SUPERVISED TRAINING

Guiding Neural Entity Alignment with Compatibility (2022.emnlp-main)

Challenge:	Currently, there are only 24 languages in the world that have not been annotated . transferring knowledge across domains is a common solution .
Approach:	They propose a Bayesian generative model for the space of neural parameters that factorizes into latent variables for each language and each task.
Outcome:	The proposed model can perform better than state-of-the-art methods with a typologically diverse sample of 33 languages from 4 continents and 11 families.

Copied to clipboard

Bing Liu, Harrisen Scells, Wen Hua, Guido Zuccon, Genghong Zhao, Xia Zhang

Structured Data in NLP

Challenge:	Entity Alignment (EA) aims to find equivalent entities between two Knowledge Graphs (KGs) labelled data is used to learn neural EA models, but this aspect is neglected .
Approach:	They propose a framework to integrate compatibility into neural EA models . they aim to find equivalent entities between two Knowledge Graphs (KGs)
Outcome:	The proposed framework can achieve comparable effectiveness with supervised training using 20% of labelled data.

Temporal Knowledge Graph Forecasting Without Knowledge Using In-Context Learning (2023.emnlp-main)

Copied to clipboard

Dong-Ho Lee, Kian Ahrabian, Woojeong Jin, Fred Morstatter, Jay Pujara

Hierarchical Attention Prototypical Networks for Few-Shot Text Classification (D19-1)

Challenge:	Temporal knowledge graphs (TKGs) are used to represent real-world facts in a structured way.
Approach:	They propose to use in-context learning with large language models for TKG forecasting . they compare naive LLMs to state-of-the-art (SOTA) supervised models .
Outcome:	The proposed approach performs well against pre-trained large language models . the proposed approach is based on simple heuristics and state-of-the-art models compared with pre-trainers .

Copied to clipboard

Shengli Sun, Qingfeng Sun, Kevin Zhou, Tengchao Lv

Regression-Free Model Updates for Spoken Language Understanding (2023.acl-industry)

Challenge:	Existing methods for text classification are based on large-scale labeled data, but few data are available.
Approach:	They propose a hierarchical attention prototypical networks for few-shot text classification . they use attention mechanism to highlight or weaken the importance of features, words, and instances .
Outcome:	The proposed model can capture more important features, words, and instances . it can also increase support set augmentability and accelerate convergence speed in training stage .

Copied to clipboard

Andrea Caciolai, Verena Weber, Tobias Falke, Alessandro Pedrani, Davide Bernardi

Information Retrieval

Challenge:	Recent work has proposed methods for minimizing regressions caused by model updates . focus is on spoken language understanding models, which are unexplored .
Approach:	They propose a focal distillation technique to reduce regressions in goal-oriented dialog systems . they also evaluate its effectiveness for key language understanding tasks .
Outcome:	The proposed technique outperforms naive supervised training in mislabeled data and label expansion settings.

Do Pretrained Contextual Language Models Distinguish between Hebrew Homograph Analyses? (2023.eacl-main)

Copied to clipboard

Avi Shmidman, Cheyn Shmuel Shmidman, Dan Bareket, Moshe Koppel, Reut Tsarfaty

Fine-grained Category Discovery under Coarse-grained supervision with Hierarchical Weighted Self-contrastive Learning (2022.emnlp-main)

Challenge:	Semitic morphologically-rich languages are characterized by extreme word ambiguity . many of the words are homographs with multiple possible analyses .
Approach:	They evaluate existing models for Hebrew homographs using word-piece embeddings . they find they are more effective when the number of word-part splits is limited .
Outcome:	The proposed models outperform non-contextualized embeddings on Hebrew homograph challenge sets.

Copied to clipboard

Wenbin An, Feng Tian, Ping Chen, Siliang Tang, Qinghua Zheng, QianYing Wang

LMCap: Few-shot Multilingual Image Captioning by Retrieval Augmented Language Model Prompting (2023.findings-acl)

Challenge:	Existing methods for novel category discovery focus on the scenario where known and novel categories are of the same granularity.
Approach:	They propose a novel scenario for fine-grained category discovery under coarse-grain supervision that allows for adapting models to categories of different granularity from known ones.
Outcome:	The proposed model can adapt models to categories of different granularity from known ones and reduce labeling cost.

Copied to clipboard

Rita Ramos, Bruno Martins, Desmond Elliott

Multimodality

Challenge:	Existing captioning models are mostly available on English or are specialised for other high-resource languages.
Approach:	They propose an image-blind few-shot multilingual captioning model that prompts a language model with retrieved captions.
Outcome:	The proposed model is competitive with fully-supervised multilingual captioning models without requiring any supervised training on captioning data.

Disentangled Learning of Stance and Aspect Topics for Vaccine Attitude Detection in Social Media (2022.naacl-main)

Copied to clipboard

Lixing Zhu, Zheng Fang, Gabriele Pergola, Robert Procter, Yulan He

Sentiment Analysis

Challenge:	Existing approaches to detect vaccine attitudes on social media require abundant annotations and pre-defined aspect categories.
Approach:	They propose a semi-supervised approach to detect vaccine attitudes on social media . they use an autoencoding architecture to learn from unlabelled data the topical information of the domain .
Outcome:	The proposed model outperforms existing aspect-based models on stance detection and tweet clustering.

Natural Language to Structured Query Generation via Meta-Learning (N18-2)

Copied to clipboard

Po-Sen Huang, Chenglong Wang, Rishabh Singh, Wen-tau Yih, Xiaodong He

Read to Hear: A Zero-Shot Pronunciation Assessment Using Textual Descriptions and LLMs (2025.emnlp-main)

Challenge:	Conventional supervised training is a pervasive paradigm for NLP problems . however, examples of the same problem may vary widely . a few-shot meta-learning scenario is used to learn multiple models .
Approach:	They propose a learning protocol that treats each example as a unique pseudo-task . they use a few-shot meta-learning scenario to reduce the original learning problem to a single example .
Outcome:	The proposed learning protocol achieves 1.1%–5.4% accuracy gains over non-meta-learning counterparts on a WikiSQL dataset.

Copied to clipboard

Yu-Wen Chen, Melody Ma, Julia Hirschberg

Speech & Audio in NLP

Challenge:	Automatic pronunciation assessment is typically performed by acoustic models trained on audio-score pairs.
Approach:	They propose a zero-shot, textual description-based Pronunciation Assessment approach that utilizes human-readable representations of speech signals fed into an LLM to assess pronunciation accuracy and fluency.
Outcome:	The proposed approach is cost-efficient and competitive in performance . it significantly improves the performance of conventional audio-score-trained models on out-of-domain data .

SHAPED: Shared-Private Encoder-Decoder for Text Style Adaptation (N18-1)

Copied to clipboard

Ye Zhang, Nan Ding, Radu Soricut

Product Description and QA Assisted Self-Supervised Opinion Summarization (2024.findings-naacl)

Challenge:	Experimentally, we find that the proposed models consistently outperform models that encapsulate single-style or average-style language generation capabilities.
Approach:	They propose a family of model architectures capable of capturing both generic language characteristics via shared model parameters, as well as particular style characteristics via private model parameters.
Outcome:	The proposed models outperform models that encapsulate single-style or average-style language generation capabilities.

Copied to clipboard

Tejpalsingh Siledar, Rupasai Rangaraju, Sankara Muddu, Suman Banerjee, Amey Patil, Sudhanshu Singh, Muthusamy Chelliah, Nikesh Garera, Swaprava Nath, Pushpak Bhattacharyya

Implicit Discourse Relation Classification For Nigerian Pidgin (2025.coling-main)

Challenge:	Existing methods to generate opinion summarization without supervised training data are limited due to the lack of additional sources.
Approach:	They propose a synthetic dataset creation strategy that leverages reviews and additional sources to generate a pseudo-summary.
Outcome:	The proposed approach achieves 14.5% improvement in ROUGE-1 F1 over existing models.

Copied to clipboard

Muhammed Yahia Gaffar Saeed Saeed, Peter Bourgonje, Vera Demberg

Question Generation from SQL Queries Improves Neural Semantic Parsing (D18-1)

Challenge:	Existing discourse parsing tools are not available for Nigerian Pidgin (NP) this task requires supervised training and requires prompting.
Approach:	They propose to use implicit discourse relation classification (IDRC) for Nigerian Pidgin, which requires supervised training.
Outcome:	The proposed framework outperforms baseline and NP IDR classifiers in f1 scores.

Copied to clipboard

Daya Guo, Yibo Sun, Duyu Tang, Nan Duan, Jian Yin, Hong Chi, James Cao, Peng Chen, Ming Zhou

Learning to Retrieve Passages without Supervision (2022.naacl-main)

Challenge:	Using question generation, we learn a semantic parser with 30% of the supervised training data.
Approach:	They propose to use question generation to learn a semantic parser with less supervised training data.
Outcome:	The proposed method improves the state-of-the-art model with less training data.

Copied to clipboard

Ori Ram, Gal Shachaf, Omer Levy, Jonathan Berant, Amir Globerson

Information Retrieval

Challenge:	Dense retrievers for open domain question answering have been shown to achieve impressive performance by training on large datasets of question-passage pairs.
Approach:	They propose to use recurring spans to create pseudo examples for contrastive learning.
Outcome:	The proposed model outperforms all pretrained baselines on a wide range of ODQA datasets and is competitive with BM25, a strong sparse baseline.

Recommendation as a Communication Game: Self-Supervised Bot-Play for Goal-oriented Dialogue (D19-1)

Copied to clipboard

Dongyeop Kang, Anusha Balakrishnan, Pararth Shah, Paul Crook, Y-Lan Boureau, Jason Weston

Dialogue Systems & Conversational Agents

Challenge:	Traditional recommendation systems produce static rather than interactive recommendations invariant to a user’s specific requests, clarifications, or current mood.
Approach:	They use a goal-driven recommendation dialogue dataset to develop an end-to-end dialogue system that can simultaneously converse and recommend.
Outcome:	The proposed system can converse and recommend movies to humans without considering the task goal itself.

STAR: Constraint LoRA with Dynamic Active Learning for Data-Efficient Fine-Tuning of Large Language Models (2024.findings-acl)

Copied to clipboard

Linhai Zhang, Jialong Wu, Deyu Zhou, Guoqiang Xu

SMART: Self-Aware Agent for Tool Overuse Mitigation (2025.findings-acl)

Challenge:	Existing studies show that supervised training is still necessary for complex reasoning tasks.
Approach:	They propose a method to integrate uncertainty-based active learning and LoRA to effectively integrate the two methods.
Outcome:	The proposed approach outperforms baseline models on three reasoning tasks.

Copied to clipboard

Cheng Qian, Emre Can Acikgoz, Hongru Wang, Xiusi Chen, Avirup Sil, Dilek Hakkani-Tür, Gokhan Tur, Heng Ji

Reasoning

Challenge:	Current Large Language Models (LLMs) lack self-awareness to balance reasoning and tool use, increasing computational overhead.
Approach:	They propose a paradigm that enhances an agent’s self-awareness to optimize task handling and reduce tool overuse.
Outcome:	The proposed model reduces tool use by 24% while improving performance by over 37%.

Learning to Denoise Distantly-Labeled Data for Entity Typing (N19-1)

Copied to clipboard

Yasumasa Onoe, Greg Durrett

G-Transformer for Document-Level Machine Translation (2021.acl-long)

Challenge:	Distantly-labeled data can be used to scale up statistical models, but it is noisy . specialized probabilistic models can be employed to scale the training of models, however, they require sophisticated probabilistic inference for the training.
Approach:	They propose a method for denoising and denoising noisy data with supervised training.
Outcome:	The proposed method outperforms models trained on clean and denoised data on an ultra-fine entity typing task.

Copied to clipboard

Guangsheng Bao, Yue Zhang, Zhiyang Teng, Boxing Chen, Weihua Luo

UCoder: Unsupervised Code Generation by Internal Probing of Large Language Models (2026.findings-acl)

Challenge:	Existing work extends translation unit from single sentence to multiple sentences.
Approach:	They propose to introduce locality assumption as an inductive bias into Transformer and reduce the hypothesis space of attention from target to source.
Outcome:	The proposed model achieves state-of-the-art BLEU scores on three benchmark datasets.

Copied to clipboard

Jiajun Wu, Jian Yang, Wei Zhang, Linzheng Chai, Yuchi Ma, Ensheng Shi, Yuqing Ma, Zhoujun Li, Xianglong Liu

Self-Supervised Behavior Cloned Transformers are Path Crawlers for Text Games (2023.findings-emnlp)

Challenge:	Large language models (LLMs) have demonstrated remarkable capabilities in code generation tasks, but their effectiveness relies on supervised training with extensive labeled data and computational resources.
Approach:	They propose an unsupervised method that leverages Internal Probing of Large language models for Code generation without any external corpus, even unlabeled code snippets.
Outcome:	The proposed method can achieve competitive performance compared to supervised approaches while reducing the dependency on labeled data and computational resources.

Copied to clipboard

Ruoyao Wang, Peter Jansen

Multitasking Framework for Unsupervised Simple Definition Generation (2022.acl-long)

Challenge:	Text game agents are often modeled using reinforcement learning, but their performance is limited.
Approach:	They propose a self-supervised behavior cloning transformer for text games . they explore trajectories that lead to reward within the games and then train small models . their approach consistently uncovers generalizable training data, achieving 90% performance of supervised systems across three benchmark text games.
Outcome:	The proposed model achieves 90% performance on three text games.

Copied to clipboard

Cunliang Kong, Yun Chen, Hengyuan Zhang, Liner Yang, Erhong Yang

Leveraging pre-trained language models for linguistic analysis: A case of argument structure constructions (2024.emnlp-main)

Challenge:	Existing definition generation tasks require a dictionary with complex definitions and a corpus containing arbitrary simple texts to generate them.
Approach:	They propose a multitasking framework SimpDefiner that only requires a standard dictionary with complex definitions and a corpus containing arbitrary simple texts.
Outcome:	The proposed framework outperforms the baseline model by a 1.77 SARI score on the English dataset, and raises the proportion of the low level (HSK level 1-3) words in Chinese definitions by 3.87%.

Copied to clipboard

Hakyung Sung, Kristopher Kyle

The student becomes the master: Outperforming GPT3 on Scientific Factual Error Correction (2023.findings-emnlp)

Challenge:	Argument structure constructions (ASCs) are lexicogrammatical patterns at the clausal level.
Approach:	They evaluate the effectiveness of pre-trained language models in identifying argument structure constructions . they use supervised training with RoBERTa and prompt-guided annotation with GPT-4 .
Outcome:	The proposed model outperforms the gold-standard model on three methods . the results show that the model performs better on gold-standardized data .

Copied to clipboard

Dhananjay Ashok, Atharva Kulkarni, Hai Pham, Barnabas Poczos

ConGen: Unsupervised Control and Generalization Distillation For Sentence Representation (2022.findings-emnlp)

Challenge:	Existing methods for Factual Claim Correction rely on a verification model to guide the correction process.
Approach:	They propose a claim correction system that does not require a verifier but outperforms existing methods by a considerable margin.
Outcome:	The proposed system outperforms existing methods by a considerable margin on the SciFact dataset, 77% on SciFACT-Open and 72.75% on the CovidFact data set.

Copied to clipboard

Peerat Limkonchotiwat, Wuttikorn Ponwitayarat, Lalita Lowphansirikul, Can Udomcharoenchaikit, Ekapol Chuangsuwanich, Sarana Nutanong

Perhaps PTLMs Should Go to School – A Task to Assess Open Book and Closed Book QA (2021.emnlp-main)

Challenge:	Sentence representations are essential in many NLP tasks operating at the sentence level.
Approach:	They propose an unsupervised sentence representation method to reduce the supervised-unsupervised performance gap for smaller models.
Outcome:	The proposed method outperforms supervised training on STS, text classification, and natural language inference tasks on smaller models.

Copied to clipboard

Manuel Ciosici, Joe Cecil, Dong-Ho Lee, Alex Hedges, Marjorie Freedman, Ralph Weischedel

Question Answering

Challenge:	Taking the exam closed book, but having read the textbook, yields at best minor improvement (56%), suggesting that the PTLM may not have “understood” the textbook (or perhaps misundersttoo the questions).
Approach:	They propose to use pre-trained language models to answer questions from introductory college textbooks and hundreds of true/false statements based on review questions written by the authors.
Outcome:	The proposed task includes two college-level introductory texts in the social sciences (American Government 2e) and humanities (U.S. History).

Simple Entity-Centric Questions Challenge Dense Retrievers (2021.emnlp-main)

Copied to clipboard

Christopher Sciavolino, Zexuan Zhong, Jinhyuk Lee, Danqi Chen

Robustness in NLP

Challenge:	Open-domain question answering has exploded in popularity due to the success of dense retrieval models.
Approach:	They construct a set of simple, entity-rich questions based on facts from Wikidata and test their models against supervised datasets.
Outcome:	The proposed model outperforms sparse retrieval methods on open-domain question answering datasets by a large margin.

DiffChat: Learning to Chat with Text-to-Image Synthesis Models for Interactive Image Creation (2024.findings-acl)

Copied to clipboard

Jiapeng Wang, Chengyu Wang, Tingfeng Cao, Jun Huang, Lianwen Jin

Multimodality

Challenge:	a novel method to align Large Language Models to "chat" with prompt-as-input Text-to-Image Synthesis models is proposed . a user-specified instruction can be used to create a high quality image .
Approach:	They propose a method to align Large Language Models to "chat" with prompt-as-input Text-to-Image Synthesis models for interactive image creation.
Outcome:	The proposed method can exhibit superior performance than baseline models and strong competitors based on automatic and human evaluations.

ProGene - A Large-scale, High-Quality Protein-Gene Annotated Benchmark Corpus (2020.lrec-1)

Copied to clipboard

Erik Faessler, Luise Modersohn, Christina Lohr, Udo Hahn

Challenge:	Genes and proteins are fundamental entities of molecular genetics and are important for precision medicine.
Approach:	They propose to use a corpus of gene and protein names to cope with this class of named entities in a large-scale annotation campaign at the Jena University Language & Information Engineering lab.
Outcome:	The proposed corpus is an overall subdomain-independent corpus . it consists of 3,308 MEDLINE abstracts with over 36k sentences and more than 960k tokens annotated with nearly 60k named entity mentions.

Prompted Aspect Key Point Analysis for Quantitative Review Summarization (2024.acl-long)

Copied to clipboard

An Tang, Xiuzhen Zhang, Minh Dinh, Erik Cambria

Summarization

Challenge:	Recent abstractive approaches generate KPs based on sentences, resulting in overlapping and hallucinated opinions.
Approach:	They propose to use supervised learning to extract short sentences as key points before matching them to review comments for quantification of KP prevalence.
Outcome:	The proposed framework achieves state-of-the-art performance on Yelp and SPACE.

Cross-lingual Spoken Language Understanding with Regularized Representation Alignment (2020.emnlp-main)

Copied to clipboard

Zihan Liu, Genta Indra Winata, Peng Xu, Zhaojiang Lin, Pascale Fung

Unsupervised Dual Paraphrasing for Two-stage Semantic Parsing (2020.acl-main)

Challenge:	despite promising results, current cross-lingual models suffer from imperfect cross-linguistic representation alignments between the source and target languages, which makes the performance sub-optimal.
Approach:	They propose a regularization approach to align word-level and sentence-level representations across languages without external resources.
Outcome:	The proposed model outperforms state-of-the-art models in few-shot and zero-shot scenarios and achieves comparable performance to supervised training with all training data.

Copied to clipboard

Ruisheng Cao, Su Zhu, Chenyu Yang, Chen Liu, Rao Ma, Yanbin Zhao, Lu Chen, Kai Yu

Lost in Literalism: How Supervised Training Shapes Translationese in LLMs (2025.acl-long)

Challenge:	Existing semantic parsing frameworks rely on nontrivial human labor to generate canonical utterances.
Approach:	They propose a framework that uses an unsupervised paraphrase model to parse canonical utterances.
Outcome:	The proposed framework is effective and compatible with supervised training.

Copied to clipboard

Yafu Li, Ronghao Zhang, Zhilin Wang, Huajian Zhang, Leyang Cui, Yongjing Yin, Tong Xiao, Yue Zhang

Machine Translation

Challenge:	Large language models exhibit translationese errors and generate unexpected unnatural translations . Neural machine translation (NMT) has become the dominant method in machine translation research .
Approach:	They evaluate the prevalence of translationese in LLM-generated translations and investigate its roots during supervised fine-tuning.
Outcome:	The proposed methods reduce translationese while improving translation naturalness . the proposed methods are validated by human evaluations and automatic metrics .

An automatic model and Gold Standard for translation alignment of Ancient Greek (2022.lrec-1)

Copied to clipboard

Tariq Yousef, Chiara Palladino, Farnoosh Shamsian, Anise d’Orange Ferreira, Michel Ferreira dos Reis

Machine Translation

Challenge:	Using a manual annotation tool, we evaluated the performance of various automatic translation alignment models for Ancient Greek.
Approach:	They propose a fine-tuning strategy that employs unsupervised training with mono- and bilingual texts and supervised training using manually aligned sentences.
Outcome:	The proposed model outperforms the standard on language pairs that were not part of the training data.

Analyze, Generate and Refine: Query Expansion with LLMs for Zero-Shot Open-Domain QA (2024.findings-acl)

Copied to clipboard

Xinran Chen, Xuanang Chen, Ben He, Tengfei Wen, Le Sun

Low-Resource NLP

Challenge:	Existing methods like GAR and EAR rely heavily on supervised training and struggle to maintain effectiveness across domains and datasets.
Approach:	They propose a QE approach based on a three-step prompting strategy to enhance query expansion by broadening the scope of queries with additional relevant texts.
Outcome:	The proposed approach outperforms state-of-the-art methods in out-domain zero-shot scenarios and outperformed existing methods in end-to-end evaluations.

Self-training Language Models for Arithmetic Reasoning (2024.findings-emnlp)

Copied to clipboard

Marek Kadlčík, Michal Štefánik

Learning Opinion Summarizers by Selecting Informative Reviews (2021.emnlp-main)

Challenge:	Recent work improves the reasoning capabilities of language models by scaling training data to more diverse or complex collections, but reaching further improvements becomes exceedingly expensive.
Approach:	They propose to use implicit feedback to improve models' reasoning capabilities by training from implicit feedback.
Outcome:	The proposed model can reach a correct result in +13.9% and +25.9% more cases than previous models, underlining the importance of actuality of self-training feedback.

Copied to clipboard

Arthur Bražinskas, Mirella Lapata, Ivan Titov

Learning to Generate Overlap Summaries through Noisy Synthetic Data (2022.emnlp-main)

Challenge:	supervised summarization has been traditionally approached with unsupervised, weakly-supervised and few-shot learning techniques.
Approach:	They propose to combine a large dataset of opinion summaries with user reviews to form a supervised summarizer.
Outcome:	The proposed method improves the quality of summarization and reduces hallucinations in the summarizer.

Copied to clipboard

Naman Bansal, Mousumi Akter, Shubhra Kanti Karmaker Santu

MSMO-ABSA: Multi-Scale and Multi-Objective Optimization for Cross-Lingual Aspect-Based Sentiment Analysis (2026.acl-long)

Challenge:	Existing training data for seq-to-seq models is limited due to the lack of available training data.
Approach:	They propose a data augmentation technique which allows to create large amount of synthetic data for training a seq-to-seq model.
Outcome:	The proposed technique performs better than pre-trained models on news domains and is close to the existing methods on golden training data.

Copied to clipboard

Chengyan Wu, Bolei Ma, Ningyuan Deng, He Yanqing, Yun Xue, Liu Xiaoyong

Robustness in NLP

Challenge:	Aspect-based sentiment analysis (ABSA) has seen success with English texts, but real-world social media interactions often involve multiple languages.
Approach:	They propose a framework for cross-lingual ABSA that incorporates code-switched bilingual sentences into the language discriminator and consistency training modules to enhance cross-linguistic alignment.
Outcome:	The proposed framework achieves cross-lingual sentence-level and aspect-level alignment, aligning features of aspect terms in different contextual environments.

Towards Zero-shot Learning for End-to-end Cross-modal Translation Models (2023.findings-emnlp)

Copied to clipboard

Jichen Yang, Kai Fan, Minpeng Liao, Boxing Chen, Zhongqiang Huang

Multimodality

Challenge:	End-to-end zero-shot speech translation model is based on a zero-shot approach, but it is less competitive because of the limited amount of data available for multiple modalities.
Approach:	They propose an end-to-end zero-shot speech translation model that connects two pre-trained uni-modality modules via word rotator’s distance.
Outcome:	The proposed model performs better than or as well as those of the CTC-based models and can be trained in an end-to-end style to avoid error propagation.

Rule-Guided Extraction: A Hierarchical Rule Optimization Framework for Document-Level Event Argument Extraction (2025.findings-emnlp)

Copied to clipboard

Yue Zuo, Yuxiao Fei, Wanting Ning, Jiayi Huang, Yubo Feng, Lishuang Li