haoqian Meng, Yilun Luo, Yafei Zhao, Wenyuan Liu, Peng Zhang, Xindian Ma

Language Models

Challenge:	NVFP4 supports fine-grained block isolation, 4-bit quantization errors and mixed-precision approaches . ARCQuant boosts NVFO4 performance via Augmented Residual Channels .
Approach:	They propose a framework that boosts NVFP4 performance via Augmented Residual Channels.
Outcome:	ARCQuant boosts NVFP4 performance via Augmented Residual Channels . the proposed framework achieves state-of-the-art accuracy comparable to full-precision baselines compared to FP16 .

AlphaQT-Bench: Diagnosing the Gap between Financial Code Generation and Quantitative Reasoning in LLMs (2026.findings-acl)

Copied to clipboard

Sichun Luo, Yi Huang, Shichang Meng, Fengyuan Liu, Mukai Li, Qinghua Yao, Zefa Hu, Junlan Feng, Qi Liu

Programming Languages in NLP

Challenge:	Existing benchmarks rely on outcome-driven metrics such as profitability and look-ahead bias.
Approach:	They propose a diagnostic benchmark for instruction-grounded financial code generation under strict semantic and temporal constraints.
Outcome:	The proposed benchmarks show that the models fail under causal, structural, or functional constraints.

Towards Adaptive Memory-Based Optimization for Enhanced Retrieval-Augmented Generation (2025.findings-acl)

Copied to clipboard

Qitao Qin, Yucong Luo, Yihang Lu, Zhibo Chu, Xiaoman Liu, Xianwei Meng

Information Retrieval

Challenge:	Existing methods for enhancing response accuracy and accuracy struggle with open-domain QA tasks because they perform independent retrieval operations without maintaining a summarizing memory or using adaptive retrieval strategies.
Approach:	They propose a method that integrates non-parametric knowledge from external knowledge bases into models to enhance response accuracy while mitigating factual errors and hallucinations.
Outcome:	The proposed method improves on open-domain QA datasets and reduces noise and hallucinations due to redundant information and insufficient information integration.

Graph-Assisted Large Language Models: A Perspective on Mitigating Intrinsic Limitations (2026.findings-acl)

Copied to clipboard

Haitong Luo, Fali Wang, Weiyao Zhang, Xianren Zhang, Zhiwei Zhang, Tianxiang Zhao, Minhua Lin, Jiahao Zhang, Hui Liu, Xianfeng Tang, Qi He, Suhang Wang, Xuying Meng, Yujun Zhang

Structured Data in NLP

Challenge:	Large language models exhibit intrinsic limitations such as knowledge cutoff, single-threaded reasoning that hinders finer-grained branch and aggregation, and rigid collaboration mechanisms that struggle to coordinate specialized capabilities.
Approach:	They propose a taxonomy spanning Graph-Assisted Knowledge Augmentation, Graph Assisted Reasoning and Planning, and Graphed LLM Collaboration.
Outcome:	The proposed models show that graphs can augment and correct LLMs and support dynamic coordination among experts and agents in collaborative settings.

Modeling Uncertainty in Composed Image Retrieval via Probabilistic Embeddings (2025.acl-long)

Copied to clipboard

Haomiao Tang, Jinpeng Wang, Yuang Peng, GuangHao Meng, Ruisheng Luo, Bin Chen, Long Chen, Yaowei Wang, Shu-Tao Xia