Papers by Yang Ding

Reducing Spurious Correlations in Aspect-based Sentiment Analysis with Explanation from Large Language Models (2023.findings-emnlp)

Challenge:	Existing approaches to multimodal representation learning focus on directional alignment and embedding magnitudes (L2-norm) however, these methods often fail to account for the intrinsic role of L2-norm in the contrastive process.
Approach:	They propose a plug-and-play framework that optimizes L2-norm alignment and Directional consistency jointly.
Outcome:	The proposed framework achieves consistent and significant performance gains over established baselines across 95 tasks using UniIR and VLM2Vec-V2 frameworks.

Copied to clipboard

Qianlong Wang, Keyang Ding, Bin Liang, Min Yang, Ruifeng Xu

Exploring Union and Intersection of Visual Regions for Generating Questions, Answers, and Distractors (2024.emnlp-main)

Challenge:	Aspect-based sentiment analysis models are susceptible to learning spurious correlations between words . a recent study shows that feature engineering is time-consuming and costly .
Approach:	They propose to use a template to prompt LLMs to generate an appropriate explanation for the sentiment polarity of each aspect to reduce spurious correlations.
Outcome:	The proposed methods improve ABSA models and their generalization ability.

Copied to clipboard

Wenjian Ding, Yao Zhang, Jun Wang, Adam Jatowt, Zhenglu Yang

OCR-Memory: Optical Context Retrieval for Long-Horizon Agent Memory (2026.acl-long)

Challenge:	Existing efforts to generate image-related questions, correct answers, or challenge distractors are limited.
Approach:	They propose to put the spotlight on different image regions to diversify QADs . they propose a framework that generates each QAD based on a recurrent multimodal encoder .
Outcome:	The proposed framework puts the spotlight on different image regions to diversify QADs.

Copied to clipboard

Jinze Li, Yang Zhang, Xin Yang, Jiayi QU, Jinfeng Xu, Shuo Yang, Junhua Ding, Edith Cheuk-Han Ngai

Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning (2026.acl-long)

Challenge:	Existing LLMs are limited by text-context budgets, resulting in token-expensive storage of raw trajectories . Optical Context Retrieval Memory (OCR-Memory) renders historical tra-jectorios into images annotated with unique visual identifiers.
Approach:	They propose a framework that leverages the visual modality as a high-density representation of agent experience.
Outcome:	Optical Context Retrieval Memory (OCRM) renders historical trajectories into images annotated with unique visual identifiers.

Copied to clipboard

Sikuan Yan, Xiufeng Yang, Zuchao Huang, Ercong Nie, Zifeng Ding, Zonggen Li, Xiaowen Ma, Jinhe Bi, Kristian Kersting, Jeff Z. Pan, Hinrich Schuetze, Volker Tresp, Yunpu Ma

DevEval: A Manually-Annotated Code Generation Benchmark Aligned with Real-World Code Repositories (2024.findings-acl)

Challenge:	Large Language Models (LLMs) are stateless and limited by a finite context window, preventing them from maintaining knowledge across long conversations or evolving tasks.
Approach:	They propose a reinforcement learning framework that empowers LLMs to actively manage external memory through two specialized agents.
Outcome:	The proposed framework outperforms baselines and benchmarks across diverse question types, three benchmarks, and multiple model scales.

Copied to clipboard

Jia Li, Ge Li, Yunfei Zhao, Yongmin Li, Huanyu Liu, Hao Zhu, Lecheng Wang, Kaibo Liu, Zheng Fang, Lanshen Wang, Jiazheng Ding, Xuanming Zhang, Yuqi Zhu, Yihong Dong, Zhi Jin, Binhua Li, Fei Huang, Yongbin Li, Bin Gu, Mengfei Yang

CMR Scaling Law: Predicting Critical Mixture Ratios for Continual Pre-training of Language Models (2024.emnlp-main)

Challenge:	Existing benchmarks are poorly aligned with real-world code repositories and are insufficient to evaluate the coding abilities of Large Language Models (LLMs).
Approach:	They propose a repository-level benchmark named DevEval to evaluate LLMs' coding abilities in real-world code repositories.
Outcome:	The proposed benchmarks show that the LLMs perform better in real-world code repositories than existing benchmarks.

Copied to clipboard

Jiawei Gu, Zacc Yang, Chuanghao Ding, Rui Zhao, Fei Tan

EventRAG: Enhancing LLM Generation with Event Knowledge Graphs (2025.acl-long)

Challenge:	Large Language Models (LLMs) excel in diverse tasks but often underperform in specialized fields due to limited domain-specific or proprietary corpus.
Approach:	They propose a power-law relationship between loss, mixture ratio, and training tokens scale and formalize the trade-off between general and domain-specific capabilities.
Outcome:	The proposed model achieves the desired domain transfer while maintaining general ability and highest utilization of available resources.

Copied to clipboard

Zairun Yang, Yilin Wang, Zhengyan Shi, Yuan Yao, Lei Liang, Keyan Ding, Emine Yilmaz, Huajun Chen, Qiang Zhang

Parameter-Efficient Tuning Makes a Good Classification Head (2022.emnlp-main)

Challenge:	Existing approaches to text generation often neglect event structures that shape real-world narratives.
Approach:	They propose a framework that integrates structured event semantics with iterative retrieval and inference to enhance text generation.
Outcome:	Experiments on UltraDomain and MultiHopRAG show that the proposed framework outperforms baseline RAG systems in generation effectiveness, logical consistency, and multi-hop reasoning accuracy.

Copied to clipboard

Zhuoyi Yang, Ming Ding, Yanhui Guo, Qingsong Lv, Jie Tang

GLM: General Language Model Pretraining with Autoregressive Blank Infilling (2022.acl-long)

Challenge:	In recent years, pretrained models revolutionized the paradigm of natural language understanding . but the final-layer output of the backbone, i.e. the input of the classification head, will change greatly during finetuning .
Approach:	They propose to append a randomly initialized classification head after the pretrained backbone and finetune the whole model.
Outcome:	The proposed classification head can be replaced with the randomly initialized heads for a stable performance gain.

Copied to clipboard

Zhengxiao Du, Yujie Qian, Xiao Liu, Ming Ding, Jiezhong Qiu, Zhilin Yang, Jie Tang

DALK: Dynamic Co-Augmentation of LLMs and KG to answer Alzheimer’s Disease Questions with Scientific Literature (2024.findings-emnlp)

Challenge:	Existing pretraining frameworks do not perform well for all tasks of three main categories, such as natural language understanding (NLU), unconditional generation, and conditional generation.
Approach:	They propose a general language model based on autoregressive blank infilling to address this challenge.
Outcome:	The proposed model outperforms BERT, T5, and GPT on a wide range of tasks across NLU, conditional and unconditional generation tasks.

Copied to clipboard

Dawei Li, Shu Yang, Zhen Tan, Jae Baik, Sukwon Yun, Joseph Lee, Aaron Chacko, Bojian Hou, Duy Duong-Tran, Ying Ding, Huan Liu, Li Shen, Tianlong Chen

Structured Data in NLP

Challenge:	Recent advances in large language models have achieved promising performances across various applications, but the challenge of integrating long-tail knowledge continues to impede the seamless adoption of LLMs in specialized domains.
Approach:	They propose a dynamic co-augmentation framework for the refinement of large language models and knowledge graphs in the context of Alzheimer's Disease.
Outcome:	The proposed framework can be used to study Alzheimer's Disease (AD) using LLMs and KGs.

Consolidation or Adaptation? PRISM: Disentangling SFT and RL Data via Gradient Concentration (2026.acl-long)

Copied to clipboard

Yang Zhao, Yangou Ouyang, Xiao Ding, Hepeng Wang, Bibo Cai, Kai Xiong, Jinglong Gao, Zhouhao Sun, Li Du, Bing Qin, Ting Liu

On Fake News Detection with LLM Enhanced Semantics Mining (2024.emnlp-main)

Challenge:	Existing data arbitration strategies for large language model training rely on surface-level heuristics that fail to diagnose intrinsic learning needs.
Approach:	They propose a framework that arbitrates data based on its degree of cognitive conflict with the model's existing knowledge.
Outcome:	Extensive experiments on WebShop and ALFWorld show that PRISM outperforms state-of-the-art hybrid methods while reducing computational costs by up to 3.22 .

Copied to clipboard

Xiaoxiao Ma, Yuchen Zhang, Kaize Ding, Jian Yang, Jia Wu, Hao Fan

TongGu: Mastering Classical Chinese Understanding with Knowledge-Grounded Large Language Models (2024.findings-emnlp)

Challenge:	Existing methods for detecting fake news use only news embeddings to capture the lexical semantics between tokens.
Approach:	They propose a topic-based model with prompts to extract news embeddings from LLMs and a generalized page-rank model to extract local and global semantics.
Outcome:	The proposed model shows superior performance on five benchmark datasets over seven baseline methods.

Copied to clipboard

Jiahuan Cao, Dezhi Peng, Peirong Zhang, Yongxin Shi, Yang Liu, Kai Ding, Lianwen Jin

Yang Zhao, Li Du, Xiao Ding, Yangou Ouyang, Hepeng Wang, Kai Xiong, Jinglong Gao, Zhouhao Sun, Dongliang Xu, Qing Yang, Dongchen Li, Bing Qin, Ting Liu

Challenge:	Large Language Models (LLMs) have demonstrated remarkable capability in Natural Language Processing (NLP), but struggle with Classical Chinese Understanding (CCU) Existing models, including general-purpose and preliminary LLMs, lack the ability to address CCU in data-demanding and knowledge-intensive tasks.
Approach:	They propose to use a classical Chinese corpora-based instruction-tuning dataset to unlock the full CCU potential of LLMs.
Outcome:	The proposed model unlocks the full CCU potential of LLMs by preserving its foundational knowledge while maintaining redundancy-aware tuning (RAT) and CCU-RAG.

Copied to clipboard

Learning to Selectively Learn for Weakly-supervised Paraphrase Generation (2021.emnlp-main)

Challenge:	Existing methods for selecting training data from general datasets fail to account for the joint distribution of instructions, resulting in inefficient learning and suboptimal knowledge transfer.
Approach:	They propose a method that constructs a mixed gradient-based instruction graph to capture the joint distribution and interdependencies among instructions.
Outcome:	The proposed method outperforms existing methods on domain adaptation tasks and in complex, data-scarce scenarios.

Copied to clipboard

Kaize Ding, Dingcheng Li, Alexander Hanbo Li, Xing Fan, Chenlei Guo, Yang Liu, Huan Liu

Text Generation

Challenge:	Existing approaches to generate paraphrases with weak supervision are limited in real-world scenarios due to the lack of coherent and controllable generated paraphrase.
Approach:	They propose a method to generate high-quality paraphrases with weak supervision . they obtain abundant weakly-labeled parallel sentences via retrieval-based pseudo paraphrase expansion .
Outcome:	The proposed approach achieves significant improvements over existing methods and is even comparable in performance with supervised state-of-the-arts.

Factual Consistency Evaluation for Text Summarization via Counterfactual Estimation (2021.findings-emnlp)

Copied to clipboard

Yuexiang Xie, Fei Sun, Yang Deng, Yaliang Li, Bolin Ding

Text Generation

Challenge:	Existing methods to evaluate factual consistency in text summarization neglect the intrinsic cause of factual inconsistency or rely on auxiliary tasks.
Approach:	They propose a method to evaluate the factual consistency in text summarization via counterfactual estimation, which formulates the causal relationship between source document, generated summary, and the language prior.
Outcome:	The proposed metric improves correlation with human judgments and convenience of usage on three public abstractive text summarization datasets.

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

Copied to clipboard

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

Programming Languages in NLP

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

AgentGym: Evaluating and Training Large Language Model-based Agents across Diverse Environments (2025.acl-long)

Copied to clipboard

Zhiheng Xi, Yiwen Ding, Wenxiang Chen, Boyang Hong, Honglin Guo, Junzhe Wang, Xin Guo, Dingwen Yang, Chenyang Liao, Wei He, Songyang Gao, Lu Chen, Rui Zheng, Yicheng Zou, Tao Gui, Qi Zhang, Xipeng Qiu, Xuanjing Huang, Zuxuan Wu, Yu-Gang Jiang

Quantifying and Improving the Robustness of Retrieval-Augmented Language Models Against Spurious Features in Grounding Data (2026.acl-long)

Challenge:	Large language models (LLMs) are promising foundations to build generally-capable agents . however, the community lacks a unified interactive framework that covers diverse environments for comprehensive evaluation of agents.
Approach:	They propose a framework that features 7 real-world scenarios, 14 environments, and 89 tasks for unified, real-time, and concurrent agent interaction.
Outcome:	The proposed framework features 7 real-world scenarios, 14 environments, and 89 tasks for unified, real-time, and concurrent agent interaction.

Copied to clipboard

Shiping Yang, Jie Wu, Wenbiao Ding, Ning Wu, Shining Liang, Ming Gong, Hongzhi Li, Hengyuan Zhang, Angel X. Chang, Dongmei Zhang

CoT-VTM: Visual-to-Music Generation with Chain-of-Thought Reasoning (2025.findings-acl)

Challenge:	Existing studies on robustness to explicit noise (e.g., document semantics) but overlook implicit noise (spurious features).
Approach:	They propose a framework to quantify the robustness of RAGs against spurious features by integrating a data synthesis pipeline and a taxonomy.
Outcome:	The proposed framework quantifies the robustness of RALMs against spurious features.

Copied to clipboard

Xikang Guan, Zheng Gu, Jing Huo, Tianyu Ding, Yang Gao

GASE: Graph-Aware Semantic Embedding Learning with Frozen LLMs for Text-Attributed Graphs (2026.acl-long)

Challenge:	Existing methods for visual-to-music generation lack large-scale, high-quality visual-music paired datasets and lack of direct semantic correspondence between visuals and music.
Approach:	They propose a framework that distills Chain-of-Thought reasoning to enable visual-to-music generation without paired data.
Outcome:	The proposed framework achieves optimal performance on image-to-music and video-to music tasks.

Copied to clipboard

Mingqian Ding, Jianjun Li, Wenqi Yang, Zhibo Zhang, Yushen Fang

Less is More: Improving LLM Reasoning with Minimal Test-Time Intervention (2026.acl-long)

Challenge:	Large Language Models (LLMs) have shown strong potential for text-attributed graph (TAG) learning, yet effectively integrating LLM semantics with graph structural information remains challenging.
Approach:	They propose a framework for learning Graph-Aware Semantic Embeddings using frozen LLMs.
Outcome:	The proposed framework outperforms state-of-the-art methods on node classification and achieves a 5 speedup over fine-tuning-based methods.

Copied to clipboard

Zhen Yang, Mingyang Zhang, Feng Chen, Ganggui Ding, Liang Hou, Xin Tao, Ying-Cong Chen

Topic-Oriented Open Relation Extraction with A Priori Seed Generation (2024.emnlp-main)

Challenge:	Recent advances in large language models (LLMs) have focused on test-time scaling to improve reasoning quality but at the cost of efficiency.
Approach:	They propose a training-free framework that enhances reasoning accuracy and stability with minimal overhead.
Outcome:	The proposed framework yields consistent gains across general, coding, and STEM tasks while remaining highly efficient.

Copied to clipboard

Linyi Ding, Jinfeng Xiao, Sizhe Zhou, Chaoqi Yang, Jiawei Han

Information Extraction & Text Mining

Challenge:	Existing methods for open relation extraction give sub-optimal results on specific topics.
Approach:	They propose a method that leverages the built-in knowledge of large language models to maintain a dynamic seed relation dictionary for the topic.
Outcome:	The proposed approach empowers better topic-oriented control over the generated relations and improves ORE performance along the five dimensions, especially on specialized and narrow topics.

MAESTRO: Meta-learning Adaptive Estimation of Scalarization Trade-offs for Reward Optimization (2026.acl-long)

Copied to clipboard

Yang Zhao, Hepeng Wang, Xiao Ding, Yangou Ouyang, Bibo Cai, Kai Xiong, Jinglong Gao, Zhouhao Sun, Li Du, Bing Qin, Ting Liu

Green & Sustainable NLP

Challenge:	Group-Relative Policy Optimization (GRPO) has emerged as an efficient paradigm for aligning Large Language Models (LLMs), but its efficacy is confined to domains with verifiable ground truths.
Approach:	They propose a meta-cognitive orchestration layer that treats reward scalarization as a dynamic latent policy, leveraging the model’s terminal hidden states as 'a semantic bottleneck' . Across seven benchmarks, MAESTRO consistently outperforms single-reward and static multi-objective baselines while preserving the efficiency advantages of GRPO.
Outcome:	The proposed model outperforms single-reward and static multi-objective baselines while preserving efficiency advantages.

Double-Edged Sword or Sharp Tool? Designing and Evaluating Triadic LLM-Teacher Collaboration for K-12 Writing at Scale (2026.findings-acl)

Copied to clipboard

Canran Wang, Yuwen Yang, Zhen Wang, Ming MA, Ding Yu, Chentai Wang, Keman Huang, Xiaoyong Du

StraGo: Harnessing Strategic Guidance for Prompt Optimization (2024.findings-emnlp)

Challenge:	a large-scale empirical dataset involving 57,954 essays from 10,195 students across 120 schools over two years is presented in this paper.
Approach:	They propose a triadic collaboration system that supports K-12 writing learning . they propose linguistic expansion as a pedagogical gatekeeper and bridge .
Outcome:	The proposed system improves writing quality through a strategic labor division . authors find that excessive linguistic expansion yields diminishing marginal utility .

Copied to clipboard

Yurong Wu, Yan Gao, Bin Zhu, Zineng Zhou, Xiaodi Sun, Sheng Yang, Jian-Guang Lou, Zhiming Ding, Linjun Yang

Consultant Decoding: Yet Another Synergistic Mechanism (2025.findings-acl)

Challenge:	Existing methods for prompt optimization often lead to prompt drifting, wherein newly generated prompts canadversely impact previously successful cases while addressing failures.
Approach:	They propose a method to mitigate prompt drifting by integrating in-context learning to formulate specific, actionable strategies for prompt optimization.
Outcome:	The proposed approach mitigates prompt drifting by leveraging insights from both successful and failed cases to identify critical factors for achieving optimization objectives.

Copied to clipboard

Chuanghao Ding, Jiaping Wang, Ziqing Yang, Xiaoliang Wang, Dahua Lin, Nguyen Cam-Tu, Fei Tan

AD-LLM: Benchmarking Large Language Models for Anomaly Detection (2025.findings-acl)

Challenge:	Large language models (LLMs) have attracted widespread attention and adoption across diverse domains due to their exceptional performance and robust generalization abilities.
Approach:	They propose a synergetic mechanism for Consultant Decoding (CD) that achieves a 2.5-fold increase in inference speed compared to the target model while maintaining comparable generation quality.
Outcome:	The proposed mechanism achieves 2.5-fold increase in inference speed while maintaining comparable generation quality (100% of the target model’s performance).

Copied to clipboard

Tiankai Yang, Yi Nian, Li Li, Ruiyao Xu, Yuangang Li, Jiaqi Li, Zhuo Xiao, Xiyang Hu, Ryan A. Rossi, Kaize Ding, Xia Hu, Yue Zhao

Exploring the Impact of Model Scaling on Parameter-Efficient Tuning (2023.emnlp-main)

Challenge:	Anomaly detection (AD) is an important machine learning task with many real-world uses, including fraud detection, medical diagnosis, and industrial monitoring.
Approach:	They propose a benchmark that evaluates how large language models (LLMs) can help with NLP anomaly detection.
Outcome:	The proposed model can perform zero-shot detection without tasks-specific training, data augmentation and model selection, and it can suggest unsupervised AD models.

Copied to clipboard

Yusheng Su, Chi-Min Chan, Jiali Cheng, Yujia Qin, Yankai Lin, Shengding Hu, Zonghan Yang, Ning Ding, Xingzhi Sun, Guotong Xie, Zhiyuan Liu, Maosong Sun

Exploring Concept Depth: How Large Language Models Acquire Knowledge and Concept at Different Layers? (2025.coling-main)

Challenge:	Parameter-efficient tuning (PET) methods can drive large pre-trained language models by training only minimal parameters.
Approach:	They propose a parameter-efficient tuning method that is compatible with a tunable module and uses a random number generator to optimize fewer table parameters.
Outcome:	The proposed method is compatible with a tunable module and tested on 11 NLP tasks.

Copied to clipboard

Mingyu Jin, Qinkai Yu, Jingyuan Huang, Qingcheng Zeng, Zhenting Wang, Wenyue Hua, Haiyan Zhao, Kai Mei, Yanda Meng, Kaize Ding, Fan Yang, Mengnan Du, Yongfeng Zhang

Curr-ReFT: Overcoming Training Bottlenecks in Small-scale Vision-Language Models via Curriculum Reinforcement Finetuning (2025.findings-emnlp)

Challenge:	Large language models have shown remarkable performances across a wide range of tasks, but mechanisms by which they encode tasks of varying complexity remain poorly understood.
Approach:	They propose to explore the possibility that LLMs process concepts in different layers . they propose to categorize concepts based on their level of abstraction .
Outcome:	The proposed model can process complex concepts in shallow layers, the authors show . the proposed model could be used to prob complex tasks in shallow ones .

Copied to clipboard

Huilin Deng, Ding Zou, Xinghao Zhao, Rui Ma, Yanming Guo, Yang Cao, Yu Kang

Towards Open-Domain Topic Classification (2022.naacl-demo)

Challenge:	State-of-the-art vision-language models require massive scaling that limits practical deployment.
Approach:	They propose to use supervised fine-tuning to train small-scale vision-language models but face out-of-domain collapse when trained with traditional supervised learning (SFT).
Outcome:	Experiments show that curr-reFT achieves state-of-the-art performance across visual tasks in both in- and out-of domain settings and benchmarks.

Copied to clipboard

Hantian Ding, Jinrui Yang, Yuqian Deng, Hongming Zhang, Dan Roth

Tailored Primitive Initialization is the Secret Key to Reinforcement Learning (2026.acl-long)

Challenge:	Existing supervised classification models are insensitive to class names, but are no longer effective in open-domain tasks where the taxonomy is unbounded.
Approach:	They propose a topic classification system that accepts user-defined taxonomy in real time . they train a pretrained language model on a new Wikipedia dataset and train it on Wikipedia .
Outcome:	The proposed system improves over existing zero-shot models and performs competitively with weakly-supervised models trained on in-domain data.

Copied to clipboard

Yihang Yao, Guangtao Zeng, Raina Wu, Yang Zhang, Ding Zhao, Zhang-Wei Hong, Chuang Gan

Improving Recall of Large Language Models: A Model Collaboration Approach for Relational Triple Extraction (2024.lrec-main)

Challenge:	Reinforcement learning (RL) has emerged as a powerful paradigm for improving the reasoning capabilities of large language models.
Approach:	They propose a pipeline that automatically discovers thinking token patterns with reasoning primitives and curates SFT datasets to prepare LLMs for RL.
Outcome:	The proposed pipeline outperforms baseline methods on mathematical and logical reasoning benchmarks on RL tasks.

Copied to clipboard

Zepeng Ding, Wenhao Huang, Jiaqing Liang, Yanghua Xiao, Deqing Yang

Information Extraction & Text Mining

Challenge:	Existing large language models can extract triples from simple sentences with few-shot learning or fine-tuning, but they often miss out when extracting from complex sentences.
Approach:	They propose an evaluation-filtering framework that integrates large language models with small models for relational triple extraction tasks.
Outcome:	The proposed framework integrates large language models with small models for relational triple extraction tasks.

Non-Autoregressive Sentence Ordering (2023.findings-emnlp)

Copied to clipboard

Yi Bin, Wenhao Shi, Bin Ji, Jipeng Zhang, Yujuan Ding, Yang Yang

Reasoning

Challenge:	Existing sentence ordering approaches only leverage unilateral dependencies during decoding and cannot fully explore the semantic dependency between sentences.
Approach:	They propose a non-autoregressive ordering network that explores bilateral dependencies between sentences and predicts sentences for each position in parallel.
Outcome:	The proposed model outperforms existing autoregressive sentence ordering approaches and yields competitive performance compared with the state-of-the-arts.

Generating Questions, Answers, and Distractors for Videos: Exploring Semantic Uncertainty of Object Motions (2025.findings-acl)

Copied to clipboard

Wenjian Ding, Yao Zhang, Jun Wang, Adam Jatowt, Zhenglu Yang

Visual Data in NLP

Challenge:	Existing video QADs are generated using video captions, incurring significant costs and resulting in bias.
Approach:	They propose to use temporal motion to describe video objects to generate diverse QADs focusing on different objects and interactions.
Outcome:	The proposed approach improves consistency and diversity of generated QADs on the NExT-QA and Perception Test benchmarks.

FewNLU: Benchmarking State-of-the-Art Methods for Few-Shot Natural Language Understanding (2022.acl-long)

Copied to clipboard

Yanan Zheng, Jing Zhou, Yujie Qian, Ming Ding, Chonghua Liao, Li Jian, Ruslan Salakhutdinov, Jie Tang, Sebastian Ruder, Zhilin Yang

Cogito: A Cognitive Agentic Framework Driven by Dynamic Graph of Thoughts for Financial Report Generation (2026.findings-acl)

Challenge:	Existing evaluation protocols for few-shot natural language understanding (NLU) tasks are inconsistent and hinder fair comparison and measuring progress.
Approach:	They propose an evaluation framework that improves previous evaluation procedures in three key aspects, i.e., test performance, dev-test correlation, and stability.
Outcome:	The proposed framework improves evaluation procedures in three key aspects, i.e., performance, dev-test correlation, and stability.

Copied to clipboard

Chen Lifan, Wei Ding, Jingwen Yang, Xiuze Zhou, Jingan Chen, Fan Lin

OS-Symphony: A Holistic Framework for Robust and Generalist Computer-Using Agents (2026.acl-long)

Challenge:	Existing approaches to financial report generation are insufficient to handle dynamic uncertainties of real-world financial environments.
Approach:	They propose a cognitively grounded agentic framework for professional financial report generation that is driven by Dynamic Graph of Thoughts and a social collaboration mechanism to facilitate coordinated agent interaction.
Outcome:	The proposed framework is based on a dynamic reasoning model and social collaboration mechanism.

Copied to clipboard

Bowen Yang, Kaiming Jin, Zhenyu Wu, Zhaoyang Liu, Qiushi Sun, Zehao Li, JingJing Xie, Zhoumianze Liu, Fangzhi Xu, Kanzhi Cheng, Yian Wang, Qingyun Li, Yu Qiao, Zun Wang, Zichen Ding

Robustness in NLP

Challenge:	Vision-Language Models (VLMs) lack visual-aware tutorial retrieval and historical visual context curation and pruning.
Approach:	They propose a framework that integrates an orchestrator and a Reflection-Memory Agent for robust automation.
Outcome:	Experimental results show that OS-Symphony delivers substantial performance gains across model scales.

Multi-stage Distillation Framework for Cross-Lingual Semantic Similarity Matching (2022.findings-naacl)

Copied to clipboard

Kunbo Ding, Weijie Liu, Yuejian Fang, Zhe Zhao, Qi Ju, Xuefeng Yang, Rong Tian, Zhu Tao, Haoyan Liu, Han Guo, Xingyu Bai, Weiquan Mao, Yudong Li, Weigang Guo, Taiqiang Wu, Ningyuan Sun

ProActor: Timing-Aware Reinforcement Learning for Proactive Task Scheduling Agents (2026.acl-long)

Challenge:	Existing studies have shown that cross-lingual knowledge distillation can improve the performance of pre-trained models for cross-linguistic similarity matching tasks.
Approach:	They propose a multi-stage distillation framework for constructing a small-size but high-performance cross-lingual model using contrastive learning, bottleneck, and parameter recurrent strategies.
Outcome:	The proposed model can compress the size of XLM-R and MiniLM by more than 50% while the performance is only reduced by about 1%.

Copied to clipboard

Lei Ding, Bin He, Chenguang Wang, Yang Liu

Dialogue Systems & Conversational Agents

Challenge:	Existing approaches to measuring and optimizing proactive task-oriented agents lack generalizable end-to-end solutions.
Approach:	They propose a framework for conversational task scheduling that integrates proactiveness reinforcement learning with a domain-agnostic annotation methodology.
Outcome:	The proposed framework enables scalable proactiveness reinforcement learning (RL) Experiments on two newly auto-annotated datasets demonstrate significant improvements in proactive timing while maintaining action consistency comparable to state-of-the-art baselines.

V-GameGym: Visual Game Generation for Code Large Language Models (2026.findings-acl)

Copied to clipboard

Wei Zhang, Jian Yang, Renshuai Tao, Linzheng Chai, Shuyue Guo, Jiajun Wu, Xiaoming Chen, Ganqu Cui, Ning Ding, Xander Xu, HU Wei, Bowen Zhou

Cognitive Graph for Multi-Hop Reading Comprehension at Scale (P19-1)

Challenge:	Existing code-related benchmarks focus on single modality rather than visual game development.
Approach:	They propose a multimodal benchmark for evaluating code large language models in visual game generation that integrates a clustering-based curation methodology and a pipeline for visual code synthesis.
Outcome:	The proposed framework assesses code generation and visual game generation using a sandbox environment.

Copied to clipboard

Ming Ding, Chang Zhou, Qibin Chen, Hongxia Yang, Jie Tang

Reasoning

Challenge:	a new framework for multi-hop reading comprehension question answering is needed to cross the chasm of reading comprehension between machine and human.
Approach:	They propose a CogQA framework for multi-hop reading comprehension question answering in web-scale documents that builds a cognitive graph in an iterative process by coordinating an implicit extraction module and an explicit reasoning module.
Outcome:	The proposed framework outperforms the best competitor in the hotpotQA dataset in F1 . it provides explainable reasoning paths and accurate answers, while giving accurate answers .

Self-adaptive Context and Modal-interaction Modeling For Multimodal Emotion Recognition (2023.findings-acl)

Copied to clipboard

Haozhe Yang, Xianqiang Gao, Jianlong Wu, Tian Gan, Ning Ding, Feijun Jiang, Liqiang Nie

Sentiment Analysis

Challenge:	Existing methods to predict emotion label for a given utterance lack modeling of diverse dependency ranges and inconsistent treatment of contribution for various modalities.
Approach:	They propose a multimodal emotion recognition in conversation task that uses context and multiple modalities to predict emotion label for a given utterance.
Outcome:	The proposed method outperforms the state-of-the-art methods on three multimodal datasets.

Bridging SFT and RL: Dynamic Policy Optimization for Robust Reasoning (2026.findings-acl)

Copied to clipboard

Taojie Zhu, Dongyang Xu, Ding Zou, Sen Zhao, Qiaobo Hao, Zhiguo Yang, Yonghong He

Large-Scale Corpus Construction and Retrieval-Augmented Generation for Ancient Chinese Poetry: New Method and Data Insights (2025.findings-naacl)

Challenge:	Existing unified optimization strategies overlook the statistical conflict between these distinct gradient signals.
Approach:	They propose a framework to reduce bias-variance trade-offs in Large Language Models . they propose DYPO, which leverages intrinsic group dynamics to significantly reduce RL gradient variance .
Outcome:	The proposed framework outperforms traditional pipelines on reasoning benchmarks and out-of-distribution tasks.

Copied to clipboard

Yang Liu, Lan Lan, Jiahuan Cao, Hiuyi Cheng, Kai Ding, Lianwen Jin

Parameter-efficient Continual Learning Framework in Industrial Real-time Text Classification System (2022.naacl-industry)

Challenge:	Ancient Chinese poetry presents unique challenges for Large Language Models due to data scarcity and limited ability of general LLMs when dealing with ACP.
Approach:	They propose a specialized Retrieval-Augmented Generation framework to improve LLMs' performance . they use 1.1 million ancient poems and 990K related texts to address hallucination issues .
Outcome:	The proposed framework improves performance of LLMs in ancient Chinese poetry domain from 49.2% to 89.0%.

Copied to clipboard

Tao Zhu, Zhe Zhao, Weijie Liu, Jiachi Liu, Yiren Chen, Weiquan Mao, Haoyan Liu, Kunbo Ding, Yudong Li, Xuefeng Yang

BFS-Prover: Scalable Best-First Tree Search for LLM-based Automatic Theorem Proving (2025.acl-long)

Challenge:	Existing continual learning methods use data replay, parameter isolation and regularization to mitigate catastrophic forgetting.
Approach:	They propose a parameter-efficient continual learning framework that updates parameters offline and then trains using an online regularization method.
Outcome:	The proposed framework reduces catastrophic forgetting and saves the model with the changed parameters instead of all parameters.

Copied to clipboard

Ran Xin, Chenguang Xi, Jie Yang, Feng Chen, Hang Wu, Xia Xiao, Yifan Sun, Shen Zheng, Ming Ding

Read Anywhere Pointed: Layout-aware GUI Screen Reading with Tree-of-Lens Grounding (2024.emnlp-main)

Challenge:	Existing approaches to theorem proving in large language models rely on value functions and/or Monte Carlo Tree Search (MCTS), but the potential of simpler methods like Best-First Tree Search remains underexplored.
Approach:	They propose a scalable expert iteration framework that implements strategic data filtering at each expert iteration round, excluding problems solvable via beam search node expansion to focus on harder cases.
Outcome:	The proposed framework achieves a state-of-the-art score of 72.95 on the MiniF2F test set and challenges the perceived necessity of complex tree search methods.

Copied to clipboard

Yue Fan, Lei Ding, Ching-Chen Kuo, Shan Jiang, Yang Zhao, Xinze Guan, Jie Yang, Yi Zhang, Xin Wang

Challenge:	Existing models for GUI understanding ignore a key GUI-referring task: screen reading based on user-indicated points.
Approach:	They propose a Tree-of-Lens agent that constructs a Hierarchical Layout Tree based on user input points and a GUI screenshot.
Outcome:	The proposed agent can interpret the Screen Point-and-Read task on mobile, web, and operating systems.

Vulnerability of Text-to-Image Models to Prompt Template Stealing: A Differential Evolution Approach (2025.findings-acl)

Copied to clipboard

Yurong Wu, Fangwen Mu, Qiuhong Zhang, Jinjing Zhao, Xinrun Xu, Lingrui Mei, Yang Wu, Lin Shi, Junjie Wang, Zhiming Ding, Yiwei Wang

The Agent’s First Day: Benchmarking Learning, Exploration, and Scheduling in the Workplace Scenarios (2026.findings-acl)

Challenge:	Prompt trading has emerged as a significant intellectual property concern in recent years, where vendors entice users by showcasing sample images before selling prompt templates that can generate similar images.
Approach:	They propose a prompt-stealing benchmark consisting of 50 templates and 450 images organized into Easy and Hard difficulty levels.
Outcome:	The proposed method outperforms baseline methods with an average improvement of over 10%.

Copied to clipboard

Daocheng Fu, Jianbiao Mei, Rong Wu, Xuemeng Yang, Jia Xu, Ding Wang, Pinlong Cai, Yong Liu, Licheng Wen, Botian Shi

Challenge:	Existing research mainly focuses on performance upper bounds in static environments, overlooking stochastic real-world deployment.
Approach:	They propose a dynamic evaluation environment that simulates a "trainee" agent continuously exploring a novel setting.
Outcome:	The proposed model evaluates agents in a dynamic evaluation environment that simulates a "trainee" agent continuously exploring a novel setting.

AMPO: Automatic Multi-Branched Prompt Optimization (2024.emnlp-main)

Copied to clipboard

Sheng Yang, Yurong Wu, Yan Gao, Zineng Zhou, Bin Zhu, Xiaodi Sun, Jian-Guang Lou, Zhiming Ding, Anbang Hu, Yuan Fang, Yunsong Li, Junyan Chen, Linjun Yang

A Rationale-centric Counterfactual Data Augmentation Method for Cross-Document Event Coreference Resolution (2024.naacl-long)

Challenge:	Existing prompt engineering techniques are limited to producing single flow instructions, struggling with handling diverse patterns.
Approach:	They propose an automatic prompt optimization method that iteratively develops a multi-branched prompt using failure cases as feedback.
Outcome:	The proposed method achieves the best results across five tasks and demonstrates significant optimization efficiency due to adoption of a minimal search strategy.

Copied to clipboard

Bowen Ding, Qingkai Min, Shengkun Ma, Yingjie Li, Linyi Yang, Yue Zhang

CodeContests+: High-Quality Test Case Generation for Competitive Programming (2025.findings-emnlp)

Challenge:	Existing state-of-the-art event coreference resolution systems rely on spurious and spurious associations in the input mention pair text.
Approach:	They propose a rationale-centric counterfactual data augmentation method that leverages the debiasing capability of counterfact data haussed by LLM-in-the-loop to mitigate spurious association while emphasizing causation.
Outcome:	The proposed method achieves state-of-the-art on three popular cross-document benchmarks and demonstrates robustness in out-of domain scenarios.

Copied to clipboard

Zihan Wang, Siyao Liu, Yang Sun, Ming Ding, Hongyan Li

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

Challenge:	Competitive programming has become a key task for training and evaluating large language models . but test cases of competitive programming problems are often difficult to obtain .
Approach:	They propose an LLM-based agent system that creates high-quality test cases for competitive programming problems.
Outcome:	The proposed system improves code tests on a CodeContests dataset with pass/fail labels.

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

Forge: Quality-Aware Reinforcement Learning for NP-Hard Optimization in LLMs (2026.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

Xiaozhe Li, Xinyu Fang, Shengyuan Ding, Yang Li, Linyang Li, Haodong Duan, Qingwen Liu, Kai Chen

Reasoning

Challenge:	Existing benchmarks focus on correctness, overlooking optimality . large language models excel at math, coding, logic and puzzles .
Approach:	They propose a framework for training and evaluating Large Language Models on NP-hard optimization problems through quality-aware RLVR.
Outcome:	The proposed framework outperforms existing benchmarks on math, coding, logic and puzzles.

Gradient-Attention Guided Dual-Masking Synergetic Framework for Robust Text-based Person Retrieval (2025.emnlp-main)

Copied to clipboard

Tianlu Zheng, Yifan Zhang, Xiang An, Ziyong Feng, Kaicheng Yang, Qichuan Ding

SoftDedup: an Efficient Data Reweighting Method for Speeding Up Language Model Pre-training (2024.acl-long)

Challenge:	a large-scale visionlanguage pre-training framework is limited by the scarcity of large-sized annotated vision-language data . noise-resistant data construction pipeline is needed to filter and caption web-sourced images . noisy text tokens can be a problem for fine-grained representation learning .
Approach:	They develop a noise-resistant data construction pipeline that leverages in-context learning capabilities of MLLMs to automatically filter and caption web-sourced images.
Outcome:	The proposed framework improves cross-modal alignment by masking noisy textual tokens based on the gradient-attention similarity score.

Copied to clipboard

Nan He, Weichen Xiong, Hanwen Liu, Yi Liao, Lei Ding, Kai Zhang, Guohua Tang, Xiao Han, Yang Wei

Deciphering the Impact of Pretraining Data on Large Language Models through Machine Unlearning (2024.findings-acl)

Challenge:	Current methods focus on detecting and removing duplicates, which risks the loss of valuable information and neglects the varying degrees of duplication.
Approach:	They propose a method that maintains dataset integrity while selectively reducing the sampling weight of data with high commonness.
Outcome:	The proposed method significantly improves training efficiency on deduplicated datasets and improves downstream accuracy by 1.77%.

Copied to clipboard

Yang Zhao, Li Du, Xiao Ding, Kai Xiong, Zhouhao Sun, Shi Jun, Ting Liu, Bing Qin

Analyzing the Rapid Generalization of SFT via the Perspective of Attention Head Activation Patterns (2025.acl-long)

Challenge:	Existing studies have suggested that the composition of the pretraining corpus exerts a significant impact upon the performance of LLMs.
Approach:	They analyze the impact of 48 datasets from 5 major categories of pretraining data of Large Language Models and measure their impacts on LLMs using benchmarks about nine major categories.
Outcome:	The proposed analysis provides insights into the organization of data to support more efficient pretraining of Large Language Models.

Copied to clipboard

Yang Zhao, Li Du, Xiao Ding, Kai Xiong, Ting Liu, Bing Qin

Green & Sustainable NLP

Challenge:	Currently, LLMs learn in a data-driven schema while the instructions about complex tasks are both scarce and hard to collect or construct.
Approach:	They employ a gradient-based method to dissect the process that the Supervised Fine-tuning Process (SFT) adapts LLMs to downstream tasks via the perspective of attention patterns.
Outcome:	The proposed method dissects the process that the SFT process adapts LLMs to downstream tasks via the perspective of attention patterns.

Mitigating Out-of-Entity Errors in Named Entity Recognition: A Sentence-Level Strategy (2025.coling-main)

Copied to clipboard

Guochao Jiang, Ziqin Luo, Chengwei Hu, Zepeng Ding, Deqing Yang

Information Extraction & Text Mining

Challenge:	Existing models of named entity recognition (NER) suffer from the problem of Out-of-Entity (OOE), which hinders the achievement of satisfactory performance.
Approach:	They propose a framework which fully leverages sentence-level information to improve OOE-NER performance by exploiting pre-trained language models' ability to understand target entity’s sentence context with a template set and refines sentence representation based on positive and negative templates.
Outcome:	The proposed framework outperforms state-of-the-art models on five datasets on named entity recognition (NER) tasks.

AEGIS: A Holistic Benchmark for Evaluating Forensic Analysis of AI-Generated Academic Images (2026.acl-long)

Copied to clipboard

Bo Zhang, Tzu-Yen Ma, Zichen Tang, Junpeng Ding, Zirui Wang, Yizhuo Zhao, Peilin Gao, Zijie Xi, Zixin Ding, Haiyang Sun, Haocheng Gao, Yuan Liu, Liangjia Wang, Yiling Huang, Yujie Wang, Yuyue Zhang, Ronghui Xi, Yuanze Li, Jiacheng Liu, Zhongjun Yang, Haihong E

Measuring Human Contribution in AI-Assisted Content Generation (2026.acl-long)

Challenge:	AEGIS examines whether current models can effectively audit AI-generated images in academic papers.
Approach:	They propose a holistic benchmark for forensic analysis of AI-Generated academic ImageS that reveals limitations in academic image forensics.
Outcome:	AEGIS compared with existing benchmarks on seven academic categories and features key advances in forensic analysis.

Copied to clipboard

Yueqi Xie, Tao Qi, Jingwei Yi, Xiyuan Yang, Ryan Whalen, Junming Huang, Qian Ding, Yu Xie, Xing Xie, Fangzhao Wu

Text Generation

Challenge:	generative AI has created a new way to generate content with humans . varying degrees of human contribution in content generation poses significant challenges for the delineation of originality .
Approach:	They propose a framework to measure human contribution in AI-assisted content generation by calculating mutual information between human input and AI-aided output relative to self-information of AI-assist output.
Outcome:	The proposed measure discriminates between varying degrees of human contribution across multiple creative domains and is validated in real-world applications.

CoAct: Co-Active LLM Preference Learning with Human-AI Synergy (2026.acl-long)

Copied to clipboard

Ruiyao Xu, Mihir Parmar, Tiankai Yang, Zhengyu Hu, Yue Zhao, Kaize Ding

UltraLink: An Open-Source Knowledge-Enhanced Multilingual Supervised Fine-tuning Dataset (2024.acl-long)

Challenge:	Existing methods to learn from preference-based feedback are expensive and scarce.
Approach:	They propose a framework that synergistically combines self-rewarding and active learning through human-AI collaboration.
Outcome:	The proposed framework outperforms existing methods on three reasoning benchmarks and achieves average improvements of +13.25% on GSM8K, +8.19% on MATH, and +13.16% on WebInstruct.

Copied to clipboard

Haoyu Wang, Shuo Wang, Yukun Yan, Xujia Wang, Zhiyu Yang, Yuzhuang Xu, Zhenghao Liu, Liner Yang, Ning Ding, Xu Han, Zhiyuan Liu, Maosong Sun

Towards Knowledge-Based Recommender Dialog System (D19-1)

Challenge:	Open-source large language models (LLMs) have gained strength across diverse fields, but the majority of studies focus on English.
Approach:	They propose a knowledge-grounded data augmentation approach to elicit more language-specific knowledge of LLMs by enhancing their ability to serve users from different countries.
Outcome:	The proposed method can prune the language-agnostic supervised fine-tuning dataset without any performance degradation.

Copied to clipboard

Qibin Chen, Junyang Lin, Yichang Zhang, Ming Ding, Yukuo Cen, Hongxia Yang, Jie Tang

Dialogue Systems & Conversational Agents

Challenge:	Existing frameworks that only provide information about user preferences can be inaccurate in e-commerce recommender systems.
Approach:	They propose a framework which integrates the recommender system and dialog generation system by introducing information about users’ preferences.
Outcome:	The proposed framework can achieve better performance in both dialog generation and recommendation compared with baselines.

Decoding Scientific Experimental Images: The SPUR Benchmark for Perception, Understanding, and Reasoning (2026.acl-long)

Copied to clipboard

Junpeng Ding, Zichen Tang, Haihong E, Mengyuan Ji, Yang Liu, Haolin Tian, Haiyang Sun, Pengqi Sun, Yang Xu, Yichen Liu, Haocheng Gao, Zijie Xi, Ruomeng Jiang, Peizhi Zhao, Rongjin Li, Yuanze Li, Jiacheng Liu, Zhongjun Yang, Jintong Chen, Siying Lin

DFAMS: Dynamic-flow guided Federated Alignment based Multi-prototype Search (2026.acl-long)

Challenge:	Xu and Peng, 2025) . . SPUR is a comprehensive benchmark for scientific experimental image perception, understanding, and reasoning, comprising 4,264 question-answering (QA) pairs derived from 1,084 expert-curated images.
Approach:	They propose to use 4,264 question-answering (QA) pairs derived from 1,084 expert-curated images to evaluate the visual perception of multimodal large language models (MLLMs) . they also propose to utilize cross-panel relation understanding to evaluate MLLM’s ability to decipher intricate cross-panel relations.
Outcome:	The proposed model is based on 4,264 question-answering pairs derived from 1,084 expert-curated images.

Copied to clipboard

Zhibang Yang, Xinke Jiang, Rihong Qiu, Ruiqing Li, Yihang Zhang, Yue Fang, Yongxin Xu, Hongxin Ding, Xu Chu, Junfeng Zhao, Yasha Wang

MARD: Module-Aware Reasoning Distillation for Language Models with Adaptive Supervision (2026.acl-long)

Challenge:	Existing methods for ambiguous queries struggle to retrieve high-quality documents . DFAMS outperforms advanced FR methods by 14.37% in knowledge classification accuracy .
Approach:	They propose a framework that leverages dynamic information flow to identify latent query intents and construct semantically aligned knowledge partitions for accurate retrieval across heterogeneous sources.
Outcome:	The proposed framework outperforms existing methods in classification accuracy and retrieval recall tests.

Copied to clipboard

Wenqi Yang, Jianjun Li, Zhibo Zhang, Mingqian Ding, Yushen Fang

Addressing the Vulnerability of NMT in Input Perturbations (2021.naacl-industry)

Challenge:	Multi-step reasoning remains challenging for language models with limited capacity . et al., 2025) demonstrate remarkable reasoning capabilities across diverse tasks .
Approach:	They propose a module-aware reasoning distillation framework that explicitly targets key Transformer components for effective reasoning transfer.
Outcome:	The proposed framework targets key components for effective reasoning transfer . it adopts an offline distillation setting, where a strong teacher model provides reasoning trajectories in advance .

Copied to clipboard

Weiwen Xu, Ai Ti Aw, Yang Ding, Kui Wu, Shafiq Joty

Robustness in NLP

Challenge:	Recent advances in NMT have improved translation quality but are vulnerable to input perturbations.
Approach:	They propose a method to reduce the effect of noisy inputs by using a Context-Enhanced Reconstruction approach.
Outcome:	The proposed approach improves robustness on Chinese-English and French-English translation tasks.

Large Language Models Are Still Misled by Simple Bias Ensembles (2026.findings-acl)

Copied to clipboard

Zhouhao Sun, Zhiyuan Kan, Xiao Ding, Li Du, Bibo Cai, Yang Zhao, Bing Qin, Ting Liu

MCS-Bench: A Comprehensive Benchmark for Evaluating Multimodal Large Language Models in Chinese Classical Studies (2025.acl-long)

Challenge:	Existing benchmarks for large language models are constrained to datasets where each sample is manually injected with only one type of bias.
Approach:	They propose a multi-bias benchmark where each sample contains multiple types of biases.
Outcome:	The proposed benchmark shows that existing LLMs and debiasing methods perform poorly on this benchmark, highlighting the challenge of eliminating compounded biases.

Copied to clipboard

Yang Liu, Jiahuan Cao, Hiuyi Cheng, Yongxin Shi, Kai Ding, Lianwen Jin

Among Us: Measuring and Mitigating Malicious Contributions in Model Collaboration Systems (2026.acl-long)

Challenge:	Multimodal Large Language Models (MLLMs) have advanced visual and language understanding, but their potential in Chinese Classical Studies (CCS) remains underexplored due to the lack of specialized benchmarks.
Approach:	They propose to develop a multimodal benchmark specifically designed for Chinese Classical Studies across multiple subdomains to bridge this gap.
Outcome:	The proposed benchmark spans seven core subdomains with a total of 45 meticulously designed tasks.

Copied to clipboard

Ziyuan Yang, Wenxuan Ding, Shangbin Feng, Yulia Tsvetkov

Extending Automatic Machine Translation Evaluation to Book-Length Documents (2025.emnlp-main)

Challenge:	Existing research is leveraging multiple language models with diverse skills and strengths to collaborate.
Approach:	They propose mitigation strategies to mitigate the impact of malicious models by employing external supervisors to disable/mask them out to reduce their influence.
Outcome:	The proposed mitigation strategies recover 95.31% of initial performance while making model collaboration systems fully resistant to malicious models remains an open question.

Copied to clipboard

Kuang-Da Wang, Shuoyang Ding, Chao-Han Huck Yang, Ping-Chun Hsieh, Wen-Chih Peng, Vitaly Lavrukhin, Boris Ginsburg

Machine Translation

Challenge:	Large Language Models (LLMs) have superior translation performance and long-context capabilities, but evaluation methodologies remain constrained to sentence-level assessment due to dataset limitations and token number restrictions in metrics.
Approach:	They propose an evaluation scheme that extends existing automatic metrics to long-document translation by treating documents as continuous text and applying sentence segmentation and alignment methods.
Outcome:	The proposed evaluation scheme outperforms existing long-form document evaluation schemes while accounting for under-/over-translations and varied sentence boundaries.

SeaEval for Multilingual Foundation Models: From Cross-Lingual Alignment to Cultural Reasoning (2024.naacl-long)

Copied to clipboard

Bin Wang, Zhengyuan Liu, Xin Huang, Fangkai Jiao, Yang Ding, AiTi Aw, Nancy Chen

Multilinguality

Challenge:	a new benchmark for multilingual foundation models is being developed . brittleness of foundation models in the dimensions of semantics and multilinguality is a key limitation .
Approach:	They propose a benchmark for multilingual foundation models, SeaEval . they examine how well these models comprehend cultural practices, nuances, and values .
Outcome:	The proposed model can be used to evaluate multilingual and multicultural scenarios.

Can We Learn Question, Answer, and Distractors All from an Image? A New Task for Multiple-choice Visual Question Answering (2024.lrec-main)

Copied to clipboard

Wenjian Ding, Yao Zhang, Jun Wang, Adam Jatowt, Zhenglu Yang

OmniAlign-V: Towards Enhanced Alignment of MLLMs with Human Preference (2025.acl-long)

Challenge:	Existing studies focus on generating QADs from image and question, but a novel task is needed to generate meaningful questions, correct answers, and challenging distractors.
Approach:	They propose a task to generate QADs from images and encode images together . they use contrastive learning to ensure consistency of QAD generated and tested .
Outcome:	Empirical evaluations on the benchmark dataset validate the performance of the proposed task.

Copied to clipboard

Xiangyu Zhao, Shengyuan Ding, Zicheng Zhang, Haian Huang, Maosongcao Maosongcao, Jiaqi Wang, Weiyun Wang, Xinyu Fang, Wenhai Wang, Guangtao Zhai, Hua Yang, Haodong Duan, Kai Chen

Specializing Large Models for Oracle Bone Script Interpretation via Component-Grounded Multimodal Knowledge Augmentation (2026.acl-long)

Challenge:	Existing open-source multi-modal large language models (MLLMs) focus on enhancing foundational capabilities, leaving a significant gap in human preference alignment.
Approach:	They propose a dataset of 200K high-quality training samples featuring diverse images, complex questions, and varied response formats to improve MLLMs’ alignment with human preferences.
Outcome:	The proposed dataset of 200K high-quality training samples improves human preference alignment while maintaining or enhancing performance on standard VQA benchmarks.

Copied to clipboard

Jianing Zhang, Runan Li, Honglin Pang, Ding Xia, Zhou Zhu, Qian Zhang, Chuntao Li, Xi Yang