Papers by Zheng Yuan

Text Diffusion Model with Encoder-Decoder Transformers for Sequence-to-Sequence Generation (2024.naacl-long)

Challenge:	Large Language Models (LLMs) are transforming healthcare through their ability to understand and assist with medical tasks.
Approach:	They analyze system profiles, clinical planning, medical reasoning frameworks, and external capacity enhancement.
Outcome:	The findings highlight the future directions in medical reasoning, physical system integration, and training simulations.

Copied to clipboard

Hongyi Yuan, Zheng Yuan, Chuanqi Tan, Fei Huang, Songfang Huang

PunMemeCN: A Benchmark to Explore Vision-Language Models’ Understanding of Chinese Pun Memes (2025.emnlp-main)

Challenge:	Existing diffusion models are applied to continuous feature space while texts are sequences of discrete categorical tokens.
Approach:	They propose to use an encoder-decoder Transformer architecture to approach sequence-to-sequence text generation.
Outcome:	The proposed model improves on five sequence-to-sequence generation tasks compared to other diffusion-based models regarding text quality and inference time.

Copied to clipboard

Zhijun Xu, Siyu Yuan, Yiqiao Zhang, Jingyu Sun, Tong Zheng, Deqing Yang

Grammatical Error Correction for Code-Switched Sentences by Learners of English (2024.lrec-main)

Challenge:	Pun memes combine wordplay with visual elements to create humor, irony, or other rhetorical effects.
Approach:	They propose a benchmark to assess Chinese pun memes' processing capabilities across three progressive tasks: pun meme detection, sentiment analysis, and chat-driven meme response.
Outcome:	The proposed model can detect pun memes, analyze sentiments, and respond to chats, while ignoring homophone wordplay.

Copied to clipboard

Kelvin Wey Han Chan, Christopher Bryant, Li Nguyen, Andrew Caines, Zheng Yuan

Multilinguality

Challenge:	Existing grammar error correction systems have been trained on monolingual data and not developed for CSW text.
Approach:	They propose a method of generating synthetic CSW GEC datasets by translating different spans of text within existing GEC corpora and investigate different methods of selecting these spans based on CSW ratio, switch-point factor and linguistic constraints.
Outcome:	The proposed model achieves an average increase of 1.57 F0.5 across 3 CSW test sets (English-Chinese, English-Korean and English-Japanese) without affecting the model’s performance on a monolingual dataset.

PaddleSpeech: An Easy-to-Use All-in-One Speech Toolkit (2022.naacl-demo)

Copied to clipboard

Hui Zhang, Tian Yuan, Junkun Chen, Xintong Li, Renjie Zheng, Yuxin Huang, Xiaojie Chen, Enlei Gong, Zeyu Chen, Xiaoguang Hu, Dianhai Yu, Yanjun Ma, Liang Huang

An LLM-Enhanced Adversarial Editing System for Lexical Simplification (2024.lrec-main)

Challenge:	PaddleSpeech is an open-source speech toolkit that supports speech-to-text and text-to speech tasks.
Approach:	They describe the design philosophy and core architecture of PaddleSpeech to support several essential speech-to-text and text-to speech tasks.
Outcome:	The proposed framework achieves competitive or state-of-the-art performance on various speech datasets and implements the most popular methods.

Copied to clipboard

Keren Tan, Kangyang Luo, Yunshi Lan, Zheng Yuan, Jinlong Shu

An Extended Sequence Tagging Vocabulary for Grammatical Error Correction (2023.findings-eacl)

Challenge:	Existing methods to simplify text rely heavily on annotated data, making it challenging to apply in low-resource scenarios.
Approach:	They propose a Lexical Simplification method without parallel corpora that uses an Adversarial Editing System and an LLM-enhanced loss to distill knowledge into a small-size LS system.
Outcome:	The proposed method uses an LLM-enhanced loss to distill knowledge from Large Language Models (LLMs) into a small-size LS system.

Copied to clipboard

Stuart Mesham, Christopher Bryant, Marek Rei, Zheng Yuan

Syntactic Text Processing

Challenge:	Current sequence-to-sequence and sequence-tagging approaches treat GEC as a machine-translation problem.
Approach:	They propose to introduce specialised tags for spelling correction and morphological inflection using the SymSpell and LemmInflect algorithms.
Outcome:	The proposed approach outperforms existing methods on the BEA benchmark.

DeepPresenter: Environment-Grounded Reflection for Agentic Presentation Generation (2026.findings-acl)

Copied to clipboard

Hao Zheng, Guozhao Mo, Xinru Yan, Qianhao Yuan, Wenkai Zhang, Xuanang Chen, Yaojie Lu, Hongyu Lin, Xianpei Han, Le Sun

Challenge:	Existing presentation agents rely on predefined workflows and fixed templates to generate presentations.
Approach:	They propose an agentic framework that adapts to diverse user intents and iterative refinement based on observation.
Outcome:	The proposed framework can be used to generate presentations with environmental observations.

LoNAS: Elastic Low-Rank Adapters for Efficient Large Language Models (2024.lrec-main)

Copied to clipboard

Juan Pablo Munoz, Jinjie Yuan, Yi Zheng, Nilesh Jain

MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing (2026.acl-industry)

Challenge:	Large Language Models (LLMs) reach hundreds of billions of parameters and require resources for training and inference stages.
Approach:	They propose a low-rank adapter to reduce the number of trainable parameters in a model and reduce memory requirements.
Outcome:	The proposed approach reduces memory and compute requirements while preserving performance.

Copied to clipboard

Junbo Niu, Zheng Liu, Zhuangcheng Gu, Bin Wang, Linke Ouyang, Zhiyuan Zhao, Tao Chu, Tianyao He, Fan Wu, Qintong Zhang, Zhenjiang Jin, Guang Liang, Rui Zhang, Wenzheng Zhang, Yuan Qu, Zhifei Ren, Yuefeng Sun, Zirui Tang, Boyu Niu, Yuanhong Zheng, Dongsheng Ma, Ziyang Miao, Hejun Dong, Siyi Qian, Junyuan Zhang, Fangdong Wang, Jingzhou Chen, Xiaomeng Zhao, Liqun Wei, Wei Li, Shasha Wang, RuiLiang Xu, Yuanyuan Cao, Lu Chen, Qianqian Wu, Huaiyu Gu, Lindong Lu, Dechen Lin, null Shenguanlin, Xuanhe Zhou, Linfeng Zhang, Yuhang Zang, Xiaoyi Dong, Jiaqi Wang, Bo Zhang, Lei Bai, Pei Chu, Weijia Li, Jiang Wu, Lijun Wu, Zhenxiang Li, Guangyu Wang, Zhongying Tu, Chao Xu, Kai Chen, Bowen Zhou, Dahua Lin, Wentao Zhang, Conghui He

Green & Sustainable NLP

Challenge:	Document images are characterized by higher resolutions, denser content, and more complex structural layouts.
Approach:	They propose a 1.2B-parameter document parsing vision-language model that decouples layout analysis from local content recognition.
Outcome:	The proposed model surpasses general-purpose and domain-specific models on multiple benchmarks while maintaining significantly lower computational overhead.

SELECting over Tokens: Curating Pre-training Data at Scale via Token Classification (2026.acl-long)

Copied to clipboard

Xin Tong, Weidong Zhang, Jiaang Li, Haibin Chen, Shilei Liu, Langming Liu, Kangtao Lv, Yujin Yuan, Wenbo Su, Bo Zheng

Information Retrieval

Challenge:	Existing pipelines rely on expert-crafted heuristic rules, which lack content-aware, fine-grained noise detection.
Approach:	They propose a framework that reframes data refinement as a highly efficient token classification task.
Outcome:	The proposed framework outperforms existing pipelines on benchmarks and is 2.5x faster at inference.

Prompting open-source and commercial language models for grammatical error correction of English learner text (2024.findings-acl)

Copied to clipboard

Christopher Davis, Andrew Caines, O Andersen, Shiva Taslimipoor, Helen Yannakoudakis, Zheng Yuan, Christopher Bryant, Marek Rei, Paula Buttery

Low-Resource NLP

Challenge:	Recent advances in generative AI have enabled us to prompt large language models (LLMs) to produce texts which are fluent and grammatical.
Approach:	They evaluate model performance by measuring their performance on established benchmarks.
Outcome:	The proposed models outperform supervised English GEC models on fluency correction benchmarks and commercial LLMs on edit benchmarks.

Beyond Black-Box Interventions: Latent Probing for Faithful Retrieval-Augmented Generation (2026.findings-acl)

Copied to clipboard

Linfeng Gao, Qinggang Zhang, Baolong Bi, Bo Zeng, Zheng Yuan, Zerui Chen, Zhimin Wei, Shenghua Liu, Linlong Xu, Longyue Wang, Weihua Luo, Jinsong Su

Information Retrieval

Challenge:	Existing approaches to improve contextual faithfulness treat the LLM as a black box, generating responses that are inconsistent with the provided context.
Approach:	They propose a framework for faithful RAG that operates in three stages: (i) fine-grained knowledge pruning to filter irrelevant context, (ii) latent conflict probing to identify hard conflicts in the model’s latent space, and (iv) conflict-aware attention to modulate attention heads toward faithful context integration.
Outcome:	Experiments show that ProbeRAG significantly improves both accuracy and contextual faithfulness.

Investigating Multi-Hop Factual Shortcuts in Knowledge Editing of Large Language Models (2024.acl-long)

Copied to clipboard

Tianjie Ju, Yijin Chen, Xinwei Yuan, Zhuosheng Zhang, Wei Du, Yubin Zheng, Gongshen Liu

KidsArtBench: Multi-Dimensional Children’s Art Evaluation with Attribute-Aware MLLMs (2026.eacl-long)

Challenge:	Recent work has demonstrated the power of large language models in recalling knowledge and reasoning.
Approach:	They propose to erase shortcut neurons to mitigate the associated risks . 20% of the failures are attributed to shortcuts, they find .
Outcome:	The proposed approach reduces failures in multi-hop knowledge editing caused by shortcuts by 20% .

Copied to clipboard

Mingrui Ye, Chanjin Zheng, Zengyi Yu, Chenyu Xiang, Zhixue Zhao, Zheng Yuan, Helen Yannakoudakis

Can Public Large Language Models Help Private Cross-device Federated Learning? (2024.findings-naacl)

Challenge:	Multimodal Large Language Models (MLLMs) show impressive capabilities across visual–language tasks, but their capacity to evaluate artistic expression remains limited.
Approach:	They propose an attribute-specific multi-LoRA approach where each attribute corresponds to a distinct evaluation dimension in the scoring rubric.
Outcome:	The proposed approach increases correlation from 0.468 to 0.653 on Qwen2.5-VL-7B, with the largest gains on perceptual dimensions and narrowed gaps on higher-order attributes.

Copied to clipboard

Boxin Wang, Yibo Zhang, Yuan Cao, Bo Li, Hugh McMahan, Sewoong Oh, Zheng Xu, Manzil Zaheer

Responsible & Trustworthy NLP

Challenge:	Recent studies have shown that public data can be used to improve privacy-utility trade-offs for large and small language models.
Approach:	They propose to use large-scale public data to help differentially private FL training . they propose a distribution matching algorithm with theoretical grounding to sample public data close to private data distribution .
Outcome:	The proposed method is efficient and effective for training private models by taking advantage of public data.

Generative Biomedical Entity Linking via Knowledge Base-Guided Pre-training and Synonyms-Aware Fine-tuning (2022.naacl-main)

Copied to clipboard

Hongyi Yuan, Zheng Yuan, Sheng Yu

Delving Deep into Regularity: A Simple but Effective Method for Chinese Named Entity Recognition (2022.findings-naacl)

Challenge:	Generative methods for biomedical entity linking (EL) use synonyms knowledge from knowledge bases (KB) this is not trivial to inject into a generative method, but it is cost-effective.
Approach:	They propose to inject synonyms knowledge into a generative model of biomedical EL by constructing synthetic samples with synonyms and definitions from KB and requiring the model to recover concept names.
Outcome:	The proposed method achieves state-of-the-art results on several biomedical EL tasks without candidate selection.

Copied to clipboard

Yingjie Gu, Xiaoye Qu, Zhefeng Wang, Yi Zheng, Baoxing Huai, Nicholas Jing Yuan

Information Extraction & Text Mining

Challenge:	Named entity recognition (NER) is a system for identifying text spans pertaining to specific entity types.
Approach:	They propose a method to investigate the regularity of Chinese NER's entity mentions by a regularity-aware module and a periodicity-gnostic module.
Outcome:	The proposed model significantly outperforms previous state-of-the-art methods on three benchmark datasets and a practical medical dataset.

Pingan Smart Health and SJTU at COIN - Shared Task: utilizing Pre-trained Language Models and Common-sense Knowledge in Machine Reading Tasks (D19-60)

Copied to clipboard

Xiepeng Li, Zhexi Zhang, Wei Zhu, Zheng Li, Yuan Ni, Peng Gao, Junchi Yan, Guotong Xie

Construction of the Literature Graph in Semantic Scholar (N18-3)

Challenge:	Existing approaches to represent knowledge in the low-dimensional space are to leverage large-scale unsupervised text corpus to train fixed or contextual representations.
Approach:	They propose to leverage large-scale unsupervised text corpus to train fixed or contextual language representations and to express knowledge into a knowledge graph (KG) they incorporate distributional representations of a KG onto the representations from pre-trained language models, via simply concatenation or multi-head attention.
Outcome:	The proposed models outperform the other models on the COIN: COmmonsense INference in Natural Language Processing (COIN) Workshop datasets.

Copied to clipboard

Waleed Ammar, Dirk Groeneveld, Chandra Bhagavatula, Iz Beltagy, Miles Crawford, Doug Downey, Jason Dunkelberger, Ahmed Elgohary, Sergey Feldman, Vu Ha, Rodney Kinney, Sebastian Kohlmeier, Kyle Lo, Tyler Murray, Hsu-Han Ooi, Matthew Peters, Joanna Power, Sam Skjonsberg, Lucy Lu Wang, Chris Wilhelm, Zheng Yuan, Madeleine van Zuylen, Oren Etzioni

Structured Data in NLP

Challenge:	Fig. 1 summarizes a scalable system for organizing published scientific literature into a heterogeneous graph . authors describe methods used to enable semantic features in www.semanticscholar.org .
Approach:	They describe a scalable system for organizing published scientific literature into a heterogeneous graph to facilitate algorithmic manipulation and discovery.
Outcome:	The proposed system can be deployed on a scalable platform and report empirical results for each task.

Mitigating Selection Bias in Large Language Models via Permutation-Aware GRPO (2026.acl-long)

Copied to clipboard

Jinquan Zheng, Jia Yuan, Jiacheng Yao, Chenyang Gu, Pujun Zheng, Guoxiu He

Read As Human: Compressing Context via Parallelizable Close Reading and Skimming (2026.acl-long)

Challenge:	Existing inference-time debiasing ignores that the same question should yield consistent answers across permutations.
Approach:	They propose a permutation-aware group-relative policy optimization which enforces permutations-consistent semantic reasoning.
Outcome:	The proposed model outperforms strong baselines across seven benchmarks while maintaining high overall performance.

Copied to clipboard

Jiwei Tang, Shilei Liu, Zhicheng Zhang, Qingsong Lv, Runsong Zhao, Tingwei Lu, Langming Liu, Haibin Chen, Yujin Yuan, Hai-Tao Zheng, Wenbo Su, Bo Zheng

Challenge:	Existing task-aware methods require loading the entire input sequence at once for compression, which suffer from computational inefficiency.
Approach:	They propose a framework that adopts an adaptive hybrid reading strategy to reduce computational inefficiency and redundant information in long-context scenarios.
Outcome:	Experiments show that RAM outperforms baselines on multiple question answering and summarization benchmarks while delivering up to a 12x speedup on long inputs.

Fluent and Low-latency Simultaneous Speech-to-Speech Translation with Self-adaptive Training (2020.findings-emnlp)

Copied to clipboard

Renjie Zheng, Mingbo Ma, Baigong Zheng, Kaibo Liu, Jiahong Yuan, Kenneth Church, Liang Huang

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

Challenge:	Current approaches to simultaneous speech-to-speech translation accumulate more and more latencies in later sentences when the speaker talks faster.
Approach:	They propose a method which generates more fluent target speech latency than the baseline . they propose to use self-adaptive translation to adjust the length of translations to accommodate different source speech rates.
Outcome:	Xiong et al., 2019) show that the proposed method generates more fluent target speech latency than baseline . authors say it provides more natural communication process than speech-to-text translation . xiong and colleagues say the proposed technique is more efficient than current approaches .

Copied to clipboard

Jihao Gu, Yingyao Wang, Pi Bu, Chen Wang, Ziming Wang, Tengtao Song, Donglai Wei, Jiale Yuan, Yingxiu Zhao, Yancheng He, Shilong Li, Jiaheng Liu, Meng Cao, Jun Song, Yingshui Tan, Xiang Li, Wenbo Su, Xiaoyong Zhu, Bo Zheng

DP3: Differentially Private Prompt Perturbation for Multi-turn LLM Inference (2026.findings-acl)

Challenge:	Existing models for large vision language models do not fully reflect their knowledge capacity and reliability, resulting in erroneous outputs that do not align with the image content or provide answers lacking knowledge evidence.
Approach:	They propose a Chinese-based benchmark for visual factuality across 8 major topics and 56 subtopics and a multi-hop question construction.
Outcome:	The proposed model decouples visual factuality into two parts: seeing the world and discovering knowledge.

Copied to clipboard

Lele Zheng, Chao Zhang, Feiyang Yuan, Ke Cheng, Tao Zhang, Anxiao Song, Yulong Shen

Responsible & Trustworthy NLP

Challenge:	Large language models (LLMs) are widely used for text understanding and generation . existing methods that assume single-turn interactions break down in multi-turn settings .
Approach:	They propose a differentially private prompt perturbation framework for multi-turn LLM inference . DP3 constructs a perturbation mapping table to reuse perturbations for recurring tokens .
Outcome:	The proposed framework reduces privacy costs and degrades cross-turn semantic coherence . it also provides a context-aware utility function to maintain semantic consistency across turns .

TRIGO: Benchmarking Formal Mathematical Proof Reduction for Generative Language Models (2023.emnlp-main)

Copied to clipboard

Jing Xiong, Jianhao Shen, Ye Yuan, Haiming Wang, Yichun Yin, Zhengying Liu, Lin Li, Zhijiang Guo, Qingxing Cao, Yinya Huang, Chuanyang Zheng, Xiaodan Liang, Ming Zhang, Qun Liu

Quantifying the Impact of Structured Output Format on Large Language Models through Causal Inference (2026.findings-eacl)

Challenge:	Automated theorem proving (ATP) benchmarks focus on symbolic inference but rarely involve understanding complex number combination reasoning.
Approach:	They propose a benchmark that requires a model to reduce a trigonometric expression with step-by-step proof and evaluates a generative LM’s reasoning ability on formulas and ability to manipulate, group, and factor number terms.
Outcome:	The proposed benchmark evaluates a generative LM’s reasoning ability on formulas and ability to manipulate, group, and factor number terms.

Copied to clipboard

Han Yuan, Yue Zhao, Li Zhang, Wuqiong Luo, Zheng Ma

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

Challenge:	Prior studies have examined the impact of structured output on LLMs’ generation quality, often presenting one-way findings.
Approach:	They propose to derive five potential causal structures characterizing the influence of structured output on LLMs’ generation using one assumed and two guaranteed constraints.
Outcome:	The proposed pipeline can be extended to other modules and is not limited to structured output but can be used in industrial applications.

Copied to clipboard

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

Support or Refute: Analyzing the Stance of Evidence to Detect Out-of-Context Mis- and Disinformation (2023.emnlp-main)

Challenge:	Large Language Models lack the capacity to formulate global strategies due to latency and availability constraints.
Approach:	They propose a framework to internalize the strategic oversight of large models into intrinsic Latent Guidance by synthesizing a query-conditioned Latent Guide.
Outcome:	The proposed framework outperforms strong baselines on mathematical and coding benchmarks with negligible inference latency.

Copied to clipboard

Xin Yuan, Jie Guo, Weidong Qiu, Zheng Huang, Shujun Li

LLM-based Code-Switched Text Generation for Grammatical Error Correction (2024.emnlp-main)

Challenge:	Mis- and disinformation online are a major source of harms of different kinds . out-of-context information is where different pieces of information are falsely associated . past studies have attempted to defend against OOC mis- and deinformation through external evidence, but they disregard the role of different pieces with different stances.
Approach:	They propose a stance extraction network that can extract stances of different pieces of evidence in a single framework.
Outcome:	The proposed model outperforms the state-of-the-art models on a public large-scale dataset with a performance gain of 3.2% in accuracy.

Copied to clipboard

Tom Potter, Zheng Yuan

Multilinguality

Challenge:	Code-switching (CSW) is a part of multilingual conversation and is gaining popularity in social and professional settings.
Approach:	They propose to use synthetic data to generate a model capable of correcting grammatical errors in CSW texts.
Outcome:	The proposed model improves on existing systems on an authentic dataset from English as a second language learners.

How to inject knowledge efficiently? Knowledge Infusion Scaling Law for Pre-training Large Language Models (2025.emnlp-main)

Copied to clipboard

Kangtao Lv, Haibin Chen, Yujin Yuan, Langming Liu, Shilei Liu, Yongwei Wang, Wenbo Su, Bo Zheng

Evaluating LLMs’ Assessment of Mixed-Context Hallucination Through the Lens of Summarization (2025.findings-acl)

Challenge:	Recent studies show that strategically infusing domain knowledge during pretraining can substantially improve downstream performance.
Approach:	They propose a knowledge infusion scaling law that predicts the optimal amount of domain knowledge to inject into large LLMs by analyzing their smaller counterparts.
Outcome:	The proposed model predicts the optimal amount of domain knowledge to inject into large LLMs by analyzing their smaller counterparts.

Copied to clipboard

Siya Qi, Rui Cao, Yulan He, Zheng Yuan

Text Generation

Challenge:	Large language models generate coherent text and follow instructions across diverse tasks, but a critical challenge in scaling LLM applications is hallucination, where the generated content lacks factual grounding or deviates from the intended discourse context.
Approach:	They use summarization as a representative task to evaluate LLMs' capability in detecting mixed-context hallucinations, specifically distinguishing between factual and non-factual hallucinos.
Outcome:	The proposed model distinguishes between factual and non-factual hallucinations, and their performance bottlenecks.

Assessing the Efficacy of Grammar Error Correction: A Human Evaluation Approach in the Japanese Context (2024.lrec-main)

Copied to clipboard

Qiao Wang, Zheng Yuan

Syntactic Text Processing

Challenge:	Using an automatic annotation toolkit, we evaluated the performance of the sequence tagging grammar error detection and correction model (SeqTagger) using Japanese university students’ writing samples.
Approach:	They evaluated the performance of the state-of-the-art sequence tagging grammar error detection and correction model using Japanese university students’ writing samples.
Outcome:	The proposed model shows a high precision but conservativeness in error detection and correction.

FineRAG: Fine-grained Retrieval-Augmented Text-to-Image Generation (2025.coling-main)

Copied to clipboard

Huaying Yuan, Ziliang Zhao, Shuting Wang, Shitao Xiao, Minheng Ni, Zheng Liu, Zhicheng Dou

Code Synonyms Do Matter: Multiple Synonyms Matching Network for Automatic ICD Coding (2022.acl-short)

Challenge:	Recent advances in text-to-image generation still exhibit limitations in terms of knowledge access.
Approach:	They propose a fine-grained retrieval-augmented image generation model that breaks down the retrieval task into four critical stages: query decomposition, candidate selection, retrieval augmented diffusion, and self-reflection.
Outcome:	The proposed method significantly reduces noise associated with retrieval-augmented image generation and performs better in complex, open-world scenarios.

Copied to clipboard

Zheng Yuan, Chuanqi Tan, Songfang Huang

Challenge:	Existing methods for automatic ICD coding use label attention to match related text snippets.
Approach:	They propose to use code synonyms to leverage for better code representation learning.
Outcome:	The proposed method outperforms previous state-of-the-art methods on the MIMIC-III dataset.

PRIME: A Process-Outcome Alignment Benchmark for Verifiable Reasoning in Mathematics and Engineering (2026.acl-long)

Copied to clipboard

Xiangfeng Wang, Hangyu Guo, Yanlin Lai, Mitt Huang, Liang Zhao, Chengyuan Yao, Yinmin Zhang, Qi Han, null Xiaoxiaoren, Chun Yuan, Tong Xu, Zheng Ge, Xiangyu Zhang, Daxin Jiang

V-MAGE: A Game Evaluation Framework for Assessing Vision-Centric Capabilities in Multimodal Large Language Models (2026.findings-acl)

Challenge:	Current outcome-centric verification paradigms neglect potential errors in the derivation process.
Approach:	They propose a process-aware RLVR training paradigm utilizing verifiers selected via PRIME.
Outcome:	The proposed approach outperforms the baseline verification paradigm on AIME24, AIME25, and Beyond-AIME models.

Copied to clipboard

Xiangxi Zheng, Linjie Li, Zhengyuan Yang, Ping Yu, Alex Jinpeng Wang, Rui Yan, Yuan Yao, Lijuan Wang

On the Transferability of Adversarial Attacks against Neural Text Classifier (2021.emnlp-main)

Challenge:	Existing static image-text benchmarks are insufficient for evaluating multimodal large language models’ dynamic perception and interactive reasoning abilities.
Approach:	They propose a game-based evaluation framework to assess multimodal large language models’ visual reasoning in dynamic, continuous-space environments.
Outcome:	The proposed framework systematically assesses MLLMs’ visual reasoning in dynamic, continuous-space environments.

Copied to clipboard

Liping Yuan, Xiaoqing Zheng, Yi Zhou, Cho-Jui Hsieh, Kai-Wei Chang

Robustness in NLP

Challenge:	Existing studies show that deep neural networks are vulnerable to adversarial examples . a small perturbation to an input alters the model prediction .
Approach:	They propose a genetic algorithm to find models that can induce adversarial examples to fool models . they propose word replacement rules that can be used for model diagnostics from these examples .
Outcome:	The proposed model can fool almost all existing models, while ignoring the data bias in the training set.

MLDSP-MA: Multidimensional Attention for Multi-Round Long Dialogue Sentiment Prediction (2024.lrec-main)

Copied to clipboard

Yunfei Yin, Congrui Zou, Zheng Yuan, Xianjian Bao

Natural Language Interfaces

Challenge:	Existing methods for dialogue sentiment prediction are weak, resulting in errors.
Approach:	They propose a multi-round long dialogue sentiment prediction model based on multidimensional attention that captures historical dialogues and integrates with local attention.
Outcome:	The proposed model improves by 3.5% in accuracy and 5.7% in Micro-F1 score on dialogue datasets.

Rubrik’s Cube: Testing a New Rubric for Evaluating Explanations on the CUBE dataset (2025.acl-long)

Copied to clipboard

Diana Galvan-Sosa, Gabrielle Gaudeau, Pride Kavumba, Yunmeng Li, Hongyi Gu, Zheng Yuan, Keisuke Sakaguchi, Paula Buttery

Explainability & Interpretability in NLP

Challenge:	Large-Language Models (LLMs) are increasingly being used in explanation generation tasks due to their unreliability.
Approach:	They propose a rubric and a dataset of 26k explanations written and quality-annotated using the rubric by humans and six open- and closed-source LLMs to test their proposed rubric.
Outcome:	The proposed rubric and CUBE dataset focuses on reasoning and language tasks and provides the necessary diversity to test it.

HiGoE: Hierarchical Graph of Evidence to Enhance Retrieval-Augmented Generation for Long-context Summarization (2026.acl-long)

Copied to clipboard

Long Yuan, Kaiwen Tian, Zi Chen, Bolong Zheng, Chuan Ma

Text Generation

Challenge:	Existing methods for long-context summarization fail to capture high-level thematic structures and long-range dependencies.
Approach:	They propose a hierarchical Graph of Evidence to reduce hallucination and attention dilution by replacing unreliable chunk-based methods with a filtered proposition–evidence graph.
Outcome:	Experiments show that HiGoE surpasses baselines in quality and efficiency.

Paraphrase Makes Perfect: Leveraging Expression Paraphrase to Improve Implicit Sentiment Learning (2025.coling-main)

Copied to clipboard

Xia Li, Junlang Wang, Yongqiang Zheng, Yuan Chen, Yangjia Zheng

Sentiment Analysis

Challenge:	Existing implicit sentiment learning methods focus on capturing implicit sentiment knowledge individually, without considering the potential connection between implicit and explicit sentiment.
Approach:	They propose an expression paraphrase strategy and a sentiment-consistent contrastive learning mechanism to learn the connections between implicit and explicit sentiment expressions and integrate them into the model.
Outcome:	The proposed method is effective on implicit sentiment analysis on public datasets.

Beyond the Score: Uncertainty-Calibrated LLMs for Automated Essay Assessment (2025.emnlp-main)

Copied to clipboard

Ahmed Karim, Qiao Wang, Zheng Yuan

Challenge:	Automated Essay Scoring (AES) systems attain near–human agreement on some public benchmarks, but real-world adoption is limited.
Approach:	They propose a distribution-free wrapper that equips any classifier with set-valued outputs enjoying formal coverage guarantees.
Outcome:	The proposed model achieves coverage targets while keeping prediction sets compact.

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

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

Speculative Contrastive Decoding (2024.acl-short)

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

Hongyi Yuan, Keming Lu, Fei Huang, Zheng Yuan, Chang Zhou

Uncertainty-Aware Iterative Preference Optimization for Enhanced LLM Reasoning (2025.acl-long)

Challenge:	Large language models (LLMs) exhibit exceptional performance in language tasks, yet their auto-regressive inference is limited due to high computational requirements and is sub-optimal due to the exposure bias.
Approach:	They propose a decoding approach that leverages predictions from smaller language models to achieve both decoding acceleration and quality improvement.
Outcome:	The proposed method achieves both decoding acceleration and quality improvement on four diverse language tasks.

Copied to clipboard

Lei Li, Hehuan Liu, Yaxin Zhou, ZhaoYang Gui, Xudong Weng, Yi Yuan, Zheng Wei, Zang Li

Can LLMs Simulate L2-English Dialogue? An Information-Theoretic Analysis of L1-Dependent Biases (2025.acl-long)

Challenge:	Existing methods for enhancing the performance of large language models require expensive manual annotations.
Approach:	They propose an offline direct preference optimization method that collects preference pairs through iterative sampling and execution feedback to improve model confidence.
Outcome:	The proposed method improves performance on three reasoning tasks and shows a 3.6% improvement over the standard method.

Copied to clipboard

Rena Wei Gao, Xuetong Wu, Tatsuki Kuribayashi, Mingrui Ye, Siya Qi, Carsten Roever, Yuanxing Liu, Zheng Yuan, Jey Han Lau

Dialogue Systems & Conversational Agents

Challenge:	Large Language Models (LLMs) can simulate non-native-like English use observed in human second language (L2) learners interfered with by their native first language (N1) knowledge.
Approach:	They use large language models to simulate non-native-like English use observed in human second language (L2) learners, and then compare their outputs to real L2 learner data.
Outcome:	The proposed models replicate L1-dependent patterns observed in human second language (L2) learners, with distinct influences from various languages.

MoleculeQA: A Dataset to Evaluate Factual Accuracy in Molecular Comprehension (2024.findings-emnlp)

Copied to clipboard

Xingyu Lu, He Cao, Zijing Liu, Shengyuan Bai, Leqing Chen, Yuan Yao, Hai-Tao Zheng, Yu Li

Question Answering

Challenge:	Existing models generate erroneous information and evaluations fail to assess factual correctness of models.
Approach:	They propose to use MoleculeQA to evaluate molecular factual correctness in large language models by organizing molecules into a taxonomy and building QA pairs through human and LLM efforts.
Outcome:	The proposed model improves the factual correctness of generated information and enables the development of new models.

MuggleMath: Assessing the Impact of Query and Response Augmentation on Math Reasoning (2024.acl-long)

Copied to clipboard

Chengpeng Li, Zheng Yuan, Hongyi Yuan, Guanting Dong, Keming Lu, Jiancan Wu, Chuanqi Tan, Xiang Wang, Chang Zhou

HyPe: Better Pre-trained Language Model Fine-tuning with Hidden Representation Perturbation (2023.acl-long)

Challenge:	In math reasoning with large language models, fine-tuning data augmentation by query evolution and diverse reasoning paths is empirically verified effective.
Approach:	They propose to fine-tune data augmentation by query evolution and diverse reasoning paths.
Outcome:	The proposed model achieves new state-of-the-art on GSM8K and MATH.

Copied to clipboard

Hongyi Yuan, Zheng Yuan, Chuanqi Tan, Fei Huang, Songfang Huang

VehicleWorld: A Highly Integrated Multi-Device Environment for Intelligent Vehicle Interaction (2025.findings-emnlp)

Challenge:	Existing techniques to fine-tune pre-trained language models on downstream tasks are inadequate.
Approach:	They propose a technique to perturb hidden Transformers representations by enhancing generalization of hidden representations from different layers.
Outcome:	The proposed technique outperforms vanilla fine-tuning and enhances generalization of hidden representations from different layers.

Copied to clipboard

Jie Yang, Jiajun Chen, Zhangyue Yin, Shuo Chen, Yuxin Wang, Yiran Guo, Yuan Li, Yining Zheng, Xuanjing Huang, Xipeng Qiu

Challenge:	Traditional Function Calling (FC) approaches operate statelessly, requiring multiple exploratory calls to build environmental awareness before execution, leading to inefficiency and limited error recovery.
Approach:	They propose a state-based function call approach that maintains explicit system state awareness and implements direct state transitions to achieve target conditions.
Outcome:	The proposed approach outperforms traditional function calling approaches, achieving superior execution accuracy and reduced latency.

Med-MoE: Mixture of Domain-Specific Experts for Lightweight Medical Vision-Language Models (2024.findings-emnlp)

Copied to clipboard

Songtao Jiang, Tuo Zheng, Yan Zhang, Yeying Jin, Li Yuan, Zuozhu Liu

How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition (2024.acl-long)

Challenge:	Recent advances in multimodal large language models have seen remarkable progress for medical decision-making, however, they are designated for specific classification or generative tasks and require model training or finetuning on large-scale datasets with sizeable parameters and tremendous computing.
Approach:	They propose a framework that tackles discriminative and generative multimodal medical tasks using multimodal alignment, instruction tuning and routing.
Outcome:	The proposed model can achieve superior performance to or on par with state-of-the-art baselines while only requiring 30%-50% of activated model parameters.

Copied to clipboard

Guanting Dong, Hongyi Yuan, Keming Lu, Chengpeng Li, Mingfeng Xue, Dayiheng Liu, Wei Wang, Zheng Yuan, Chang Zhou, Jingren Zhou

Do LLMs Overcome Shortcut Learning? An Evaluation of Shortcut Challenges in Large Language Models (2024.emnlp-main)

Challenge:	supervised fine-tuning (SFT) is a technique used to enhance multiple abilities in large language models.
Approach:	They propose to study the interplay of data composition between mathematical reasoning, code generation, and general human-aligning abilities during supervised fine-tuning.
Outcome:	The proposed model improves math reasoning and code generation with increasing data amount . the proposed model size and SFT strategies can be used to learn multiple skills with different scaling patterns.

Copied to clipboard

Yu Yuan, Lili Zhao, Kai Zhang, Guangting Zheng, Qi Liu

Responsible & Trustworthy NLP

Challenge:	Large Language Models (LLMs) have shown remarkable capabilities in various tasks, but may rely on dataset biases as shortcuts for prediction.
Approach:	They propose to use a test suite to evaluate the impact of shortcuts on LLMs' performance.
Outcome:	The proposed test suite incorporates six shortcut types, five evaluation metrics, and four prompting strategies.

R3-RAG: Learning Step-by-Step Reasoning and Retrieval for LLMs via Reinforcement Learning (2025.findings-emnlp)

Copied to clipboard

Yuan Li, Qi Luo, Xiaonan Li, Bufan Li, Qinyuan Cheng, Bo Wang, Yining Zheng, Yuxin Wang, Zhangyue Yin, Xipeng Qiu

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

Challenge:	RAG systems that integrate external knowledge with Large Language Models often become bottlenecks due to their limited parameters compared to LLMs and their inability to perform step-by-step reasoning.
Approach:	They propose a model that integrates external knowledge with Large Language Models to enhance factual correctness and mitigate hallucination.
Outcome:	The proposed model outperforms baselines and can transfer well to different retrievers.

Copied to clipboard

Runsong Zhao, Shilei Liu, Jiwei Tang, Langming Liu, Haibin Chen, Weidong Zhang, Yujin Yuan, Tong Xiao, JingBo Zhu, Wenbo Su, Bo Zheng

Knowledge-to-SQL: Enhancing SQL Generation with Data Expert LLM (2024.findings-acl)

Challenge:	a novel architecture that enables LLMs to handle arbitrarily long sequences with constant memory usage and linear time complexity is a major barrier to long-context processing.
Approach:	They propose a novel architecture that enables LLMs to handle arbitrarily long sequences with constant memory usage and linear time complexity.
Outcome:	The proposed architecture can handle arbitrarily long sequences with constant memory usage and linear time complexity.

Copied to clipboard

Zijin Hong, Zheng Yuan, Hao Chen, Qinggang Zhang, Feiran Huang, Xiao Huang

Programming Languages in NLP

Challenge:	Existing methods for Generating accurate SQL queries for user questions rely on the capability of large language models (LLMs) however, some knowledge is not explicitly included in the database schema and user question or has been learned by LLMs.
Approach:	They propose a Knowledge-to-SQL framework that employs tailored Data Expert LLM (DELLM) to provide helpful knowledge for all text-to SQL models.
Outcome:	The proposed framework improves the state-of-the-art approaches for text-to-SQL tasks by leveraging a data expert LLM (DELLM) to provide useful knowledge for all text- to-SqL models.

Fusing Heterogeneous Factors with Triaffine Mechanism for Nested Named Entity Recognition (2022.findings-acl)

Copied to clipboard

Zheng Yuan, Chuanqi Tan, Songfang Huang, Fei Huang

Information Extraction & Text Mining

Challenge:	Named entity recognition (NER) is a fundamental natural language processing task that extracts entities from texts.
Approach:	They propose a triaffine mechanism which integrates heterogeneous factors into a single model to fuse these factors into one model to achieve better span representation.
Outcome:	The proposed method outperforms previous span-based methods and achieves state-of-the-art F1 scores on nested NER datasets GENIA and KBP2017.

COIG-P: A High-Quality and Large-Scale Chinese Preference Dataset for Alignment with Human Values (2026.findings-eacl)

Copied to clipboard

Siwei Wu, JinCheng Ren, Xeron Du, Shuyue Guo, Xingwei Qu, Yiming Liang, Jie Liu, Yunwen Li, Tyler Loakman, Tianyu Zheng, Boyu Feng, Huaqing Yuan, Zili Wang, Jiaheng Liu, Wenhao Huang, Chenglin Cai, Haoran Que, Jian Yang, Yuelin Bai, Zekun Moore Wang, Zhouliang Yu, Qunshu Lin, Ding Pan, Yuchen Eleanor Jiang, Tiannan Wang, Wangchunshu Zhou, Shenzhi Wang, Xingyuan Bu, Minghao Liu, Guoyin Wang, Ge Zhang, Chenghua Lin

How effective is machine translation on low-resource code-switching? A case study comparing human and automatic metrics (2023.findings-acl)

Challenge:	Existing Chinese preference datasets suffer from limited scale, restricted domain coverage, and insufficiently rigorous data validation.
Approach:	They propose an LLM-based data annotation pipeline with no human intervention to annotate Chinese preference datasets.
Outcome:	The proposed pipeline outperforms existing Chinese preference datasets on AlignBench and Chinese Reward Benchmark.

Copied to clipboard

Li Nguyen, Christopher Bryant, Oliver Mayeux, Zheng Yuan

Multilinguality

Challenge:	Specifically, we compare the performance of three MT systems in terms of their ability to translate monolingual Vietnamese, a low-resource language, and Vietnamese-English CSW respectively.
Approach:	They compare the performance of three machine translation systems in the context of machine translation (MT) they find that state-of-the-art neural translation systems achieve higher scores on automatic metrics when processing CSW input .
Outcome:	The proposed system can translate monolingual Vietnamese, a low-resource language, and Vietnamese-English CSW respectively.

Routing to the Expert: Efficient Reward-guided Ensemble of Large Language Models (2024.naacl-long)

Copied to clipboard

Keming Lu, Hongyi Yuan, Runji Lin, Junyang Lin, Zheng Yuan, Chang Zhou, Jingren Zhou

SOAR: Supervision from Observation for Agentic Reinforcement Learning (2026.acl-long)

Challenge:	Existing ensemble methods for Large Language Models focus on reward model ranking of outputs, leading to significant computation overhead.
Approach:	They propose a reward-guided routing method distilling rewards on training queries to train a routing function.
Outcome:	The proposed method outperforms the best single model and ranks first on 44% of tasks.

Copied to clipboard

Meng Li, Lei Li, Xiting Wang, Yi Yuan, Zheng Wei, null Brucebian, Zang Li

Disentangling Reasoning Logic to Resolve Explicit Knowledge Conflicts (2026.acl-long)

Challenge:	Prior work assigns supervision based on outcome rewards or external reward models, but ignores environment observations, a critical source of learning.
Approach:	They propose a supervision-based agentic reinforcement learning system that integrates environment observations as an explicit supervision signal.
Outcome:	The proposed model improves performance on reasoning and deep research tasks while reducing erroneous and inefficient tool usage.

Copied to clipboard

Xianda Zheng, Zijian Huang, Meng-Fen Chiang, Jiamou Liu, Yuan Fang, Michael J. Witbrock, Kaiqi Zhao

PretrainRL: Alleviating Factuality Hallucination of Large Language Models at the Beginning (2026.findings-acl)

Challenge:	Existing approaches to resolve explicit knowledge conflicts are based on semantic decoding and auxiliary embedding.
Approach:	They propose a framework that adjudicates conflicts by structuring the underlying logic.
Outcome:	Experiments show that the proposed framework improves on existing models.

Copied to clipboard

Langming Liu, Kangtao Lv, Haibin Chen, Weidong Zhang, Yejing Wang, Shilei Liu, Xin Tong, Yujin Yuan, Yongwei Wang, Wenbo Su, Bo Zheng

CharTide: Data-Centric Chart-to-Code Generation via Tri-Perspective Tuning and Inquiry-Driven Evolution (2026.acl-long)

Challenge:	Large language models suffer from factual hallucinations where they generate verifiable falsehoods.
Approach:	They propose a framework that integrates reinforcement learning into the pretraining phase to consolidate factual knowledge.
Outcome:	The proposed framework significantly alleviates factual hallucinations and outperforms state-of-the-art methods.

Copied to clipboard

Xiangxi Zheng, Kuang He, Jiayi Hu, Ping Yu, Rui Yan, Yuan Yao, Peng Hou, Anxiang Zeng, Alex Jinpeng Wang

MavenCoder: Competitive Code Generation via Model Adaptive Planning Strategies and Multi-Perspective Verification Enhancement (2026.acl-long)

Challenge:	Existing approaches to chart-to-code generation are constrained by data-centric limitations . authors present a new framework that redesigns both training and alignment data .
Approach:	They propose a data-centric framework that redesigns both training and alignment data for chart-to-code generation.
Outcome:	The proposed framework outperforms open-source baselines and is competitive with GPT-5.

Copied to clipboard

ZhenChun Xu, Yi Cai, Dajun Zheng, li Yuan, Mengchen Zhao, Qixiang Wang, Jiexin Wang

Programming Languages in NLP

Challenge:	Recent advances in large language models (LLMs) have significantly enhanced automated program synthesis.
Approach:	They propose a model-adaptive and verification–enhanced framework for competition-level code generation that leverages adaptive assessment aligned with the model’s capabilities to select planning strategies while providing timely feedback and correction via multi-perspective verification.
Outcome:	The proposed framework outperforms existing state-of-the-art approaches on livecodebench, humanEval+, MBPP+, and codecontests, and achieves pass@1 results exceeding 3%–40%.

Multimodal Transformers are Hierarchical Modal-wise Heterogeneous Graphs (2025.acl-long)

Copied to clipboard

Yijie Jin, Junjie Peng, Xuanchao Lin, Haochen Yuan, Lan Wang, Cangzhi Zheng

Collision to Cognition: Hash-Driven Graph Construction for Efficient RAG (2026.acl-long)

Challenge:	Multimodal Sentiment Analysis (MSA) is a rapidly developing field that integrates multimodal information to recognize sentiments.
Approach:	They propose a multimodal fusion model that integrates multimodal information to recognize sentiments using multimodal transformers.
Outcome:	The proposed model achieves significantly higher performance than MulTs and the existing model is robust.

Copied to clipboard

Chuang Zhou, Zheng Yuan, Linhao Luo, Zhaozhuo Xu, Yilin Xiao, Junnan Dong, Siyu An, di Yin, Xing Sun, Xiao Huang

Noise Robust Named Entity Understanding for Voice Assistants (2021.naacl-industry)

Challenge:	Retrieval-augmented generation (RAG) has been used for enhancing large language models with external knowledge.
Approach:	They propose a framework for mining efficient graph structures via hashing to enhance RAG . they adopt an inductive paradigm where global graph structure emerges from local hash collisions .
Outcome:	The proposed framework outperforms existing baselines while requiring no GPU resources or token budget.

Copied to clipboard

Deepak Muralidharan, Joel Ruben Antony Moniz, Sida Gao, Xiao Yang, Justine Kao, Stephen Pulman, Atish Kothari, Ray Shen, Yinying Pan, Vivek Kaul, Mubarak Seyed Ibrahim, Gang Xiang, Nan Dun, Yidan Zhou, Andy O, Yuan Zhang, Pooja Chitkara, Xuan Wang, Alkesh Patel, Kushal Tayal, Roger Zheng, Peter Grasch, Jason D Williams, Lin Li

Robustness in NLP

Challenge:	Named Entity Recognition and Entity Linking are challenging for voice assistants . utterances are relatively short, so there is not much context to help disambiguate .
Approach:	They propose a Named Entity Understanding system that combines NER and EL in a joint reranking module.
Outcome:	The proposed framework improves NER accuracy by up to 3.13% and EL accuracy by 3.6% in F1 score . it also leads to better accuracies in other natural language understanding tasks .

LongDocURL: a Comprehensive Multimodal Long Document Benchmark Integrating Understanding, Reasoning, and Locating (2025.acl-long)

Copied to clipboard

Chao Deng, Jiale Yuan, Pi Bu, Peijie Wang, Zhong-Zhi Li, Jian Xu, Xiao-Hui Li, Yuan Gao, Jun Song, Bo Zheng, Cheng-Lin Liu

War of Thoughts: Competition Stimulates Stronger Reasoning in Large Language Models (2025.findings-acl)

Challenge:	Existing document understanding benchmarks only handle a small number of pages . existing models are limited to handling only a limited number of documents .
Approach:	They propose a long document understanding benchmark that integrates three primary tasks and 20 sub-tasks based on different primary tasks.
Outcome:	The proposed model outperforms existing benchmarks on open-source and closed-source models . the model outpersforms other models on more than 33,000 pages of documents .

Copied to clipboard

Yibin Chen, Jinyi Liu, Yan Zheng, Yifu Yuan, Jianye Hao

An Empirical Study of LLM Reasoning Ability Under Strict Output Length Constraint (2025.emnlp-main)

Challenge:	Recent advances in Large Language Models (LLMs) have reshaped the landscape of reasoning tasks.
Approach:	They propose a method that enhances LLM reasoning without finetuning by using test-time scaling.
Outcome:	The proposed method outperforms baseline models in both budget and model size.

Copied to clipboard

Yi Sun, Han Wang, Jiaqiang Li, Jiacheng Liu, Xiangyu Li, Hao Wen, Yizhen Yuan, Huiwen Zheng, Yan Liang, Yuanchun Li, Yunxin Liu

Low-Resource NLP

Challenge:	Large Language Models (LLMs) are a powerful tool for test-time scaling, but they are often used under time constraints.
Approach:	They propose to use LLMs to make models think before answering questions . they also use self-correction and best-of-N decoding to encourage deeper thinking .
Outcome:	The proposed models are able to achieve higher inference accuracy with extra inference computation under time constraints.

Improving Visual-Semantic Embedding with Adaptive Pooling and Optimization Objective (2023.eacl-main)

Copied to clipboard

Zijian Zhang, Chang Shu, Ya Xiao, Yuan Shen, Di Zhu, Youxin Chen, Jing Xiao, Jey Han Lau, Qian Zhang, Zheng Lu

Visual Data in NLP

Challenge:	Recent VSE models combine simple pooling methods with hard triplet loss to improve performance.
Approach:	They propose an adaptive pooling strategy that allows the model to learn how to aggregate features through a combination of simple pooling methods.
Outcome:	The proposed strategy outperforms current state-of-the-art systems on image-to-text and text-toimage retrieval.

COIG-CQIA: Quality is All You Need for Chinese Instruction Fine-tuning (2025.findings-naacl)

Copied to clipboard

Yuelin Bai, Xeron Du, Yiming Liang, Leo Jin, Junting Zhou, Ziqiang Liu, Feiteng Fang, Mingshan Chang, Tianyu Zheng, Xincheng Zhang, Nuo Ma, Zekun Moore Wang, Ruibin Yuan, Haihong Wu, Hongquan Lin, Wenhao Huang, Jiajun Zhang, Chenghua Lin, Jie Fu, Min Yang, Shiwen Ni, Ge Zhang

CBLUE: A Chinese Biomedical Language Understanding Evaluation Benchmark (2022.acl-long)

Challenge:	Existing datasets for Chinese instruction tuning are not well-aligned with Chinese users’ interaction patterns.
Approach:	They propose to use Chinese instruction tuning datasets to improve instruction fine-tuning for Chinese users.
Outcome:	The proposed dataset shows that Chinese models achieve competitive performance in diverse benchmarks.

Copied to clipboard

Ningyu Zhang, Mosha Chen, Zhen Bi, Xiaozhuan Liang, Lei Li, Xin Shang, Kangping Yin, Chuanqi Tan, Jian Xu, Fei Huang, Luo Si, Yuan Ni, Guotong Xie, Zhifang Sui, Baobao Chang, Hui Zong, Zheng Yuan, Linfeng Li, Jun Yan, Hongying Zan, Kunli Zhang, Buzhou Tang, Qingcai Chen

Challenge:	a new benchmark for biomedical language understanding is being developed in Chinese . most benchmarks are limited to English, which makes it difficult to replicate success in other languages.
Approach:	They propose to use Chinese biomedical language understanding evaluation benchmarks to evaluate Chinese models.
Outcome:	The proposed benchmarks show that the current models perform worse than the human ceiling.

Multi-Class Grammatical Error Detection for Correction: A Tale of Two Systems (2021.emnlp-main)

Copied to clipboard

Zheng Yuan, Shiva Taslimipoor, Christopher Davis, Christopher Bryant

Syntactic Text Processing

Challenge:	a multi-class grammatical error detection system can be used to improve grammamatical errors correction (GEC) for English.
Approach:	They develop a multi-class grammatical error detection system based on pre-trained ELECTRA and extend it to multi-Class detection using different error type tagsets.
Outcome:	The proposed system outperforms previous systems on the BEA-test benchmark.

Evaluation Metrics in the Era of GPT-4: Reliably Evaluating Large Language Models on Sequence to Sequence Tasks (2023.emnlp-main)

Copied to clipboard

Andrea Sottana, Bin Liang, Kai Zou, Zheng Yuan