Papers by Tao Yu

Dolphin: Moving Towards Closed-loop Auto-research through Thinking, Practice, and Feedback (2025.acl-long)

Challenge:	Numerous architectures and pretraining methods have been proposed for context-dependent text-to-SQL, but the size of the datasets used has been limited due to the high cost of annotating multi-turn dialogue and SQL pairs.
Approach:	They propose to augment training datasets using self-play which leverages contextual information to synthesize new interactions to adapt the model to new databases.
Outcome:	The proposed model improves accuracy on SParC and CoSQL, two widely used cross-domain text-to-SQl datasets.

Copied to clipboard

Jiakang Yuan, Xiangchao Yan, Bo Zhang, Tao Chen, Botian Shi, Wanli Ouyang, Yu Qiao, Lei Bai, Bowen Zhou

Challenge:	Recent studies show that AI-assisted research methods can improve research efficiency . a closed-loop framework is used to enhance the automation level of scientific research .
Approach:	They propose a closed-loop LLM-driven framework to enhance the automation level of scientific research.
Outcome:	The proposed framework improves the efficiency of scientific research by improving data analysis, accelerating computation, and fostering novel idea generation.

Corpus-Steered Query Expansion with Large Language Models (2024.eacl-short)

Copied to clipboard

Yibin Lei, Yu Cao, Tianyi Zhou, Tao Shen, Andrew Yates

Crossing Variational Autoencoders for Answer Retrieval (2020.acl-main)

Challenge:	Recent studies show query expansions generate hypothetical documents that answer queries as expansions.
Approach:	They propose a corpus-steered query expansion to promote incorporation of knowledge embedded within the corpus.
Outcome:	et al. analyzed corpus-based Query Expansion (CSQE) using LLMs to generate hypothetical documents that answer the query.

Copied to clipboard

Wenhao Yu, Lingfei Wu, Qingkai Zeng, Shu Tao, Yu Deng, Meng Jiang

LLMs Assist NLP Researchers: Critique Paper (Meta-)Reviewing (2024.emnlp-main)

Challenge:	Existing methods learned semantic representations with dual encoders or dual variational auto-encoders failed to capture the aligned semantics between question and answer.
Approach:	They propose to use two variational auto-encoders to generate questions with aligned answers and generating answers with align questions.
Outcome:	The proposed method outperforms the state-of-the-art answer retrieval method on SQuAD.

Copied to clipboard

Jiangshu Du, Yibo Wang, Wenting Zhao, Zhongfen Deng, Shuaiqi Liu, Renze Lou, Henry Zou, Pranav Narayanan Venkit, Nan Zhang, Mukund Srinath, Haoran Zhang, Vipul Gupta, Yinghui Li, Tao Li, Fei Wang, Qin Liu, Tianlin Liu, Pengzhi Gao, Congying Xia, Chen Xing, Cheng Jiayang, Zhaowei Wang, Ying Su, Raj Shah, Ruohao Guo, Jing Gu, Haoran Li, Kangda Wei, Zihao Wang, Lu Cheng, Surangika Ranathunga, Meng Fang, Jie Fu, Fei Liu, Ruihong Huang, Eduardo Blanco, Yixin Cao, Rui Zhang, Philip Yu, Wenpeng Yin

Challenge:	a comparative analysis of paper (meta-)reviews by large language models (LLMs) aims to identify and distinguish LLMs from human activities .
Approach:	They present a comparative analysis to identify and distinguish LLM activities from human activities.
Outcome:	The proposed analysis aims to improve recognition of instances when someone implicitly uses LLMs for reviewing activities.

FOLIO: Natural Language Reasoning with First-Order Logic (2024.emnlp-main)

Copied to clipboard

Simeng Han, Hailey Schoelkopf, Yilun Zhao, Zhenting Qi, Martin Riddell, Wenfei Zhou, James Coady, David Peng, Yujie Qiao, Luke Benson, Lucy Sun, Alexander Wardle-Solano, Hannah Szabó, Ekaterina Zubova, Matthew Burtell, Jonathan Fan, Yixin Liu, Brian Wong, Malcolm Sailor, Ansong Ni, Linyong Nan, Jungo Kasai, Tao Yu, Rui Zhang, Alexander Fabbri, Wojciech Kryscinski, Semih Yavuz, Ye Liu, Xi Lin, Shafiq Joty, Yingbo Zhou, Caiming Xiong, Rex Ying, Arman Cohan, Dragomir Radev

Llama SLayer 8B: Shallow Layers Hold the Key to Knowledge Injection (2024.findings-emnlp)

Challenge:	Existing benchmarks for logical reasoning in large language models lack language naturalness or limited complexity.
Approach:	They propose to use first-order logic annotations to evaluate logical reasoning capabilities of large language models.
Outcome:	The proposed dataset evaluates the FOL reasoning ability of supervised fine-tuning on medium-sized language models.

Copied to clipboard

Tianxiang Chen, Zhentao Tan, Tao Gong, Yue Wu, Qi Chu, Bin Liu, Jieping Ye, Nenghai Yu

Challenge:	Existing methods to augment pre-trained large language models require extensive computational efforts and massive data volumes, challenging the widespread accessibility of LLM research.
Approach:	They propose a post-pretraining strategy of selectively enhancing shallow layers while pruning less effective deep ones to augment pretrained large language models.
Outcome:	The proposed approach improves performance on the corpus of code & math and a legal corpus and is widely applicable.

Native Hybrid Attention for Efficient Sequence Modeling (2026.acl-long)

Copied to clipboard

Jusen Du, Jiaxi Hu, Zhang Tao, Weigao Sun, Yu Cheng

Self-Powered LLM Modality Expansion for Large Speech-Text Models (2024.emnlp-main)

Challenge:	Experimental results show that NHA surpasses Transformers on recall-intensive tasks.
Approach:	They propose a hybrid architecture of linear and full attention that integrates both into a unified layer design.
Outcome:	The proposed architecture surpasses Transformers and other hybrid baselines on recall-intensive and commonsense reasoning tasks.

Copied to clipboard

Tengfei Yu, Xuebo Liu, Zhiyi Hou, Liang Ding, Dacheng Tao, Min Zhang

Effective Fine-Tuning Methods for Cross-lingual Adaptation (2021.emnlp-main)

Challenge:	Large language models exhibit remarkable performance across diverse tasks . however, these methods require significant resource demands and tend to overfit specific tasks.
Approach:	They propose a self-powered LSM that leverages augmented automatic speech recognition data generated by the model itself for more effective instruction tuning.
Outcome:	The proposed model mitigates speech anchor bias and improves the fusion of speech and text modalities in large language models.

Copied to clipboard

Tao Yu, Shafiq Joty

TexSmart: A System for Enhanced Natural Language Understanding (2021.acl-demo)

Challenge:	Large scale multilingual pre-trained language models have shown promising results in zero- and few-shot cross-lingual tasks.
Approach:	They propose a co-tuning method that aims to learn more generalized semantic equivalences when the languages are structurally dissimilar.
Outcome:	The proposed method improves on cross-lingual inference and review tasks by capturing the semantic relationship in the parallel data when a few translation pairs are available.

Copied to clipboard

Lemao Liu, Haisong Zhang, Haiyun Jiang, Yangming Li, Enbo Zhao, Kun Xu, Linfeng Song, Suncong Zheng, Botong Zhou, Dick Zhu, Xiao Feng, Tao Chen, Tao Yang, Dong Yu, Feng Zhang, ZhanHui Kang, Shuming Shi

Nutri-bullets Hybrid: Consensual Multi-document Summarization (2021.naacl-main)

Challenge:	TexSmart supports fine-grained named entity recognition (NER) Large-scale fine-granular entity types are expected to provide richer semantic information for downstream NLP applications.
Approach:	They introduce TexSmart, a text understanding system that supports fine-grained named entity recognition (NER) and enhanced semantic analysis functionalities.
Outcome:	The proposed system supports fine-grained named entity recognition (NER) and enhanced semantic analysis functions.

Copied to clipboard

Darsh Shah, Lili Yu, Tao Lei, Regina Barzilay

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models (2026.findings-acl)

Challenge:	Existing methods for generating comparative summaries that highlight similarities and contradictions in input documents are lacking large parallel training data for their training.
Approach:	They propose a method for generating comparative summaries that highlight similarities and contradictions in input documents by using a neural interpretation of traditional concept-to-text generation systems.
Outcome:	The proposed model is compared with conventional methods in the domain of nutrition and health, where the existing models lack large parallel training data.

Copied to clipboard

Hengyuan Zhang, Zhihao Zhang, Ercong Nie, Mingyang Wang, Zunhai Su, Yiwei Wang, Qianli Wang, Shuzhou Yuan, Xufeng Duan, Qibo Xue, Zeping Yu, Chenming Shang, Xiao Liang, Jing Xiong, Hui Shen, Chaofan Tao, Zhengwu Liu, Senjie Jin, Zhiheng Xi, Dongdong Zhang, Sophia Ananiadou, Tao Gui, Ruobing Xie, Hayden Kwok-Hay So, Hinrich Schuetze, Xuanjing Huang, Qi Zhang, Ngai Wong

Explainability & Interpretability in NLP

Challenge:	Existing literature on mechanistic interpretation (MI) treats it as an observational science, leaving practical applications underexplored.
Approach:	They propose a survey structured around the pipeline to identify and improve MI models.
Outcome:	The proposed framework enables tangible improvements in Alignment, Capability, and Efficiency.

Simple Recurrent Units for Highly Parallelizable Recurrence (D18-1)

Copied to clipboard

Tao Lei, Yu Zhang, Sida I. Wang, Hui Dai, Yoav Artzi

Stronger, Lighter, Better: Towards Life-Long Attribute Value Extraction for E-Commerce Products (2024.findings-acl)

Challenge:	recurrent neural networks scale poorly due to the intrinsic difficulty in parallelizing their state computations.
Approach:	They propose a simple recurrent unit that provides expressive recurrence and allows highly parallel implementation.
Outcome:	The proposed model achieves 5—9x speed-up over cuDNN-optimized LSTM on classification and question answering datasets and delivers stronger results than LS and convolutional models.

Copied to clipboard

Tao Zhang, Chenwei Zhang, Xian Li, Jingbo Shang, Hoang Nguyen, Philip Yu

Online Conversation Disentanglement with Pointer Networks (2020.emnlp-main)

Challenge:	Existing models for attribute value extraction struggle for parameter efficiency and reliability due to data contamination and catastrophic forgetting.
Approach:	They propose to decouple product type and attribute to promote de-contamination and parameter efficiency while scaling up.
Outcome:	The proposed model achieves state-of-the-art performance with affordable parameter size, least historical knowledge forgetting, and greatest robustness against noises.

Copied to clipboard

Tao Yu, Shafiq Joty

Tell-and-Answer: Towards Explainable Visual Question Answering using Attributes and Captions (D18-1)

Challenge:	Existing methods for disentangling textual conversations rely on dataset specific features that hinder generalization and adaptability.
Approach:	They propose an end-to-end online framework for conversation disentanglement that embeds the whole utterance that comprises timestamp, speaker, and message text.
Outcome:	The proposed method performs state-of-the-art on the Ubuntu IRC dataset and on other social and organizational platforms.

Copied to clipboard

Qing Li, Jianlong Fu, Dongfei Yu, Tao Mei, Jiebo Luo

Decomposition for Enhancing Attention: Improving LLM-based Text-to-SQL through Workflow Paradigm (2024.findings-acl)

Challenge:	Existing approaches to visual question answering represent images using pre-trained CNNs . but they rarely provide any insight, apart from the answer, into the VQA process .
Approach:	They propose to break up the end-to-end VQA into two steps: explaining and reasoning . they first extract attributes and generate descriptions as explanations for an image . a reasoning module utilizes these explanations in place of the image to infer an answer .
Outcome:	The proposed system achieves comparable performance with baselines, but with added benefits of explanability and the ability to improve with higher quality explanations.

Copied to clipboard

Yuanzhen Xie, Xinzhou Jin, Tao Xie, Matrixmxlin Matrixmxlin, Liang Chen, Chenyun Yu, Cheng Lei, Chengxiang Zhuo, Bo Hu, Zang Li

Improving Chinese Grammatical Error Detection via Data augmentation by Conditional Error Generation (2022.findings-acl)

Challenge:	In-context learning of large-language models has achieved remarkable success in the field of natural language processing . however, the single-step chain-of-thought prompting approach faces challenges such as attention diffusion and inadequate performance in complex tasks like text-to-SQL.
Approach:	They propose a workflow paradigm method to enhance the attention and problem-solving scope of large-language models through decomposition.
Outcome:	The proposed method outperforms existing methods on three datasets and improves the upper limit of LLM-based approaches.

Copied to clipboard

Tianchi Yue, Shulin Liu, Huihui Cai, Tao Yang, Shengkang Song, TingHao Yu

Low-Resource NLP

Challenge:	Chinese Grammatical Error Detection is a non-automatic method to detect grammatical errors in texts.
Approach:	They propose a Conditional Non-Autoregressive Error Generation model for Chinese grammatical errors that uses a masking and prediction method to generate a context-dependent error.
Outcome:	The proposed method achieves better performance than all compared data augmentation methods on the CGED-2018 and CGAD-2020 benchmarks.

Active Domain Knowledge Acquisition with 100-Dollar Budget: Enhancing LLMs via Cost-Efficient, Expert-Involved Interaction in Sensitive Domains (2025.findings-emnlp)

Copied to clipboard

Yang Wu, Raha Moraffah, Rujing Yao, Jinhong Yu, Zhimin Tao, Xiaozhong Liu

BPP-Search: Enhancing Tree of Thought Reasoning for Mathematical Modeling Problem Solving (2025.acl-long)

Challenge:	Large Language Models (LLMs) have demonstrated an impressive level of general knowledge, but often struggle in highly specialized domains due to the lack of expert knowledge.
Approach:	They propose a framework to actively engage domain experts within a fixed budget to enhance domain-specific LLMs.
Outcome:	The proposed framework improves LLMs in highly specialized domains while adhering to budget constraints.

Copied to clipboard

Teng Wang, Wing Yin Yu, Zhenqi He, Zehua Liu, HaileiGong HaileiGong, Han Wu, Xiongwei Han, Wei Shi, Ruifeng She, Fangzhou Zhu, Tao Zhong

An Exploratory Study on Long Dialogue Summarization: What Works and What’s Next (2021.findings-emnlp)

Challenge:	Existing datasets in operations research domain lack detailed annotations of the modeling process, focusing only on objective values.
Approach:	They propose an annotation-based tree-of-thought tree-based reasoning algorithm that integrates reinforcement learning into a tree- of-though.
Outcome:	The proposed algorithm outperforms state-of-the-art methods on StructuredOR, NL4OPT, and MAMO-ComplexLP datasets.

Copied to clipboard

Yusen Zhang, Ansong Ni, Tao Yu, Rui Zhang, Chenguang Zhu, Budhaditya Deb, Asli Celikyilmaz, Ahmed Hassan Awadallah, Dragomir Radev

Information Retrieval

Challenge:	Existing models for dialogue summarization focus on extracting the main events of short conversations, but real-world dialogues are difficult to train.
Approach:	They propose three strategies to deal with the lengthy input problem and locate relevant information using long dialogue datasets.
Outcome:	The retrieve-then-summarize pipeline models yield the best performance on three long dialogue datasets.

TASA: Deceiving Question Answering Models by Twin Answer Sentences Attack (2022.emnlp-main)

Copied to clipboard

Yu Cao, Dianqi Li, Meng Fang, Tianyi Zhou, Jun Gao, Yibing Zhan, Dacheng Tao

DYLE: Dynamic Latent Extraction for Abstractive Long-Input Summarization (2022.acl-long)

Challenge:	Existing adversarial models rely on keyword matching and ignore relevant contextual relations for answer prediction.
Approach:	They propose to use keyword matching to attack model with two biases that rely on a perturbed answer sentence and a distracting answer sentence to misguide model.
Outcome:	The proposed method produces fluent and grammatical adversarial contexts while maintaining gold answers.

Copied to clipboard

Ziming Mao, Chen Henry Wu, Ansong Ni, Yusen Zhang, Rui Zhang, Tao Yu, Budhaditya Deb, Chenguang Zhu, Ahmed Awadallah, Dragomir Radev

Enhancing Cross-lingual Transfer via Phonemic Transcription Integration (2023.findings-acl)

Challenge:	Existing models struggle with summarizing long text due to high memory complexity of the full self-attention.
Approach:	They propose a dynamic latent extraction approach for abstractive long-input summarization that treats extracted text snippets as latent variables and allows dynamic attention weights during decoding.
Outcome:	The proposed method outperforms existing methods on GovReport, QMSum, and arXiv while yielding strong results on arX.

Copied to clipboard

Hoang Nguyen, Chenwei Zhang, Tao Zhang, Eugene Rohrbaugh, Philip Yu

Multilinguality

Challenge:	Previous cross-lingual transfer methods are limited to orthographic representation learning via textual scripts.
Approach:	They propose a phonemic transcription framework that incorporates phonemic translations as an additional linguistic modality beyond the orthographic transcriptions for cross-lingual transfer.
Outcome:	The proposed framework captures local one-to-one alignment between two different modalities and integrates bilingual dictionaries into multilingual contexts.

SParC: Cross-Domain Semantic Parsing in Context (P19-1)

Copied to clipboard

Tao Yu, Rui Zhang, Michihiro Yasunaga, Yi Chern Tan, Xi Victoria Lin, Suyi Li, Heyang Er, Irene Li, Bo Pang, Tao Chen, Emily Ji, Shreya Dixit, David Proctor, Sungrok Shim, Jonathan Kraft, Vincent Zhang, Caiming Xiong, Richard Socher, Dragomir Radev

Semantic Evaluation for Text-to-SQL with Distilled Test Suites (2020.emnlp-main)

Challenge:	Xu et al., 2017): a dataset for cross-domain semantic parsing in context with 4,298 question sequences.
Approach:	They present a dataset for cross-domainSemanticParsing inContext that consists of 4,298 coherent question sequences.
Outcome:	The proposed dataset demonstrates that it has greater semantic diversity and can be generalized to unseen domains due to its cross-domain nature and the unseened databases at test time.

Copied to clipboard

Ruiqi Zhong, Tao Yu, Dan Klein

DART: Open-Domain Structured Data Record to Text Generation (2021.naacl-main)

Challenge:	Existing methods to evaluate semantic accuracy of Text-to-SQL models are not accurate.
Approach:	They propose a test suite accuracy method to approximate semantic accuracy for Text-to-SQL models.
Outcome:	The proposed method evaluates 21 models submitted to the Spider leader board and manually checks on 100 examples.

Copied to clipboard

Linyong Nan, Dragomir Radev, Rui Zhang, Amrit Rau, Abhinand Sivaprasad, Chiachun Hsieh, Xiangru Tang, Aadit Vyas, Neha Verma, Pranav Krishna, Yangxiaokang Liu, Nadia Irwanto, Jessica Pan, Faiaz Rahman, Ahmad Zaidi, Mutethia Mutuma, Yasin Tarabar, Ankit Gupta, Tao Yu, Yi Chern Tan, Xi Victoria Lin, Caiming Xiong, Richard Socher, Nazneen Fatema Rajani

Structured Data in NLP

Challenge:	Data-to-text annotations can be costly when dealing with tables with nontrivial structures.
Approach:	They propose a procedure for extracting semantic triples from tables that encodes their structures by exploiting table headers and table title.
Outcome:	The proposed method exploits the semantic dependencies between table headers and title to extract semantic triples from tables.

SEAD: A Surrogate-free Label-only Membership Inference Attack against Pre-trained LLMs with Semantic-Aware Density (2026.findings-acl)

Copied to clipboard

Biao Yi, Jiahao Li, Yiming Li, Yu He, Baolei Zhang, Zheli Liu, Dacheng Tao

AsymKV: Enabling 1-Bit Quantization of KV Cache with Layer-Wise Asymmetric Quantization Configurations (2025.coling-main)

Challenge:	Existing membership inference attacks require access to complete logits, but such access is often unavailable in real-world deployments where only the generated text is exposed.
Approach:	They propose a surrogate-free label-only MIA approach that directly estimates token probabilities through Monte Carlo sampling of the target model.
Outcome:	The proposed approach outperforms existing label-only attacks and serves as a foundational density estimator in the label-exclusive setting.

Copied to clipboard

Qian Tao, Wenyuan Yu, Jingren Zhou

PLACES: Prompting Language Models for Social Conversation Synthesis (2023.findings-eacl)

Challenge:	Large language models require substantial storage space to perform tasks such as text generation and video generation.
Approach:	They propose to compress large language models using integer replacements for floating-point numbers, in a process known as Quantization.
Outcome:	The proposed model allows for quantization of up to 75% decoder layers with 1 bit while maintaining performance levels comparable to those of the models with floating parameters.

Copied to clipboard

Maximillian Chen, Alexandros Papangelis, Chenyang Tao, Seokhwan Kim, Andy Rosenbaum, Yang Liu, Zhou Yu, Dilek Hakkani-Tur

CRASpell: A Contextual Typo Robust Approach to Improve Chinese Spelling Correction (2022.findings-acl)

Challenge:	Currently, collecting high quality conversational data is expensive and infeasible for many applications . a promising direction is to generate synthetic dialogues by prompting large language models .
Approach:	They propose to use expert-written conversations as in-context examples to generate synthetic dialogues by prompting large language models.
Outcome:	The proposed approach is generalizable to multi-party conversations, compared to human-collected conversations.

Copied to clipboard

Shulin Liu, Shengkang Song, Tianchi Yue, Tao Yang, Huihui Cai, TingHao Yu, Shengli Sun

Complex Reasoning in Natural Language (2023.acl-tutorials)

Challenge:	Recent research on Chinese spelling correction methods has poor performance on multi-typo texts.
Approach:	They propose to use Bert-based Chinese spelling correction models to overcome these limitations by constructing a noisy context for each training sample and a copy mechanism to encourage the model to choose the input character when the miscorrected and input character are both valid.
Outcome:	The proposed model outperforms state-of-the-art models on widely used benchmarks and achieves a remarkable gain.

Copied to clipboard

Wenting Zhao, Mor Geva, Bill Yuchen Lin, Michihiro Yasunaga, Aman Madaan, Tao Yu

SyntaxSQLNet: Syntax Tree Networks for Complex and Cross-Domain Text-to-SQL Task (D18-1)

Challenge:	Recent research shows that pretrained language models are often brittle for complex reasoning tasks.
Approach:	They propose to use pre-trained language models to teach machines to reason over texts . they will review recent promising approaches to tackling complex reasoning tasks .
Outcome:	This tutorial reviews promising approaches to complex reasoning tasks . it reviews the methods that can be used to augment models with robustness .

Copied to clipboard

Tao Yu, Michihiro Yasunaga, Kai Yang, Rui Zhang, Dongxu Wang, Zifan Li, Dragomir Radev

GS-Quant: Granular Semantic and Generative Structural Quantization for Knowledge Graph Completion (2026.acl-long)

Challenge:	Existing studies in text-to-SQL do not require generating complex SQL queries with multiple clauses or sub-queries.
Approach:	They propose a syntax tree network to address the complex text-to-SQL generation task.
Outcome:	The proposed model outperforms the current state-of-the-art model by 9.5% on a large text-to-SQL corpus.

Copied to clipboard

Qizhuo Xie, Yunhui Liu, Yu Xing, Qianzi Hou, Xudong Jin, Tao Zheng, Tieke He

Outcome Accuracy is Not Enough: Aligning the Reasoning Process of Reward Models (2026.acl-long)

Challenge:	Existing quantization-based approaches to knowledge Graph Completion (KGC) are incomplete.
Approach:	They propose a framework that generates semantically coherent discrete codes for KG entities . they introduce a Granular Semantic Enhancement module that injects hierarchical knowledge into the codebook .
Outcome:	The proposed framework outperforms existing text-based and embedding-based baselines in the KGC domain.

Copied to clipboard

Binghai Wang, Yantao Liu, Yuxuan Liu, Tianyi Tang, Shenzhi Wang, Chang Gao, Chujie Zheng, Yichang Zhang, Le Yu, Shixuan Liu, Tao Gui, Qi Zhang, Xuanjing Huang, Bowen Yu, Fei Huang, Junyang Lin

In-Context Learning for Few-Shot Dialogue State Tracking (2022.findings-emnlp)

Challenge:	Recent studies observe a phenomenon where reward models achieve high accuracy on static datasets but fail to generalize effectively during RLHF.
Approach:	They propose a method that combines rationale consistency with outcome accuracy to improve performance on RM-Bench and JudgeBench.
Outcome:	The proposed method surpasses baselines on RM-Bench and JudgeBench by an average of 5% and improves creative writing tasks by 7%.

Copied to clipboard

Yushi Hu, Chia-Hsuan Lee, Tianbao Xie, Tao Yu, Noah A. Smith, Mari Ostendorf

Low-Resource NLP

Challenge:	Existing methods for zero-shot and few-shot learning dialogue state tracking are hard and expensive.
Approach:	They propose an in-context learning framework for zero-shot and few-shot learning dialogue state tracking (DST) a large pretrained language model takes a test instance and a few exemplars as input and directly decodes the dialogue state .
Outcome:	The proposed framework outperforms state-of-the-art models in few-shot settings . it is flexible and scalable, and requires less data to adapt to new domains and scenarios .

Type Enhanced BERT for Correcting NER Errors (2023.findings-acl)

Copied to clipboard

Kuai Li, Chen Chen, Tao Yang, Tianming Du, Peijie Yu, Dong Du, Feng Zhang

MARS-Bench: A Multi-turn Athletic Real-world Scenario Benchmark for Dialogue Evaluation (2025.findings-emnlp)

Challenge:	Named entity recognition (NER) is the task of identifying spans that belong to particular categories, such as person, location, organization, etc.
Approach:	They propose a method that integrates named entity’s type information into BERT by an adapter layer and integrates it into a gazetteer.
Outcome:	The proposed method outperforms baselines in multiple corpus.

Copied to clipboard

Chenghao Yang, Yinbo Luo, Zhoufutu Wen, Qi Chu, Tao Gong, Longxiang Liu, Kaiyuan Zhang, Jianpeng Jiao, Ge Zhang, Wenhao Huang, Nenghai Yu

PAD-Net: An Efficient Framework for Dynamic Networks (2023.acl-long)

Challenge:	Large Language Models (LLMs) have been widely adopted in real-world dialogue applications, but their robustness is criticized all along.
Approach:	They propose to use play-by-play text commentary to build a multi-turn athletic real-world scenario dialogue benchmark to evaluate three critical aspects of multi-turned conversations: ultra multi- turn, interactive multi-twist, and cross-turn tasks.
Outcome:	The proposed benchmarks outperform open-source LLMs on three critical aspects of multi-turn conversations: ultra multi-turned, interactive multi- turn, and cross-turn tasks.

Copied to clipboard

Shwai He, Liang Ding, Daize Dong, Boan Liu, Fuqiang Yu, Dacheng Tao

Pretrained Language Models for Dialogue Generation with Multiple Input Sources (2020.findings-emnlp)

Challenge:	Dynamic networks can significantly improve the model’s representation power with acceptable computational cost.
Approach:	They propose a partially dynamic network to transform redundant dynamic parameters into static ones and iterative mode partition to partition dynamic and static parameters efficiently.
Outcome:	The proposed network surpasses fully dynamic networks by +0.7% top-1 acc with only 30% dynamic parameters for DY-Conv and +1.9% average score in language understanding with only 50% dynamic parameters.

Copied to clipboard

Yu Cao, Wei Bi, Meng Fang, Dacheng Tao

Low-Bit Quantization Favors Undertrained LLMs (2025.acl-long)

Challenge:	Large-scale pretrained language models have achieved outstanding performance on natural language understanding tasks.
Approach:	They propose to fuse attention information from multiple input sources to achieve better relevance with dialogue history than simple fusion baselines.
Outcome:	The proposed models deliver higher relevance with dialogue history than baselines.

Copied to clipboard

Xu Ouyang, Tao Ge, Thomas Hartvigsen, Zhisong Zhang, Haitao Mi, Dong Yu

Challenge:	Larger models or those trained on fewer tokens exhibit less quantization-induced degradation (QiD), while smaller, well-trained models face significant performance losses.
Approach:	They propose to use QiD to measure an LLM’s training levels and determine the number of training tokens required for fully training LLMs of various sizes.
Outcome:	The proposed scaling laws can predict the quantization performance of different-sized LLMs trained with tokens.

Editing-Based SQL Query Generation for Cross-Domain Context-Dependent Questions (D19-1)

Copied to clipboard

Rui Zhang, Tao Yu, Heyang Er, Sungrok Shim, Eric Xue, Xi Victoria Lin, Tianze Shi, Caiming Xiong, Richard Socher, Dragomir Radev

Improved Pseudo Data for Machine Translation Quality Estimation with Constrained Beam Search (2023.emnlp-main)

Challenge:	Generating SQL queries from user utterances is an important task to help end users acquire information from databases.
Approach:	They propose a context-dependent text-to-SQL generation task that edits previous queries . they use an utterance-table encoder and a table-aware decoder to incorporate context .
Outcome:	The proposed model is flexible to change individual tokens and robust to error propagation.

Copied to clipboard

Xiang Geng, Yu Zhang, Zhejian Lai, Shuaijie She, Wei Zou, Shimin Tao, Hao Yang, Jiajun Chen, Shujian Huang

Teaching Small Language Models Reasoning through Counterfactual Distillation (2024.emnlp-main)

Challenge:	evaluating the quality of machine translation outputs becomes increasingly essential with the rapid development of machine language (MT).
Approach:	They propose to generate pseudo data using the MT model with constrained beam search (CBSQE) they propose to preserve the reference parts with high MT probabilities as correct translations .
Outcome:	The proposed model outperforms strong baselines in both supervised and unsupervised settings.

Copied to clipboard

Tao Feng, Yicheng Li, Li Chenglin, Hao Chen, Fei Yu, Yin Zhang

SpecCache: Speculative KV Cache Reuse for Efficient RAG Serving (2026.acl-long)

Challenge:	Large language models (LLMs) have demonstrated remarkable performance in a wide range of downstream tasks.
Approach:	They propose a counterfactual distillation framework that leverages LLMs to generate high-quality counterfacts and utilizes multi-view CoT to enhance the diversity of reasoning samples.
Outcome:	The proposed framework enhances reasoning capabilities of large language models and is more robust to OOD data.

Copied to clipboard

Zijian Wen, Tao Zhang, Shuangwu Chen, Shenghao Ye, Yu Guo, Qirui Chen, Jingxian Shuai, Yunpeng Hou, Huasen He, null Jianyang

BAG: Bi-directional Attention Entity Graph Convolutional Network for Multi-hop Reasoning Question Answering (N19-1)

Challenge:	Retrieval-Augmented Generation (RAG) improves LLMs but faces high prefill latency during long contexts.
Approach:	They propose a method that uses deep-layer hidden-state norms to guide token selection . they propose to use deep-layered hidden-status norms as a proxy to guide the token selection.
Outcome:	The proposed SpecCache outperforms state-of-the-art (SOTA) benchmarks.

Copied to clipboard

Yu Cao, Meng Fang, Dacheng Tao

Structured Data in NLP

Challenge:	Existing datasets for question answering and machine comprehension (MC) are limited to a single paragraph, or even part of it.
Approach:	They propose a bi-directional Attention Entity Graph Convolutional Network (BAG) that leverages relationships between nodes in an entity graph and attention information between a query and the entity graph to generate a prediction.
Outcome:	Experimental results show that the proposed network achieves state-of-the-art accuracy on the QAngaroo WIKIHOP dataset.

DeepKE: A Deep Learning Based Knowledge Extraction Toolkit for Knowledge Base Population (2022.emnlp-demos)

Copied to clipboard

Ningyu Zhang, Xin Xu, Liankuan Tao, Haiyang Yu, Hongbin Ye, Shuofei Qiao, Xin Xie, Xiang Chen, Zhoubo Li, Lei Li

EvoR: Evolving Retrieval for Code Generation (2024.findings-emnlp)

Challenge:	Existing knowledge extraction tools are not complete due to emerging entities and relations in real-world applications.
Approach:	They propose an open-source knowledge extraction toolkit DeepKE that supports low-resource, document-level and multimodal scenarios in the knowledge base population.
Outcome:	The proposed toolkit supports low-resource, document-level and multimodal scenarios in the knowledge base population.

Copied to clipboard

Hongjin Su, Shuyang Jiang, Yuhang Lai, Haoyuan Wu, Boao Shi, Che Liu, Qian Liu, Tao Yu

Structured Attention for Unsupervised Dialogue Structure Induction (2020.emnlp-main)

Challenge:	Existing pipelines for retrieval-augmented code generation (RACG) use static knowledge bases with a single source, limiting adaptation capabilities of Large Language Models (LLMs) Extensive experiments demonstrate that EVOR achieves two to four times of execution accuracy compared to other methods such as Reflexion.
Approach:	They propose a retrieval-augmented code generation pipeline that employs the synchronous evolution of queries and diverse knowledge bases.
Outcome:	The proposed pipeline achieves two to four times of execution accuracy compared to other methods.

Copied to clipboard

Liang Qiu, Yizhou Zhao, Weiyan Shi, Yuan Liang, Feng Shi, Tao Yuan, Zhou Yu, Song-Chun Zhu

Refining Corpora from a Model Calibration Perspective for Chinese Spelling Correction (2024.findings-acl)

Challenge:	Using structured attention, a model can learn dialogue structure in unsupervised fashion.
Approach:	They propose to incorporate structured attention layers into a Variational Recurrent Neural Network model with discrete latent states to learn dialogue structure in an unsupervised fashion.
Outcome:	The proposed model learns semantic structures similar to templates used to generate a dialogue corpus on two-party datasets and on multi-party dialogues, disentangling dialogues without human annotation.

Copied to clipboard

Dingyao Yu, Yang An, Wei Ye, Xiongfeng Xiao, Shaoguang Mao, Tao Ge, Shikun Zhang

MdEval: Massively Multilingual Code Debugging (2026.findings-acl)

Challenge:	Chinese Spelling Correction (CSC) lacks large-scale high-quality corpora due to labor-intensive labeling of spelling errors in real-life writing or typing scenarios.
Approach:	They propose to use OCR/ASR-based generation to refine Chinese Spelling Correction models on random replacement-based corpora and filter them based on prediction confidence.
Outcome:	The proposed model outperforms existing models on three widely-used benchmarks while significantly alleviating over-correction.

Copied to clipboard

Shukai Liu, Linzheng Chai, Jian Yang, Jiajun Shi, He Zhu, Liran Wang, Jin Ke, Wei Zhang, Hualei Zhu, Shuyue Guo, Tao Sun, Jiaheng Liu, Yunlong Duan, Yu Hao, Liqun Yang, Guanglin Niu, Ge Zhang, Zhoujun Li

HieRec: Hierarchical User Interest Modeling for Personalized News Recommendation (2021.acl-long)

Challenge:	Existing benchmarks primarily focus on Python and are limited in terms of language diversity.
Approach:	They propose a multilingual debugging benchmark that includes 3.9K test samples of 20 programming languages and introduces the debug instruction corpora MdEval-Instruct by injecting bugs into the correct multilingual queries and solutions.
Outcome:	The proposed benchmark includes 3.9K test samples of 20 programming languages and covers the automated program repair task, bug localization task, and bug identification task.

Copied to clipboard

Tao Qi, Fangzhao Wu, Chuhan Wu, Peiru Yang, Yang Yu, Xing Xie, Yongfeng Huang

Representation Learning

Challenge:	Existing news recommendation methods learn a single user embedding for each user from their previous behaviors to represent their overall interest. Existing methods only learn 'one' embeddable representation vectors to model user interest.
Approach:	They propose a news recommendation method with hierarchical user interest modeling that captures user interest in news rather than a single user embedding.
Outcome:	The proposed method can better capture multi-grained user interest in news.

Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task (D18-1)

Copied to clipboard

Tao Yu, Rui Zhang, Kai Yang, Michihiro Yasunaga, Dongxu Wang, Zifan Li, James Ma, Irene Li, Qingning Yao, Shanelle Roman, Zilin Zhang, Dragomir Radev

On the Complementarity between Pre-Training and Random-Initialization for Resource-Rich Machine Translation (2022.coling-1)

Challenge:	Existing datasets for semantic parsing are too small in terms of number of programs for training modern data-intensive models.
Approach:	They propose a large-scale complex and cross-domain semantic parsing task for a database . they use a dataset with 10,181 questions and 5,693 unique complex SQL queries .
Outcome:	The proposed task is different from previous tasks because it uses the same database and program . the best model achieves only 9.7% exact matching accuracy on a database split setting.

Copied to clipboard

Changtong Zan, Liang Ding, Li Shen, Yu Cao, Weifeng Liu, Dacheng Tao

Multilinguality

Challenge:	Pre-Training (PT) of text representations has been successfully applied to low-resource Neural Machine Translation (NMT) however, it often fails to achieve notable gains on resource-rich NMT on par with its Random-Initialization (RI) counterpart.
Approach:	They propose to combine pre-training and random-initialization techniques to achieve significant improvements in NMT.
Outcome:	The proposed model fusion algorithm can achieve significant improvements on two resource-rich translation benchmarks.

Controllable Contamination Detection for Reliable LLM Evaluation with Statistical Guarantees (2026.acl-long)

Copied to clipboard

Zheng Zhang, Qi Liu, Siyuan Liang, Ning Li, Zirui Hu, Weibo Gao, Rui Li, Zhenya Huang, Leszek Rutkowski, Baosheng Yu, Dacheng Tao

TriPlay-RL: Tri-Role Self-Play Reinforcement Learning for LLM Safety Alignment (2026.acl-long)

Challenge:	Existing training data detectors fail to detect clean samples from contaminated test sets . existing methods fail to identify clean samples due to black-box nature of LLMs .
Approach:	They propose a framework that detects and filters contaminated evaluation data . they propose 'failure detection' to reduce the proportion of contaminated samples mistakenly retained .
Outcome:	The proposed framework reduces false discovery rate (FDR) under valid FDR control while maintaining evaluation consistency.

Copied to clipboard

Zhewen Tan, Wenhan Yu, Jianfeng Si, Tongxin Liu, Kaiqi Guan, Huiyan Jin, Jiawen Tao, Xiaokun Yuan, Xiangzheng Zhang, Duohe Ma, Tong Yang, Lin Sun

Logic-Consistency Text Generation from Semantic Parses (2021.findings-acl)

Challenge:	Existing approaches to safety alignment of large language models rely on costly manual annotations or human review.
Approach:	They propose a closed-loop reinforcement learning framework called TriPlay-RL that enables iterative collaboration among three roles with near-zero manual annotation.
Outcome:	The proposed framework achieves 20%–50% improvement in adversarial effectiveness while preserving high output diversity while achieving 10%–30% gains in safety performance without degrading general reasoning capability.

Copied to clipboard

Chang Shu, Yusen Zhang, Xiangyu Dong, Peng Shi, Tao Yu, Rui Zhang

Interactive Classification by Asking Informative Questions (2020.acl-main)

Challenge:	Text generation from semantic parses is challenging due to the complexity of the inner logic and the lack of automatic evaluation metrics for logic consistency.
Approach:	They propose a framework for logic consistent text generation from semantic parses that employs iterative training procedures and quality control.
Outcome:	The proposed framework enhances logic consistency and human evaluation on two benchmark datasets.

Copied to clipboard

Lili Yu, Howard Chen, Sida I. Wang, Tao Lei, Yoav Artzi

Information Retrieval

Challenge:	Existing methods for intent classification rely on a single user input and do not interact with the user to reduce ambiguity and improve the final prediction.
Approach:	They propose a limited form of interaction to natural language intent classification . they add binary or multi-choice questions to the system to ask missing information .
Outcome:	The proposed method can be bootstrapped without interaction data and is scalable to two domains.

PDALN: Progressive Domain Adaptation over a Pre-trained Model for Low-Resource Cross-Domain Named Entity Recognition (2021.emnlp-main)

Copied to clipboard

Tao Zhang, Congying Xia, Philip S. Yu, Zhiwei Liu, Shu Zhao

Boost Transformer-based Language Models with GPU-Friendly Sparsity and Quantization (2023.findings-acl)

Challenge:	Existing approaches to Named Entity Recognition (NER) are limited in labeled resources and domain shift.
Approach:	They propose a progressive domain adaptation knowledge distillation approach to adapt high-resource domains to low-resourced target domains by employing three components to achieve superior domain adaptability.
Outcome:	The proposed approach can adapt high-resource domains to low-resourced target domains even if they are diverse in terms and writing styles.

Copied to clipboard

Chong Yu, Tao Chen, Zhongxue Gan

Enhancing Lexicon-Based Text Embeddings with Large Language Models (2025.acl-long)

Challenge:	Existing studies have shown that transformer-based language models can achieve state-of-the-art performance on various natural language processing tasks.
Approach:	They propose a GPU-friendly 2:4 fine-grained structured sparsity and quantization scheme to maximize the GPU's acceleration constraints.
Outcome:	The proposed scheme achieves state-of-the-art compression on TLM model of various encoder and decoder blocks with negligible accuracy degradation on SQuAD, GLUE, CNN-DM & XSum and WikiText benchmarking tasks.

Copied to clipboard

Yibin Lei, Tao Shen, Yu Cao, Andrew Yates

One Embedder, Any Task: Instruction-Finetuned Text Embeddings (2023.findings-acl)

Challenge:	Recent large language models (LLMs) have demonstrated exceptional performance on general-purpose text embedding tasks.
Approach:	They introduce the first lexicon-based embeddings that consolidates the vocabulary space through token embeddation clustering to handle the issue of token redundancy in LLM vocabularies.
Outcome:	The proposed model outperforms dense embeddings on the Massive Text Embedding Benchmark (MTEB) it also supports efficient dimension pruning without any specialized objectives like Matryoshka Representation Learning.

Copied to clipboard

Hongjin Su, Weijia Shi, Jungo Kasai, Yizhong Wang, Yushi Hu, Mari Ostendorf, Wen-tau Yih, Noah A. Smith, Luke Zettlemoyer, Tao Yu

Meta-Task Prompting Elicits Embeddings from Large Language Models (2024.acl-long)

Challenge:	a new method for embedding text is developed for tasks that require specialized encoders . INSTRUCTOR is a single embedder that can generate text embeddables tailored to different tasks and domains based on instruction finetuning .
Approach:	They introduce a new method for computing text embeddings given task instructions . they first annotate instructions for 330 diverse tasks and train INSTRUCTOR on this multitask mixture .
Outcome:	The proposed method improves on 70 embedding evaluation tasks with fewer parameters than the previous best model.

Copied to clipboard

Yibin Lei, Di Wu, Tianyi Zhou, Tao Shen, Yu Cao, Chongyang Tao, Andrew Yates

How do Language Models Reshape Entity Alignment? A Survey of LM-Driven EA Methods: Advances, Benchmarks, and Future (2025.emnlp-main)

Challenge:	Existing methods for large language modeling are based on task-related instructions or prompts.
Approach:	They propose a method for generating high-quality sentence embeddings from Large Language Models (LLMs) using meta-task prompts.
Outcome:	The proposed method produces high-quality sentences without fine-tuning . it excels on STS benchmarks and in downstream tasks, surpassing models with similar prompts .

Copied to clipboard

Zerui Chen, Huiming Fan, Qianyu Wang, Tao He, Ming Liu, Heng Chang, Weijiang Yu, Ze Li, Bing Qin

Attacking Vision-Language Computer Agents via Pop-ups (2025.acl-long)

Challenge:	Entity alignment (EA) is critical for knowledge graph (KG) integration.
Approach:	They propose a taxonomy that categorizes methods in three stages: data preparation, feature embedding, and alignment.
Outcome:	The proposed taxonomy categorizes methods in three key stages: data preparation, feature embedding, and alignment.

Copied to clipboard

Yanzhe Zhang, Tao Yu, Diyi Yang

EvoCoT: Overcoming the Exploration Bottleneck in Reinforcement Learning for LLMs (2026.findings-acl)

Challenge:	Existing tools for analyzing and testing VLMs are lacking in understanding what types of attacks are possible and what types are effective.
Approach:	They propose to integrate pop-ups into existing agent testing environments to attack VLM agents by ignoring them.
Outcome:	The proposed attack success rate is 86% and decreases by 47% when integrating pop-ups into existing agent testing environments.

Copied to clipboard

Huanyu Liu, Jia Li, Yihong Dong, Chang Yu, Taozhi Chen, Lecheng Wang, Yongding Tao, Bin Gu, Ge Li

FaD-VLP: Fashion Vision-and-Language Pre-training towards Unified Retrieval and Captioning (2022.emnlp-main)

Challenge:	Existing approaches to reinforcement learning with verifiable reward (RLVR) are limited by difficulty or lack of exploration.
Approach:	They propose a self-evolving curriculum learning framework based on chain-of-thought reasoning optimization that constrains exploration space by self-generating and verifying CoT trajectories.
Outcome:	The proposed framework enables LLMs to solve previously unsolved problems without external supervision and is compatible with various RL fine-tuning methods.

Copied to clipboard

Suvir Mirchandani, Licheng Yu, Mengjiao Wang, Animesh Sinha, Wenwen Jiang, Tao Xiang, Ning Zhang

Bridging the Editing Gap in LLMs: FineEdit for Precise and Targeted Text Modifications (2025.findings-emnlp)

Challenge:	Prior work on multimodal fashion tasks has been limited by the data in individual benchmarks or has leveraged generic vision-and-language pre-training but have not taken advantage of the characteristics of fashion data.
Approach:	They propose a fashion-specific pre-training framework based on weakly-supervised triplets constructed from fashion image-text pairs.
Outcome:	The proposed framework is based on weakly-supervised triplets constructed from fashion image-text pairs and is competitive on a diverse set of fashion tasks.

Copied to clipboard

Yiming Zeng, Wanhao Yu, Zexin Li, Tao Ren, Yu Ma, Jinghan Cao, Xiyan Chen, Tingting Yu

Challenge:	a recent study shows that large language models can perform precise text editing tasks.
Approach:	InstrEditBench is a benchmark dataset that compares 30,000 structured editing tasks . experimental evaluations show FineEdit outperforms state-of-the-art models .
Outcome:	The proposed model outperforms state-of-the-art models on single-turn edits and mistral-7B-OpenOrca on direct edits.

PromptST: Abstract Prompt Learning for End-to-End Speech Translation (2023.emnlp-main)

Copied to clipboard

Tengfei Yu, Liang Ding, Xuebo Liu, Kehai Chen, Meishan Zhang, Dacheng Tao, Min Zhang

SummerTime: Text Summarization Toolkit for Non-experts (2021.emnlp-demo)

Challenge:	Experimental results show that PromptST can improve speech-to-text translation by capturing richer linguistic knowledge.
Approach:	They propose a plug-in prompt-enhanced S2T model that captures richer linguistic knowledge . they use a 10GB linguistic probing benchmark to investigate the fusion of speech and text features .
Outcome:	The proposed model can improve on a strong baseline by capturing richer linguistic knowledge.

Copied to clipboard

Ansong Ni, Zhangir Azerbayev, Mutethia Mutuma, Troy Feng, Yusen Zhang, Tao Yu, Ahmed Hassan Awadallah, Dragomir Radev

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

Challenge:	Recent advances in summarization provide models that can generate high quality summaries . a new toolkit for summarizing text is being developed to make it easier for non-experts to keep track of them.
Approach:	They develop a toolkit for text summarization that integrates with libraries designed for NLP researchers.
Outcome:	SummerTime is a toolkit for text summarization, including models, datasets, and evaluation metrics.

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

EIFBENCH: Extremely Complex Instruction Following Benchmark for Large Language Models (2025.emnlp-main)

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.

Copied to clipboard

Tao Zou, Xinghua Zhang, Haiyang Yu, Minzheng Wang, Fei Huang, Yongbin Li

A Model-agnostic Data Manipulation Method for Persona-based Dialogue Generation (2022.acl-long)

Challenge:	Existing benchmarks focusing on single-task environments with limited constraints lack the complexity required to fully reflect the evolution of large language models (LLMs).
Approach:	They propose to use a Segment Policy Optimization algorithm to enhance the LLM's ability to accurately fulfill multi-task workflows.
Outcome:	The proposed benchmarks show that existing benchmarks lack the complexity required to fully reflect the evolution of large language models.

Copied to clipboard

Yu Cao, Wei Bi, Meng Fang, Shuming Shi, Dacheng Tao

Rethinking Table Pruning in TableQA: From Sequential Revisions to Gold Trajectory-Supervised Parallel Search (2026.acl-long)

Challenge:	Existing models for introducing explicit personas are expensive due to their expensive collection costs.
Approach:	They propose a data manipulation method which is model-agnostic to be packed with any persona-based dialogue generation model to improve their performance.
Outcome:	The proposed method is model-agnostic to be packed with any persona-based dialogue generation model to improve their performance.

Copied to clipboard

Yu Guo, Shenghao Ye, Shuangwu Chen, Zijian Wen, Tao Zhang, Bai Qirui, Dong Jin, Yunpeng Hou, Huasen He, null Jianyang, Xiaobin Tan

TCSinger 2: Customizable Multilingual Zero-shot Singing Voice Synthesis (2025.findings-acl)

Challenge:	Existing pruning methods rely on sequential revisions and unreliable critique signals . Existing methods fail to detect the loss of answer-critical data .
Approach:	They propose a table pruning framework which transforms table pruning to gold trajectory-supervised parallel search.
Outcome:	The proposed framework outperforms the strongest baseline pruning framework by 3.2% on various tabular reasoning tasks.

Copied to clipboard

Yu Zhang, Wenxiang Guo, Changhao Pan, Dongyu Yao, Zhiyuan Zhu, Ziyue Jiang, Yuhan Wang, Tao Jin, Zhou Zhao

Responsible & Trustworthy NLP

Challenge:	Existing zero-shot singing voice synthesis models depend on phoneme and note boundary annotations, limiting their robustness and producing poor transitions between phonemes and notes.
Approach:	They propose a multi-task multilingual zero-shot SVS model with style transfer and style control based on various prompts.
Outcome:	Experimental results show that TCSinger 2 outperforms baseline models in subjective and objective metrics across multiple related tasks.

APo-VAE: Text Generation in Hyperbolic Space (2021.naacl-main)

Copied to clipboard

Shuyang Dai, Zhe Gan, Yu Cheng, Chenyang Tao, Lawrence Carin, Jingjing Liu

ZeroGen: Efficient Zero-shot Learning via Dataset Generation (2022.emnlp-main)

Challenge:	Existing models that learn embeddings only in Euclidean vector space do not account for such structural property of language.
Approach:	They propose a Poincare Variational Autoencoder to capture latent hierarchies in hyperbolic space . they propose enabling adversarial learning procedures to empower robust model training .
Outcome:	The proposed model outperforms existing models in a hyperbolic latent space . it captures latent language hierarchies in hyperbolical space and is robust to training .

Copied to clipboard

Jiacheng Ye, Jiahui Gao, Qintong Li, Hang Xu, Jiangtao Feng, Zhiyong Wu, Tao Yu, Lingpeng Kong

Responsible & Trustworthy NLP

Challenge:	Existing approaches to generate training data with pre-trained language models have been found effective in various scenarios.
Approach:	They propose an unsupervised zero-shot learning method that generates a dataset from scratch and trains a tiny task model under supervision of the synthesized dataset.
Outcome:	The proposed method is annotated-free and efficient, but can provide useful insights from the perspective of data-free model-agnostic knowledge distillation and unreferenced text generation evaluation.

Speech Sense Disambiguation: Tackling Homophone Ambiguity in End-to-End Speech Translation (2024.acl-long)

Copied to clipboard

Tengfei Yu, Xuebo Liu, Liang Ding, Kehai Chen, Dacheng Tao, Min Zhang

Multilinguality

Challenge:	End-to-end speech translation (ST) models require simultaneous crossmodal and crosslingual transformations to be effective.
Approach:	They propose a homophone-aware contrastive learning approach that integrates a speech-text masking strategy to reduce ambiguity.
Outcome:	The proposed approach achieves SOTA results on BLEU scores on different MuST-C and CoVoST ST tasks, underlining its effectiveness in reducing speech sense ambiguity.

Digest the Knowledge: Large Language Models empowered Message Passing for Knowledge Graph Question Answering (2025.acl-long)

Copied to clipboard

Junhong Wan, Tao Yu, Kunyu Jiang, Yao Fu, Weihao Jiang, Jiang Zhu

"Excuse me, may I say something..." CoLabScience, A Proactive AI Assistant for Biomedical Discovery and LLM-Expert Collaborations (2026.acl-long)

Challenge:	Existing methods to augment large language models (LLMs) with external knowledge are unorganized and unorganized.
Approach:	They propose a method that learns a concise facts graph and encodes it into multi-level lists of texts to augment LLMs.
Outcome:	The proposed method improves on all 5 knowledge graph question answering datasets and offers human-level semantic explainability.

Copied to clipboard

Yang Wu, Jinhong Yu, Jingwei Xiong, Zhimin Tao, Xiaozhong Liu

Generating Data for Symbolic Language with Large Language Models (2023.emnlp-main)

Challenge:	Existing large language models (LLMs) are reactive and respond only when prompted, limiting their effectiveness in collaborative settings.
Approach:	They introduce a proactive LLM assistant designed to enhance biomedical collaboration between AI systems and human experts through timely, context-aware interventions.
Outcome:	The proposed model outperforms baselines in intervention precision and collaborative task utility, highlighting the potential of proactive LLMs as intelligent scientific assistants.

Copied to clipboard

Jiacheng Ye, Chengzu Li, Lingpeng Kong, Tao Yu

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

Challenge:	Large language models (LLMs) bring performance and complexity, but they incur a large computational cost in practice.
Approach:	They propose a task-based model which uses large language models to generate symbolic language data by an informative prompt and agreement-based verifier.
Outcome:	The proposed model can generate symbolic language data with a few human demonstrations and saves a considerable amount of inference effort.

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

Unsupervised Dense Retrieval with Relevance-Aware Contrastive Pre-Training (2023.findings-acl)

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

Yibin Lei, Liang Ding, Yu Cao, Changtong Zan, Andrew Yates, Dacheng Tao

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

Challenge:	Dense retrievers have impressive performance, but their demand for abundant training data limits their application scenarios.
Approach:	They propose a method which uses unlabeled data to construct pseudo-positive examples from unlabelled data and then contrastively weighs the contrastive loss of different pairs according to the estimated relevance.
Outcome:	The proposed method beats the SOTA unsupervised Contriever model on BEIR and open-domain QA retrieval benchmarks and is a good few-shot learner.

Copied to clipboard

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

Language Agents: Foundations, Prospects, and Risks (2024.emnlp-tutorials)

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.

Copied to clipboard

Yu Su, Diyi Yang, Shunyu Yao, Tao Yu

Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Future (2024.acl-long)

Challenge:	Language agents are autonomous agents that can follow language instructions to perform diverse tasks in real-world or simulated environments.
Approach:	They propose to provide a conceptual framework for language agents and a comprehensive discussion on key topics.
Outcome:	The proposed tutorial provides a conceptual framework of language agents and comprehensive discussion on important topic areas.

Copied to clipboard

Zheng Chu, Jingchang Chen, Qianglong Chen, Weijiang Yu, Tao He, Haotian Wang, Weihua Peng, Ming Liu, Bing Qin, Ting Liu

Pretraining Language Models with Text-Attributed Heterogeneous Graphs (2023.findings-emnlp)

Challenge:	Recent studies have revealed that chain-of-thought prompting significantly enhances LLM’s reasoning capabilities, which attracts widespread attention from both academics and industry.
Approach:	They propose to summarize advanced methods through a taxonomy that offers novel perspectives.
Outcome:	The proposed method delineates the challenges and future directions, thereby shedding light on future research.

Copied to clipboard

Tao Zou, Le Yu, Yifei Huang, Leilei Sun, Bowen Du

Batch Prompting: Efficient Inference with Large Language Model APIs (2023.emnlp-industry)

Challenge:	Existing pretraining tasks for Language Models (LMs) focus on learning the textual information of each entity and overlook the crucial aspect of capturing topological connections among entities in TAHGs.
Approach:	They propose a topology-aware pretraining task that explicitly considers the topological and heterogeneous information in TAHGs by optimizing an LM and an auxiliary heterogenous graph neural network.
Outcome:	The proposed framework explicitly considers the topological and heterogeneous information in TAHGs.

Copied to clipboard

Zhoujun Cheng, Jungo Kasai, Tao Yu

Responsible & Trustworthy NLP

Challenge:	Performing inference on large volumes of samples can be computationally and financially costly.
Approach:	They propose a prompting approach that enables large language models to run inference in batches instead of one sample at a time.
Outcome:	The proposed prompting reduces both token and time costs while retaining downstream performance.

Learn Beyond The Answer: Training Language Models with Reflection for Mathematical Reasoning (2024.emnlp-main)

Copied to clipboard

Zhihan Zhang, Tao Ge, Zhenwen Liang, Wenhao Yu, Dian Yu, Mengzhao Jia, Dong Yu, Meng Jiang

CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databases (D19-1)

Challenge:	Existing studies focus on broadening the training set with data augmentation techniques to maximize such benefits.
Approach:	They propose a method that embeds problem reflection into each training instance.
Outcome:	The proposed method enhances performance in standard and complex scenarios that require reflective thinking.

Copied to clipboard

Tao Yu, Rui Zhang, Heyang Er, Suyi Li, Eric Xue, Bo Pang, Xi Victoria Lin, Yi Chern Tan, Tianze Shi, Zihan Li, Youxuan Jiang, Michihiro Yasunaga, Sungrok Shim, Tao Chen, Alexander Fabbri, Zifan Li, Luyao Chen, Yuwen Zhang, Shreya Dixit, Vincent Zhang, Caiming Xiong, Richard Socher, Walter Lasecki, Dragomir Radev

CritiQ: Mining Data Quality Criteria from Human Preferences (2025.acl-long)

Challenge:	CoSQL is a corpus for building cross-domain, general-purpose database querying dialogue systems.
Approach:	They present a corpus for building cross-domain, general-purpose database querying dialogue systems . they use a Wizard-of-Oz collection of 3k turns plus 10k+ annotated SQL queries .
Outcome:	The proposed corpus is based on a Wizard-of-Oz dataset of 3k dialogues querying 200 complex DBs spanning 138 domains.

Copied to clipboard

Honglin Guo, Kai Lv, Qipeng Guo, Tianyi Liang, Zhiheng Xi, Demin Song, Qiuyinzhe Zhang, Yu Sun, Kai Chen, Xipeng Qiu, Tao Gui

Information Retrieval

Challenge:	Existing methods to train language models rely on manual design, perplexity, or careful prompt engineering.
Approach:	They propose a method that automatically mines criteria from human preferences for data quality with only 30 human-annotated pairs and performs efficient data selection.
Outcome:	The proposed method improves on human-annotated test sets and shows high accuracy on code, math, and logic domains.

Rectifying the Emotional Flow: Aligning Priors and Dynamic Guidance for High-Arousal Text-to-Speech (2026.acl-long)

Copied to clipboard

Fangming Feng, Dongjie Fu, Zequn Xie, Yu Zhang, Yangyang Wu, Zhou Zhao, Tao Jin

Sparse Frame Grouping Network with Action Centered for Untrimmed Video Paragraph Captioning (2023.findings-emnlp)

Challenge:	Existing systems suffer from linguistic collapse when pursuing high intensity or fail to meet target emotional levels.
Approach:	They propose an inference framework that introduces a neutral prosody bias and a uniform Classifier-Free Guidance that distorts the acoustic manifold, leading to artifacts.
Outcome:	The proposed framework achieves superior linguistic accuracy and expressiveness without model retraining.

Copied to clipboard

Guorui Yu, Yimin Hu, Yuejie Zhang, Rui Feng, Tao Zhang, Shang Gao

Router-Tuning: A Simple and Effective Approach for Dynamic Depth (2025.emnlp-main)

Challenge:	Existing methods for paragraph captioning videos without event ground truths generate one sentence for each event, but without event labels, it is difficult to locate the transitions between events and minimize repetition.
Approach:	They propose a module that dynamically groups event information with the help of action information for the entire video and excludes redundant frames within pre-defined clips.
Outcome:	The proposed module outperforms the state-of-the-art methods on all metrics.

Copied to clipboard

Shwai He, Tao Ge, Guoheng Sun, Bowei Tian, Xiaoyang Wang, Dong Yu

Safe-FedLLM: Delving into the Safety of Federated Large Language Models (2026.acl-long)

Challenge:	Existing methods to improve computational efficiency are under-explored and face several critical challenges.
Approach:	They propose a method that selectively activates only a subset of the model's layers, skipping those deemed less important.
Outcome:	The proposed method significantly improves performance on Attention layers and MoE layers while reducing redundant computation and memory usage.

Copied to clipboard

Mingxiang Tao, Yu Tian, Wenxuan Tu, Yue Yang, Xue Yang, Xiangyan Tang

Text Classification

Challenge:	Existing work on federated learning for large language models (FL) addresses privacy and data-silo issues in the training of large language model training.
Approach:	They propose a probe-based defense framework for FedLLM that constructs defenses across three levels: Step-Level, Client-Level and Shadow-Level.
Outcome:	The proposed framework improves FedLLM's robustness against malicious clients while maintaining competitive performance on benign data.

STA-CoT: Structured Target-Centric Agentic Chain-of-Thought for Consistent Multi-Image Geological Reasoning (2025.findings-emnlp)

Copied to clipboard

Beibei Yu, Tao Shen, Ling Chen

TypeSQL: Knowledge-Based Type-Aware Neural Text-to-SQL Generation (N18-2)

Challenge:	Reliable multi-image geological reasoning is essential for automating expert tasks in remote-sensing mineral exploration.
Approach:	They propose a framework that orchestrates planning, execution, and verification agents to decompose, ground, and iteratively refine reasoning steps over geological and hyperspectral image sets.
Outcome:	The proposed framework decomposes, ground, and iteratively refines reasoning steps over geological and hyperspectral image sets.

Copied to clipboard

Tao Yu, Zifan Li, Zilin Zhang, Rui Zhang, Dragomir Radev

When Agents Look the Same: Quantifying Distillation-Induced Similarity in Tool-Use Behaviors (2026.acl-long)

Challenge:	Existing systems that can understand natural language questions and generate corresponding SQL queries are not able to do this.
Approach:	They propose a novel approach which formats the problem as a slot filling task in a more reasonable way and utilizes type information to better understand rare entities and numbers in the questions.
Outcome:	The proposed approach outperforms the prior art on the WikiSQL dataset and can reach 82.6% accuracy, a 17.5% improvement compared to the previous content-sensitive model.

Copied to clipboard

Chenghao Yang, Yuning Zhang, Zhoufutu Wen, Tao Gong, Jiaheng Liu, Qi Chu, Nenghai Yu

MZET: Memory Augmented Zero-Shot Fine-grained Named Entity Typing (2020.coling-main)

Challenge:	Existing metrics fail to distinguish mandatory behaviors required for task success from non-mandatory patterns that reflect a model’s autonomous preferences.
Approach:	They propose to use response pattern similarity and action graph similarity to isolate non-mandatory behaviors from mandatory behaviors.
Outcome:	Evaluating 18 models from 8 providers on -Bench and 2-Bench against Claude Sonnet 4.5, the authors find that within-family model pairs score 5.9 pp higher in response pattern similarity and action graph similarity .

Copied to clipboard

Tao Zhang, Congying Xia, Chun-Ta Lu, Philip Yu

Rationalizing Text Matching: Learning Sparse Alignments via Optimal Transport (2020.acl-main)

Challenge:	Named entity typing (NET) is a classification task of assigning an entity mention in the context with given semantic types.
Approach:	They propose a memory-augmented FNET model to tackle unseen types in a zero-shot manner.
Outcome:	The proposed model outperforms the state-of-the-art models with up to 8% gain in Micro-F1 and Macro-F1.

Copied to clipboard

Kyle Swanson, Lili Yu, Tao Lei

Explainability & Interpretability in NLP

Challenge:	Existing models that use only rationales to explain a prediction are limited by the complexity of deep neural networks.
Approach:	They extend selective rationalization to text matching by using optimal transport to find a minimal cost alignment between inputs.
Outcome:	The proposed model achieves very sparse rationale selections with high fidelity while preserving prediction accuracy compared to strong attention baseline models.

NewsBERT: Distilling Pre-trained Language Model for Intelligent News Application (2021.findings-emnlp)

Copied to clipboard

Chuhan Wu, Fangzhao Wu, Yang Yu, Tao Qi, Yongfeng Huang, Qi Liu

CoF-CoT: Enhancing Large Language Models with Coarse-to-Fine Chain-of-Thought Prompting for Multi-domain NLU Tasks (2023.emnlp-main)

Challenge:	Existing language models are pre-trained and distilled on general corpus like Wikipedia, which has gaps with the news domain and may be suboptimal for news intelligence.
Approach:	They propose a method to distill existing language models on Wikipedia to enable efficient news intelligence.
Outcome:	The proposed model can be used to build and test a news intelligence application on Wikipedia and Wikipedia.

Copied to clipboard

Hoang Nguyen, Ye Liu, Chenwei Zhang, Tao Zhang, Philip Yu

Multi-grained Named Entity Recognition (P19-1)

Challenge:	Chain-of-Thought prompting is popular in reasoning tasks, but its application to Large Language Models (LLMs) in Natural Language Understanding (NLU) is under-explored.
Approach:	They propose a Coarse-to-Fine Chain-of-Thought approach that breaks down NLU tasks into multiple reasoning steps where LLMs can learn to acquire essential concepts.
Outcome:	The proposed approach is effective in assisting the LLMs adapt to multi-grained NLU tasks under zero-shot and few-shot multi-domain settings.

Copied to clipboard

Congying Xia, Chenwei Zhang, Tao Yang, Yaliang Li, Nan Du, Xian Wu, Wei Fan, Fenglong Ma, Philip Yu

Scaling Law for Multimodal Large Language Model Supervised Fine-Tuning (2026.acl-long)

Challenge:	Existing approaches treat Named Entity Recognition (NER) as a sequence labeling task.
Approach:	They propose a framework for Multi-Grained Named Entity Recognition where multiple entities or entity mentions in a sentence could be non-overlapping or totally nested.
Outcome:	The proposed framework outperforms current state-of-the-art frameworks by 4.4% in terms of the F1 score among nested/non-overlapping NER tasks.

Copied to clipboard

YiFan Zhang, Tao Yu, Feng Li, Chaoyou Fu, Yibo Hu, Kun Wang, Qingsong Wen, Zhang Zhang, Liang Wang, Rong Jin