Papers by Ming Yin

Evidence-Aware Inferential Text Generation with Vector Quantised Variational AutoEncoder (2020.acl-main)

Challenge:	Chain-of-Thought prompting is a de facto method to elicit reasoning capabilities from large language models (LLMs).
Approach:	They propose a step-aware formal verification framework Safe to address hallucinations in CoT prompting . they propose 'formal step' as a benchmark for step correctness theorem proving with 30,809 formal statements.
Outcome:	The proposed framework shows significant performance improvement while offering interpretable and verifiable evidence.

Copied to clipboard

Daya Guo, Duyu Tang, Nan Duan, Jian Yin, Daxin Jiang, Ming Zhou

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

Challenge:	Existing approaches for inferential text generation ignore context that is not explicitly provided . Existing models ignore background knowledge that provides crucial evidence to generate inferences .
Approach:	They propose an approach that automatically finds evidence for an event from a large text corpus and leverages it to guide the generation of inferential texts.
Outcome:	The proposed model generates inferential texts from a large text corpus and uses evidence to guide it.

Copied to clipboard

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

Text Generation

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

SAC: Neural Speech Codec with Semantic-Acoustic Dual-Stream Quantization (2026.acl-long)

Copied to clipboard

Wenxi Chen, Ruiqi Yan, Yushen Chen, Zhikang Niu, Ziyang Ma, Xiquan Li, Yuzhe Liang, null Wenhanlin, Shunshun Yin, Ming Tao, Xinsheng Wang, Xie Chen

Multimodality

Challenge:	Existing speech codecs struggle to balance high-quality reconstruction with semantically rich representations, limiting their effectiveness in both generative and understanding tasks.
Approach:	They propose a neural speech codec with semantic-acoustic dual-stream quantization that disentangles semantic and acousian modeling into two dedicated streams.
Outcome:	The proposed codec outperforms state-of-the-art speech tokenizers in auto-propagating text-to-speech models.

Aligning Large Language Models with Implicit Preferences from User-Generated Content (2025.acl-long)

Copied to clipboard

Zhaoxuan Tan, Zheng Li, Tianyi Liu, Haodong Wang, Hyokun Yun, Ming Zeng, Pei Chen, Zhihan Zhang, Yifan Gao, Ruijie Wang, Priyanka Nigam, Bing Yin, Meng Jiang

Mitigating Lost in Multi-turn Conversation via Curriculum RL with Verifiable Accuracy and Abstention Rewards (2026.acl-long)

Challenge:	Existing preference learning methods rely heavily on curated data from humans or advanced LLMs, which is costly and difficult to scale.
Approach:	They propose a framework that leverages implicit preferences in unlabeled user-generated content to generate preference data.
Outcome:	The proposed framework transforms user-generated content into user queries and generates responses from the policy model.

Copied to clipboard

Ming Li, Pei Chen, Zhenhao Zhang, Tao Yang, Xinyang Zhang, Han Li, Tianyu Cao, Ming Zeng, Zhuofeng Wu, Meng Jiang, Huasheng Li, Lihong Li, Bing Yin

Dialogue Systems & Conversational Agents

Challenge:	Large Language Models exhibit strong capabilities in single-turn instruction following but suffer from Lost-in-Conversation (LiC) when instructions are revealed progressively in multi-turn settings, models get "Lost in Conversation"
Approach:	They propose a framework that encourages models to generate correct answers and judge solvability in multi-turn conversations.
Outcome:	The proposed framework improves models' ability to balance problem-solving with abstention . it reduces premature answering behaviors that cause lost-in-conversation (LiC)

A Survey on Efficient Large Language Model Training: From Data-centric Perspectives (2025.acl-long)

Copied to clipboard

Junyu Luo, Bohan Wu, Xiao Luo, Zhiping Xiao, Yiqiao Jin, Rong-Cheng Tu, Nan Yin, Yifan Wang, Jingyang Yuan, Wei Ju, Ming Zhang

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

Challenge:	achieving data-efficient post-training of Large Language Models is a key research question.
Approach:	They propose a taxonomy of data-efficient LLM post-training methods from a data-centric perspective.
Outcome:	The proposed methods cover data selection, data quality enhancement, synthetic data generation, data distillation and compression, and self-evolving data ecosystems.

Copied to clipboard

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

Text Generation

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.

ProQA: Structural Prompt-based Pre-training for Unified Question Answering (2022.naacl-main)

Copied to clipboard

Wanjun Zhong, Yifan Gao, Ning Ding, Yujia Qin, Zhiyuan Liu, Ming Zhou, Jiahai Wang, Jian Yin, Nan Duan

TheoremQA: A Theorem-driven Question Answering Dataset (2023.emnlp-main)

Challenge:	Existing QA research on question answering is focused on specific question types, knowledge domains, or reasoning skills.
Approach:	They propose a unified QA paradigm that solves various tasks through a single model.
Outcome:	The proposed model improves QA-centric ability on 11 QA benchmarks.

Copied to clipboard

Wenhu Chen, Ming Yin, Max Ku, Pan Lu, Yixin Wan, Xueguang Ma, Jianyu Xu, Xinyi Wang, Tony Xia

From Fallback to Frontline: When Can LLMs be Superior Annotators of Human Perspectives? (2026.findings-acl)

Challenge:	Recent LLMs like GPT-4 and PaLM-2 have made tremendous progress in solving fundamental math problems like GSM8K by achieving over 90% accuracy.
Approach:	They propose to use theorem-driven question-answering dataset to evaluate AI models' ability to apply theoretic concepts to solving challenging science problems.
Outcome:	TheoremQA is curated by domain experts and contains 800 high-quality questions covering 350 theoremics from Math, Physics, EE&CS, and Finance.

Copied to clipboard

Hasan Amin, Harry Yizhou Tian, Xiaoni Duan, Chien-Ju Ho, Rajiv Khanna, Ming Yin

Challenge:	large language models are often used as annotators at scale, but are not faithful estimators of human perspectives.
Approach:	They characterize the conditions under which large language models outperform human annotators . they find they are statistically superior frontline estimators based on low variance .
Outcome:	The proposed model outperforms human annotators when predicting subgroup opinions on subjective tasks.

A Holistic Framework for Analyzing the COVID-19 Vaccine Debate (2022.naacl-main)

Copied to clipboard

Maria Leonor Pacheco, Tunazzina Islam, Monal Mahajan, Andrey Shor, Ming Yin, Lyle Ungar, Dan Goldwasser

Sentiment Analysis

Challenge:	Covid-19 infodemic has led to low quality information leading to poor health decisions . authors propose a framework for analyzing false claims and reasoning about the decisions a person makes .
Approach:	They propose a framework linking stance and reason analysis and moral sentiment analysis.
Outcome:	The proposed framework provides reliable predictions even in low-supervision settings.

PA-RAG: RAG Alignment via Multi-Perspective Preference Optimization (2025.naacl-long)

Copied to clipboard

Jiayi Wu, Hengyi Cai, Lingyong Yan, Hao Sun, Xiang Li, Shuaiqiang Wang, Dawei Yin, Ming Gao

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

Challenge:	Existing approaches to optimize RAG generators fail to align with RAG requirements thoroughly.
Approach:	They propose a method for optimizing the RAG generator from multiple preference perspectives to align with RAG requirements comprehensively.
Outcome:	The proposed method improves the performance of RAG generators by incorporating retrieved documents into the prompt.

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

UniXcoder: Unified Cross-Modal Pre-training for Code Representation (2022.acl-long)

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

Daya Guo, Shuai Lu, Nan Duan, Yanlin Wang, Ming Zhou, Jian Yin

Reasoning Over Semantic-Level Graph for Fact Checking (2020.acl-main)

Challenge:	Pre-trained models for programming languages have demonstrated great success on code intelligence . however, such pre-tried models are sub-optimal for auto-regressive tasks .
Approach:	They propose a unified cross-modal pre-trained model for programming language that leverages cross-module contents like AST and code comment to enhance code representation.
Outcome:	The proposed model achieves state-of-the-art on most code-related tasks and compares with existing models on zero-shot code-to-code search.

Copied to clipboard

Wanjun Zhong, Jingjing Xu, Duyu Tang, Zenan Xu, Nan Duan, Ming Zhou, Jiahai Wang, Jian Yin

Distinguish Before Answer: Generating Contrastive Explanation as Knowledge for Commonsense Question Answering (2023.findings-acl)

Challenge:	Existing methods for fact checking use string concatenation or fusing features of isolated evidence sentences.
Approach:	They propose a method suitable for reasoning about the semantic-level structure of evidence . they use graph convolutional network and graph attention network to exploit the structure .
Outcome:	The proposed method improves claim verification accuracy and FEVER score on a benchmark dataset.

Copied to clipboard

Qianglong Chen, Guohai Xu, Ming Yan, Ji Zhang, Fei Huang, Luo Si, Yin Zhang

Responsible & Trustworthy NLP

Challenge:	Existing knowledge-enhanced methods have trouble obtaining knowledge from different knowledge bases . a concept-centric model can be used to generate a contrastive explanation for QA tasks .
Approach:	They propose a Concept-centric Prompt-bAsed Contrastive Explanation Generation model which converts obtained symbolic knowledge into the contrastive explanation for better distinguishing the differences among given candidates.
Outcome:	The proposed model achieves new SOTA on CSQA, QASC, and OBQA.

Interactive Concept Learning for Uncovering Latent Themes in Large Text Collections (2023.findings-acl)

Copied to clipboard

Maria Leonor Pacheco, Tunazzina Islam, Lyle Ungar, Ming Yin, Dan Goldwasser

Challenge:	Topic modeling is a popular method for identifying emerging themes from text collections.
Approach:	They propose a framework that receives and encodes expert feedback at different levels of abstraction.
Outcome:	The proposed framework combines automation and manual coding, allowing experts to maintain control while reducing the manual effort required.

Generate & Rank: A Multi-task Framework for Math Word Problems (2021.findings-emnlp)

Copied to clipboard

Jianhao Shen, Yichun Yin, Lin Li, Lifeng Shang, Xin Jiang, Ming Zhang, Qun Liu

Large Language Models Are Poor Clinical Decision-Makers: A Comprehensive Benchmark (2024.emnlp-main)

Challenge:	Existing studies formalize MWP as a generation task but mathematical expressions are prone to minor mistakes.
Approach:	They propose a ranking task for math word problem (MWP) that learns from its own mistakes and distinguishes between correct and incorrect expressions.
Outcome:	The proposed model outperforms baselines on the classical Math23k dataset and is 7% higher than the state-of-the-art.

Copied to clipboard

Fenglin Liu, Zheng Li, Hongjian Zhou, Qingyu Yin, Jingfeng Yang, Xianfeng Tang, Chen Luo, Ming Zeng, Haoming Jiang, Yifan Gao, Priyanka Nigam, Sreyashi Nag, Bing Yin, Yining Hua, Xuan Zhou, Omid Rohanian, Anshul Thakur, Lei Clifton, David Clifton

Dynosaur: A Dynamic Growth Paradigm for Instruction-Tuning Data Curation (2023.emnlp-main)

Challenge:	Existing studies focus on evaluating large language models in close-ended QA tasks, but many clinical decisions involve answering open-ended questions without pre-set options.
Approach:	They construct a benchmark to better understand large language models in the clinic . they use existing datasets to evaluate LLMs in clinical situations .
Outcome:	The proposed model outperforms human experts in multiple medical tasks.

Copied to clipboard

Da Yin, Xiao Liu, Fan Yin, Ming Zhong, Hritik Bansal, Jiawei Han, Kai-Wei Chang

QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarization (2021.naacl-main)

Challenge:	Existing methods for instruction tuning do not include associating instructions with existing datasets.
Approach:	They propose a dynamic growth paradigm for the automatic curation of instruction-tuning data . they use existing datasets to automatically construct instruction-uning datasets .
Outcome:	The proposed model reduces the API cost for generating instructions and provides high-quality data.

Copied to clipboard

Ming Zhong, Da Yin, Tao Yu, Ahmad Zaidi, Mutethia Mutuma, Rahul Jha, Ahmed Hassan Awadallah, Asli Celikyilmaz, Yang Liu, Xipeng Qiu, Dragomir Radev

Text Generation

Challenge:	Existing work on meeting summarization tasks is limited to short summaries that cover all the content of a meeting.
Approach:	They propose a query-based multi-domain meeting summarization task that generates a single short summary of meetings based on a transcript.
Outcome:	The proposed task is based on 1,808 query-summary pairs over 232 meetings in multiple domains.

Exploring the Cost-Effectiveness of Perspective Taking in Crowdsourcing Subjective Assessment: A Case Study of Toxicity Detection (2025.naacl-long)

Copied to clipboard

Xiaoni Duan, Zhuoyan Li, Chien-Ju Ho, Ming Yin

Challenge:	toxicity evaluation tasks require annotations to accurately reflect opinions of subgroups . toxicity tasks require annotators to take the opinions of a subgroup simultaneously .
Approach:	They propose to use perspective taking to obtain opinions from subgroups . they propose to prompt annotators to take perspectives of contrasting subgroup simultaneously .
Outcome:	The proposed approach can be cost-effective and improve quality under limited budget.

Coupling Retrieval and Meta-Learning for Context-Dependent Semantic Parsing (P19-1)

Copied to clipboard

Daya Guo, Duyu Tang, Nan Duan, Ming Zhou, Jian Yin

Analytical Reasoning of Text (2022.findings-naacl)

Challenge:	a context-aware retrieval model and a meta-learning paradigm are used for context-dependent semantic parsing .
Approach:	They propose a retrieval model and a meta-learner to incorporate retrieved datapoints as context-dependent semantic parsing evidence.
Outcome:	The proposed approach performs better than retrieve-and-edit baselines on CONCODE and CSQA datasets.

Copied to clipboard

Wanjun Zhong, Siyuan Wang, Duyu Tang, Zenan Xu, Daya Guo, Yining Chen, Jiahai Wang, Jian Yin, Ming Zhou, Nan Duan

Neural Deepfake Detection with Factual Structure of Text (2020.emnlp-main)

Challenge:	Existing models with implicit reasoning ability struggle to solve analytical reasoning of text.
Approach:	They propose an approach to analyze text and use it to perform reasoning over it.
Outcome:	The proposed approach outperforms pre-trained models on an analysis of the Law School Admission Test dataset.

Copied to clipboard

Wanjun Zhong, Duyu Tang, Zenan Xu, Ruize Wang, Nan Duan, Ming Zhou, Jiahai Wang, Jian Yin

Structured Data in NLP

Challenge:	Existing approaches to deepfake detection typically represent documents with coarse-grained representations, but they struggle to capture factual structures of documents.
Approach:	They propose a graph-based model that captures factual structures of documents for deepfake detection.
Outcome:	The proposed model improves strong base models built with RoBERTa on two public deepfake datasets.

Improving Abstractive Dialogue Summarization with Speaker-Aware Supervised Contrastive Learning (2022.coling-1)

Copied to clipboard

Zhichao Geng, Ming Zhong, Zhangyue Yin, Xipeng Qiu, Xuanjing Huang

UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models (2022.emnlp-main)

Challenge:	Existing summarization systems based on pre-trained models cannot recognize the unique format of the speaker-utterance pair well in the dialogue.
Approach:	They propose three speaker-aware supervised contrastive learning tasks to solve the speaker identification problem in dialogue summarization task.
Outcome:	The proposed methods improve on two mainstream dialogue summarization datasets.

Copied to clipboard

Tianbao Xie, Chen Henry Wu, Peng Shi, Ruiqi Zhong, Torsten Scholak, Michihiro Yasunaga, Chien-Sheng Wu, Ming Zhong, Pengcheng Yin, Sida I. Wang, Victor Zhong, Bailin Wang, Chengzu Li, Connor Boyle, Ansong Ni, Ziyu Yao, Dragomir Radev, Caiming Xiong, Lingpeng Kong, Rui Zhang, Noah A. Smith, Luke Zettlemoyer, Tao Yu

LogicalFactChecker: Leveraging Logical Operations for Fact Checking with Graph Module Network (2020.acl-main)

Challenge:	Structured knowledge grounding (SKG) uses structured knowledge to complete user requests . since inputs and outputs of SKG tasks are heterogeneous, they have been studied separately .
Approach:	They propose a framework that unifies 21 SKG tasks into a text-to-text format . they use unifiedSKG to benchmark T5 with different sizes .
Outcome:	The proposed framework unifies 21 SKG tasks into a text-to-text format . it achieves state-of-the-art performance on almost all of the 21 tasks, the authors show .

Copied to clipboard

Wanjun Zhong, Duyu Tang, Zhangyin Feng, Nan Duan, Ming Zhou, Ming Gong, Linjun Shou, Daxin Jiang, Jiahai Wang, Jian Yin

Multimodality

Challenge:	Existing methods for fact checking textual statements are not yet available.
Approach:	They propose a neural network approach capable of leveraging logical operations for fact checking . they use a textual statement and semi-structured tables to generate a program from it .
Outcome:	The proposed approach achieves state-of-the-art performance on TABFACT dataset . it derives a program (a.k.a. logical form) of the statement in semantic parsing manner .

Discover and Prove: An Open-source Agentic Framework for Hard Mode Automated Theorem Proving in Lean 4 (2026.acl-long)

Copied to clipboard

Chengwu Liu, Yichun Yin, Ye Yuan, Jiaxuan Xie, Botao Li, Siqi Li, Jianhao Shen, Yan Xu, Lifeng Shang, Ming Zhang

NUWA-XL: Diffusion over Diffusion for eXtremely Long Video Generation (2023.acl-long)

Challenge:	Existing approaches to solving mathematical problems fall into two broad categories: informal methods and formal methods.
Approach:	They propose to use LLM natural-language reasoning to discover answers . they introduce Discover And Prove framework that rewrites Hard Mode statements into Easy Mode ones for existing ATP provers.
Outcome:	The proposed framework can be used to prove hard mode statements on ATP benchmarks.

Copied to clipboard

Shengming Yin, Chenfei Wu, Huan Yang, Jianfeng Wang, Xiaodong Wang, Minheng Ni, Zhengyuan Yang, Linjie Li, Shuguang Liu, Fan Yang, Jianlong Fu, Ming Gong, Lijuan Wang, Zicheng Liu, Houqiang Li, Nan Duan

Multimodality

Challenge:	Existing work generates long videos segment by segment sequentially, which is inefficient.
Approach:	They propose a Diffusion over Difference architecture for eXtremely Long video generation.
Outcome:	The proposed architecture reduces the average inference time from 7.55min to 26s (94.26%) and generates high-quality long videos with both global and local coherence.

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

Copied to clipboard

Zhuoyan Li, Hangxiao Zhu, Zhuoran Lu, Ming Yin

Information Retrieval

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

How Does the Disclosure of AI Assistance Affect the Perceptions of Writing? (2024.emnlp-main)

Copied to clipboard

Zhuoyan Li, Chen Liang, Jing Peng, Ming Yin