Papers by Yu Chang

Self-Supervised Learning for Contextualized Extractive Summarization (P19-1)

Challenge:	Existing approaches to modifying large language models require continual updates to rectify outdated or erroneous knowledge.
Approach:	They propose a model editing strategy that mitigates catastrophic interference through sequential null-space alignment.
Outcome:	EvoEdit achieves better or comparable performance than prior state-of-the-art techniques with up to 3.53 speedup.

Copied to clipboard

Hong Wang, Xin Wang, Wenhan Xiong, Mo Yu, Xiaoxiao Guo, Shiyu Chang, William Yang Wang

Simple yet Effective Bridge Reasoning for Open-Domain Multi-Hop Question Answering (D19-58)

Challenge:	Existing models for extractive summarization are usually trained from scratch with a cross-entropy loss . previous work builds an end-to-end system to learn to choose sentences without explicitly modeling document context .
Approach:	They propose three auxiliary pre-training tasks that learn to capture the document context in a self-supervised fashion.
Outcome:	The proposed models outperform existing models on a CNN/DM dataset.

Copied to clipboard

Wenhan Xiong, Mo Yu, Xiaoxiao Guo, Hong Wang, Shiyu Chang, Murray Campbell, William Yang Wang

Extracting Multiple-Relations in One-Pass with Pre-Trained Transformers (P19-1)

Challenge:	Existing work on open-domain multi-hop question answering relies on off-the-shelf information retrieval techniques to retrieve answer passages.
Approach:	They propose a new subproblem for open-domain multi-hop question answering . they aim to recognize the anchor from a set of start passages with a reading comprehension model .
Outcome:	The proposed method significantly improves the baseline method on the open-domain hotpotQA benchmark.

Copied to clipboard

Haoyu Wang, Ming Tan, Mo Yu, Shiyu Chang, Dakuo Wang, Kun Xu, Xiaoxiao Guo, Saloni Potdar

Rethinking Cooperative Rationalization: Introspective Extraction and Complement Control (D19-1)

Challenge:	Existing approaches to extract multiple relations from a paragraph require multiple passes over the paragraph.
Approach:	They propose a method to extract multiple relations from a paragraph by encoding the paragraph only once.
Outcome:	The proposed approach can perform state-of-the-art on the benchmark ACE 2005.

Copied to clipboard

Mo Yu, Shiyu Chang, Yang Zhang, Tommi Jaakkola

Leveraging Abstract Meaning Representation for Knowledge Base Question Answering (2021.findings-acl)

Challenge:	Selective rationalization is a common mechanism to ensure that predictive models reveal how they use any available features.
Approach:	They propose a co-operative method which uses introspection to explicitly predict and incorporate the outcome into the selection process.
Outcome:	The proposed model maintains high predictive accuracy and leads to comprehensive rationales.

Copied to clipboard

Pavan Kapanipathi, Ibrahim Abdelaziz, Srinivas Ravishankar, Salim Roukos, Alexander Gray, Ramón Fernandez Astudillo, Maria Chang, Cristina Cornelio, Saswati Dana, Achille Fokoue, Dinesh Garg, Alfio Gliozzo, Sairam Gurajada, Hima Karanam, Naweed Khan, Dinesh Khandelwal, Young-Suk Lee, Yunyao Li, Francois Luus, Ndivhuwo Makondo, Nandana Mihindukulasooriya, Tahira Naseem, Sumit Neelam, Lucian Popa, Revanth Gangi Reddy, Ryan Riegel, Gaetano Rossiello, Udit Sharma, G P Shrivatsa Bhargav, Mo Yu

Extreme Zero-Shot Learning for Extreme Text Classification (2022.naacl-main)

Challenge:	Existing approaches face challenges including complex question understanding and lack of large end-to-end training datasets.
Approach:	They propose a modular knowledge base question answering system that leverages AMR parses for task-independent question understanding.
Outcome:	The proposed system achieves state-of-the-art performance on two prominent KBQA datasets based on DBpedia.

Copied to clipboard

Yuanhao Xiong, Wei-Cheng Chang, Cho-Jui Hsieh, Hsiang-Fu Yu, Inderjit Dhillon

Make-A-Voice: Revisiting Voice Large Language Models as Scalable Multilingual and Multitask Learners (2024.acl-long)

Challenge:	Experimental results show that MACLR achieves superior performance compared to other baseline methods.
Approach:	They propose to pre-train Transformer-based encoders with self-supervised contrastive losses to learn the semantic embeddings of instances and labels with raw text.
Outcome:	The proposed method improves on the EZ-XMC model with a limited number of ground-truth positive pairs.

Copied to clipboard

Rongjie Huang, Chunlei Zhang, Yongqi Wang, Dongchao Yang, Jinchuan Tian, Zhenhui Ye, Luping Liu, Zehan Wang, Ziyue Jiang, Xuankai Chang, Jiatong Shi, Chao Weng, Zhou Zhao, Dong Yu

Conditional Supervised Contrastive Learning for Fair Text Classification (2022.findings-emnlp)

Challenge:	Large language models (LLMs) have been used for general-purpose interfaces across multiple tasks and languages.
Approach:	They propose to use large language models as a general-purpose interface across multiple tasks and languages.
Outcome:	The proposed model performs better on 200K hours of 6-language data for voice generation applications.

Copied to clipboard

Jianfeng Chi, William Shand, Yaodong Yu, Kai-Wei Chang, Han Zhao, Yuan Tian

Out-of-Domain Detection for Low-Resource Text Classification Tasks (D19-1)

Challenge:	Recent advances in natural language processing have demonstrated societal bias in existing NLP models.
Approach:	They propose to use contrastive learning to learn fair representations for text classification . they conduct experiments on two text datasets to demonstrate their methods are stable .
Outcome:	The proposed methods balancing task performance and bias mitigation are stable in different hyperparameter settings.

Copied to clipboard

Ming Tan, Yang Yu, Haoyu Wang, Dakuo Wang, Saloni Potdar, Shiyu Chang, Mo Yu

Low-Resource NLP

Challenge:	Existing methods for OOD detection and ID classification tasks require massive amounts of ID labeled data and no OOD labeles.
Approach:	They propose to use OOD-resistant Prototypical Network to detect OOD cases with limited in-domain (ID) training data to solve this task.
Outcome:	The proposed solution outperforms state-of-the-art methods in zero-shot OOD detection task while maintaining a competitive performance on ID classification task.

MinPrompt: Graph-based Minimal Prompt Data Augmentation for Few-shot Question Answering (2024.acl-long)

Copied to clipboard

Xiusi Chen, Jyun-Yu Jiang, Wei-Cheng Chang, Cho-Jui Hsieh, Hsiang-Fu Yu, Wei Wang

SPEED++: A Multilingual Event Extraction Framework for Epidemic Prediction and Preparedness (2024.emnlp-main)

Challenge:	Recent advances in few-shot question answering rely on pre-trained large language models and fine-tuning in specific settings.
Approach:	They propose to select the most informative data for fine-tuning to improve efficiency . they use an approximate graph algorithm and unsupervised question generation to generate QA pairs .
Outcome:	The proposed framework improves the performance of the few-shot question answering task on the open-domain QA task.

Copied to clipboard

Tanmay Parekh, Jeffrey Kwan, Jiarui Yu, Sparsh Johri, Hyosang Ahn, Sreya Muppalla, Kai-Wei Chang, Wei Wang, Nanyun Peng

Multilinguality

Challenge:	Prior studies focused on English posts to provide early warnings for epidemic prediction, but these work focused on non-English posts.
Approach:	They propose a multilingual event extraction framework for extracting epidemic event information for any disease and language using 5.1K tweets in four languages.
Outcome:	The proposed framework can provide epidemic warnings for COVID-19 in its earliest stages in Dec 2019 (3 weeks before global discussions) and aggregate community epidemic discussions like symptoms and cure measures, aiding misinformation detection and public attention monitoring.

CB-Whisper: Contextual Biasing Whisper Using Open-Vocabulary Keyword-Spotting (2024.lrec-main)

Copied to clipboard

Yuang Li, Yinglu Li, Min Zhang, Chang Su, Jiawei Yu, Mengyao Piao, Xiaosong Qiao, Miaomiao Ma, Yanqing Zhao, Hao Yang

Augment before You Try: Knowledge-Enhanced Table Question Answering via Table Expansion (2025.findings-emnlp)

Challenge:	End-to-end automatic speech recognition systems struggle to recognize rare name entities such as personal names, organizations and terminologies that are not frequently encountered in the training data.
Approach:	They propose a convolutional neural network-based ASR system that performs open-vocabulary keyword-spotting before the decoder to match the features between the entities and the utterances.
Outcome:	The proposed system significantly improves mixed-error-rate (MER) and entity recall compared to the original Whisper model on three internal datasets and two publicly available datasets.

Copied to clipboard

Yujian Liu, Jiabao Ji, Tong Yu, Ryan A. Rossi, Sungchul Kim, Handong Zhao, Ritwik Sinha, Yang Zhang, Shiyu Chang

PrinciplismQA: A Philosophy-Grounded Approach to Assessing LLM-Human Clinical Medical Ethics Alignment (2026.findings-acl)

Challenge:	Existing methods to integrate external information into a given table neglect the structured nature of the table.
Approach:	They propose a simple yet effective method to integrate external information into a given table by first building an augmenting table and then generating a SQL query over the two tables to answer the question.
Outcome:	The proposed method outperforms strong baselines on three table QA benchmarks.

Copied to clipboard

Chang Hong, Minghao Wu, Qingying Xiao, Yuchi Wang, Xiang Wan, Guangjun Yu, Benyou Wang, Yan Hu

Empowering Language Models with Knowledge Graph Reasoning for Open-Domain Question Answering (2022.emnlp-main)

Challenge:	Existing benchmarks lack systematic approaches to integrate philosophical frameworks and expert validation for ethical reasoning assessment.
Approach:	They propose a philosophy-grounded approach to assess medical ethics alignment . PrinciplismQA comprises 3,648 expert-validated questions spanning knowledge assessment and clinical reasoning .
Outcome:	PrinciplismQA provides a philosophy-grounded approach to assessing medical ethics alignment.

Copied to clipboard

Ziniu Hu, Yichong Xu, Wenhao Yu, Shuohang Wang, Ziyi Yang, Chenguang Zhu, Kai-Wei Chang, Yizhou Sun

Revisiting the Architectures like Pointer Networks to Efficiently Improve the Next Word Distribution, Summarization Factuality, and Beyond (2023.findings-acl)

Challenge:	Existing Language Models lack the power to store all required knowledge, resulting in a lack of ability to infer out-of-context knowledge.
Approach:	They propose a Knowledge Interaction Layer that can be flexibly plugged into existing Transformer-based LMs to interact with a differentiable Knowledge Graph Reasoning module collaboratively.
Outcome:	The proposed model can be plugged into existing Transformer-based LMs to interact with a differentiable Knowledge Graph Reasoning module collaboratively.

Copied to clipboard

Haw-Shiuan Chang, Zonghai Yao, Alolika Gon, Hong Yu, Andrew McCallum

Summarization

Challenge:	Existing solutions for word probability distributions are limited and the output softmax layer is inherently limited.
Approach:	They propose to use the output softmax layer to compute the word probability distribution instead of using pointer networks to break the bottleneck.
Outcome:	The proposed method improves factCC score by 2 points in CNN/DM and XSUM dataset, and MAUVE scores by 30% in bookSum paragraph-level dataset.

One-Shot Relational Learning for Knowledge Graphs (D18-1)

Copied to clipboard

Wenhan Xiong, Mo Yu, Shiyu Chang, Xiaoxiao Guo, William Yang Wang

Document Modeling with External Attention for Sentence Extraction (P18-1)

Challenge:	Existing studies on knowledge graph completion require a large number of positive examples for each relation, but long-tail relations are more common in KGs and those newly added relations do not have many known triples for training.
Approach:	They propose a one-shot relational learning framework that utilizes the knowledge distilled by embedding models and learns a matching metric by considering both the learned embeddments and one-hop graph structures.
Outcome:	The proposed framework improves on existing embedding models and eliminates the need for retraining when dealing with newly added relations.

Copied to clipboard

Shashi Narayan, Ronald Cardenas, Nikos Papasarantopoulos, Shay B. Cohen, Mirella Lapata, Jiangsheng Yu, Yi Chang

Query and Extract: Refining Event Extraction as Type-oriented Binary Decoding (2022.findings-acl)

Challenge:	Document modeling is essential to a variety of natural language understanding tasks.
Approach:	They propose to use external information to improve document modeling for sentence extraction problems.
Outcome:	The proposed model outperforms baseline models on document summarization and answer selection tasks and achieves state-of-the-art results on WikiQA and NewsQA.

Copied to clipboard

Sijia Wang, Mo Yu, Shiyu Chang, Lichao Sun, Lifu Huang

MedEval: A Multi-Level, Multi-Task, and Multi-Domain Medical Benchmark for Language Model Evaluation (2023.emnlp-main)

Challenge:	Existing approaches to event extraction are limited to a set of pre-defined types.
Approach:	They propose a natural language query framework that uses event types and argument roles to extract candidate triggers and arguments from input text.
Outcome:	The proposed framework outperforms existing methods on zero-shot event extraction.

Copied to clipboard

Zexue He, Yu Wang, An Yan, Yao Liu, Eric Chang, Amilcare Gentili, Julian McAuley, Chun-Nan Hsu

Sentence Embedding Alignment for Lifelong Relation Extraction (N19-1)

Challenge:	Existing medical datasets require high quality domain-specific datasets.
Approach:	They propose a multi-level, multi-task, and multi-domain medical benchmark to facilitate the development of language models for healthcare.
Outcome:	The proposed model provides granular potential usage and supports a wide range of tasks.

Copied to clipboard

Hong Wang, Wenhan Xiong, Mo Yu, Xiaoxiao Guo, Shiyu Chang, William Yang Wang

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

Challenge:	Existing approaches to relation extraction require a fixed set of relations . Existing methods assume a closed set of relationships and perform once-and-for-all training on a set of datasets.
Approach:	They propose to improve the stochastic gradient methods with a replay memory to alleviate the forgetting problem by anchoring the sentence embedding space.
Outcome:	The proposed method outperforms state-of-the-art methods on multiple benchmarks.

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

RESIN: A Dockerized Schema-Guided Cross-document Cross-lingual Cross-media Information Extraction and Event Tracking System (2021.naacl-demos)

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

Haoyang Wen, Ying Lin, Tuan Lai, Xiaoman Pan, Sha Li, Xudong Lin, Ben Zhou, Manling Li, Haoyu Wang, Hongming Zhang, Xiaodong Yu, Alexander Dong, Zhenhailong Wang, Yi Fung, Piyush Mishra, Qing Lyu, Dídac Surís, Brian Chen, Susan Windisch Brown, Martha Palmer, Chris Callison-Burch, Carl Vondrick, Jiawei Han, Dan Roth, Shih-Fu Chang, Heng Ji

Visual Data in NLP

Challenge:	We present a new information extraction system that can construct temporal event graphs from news documents.
Approach:	They propose a temporal event graph extraction system that can extract news documents . they extend the system from sentence-level event extraction to cross-document cross-media event extraction .
Outcome:	The proposed system can extract temporal event graphs from news documents in multiple languages and multiple data modalities.

Bypassing Neural Evaluations for Fast Audio Editing via Adaptive Trajectory Extrapolation (2026.findings-acl)

Copied to clipboard

Xiaoqian Liu, Zhengkun Ge, Jianjin Wang, Haoran Zhang, Yuan Ge, Kaiyan Chang, Chen Xu, Tong Xiao, Zhengtao Yu, Linfeng Zhang, JingBo Zhu

RESIN-11: Schema-guided Event Prediction for 11 Newsworthy Scenarios (2022.naacl-demo)

Challenge:	Recent advances in audio diffusion models have significantly improved text-to-audio editing via inversion techniques, but these models typically rely on dense, fixed-step sampling trajectories to maintain structural integrity.
Approach:	They propose a model-agnostic Adaptive Trajectory Extrapolation framework that accelerates inversion-based editing process by dynamically evaluating only the most critical generative phases.
Outcome:	The proposed framework achieves a 3.9 speedup with negligible loss in fidelity.

Copied to clipboard

Xinya Du, Zixuan Zhang, Sha Li, Pengfei Yu, Hongwei Wang, Tuan Lai, Xudong Lin, Ziqi Wang, Iris Liu, Ben Zhou, Haoyang Wen, Manling Li, Darryl Hannan, Jie Lei, Hyounghun Kim, Rotem Dror, Haoyu Wang, Michael Regan, Qi Zeng, Qing Lyu, Charles Yu, Carl Edwards, Xiaomeng Jin, Yizhu Jiao, Ghazaleh Kazeminejad, Zhenhailong Wang, Chris Callison-Burch, Mohit Bansal, Carl Vondrick, Jiawei Han, Dan Roth, Shih-Fu Chang, Martha Palmer, Heng Ji

PRESTO: A Multilingual Dataset for Parsing Realistic Task-Oriented Dialogs (2023.emnlp-main)

Challenge:	Existing methods for event prediction are incomplete and noisy.
Approach:	They propose to use news-related event schemas to extract newsworthy events . they build a demo website and include a video demonstrating the framework .
Outcome:	The proposed framework can be applied to a wide variety of newsworthy scenarios.

Copied to clipboard

Rahul Goel, Waleed Ammar, Aditya Gupta, Siddharth Vashishtha, Motoki Sano, Faiz Surani, Max Chang, HyunJeong Choe, David Greene, Chuan He, Rattima Nitisaroj, Anna Trukhina, Shachi Paul, Pararth Shah, Rushin Shah, Zhou Yu

Natural Language Interfaces

Challenge:	PRESTO dataset contains 550K contextual multilingual conversations between humans and virtual assistants.
Approach:	They propose to use a dataset of 550K contextual multilingual conversations between humans and virtual assistants to study some of the more challenging aspects of parsing realistic conversations.
Outcome:	The dataset contains 550K contextual conversations between humans and virtual assistants.

Improving Question Answering over Incomplete KBs with Knowledge-Aware Reader (P19-1)

Copied to clipboard

Wenhan Xiong, Mo Yu, Shiyu Chang, Xiaoxiao Guo, William Yang Wang

Natural Language Interfaces

Challenge:	Existing models that use incomplete knowledge bases and text data to answer open-domain questions are insufficient to cover full evidence.
Approach:	They propose a model which learns to aggregate answer evidence from incomplete knowledge bases and text snippets.
Outcome:	The proposed model improves on the widely-used KBQA benchmark WebQSP across settings with different extents of incompleteness.

From Specific-MLLMs to Omni-MLLMs: A Survey on MLLMs Aligned with Multi-modalities (2025.findings-acl)

Copied to clipboard

Shixin Jiang, Jiafeng Liang, Jiyuan Wang, Xuan Dong, Heng Chang, Weijiang Yu, Jinhua Du, Ming Liu, Bing Qin

Training LLMs to be Better Text Embedders through Bidirectional Reconstruction (2025.emnlp-main)

Challenge:	MLLMs are able to integrate multiple modalities into a single model to tackle complex tasks in real-world scenarios.
Approach:	They propose a comprehensive survey of Omni-MLLMs to address the challenges and opportunities of multimodal modeling.
Outcome:	The proposed model can integrate multiple modalities into a single model and provide novel perspectives.

Copied to clipboard

Chang Su, Dengliang Shi, Siyuan Huang, Jintao Du, Changhua Meng, Yu Cheng, Weiqiang Wang, Zhouhan Lin

Few-Shot Intent Detection via Contrastive Pre-Training and Fine-Tuning (2021.emnlp-main)

Challenge:	Existing text embedding approaches often leverage the embeddment of the final token, typically a reserved special token such as ‘[EOS]‘.
Approach:	They propose to add a new training stage before contrastive learning to enrich the semantics of the final token embedding.
Outcome:	The proposed training stage improves performance on the Massive Text Embedding Benchmark (MTEB), achieving new state-of-the-art results across different LLM base models and scales.

Copied to clipboard

Jianguo Zhang, Trung Bui, Seunghyun Yoon, Xiang Chen, Zhiwei Liu, Congying Xia, Quan Hung Tran, Walter Chang, Philip Yu

Sentiment Analysis

Challenge:	Existing methods address few-shot intent detection tasks from two perspectives: data augmentation and task-adaptive training with pre-trained models.
Approach:	They propose a few-shot intent detection schema using contrastive pre-training and fine-tuning.
Outcome:	The proposed method achieves state-of-the-art performance on three challenging intent detection datasets under 5-shot and 10-shot settings.

Selection Bias Explorations and Debias Methods for Natural Language Sentence Matching Datasets (P19-1)

Copied to clipboard

Guanhua Zhang, Bing Bai, Jian Liang, Kun Bai, Shiyu Chang, Mo Yu, Conghui Zhu, Tiejun Zhao

C2PO: Diagnosing and Disentangling Bias Shortcuts in LLMs (2026.findings-acl)

Challenge:	Natural Language Sentence Matching (NLSM) is a popular NLP task.
Approach:	They propose to use QuoraQP to train and evaluate NLSM models using a selection bias framework.
Outcome:	The proposed framework can improve generalization ability of trained models and give more trustworthy evaluation results for real-world adoptions.

Copied to clipboard

Xuan Feng, Bo An, Tianlong Gu, Liang Chang, Fengrui Hao, Peipeng Yu, Shuai Zhao

On Measures of Biases and Harms in NLP (2022.findings-aacl)

Challenge:	Existing approaches to solve large language models address stereotypical and structural biases in isolation . however, prior paradigms address these in isolation, often at the expense of exacerbating the other .
Approach:	They propose a framework to tackle latent spurious feature correlations within input that drive erroneous reasoning shortcuts.
Outcome:	The proposed framework mitigates stereotypical and structural biases while preserving robust general reasoning capabilities.

Copied to clipboard

Sunipa Dev, Emily Sheng, Jieyu Zhao, Aubrie Amstutz, Jiao Sun, Yu Hou, Mattie Sanseverino, Jiin Kim, Akihiro Nishi, Nanyun Peng, Kai-Wei Chang

VReST: Enhancing Reasoning in Large Vision-Language Models through Tree Search and Self-Reward Mechanism (2025.acl-long)

Challenge:	Recent studies show that natural language processing (NLP) technologies propagate societal biases about demographic groups associated with attributes such as gender, race, and nationality.
Approach:	They propose a framework for harms and questions to help practitioners understand biases . they propose measurable measures to detect and mitigate biased groups .
Outcome:	The proposed framework provides a framework for harms and questions for practitioners to answer to guide the development of bias measures.

Copied to clipboard

Congzhi Zhang, Jiawei Peng, Zhenglin Wang, Yilong Lai, Haowen Sun, Heng Chang, Fei Ma, Weijiang Yu

Measuring Social Bias in Vision-Language Models with Face-Only Counterfactuals from Real Photos (2026.acl-long)

Challenge:	Large Vision-Language Models (LVLMs) have shown exceptional performance in multimodal tasks, but their effectiveness in complex visual reasoning is constrained.
Approach:	They propose a training-free approach that enhances Reasoning in Large Vision-Language Models . they propose integrating Monte Carlo Tree Search and Self-Reward mechanisms into the reasoning tree .
Outcome:	The proposed approach surpasses current prompting methods and secures state-of-the-art performance across three multimodal reasoning benchmarks.

Copied to clipboard

Haodong Chen, Qiang Huang, Jiaqi Zhao, Qiuping Jiang, Xiaojun Chang, Jun Yu

Visual Data in NLP

Challenge:	Vision-Language Models (VLMs) are increasingly deployed in socially consequential settings . attribution under visual confounding is a central challenge in measuring social bias .
Approach:	They propose a face-only counterfactual evaluation paradigm that isolates demographic effects while preserving real-image realism.
Outcome:	The proposed paradigm isolates demographic effects while preserving real-image realism.

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

Copied to clipboard

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

Text Generation

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.

Complementary Evidence Identification in Open-Domain Question Answering (2021.eacl-main)

Copied to clipboard

Xiangyang Mou, Mo Yu, Shiyu Chang, Yufei Feng, Li Zhang, Hui Su

Natural Language Interfaces

Challenge:	Existing approaches to QA that only measure the relevance between the question and each paragraph are not effective.
Approach:	They propose a method that learns vector representations of passages and models the sufficiency and diversity within the selected set, in addition to the relevance between the question and passages.
Outcome:	The proposed method significantly improves the accuracy of complementary evidence selection in open-domain question answering domain.

Learning Word Embeddings for Low-Resource Languages by PU Learning (N18-1)

Copied to clipboard

Chao Jiang, Hsiang-Fu Yu, Cho-Jui Hsieh, Kai-Wei Chang

PRA-RAG: Provably Robust Aggregation in Retrieval-Augmented Generation against Retrieval Corruption (2026.findings-acl)

Challenge:	Existing approaches to learn word embedding on a corpus with only a few million tokens are limited to low-resource languages.
Approach:	They propose to use a sparse co-occurrence matrix to factorize the co-existence matrix and validate the proposed approaches in four different languages.
Outcome:	The proposed model is validated in four different languages.

Copied to clipboard

Xue Tan, Yi Zheng, Chang Huo, Yunruo Zhang, Yu Liu, Hao Luan, Zhuyang Yu, Jun Dai, Xiaoyan Sun, Ping Chen

Robustness in NLP

Challenge:	Existing defense mechanisms lack theoretical robustness guarantees and perform unreliably when the LLM has limited knowledge of the retrieved content.
Approach:	They propose a provably robust retrieval aggregation algorithm designed to defend against poisoning attacks on retrieved texts.
Outcome:	Experiments show that PRA-RAG reduces the attack success rate to as low as 1% while maintaining an accuracy of 71%, significantly outperforming representative state-of-the-art (SOTA) methods.

Skill Discovery for Software Scripting Automation via Offline Simulations with LLMs (2026.findings-eacl)

Copied to clipboard

Paiheng Xu, Gang Wu, Xiang Chen, Tong Yu, Chang Xiao, Franck Dernoncourt, Tianyi Zhou, Wei Ai, Viswanathan Swaminathan

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

Challenge:	Large Language Models (LLMs) can generate code from natural language queries, but runtime code generation is limited due to unverified code, security risks, longer response times, and higher computational costs.
Approach:	They propose an offline simulation framework to curate a software-specific skillset by exploiting large language models and publicly available scripting guides.
Outcome:	The proposed framework significantly improves automation success rates, reduces response time, and saves runtime token costs compared to traditional runtime code generation.

Copied to clipboard

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

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

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

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

Self-supervised Cross-modal Pretraining for Speech Emotion Recognition and Sentiment Analysis (2022.findings-emnlp)

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

Iek-Heng Chu, Ziyi Chen, Xinlu Yu, Mei Han, Jing Xiao, Peng Chang

Context-Aware Conversation Thread Detection in Multi-Party Chat (D19-1)

Challenge:	Existing approaches to multimodal speech emotion recognition and sentiment analysis have not improved results due to their relatively simple fusion mechanisms and lack of proper cross-modal pretraining.
Approach:	They propose a deep-fused audio-text bi-modal transformer with carefully designed cross-modal fusion mechanism and stage-wise cross-mod pretraining scheme to facilitate cross-modulation.
Outcome:	The proposed method exceeds benchmarks on public IEMOCAP emotion and CMU-MOSEI sentiment datasets by a large margin.

Copied to clipboard

Ming Tan, Dakuo Wang, Yupeng Gao, Haoyu Wang, Saloni Potdar, Xiaoxiao Guo, Shiyu Chang, Mo Yu

Dialogue Systems & Conversational Agents

Challenge:	In multi-party chat, it is common for multiple conversations to occur concurrently . a new model that automatically disentangles conversation threads is proposed .
Approach:	They propose a Context-Aware Thread Detection model that automatically disentangles conversation threads in chat logs.
Outcome:	The proposed model outperforms state-of-the-art models on four real-world chat logs.

A Survey of Deep Learning for Mathematical Reasoning (2023.acl-long)

Copied to clipboard

Pan Lu, Liang Qiu, Wenhao Yu, Sean Welleck, Kai-Wei Chang

Improving Reinforcement Learning Based Image Captioning with Natural Language Prior (D18-1)

Challenge:	a survey of deep learning for mathematical reasoning examines the field . a comprehensive reading list is provided to assist readers interested in the field.
Approach:	They present a survey of deep learning for mathematical reasoning over the past decade . they outline directions for future research and highlight potential for further exploration .
Outcome:	The proposed framework is based on the results of a decade-long survey of deep learning for mathematical reasoning.

Copied to clipboard

Tszhang Guo, Shiyu Chang, Mo Yu, Kun Bai

UltraIF: Advancing Instruction Following from the Wild (2025.emnlp-main)

Challenge:	Recent research shows that Reinforcement Learning (RL) approaches suffer from the exposure bias problem.
Approach:	They propose a Reinforcement Learning (RL) based training framework that constrains the action space using an n-gram language prior.
Outcome:	The proposed model is more human readable and graceful.

Copied to clipboard

Kaikai An, Li Sheng, Ganqu Cui, Shuzheng Si, Ning Ding, Yu Cheng, Baobao Chang

Predicting Rewards Alongside Tokens: Non-disruptive Parameter Insertion for Efficient Inference Intervention in Large Language Model (2024.emnlp-main)

Challenge:	a lack of transparency has resulted in a gap between research community and leading companies . large language models have demonstrated remarkable capabilities in following complex instructions .
Approach:	They propose a method to build large language models that can follow complex instructions with open-source data.
Outcome:	The proposed approach can synergize complex instructions and filter responses with evaluation questions.

Copied to clipboard

Chenhan Yuan, Fei Huang, Ru Peng, Keming Lu, Bowen Yu, Chang Zhou, Jingren Zhou

MCP-Guard: A Multi-Stage Defense-in-Depth Framework for Securing Model Context Protocol in Agentic AI (2026.findings-acl)

Challenge:	Existing approaches to fine tune LLMs produce unsafe responses and unreliable reasoning, but this solution introduces substantial time and space overhead due to the separate models required.
Approach:	They propose to insert extra parameters into transformer architecture to predict calibration signals along with original LLM output.
Outcome:	The proposed model reduces time and space costs while enabling seamless online deployment.

Copied to clipboard

Wenpeng Xing, Zhonghao Qi, Yupeng Qin, Yilin Li, Caini Chang, Jiahui Yu, Changting Lin, Zhenzhen Xie, Meng Han

ToHRE: A Top-Down Classification Strategy with Hierarchical Bag Representation for Distantly Supervised Relation Extraction (2020.coling-main)

Challenge:	Large Language Models (LLMs) are vulnerable to jailbreak, authors say . authors propose a robust, layered defense architecture designed for LLM–tool interactions .
Approach:	They propose a robust, layered defense architecture designed for LLM–tool interactions . they propose XCP-Guard, which employs a three-stage detection pipeline .
Outcome:	The proposed model achieves 96.01% accuracy in identifying adversarial prompts . the model is based on a three-stage detection pipeline that balances efficiency with accuracy .

Copied to clipboard

Erxin Yu, Wenjuan Han, Yuan Tian, Yi Chang

Large Language Models are Superpositions of All Characters: Attaining Arbitrary Role-play via Self-Alignment (2024.acl-long)

Challenge:	Existing methods to find relational facts from texts lack hierarchical information of relations.
Approach:	They propose a hierarchical classification framework which extracts relation in a top-down manner.
Outcome:	The proposed method significantly outperforms state-of-the-art methods on NYT dataset . the proposed method generates large amounts of training data by aligning KBs with unlabeled corpora .

Copied to clipboard

Keming Lu, Bowen Yu, Chang Zhou, Jingren Zhou

Me-Agent: A Personalized Mobile Agent with Two-Level User Habit Learning for Enhanced Interaction (2026.findings-acl)

Challenge:	Existing work cheaply emulates LLMs, allowing users to create profiles for their preferred characters.
Approach:	They propose a self-alignment method that encourages an instruction-following LLM to simulate role-play dialogues as a variant of reading comprehension.
Outcome:	The proposed model outperforms open-source role-play benchmarks and the roleplay subset of MT-Bench in multiple parameters.

Copied to clipboard

Shuoxin Wang, Chang Liu, Gowen Loo, Lifan Zheng, Kaiwen Wei, Huanqian Yan, Xinyi Zeng, Jingyuan Zhang, Yu Tian

Instructions are all you need: Self-supervised Reinforcement Learning for Instruction Following (2026.acl-long)

Challenge:	Existing Large Language Model (LLM)-based mobile agents follow explicit user instructions without personalized needs.
Approach:	They propose a user preference learning strategy enhanced with a Personal Reward Model to improve personalization performance.
Outcome:	The proposed agent achieves state-of-the-art performance while maintaining competitive instruction execution performance.

Copied to clipboard

Qingyu Ren, Qianyu He, Powei Chang, Jie Zeng, Zeye Sun, Fei Yu, Jiaqing Liang, Yanghua Xiao

Symbolic Chain-of-Thought Distillation: Small Models Can Also “Think” Step-by-Step (2023.acl-long)

Challenge:	Existing reinforcement learning approaches suffer from dependency on external supervision and sparse reward signals from multi-constraint tasks.
Approach:	They propose a self-supervised reinforcement learning framework that eliminates dependency on external supervision by deriving reward signals directly from instructions and generating pseudo-labels for reward model training.
Outcome:	The proposed framework achieves strong improvements across 3 in-domain and 5 out-of-domain datasets while maintaining computational efficiency.

Copied to clipboard

Liunian Harold Li, Jack Hessel, Youngjae Yu, Xiang Ren, Kai-Wei Chang, Yejin Choi

Language Models can Evaluate Themselves via Probability Discrepancy (2024.findings-acl)

Challenge:	Symbolic Chain-of-thought Distillation (SCoTD) is a method to train a smaller student model on rationalizations sampled from a significantly larger teacher model.
Approach:	They propose a method to train a smaller student model on rationalizations from a larger teacher model.
Outcome:	The proposed method improves the performance of a student model in supervised and few-shot settings and especially for challenge sets.

Copied to clipboard

Tingyu Xia, Bowen Yu, Yuan Wu, Yi Chang, Chang Zhou

Can AI Revise Research Papers with Human Review Feedback? An Empirical Study and Benchmark (2026.findings-acl)

Challenge:	Existing evaluation frameworks focus on superficial text differences and fail to align with human judgment.
Approach:	They propose a new method to evaluate the performance of Large Language Models (LLMs) by calculating probability discrepancies between original response generation and revised versions of LLMs.
Outcome:	The proposed method eliminates the need for training an additional evaluation model or relying on external proprietary models such as GPT-4 as a judger.

Copied to clipboard

Zihan Luo, Hong Huang, Jianxun Lian, Yu Chang, Xing Xie, Hai Jin

Serial Lifelong Editing via Mixture of Knowledge Experts (2025.acl-long)

Challenge:	Large Language Models (LLMs) are fundamentally reshaping the scientific landscape, transitioning the role of AI from passive tools to active partners within a new paradigm of Human-AI collaboration.
Approach:	They propose a benchmark to evaluate the ability of Large Language Models to improve papers with human feedback.
Outcome:	The proposed benchmark tests the skills of Large Language Models (LLMs) on paper interpretation, experimental implementation, and paper formulation, using authors’ camera-ready versions as natural human baselines.

Copied to clipboard

YuJu Cheng, Yu-Chu Yu, Kai-Po Chang, Yu-Chiang Frank Wang

Deriving Machine Attention from Human Rationales (D18-1)

Challenge:	Existing Lifelong Knowledge Editing methods struggle to overwrite outdated knowledge with the latest one.
Approach:	They propose a new Mixture-of-Knowledge-Experts scheme with an ARM . ARM ensures that each update completely overwrites old information with the latest one . Experimental results show that ARM performs favorably against SOTA knowledge editing methods .
Outcome:	The proposed scheme overwrites old knowledge with the latest data on a benchmark . it performs favorably against existing knowledge editing methods on the same concept .

Copied to clipboard

Yujia Bao, Shiyu Chang, Mo Yu, Regina Barzilay

A Co-Matching Model for Multi-choice Reading Comprehension (P18-2)

Challenge:	Attention-based models are successful when trained on large amounts of data.
Approach:	They propose an approach to map human-annotated rationales to high-performing attention and use this to guide models trained in low-resource scenarios.
Outcome:	The proposed model yields over 15% error reduction on benchmark datasets.

Copied to clipboard

Shuohang Wang, Mo Yu, Jing Jiang, Shiyu Chang

Interactive Fiction Game Playing as Multi-Paragraph Reading Comprehension with Reinforcement Learning (2020.emnlp-main)

Challenge:	Existing approaches to machine comprehension are based on pairwise sequence matching, but this approach is not suitable for multi-choice reading comprehension since questions and answers are often equally important.
Approach:	They propose a co-matching approach that models whether a passage can match both a question and a candidate answer using a dataset from Chinese exams.
Outcome:	The proposed approach achieves state-of-the-art on the RACE dataset from Chinese middle and high school English examinations.

Copied to clipboard

Xiaoxiao Guo, Mo Yu, Yupeng Gao, Chuang Gan, Murray Campbell, Shiyu Chang

Machine Reading Comprehension

Challenge:	Interactive Fiction (IF) games with real human-written natural language texts provide a new natural evaluation for language understanding techniques.
Approach:	They propose to re-formulate IF game solving as Multi-Passage Reading Comprehension tasks using context-query attention mechanisms and structured prediction to efficiently generate and evaluate action outputs.
Outcome:	The proposed methods achieve high winning rates and low data requirements on the recent IF benchmark (Jericho)

Imposing Label-Relational Inductive Bias for Extremely Fine-Grained Entity Typing (N19-1)

Copied to clipboard

Wenhan Xiong, Jiawei Wu, Deren Lei, Mo Yu, Shiyu Chang, Xiaoxiao Guo, William Yang Wang

Structured Data in NLP

Challenge:	Existing entity typing systems exploit type hierarchy provided by KB schema to model label correlations.
Approach:	They propose a graph layer that encodes global label co-occurrence statistics and word-level similarities.
Outcome:	The proposed model achieves a 15.3% relative F1 improvement on a large dataset with over 10,000 free-form types.

Breaking the Ceiling of the LLM Community by Treating Token Generation as a Classification for Ensembling (2024.findings-emnlp)

Copied to clipboard

Yao-Ching Yu, Chun Chih Kuo, Ye Ziqi, Chang Yucheng, Yueh-Se Li

Information Retrieval

Challenge:	Large Language Models (LLMs) have demonstrated remarkable capabilities in a wide range of tasks and contexts.
Approach:	They propose to use a token-level ensembling method to exploit the probability information at each generation step and to avoid early incorrect tokens.
Outcome:	The proposed method breaks the existing community performance ceiling and improves on several benchmarks.

PAR: Political Actor Representation Learning with Social Context and Expert Knowledge (2022.emnlp-main)

Copied to clipboard

Shangbin Feng, Zhaoxuan Tan, Zilong Chen, Ningnan Wang, Peisheng Yu, Qinghua Zheng, Xiaojun Chang, Minnan Luo

Representation Learning

Challenge:	Existing approaches focus on textual data and voting records to induce political actors' stances.
Approach:	They propose a Political Actor Representation learning framework that leverages social context and expert knowledge to model ideological stances.
Outcome:	The proposed framework improves political text understanding and improves roll call vote prediction and political perspective detection.

T2R-BENCH: A Benchmark for Real World Table-to-Report Task (2025.emnlp-main)

Copied to clipboard

Jie Zhang, Changzai Pan, Sishi Xiong, Kaiwen Wei, Yu Zhao, Xiangyu Li, Jiaxin Peng, Xiaoyan Gu, Jian Yang, Wenhan Chang, Zhenhe Wu, Jiang Zhong, Shuangyong Song, Xuelong Li

Structured Data in NLP

Challenge:	Existing table benchmarks lack the capacity to adequately assess the practical application of table reasoning in industrial applications.
Approach:	They propose a bilingual table-to-report task and a table-based benchmark to assess the quality of table reasoning.
Outcome:	The proposed task is based on a bilingual benchmark with 457 industrial tables and evaluation criteria to measure the quality of report generation.

TWEETQA: A Social Media Focused Question Answering Dataset (P19-1)

Copied to clipboard

Wenhan Xiong, Jiawei Wu, Hong Wang, Vivek Kulkarni, Mo Yu, Shiyu Chang, Xiaoxiao Guo, William Yang Wang

Question Answering

Challenge:	Social media is becoming an important realtime information source, especially during natural disasters and emergencies.
Approach:	They present a large-scale dataset for question answering over social media data . they gather tweets used by journalists and ask human annotators to write questions upon them .
Outcome:	The proposed dataset shows that neural models that perform well on formal texts are limited in their performance . the proposed model is still lagging behind human performance with a large margin .

Towards A Better Initial Policy Model For Scalable Long-CoT Reinforcement Learning (2025.findings-acl)

Copied to clipboard

Bofei Gao, Yejie Wang, Yibo Miao, Ruoyu Wu, Feifan Song, Longhui Yu, Tianyu Liu, Baobao Chang

Event Detection from Social Media for Epidemic Prediction (2024.naacl-long)

Challenge:	Long-CoT reasoning and reinforcement learning are demonstrating remarkable performance and scalability, however, there is a lack of systematic guidelines for obtaining a better initial policy model.
Approach:	They propose a systematic guideline and a novel Re-RFT method to obtain more efficient reasoning patterns from different initial models.
Outcome:	The proposed method surpasses DeepSeek-R1-Distill-Qwen-14B model by 4.6%, demonstrating its effectiveness and superiority.

Copied to clipboard

Tanmay Parekh, Anh Mac, Jiarui Yu, Yuxuan Dong, Syed Shahriar, Bonnie Liu, Eric Yang, Kuan-Hao Huang, Wei Wang, Nanyun Peng, Kai-Wei Chang

Zero-shot User Intent Detection via Capsule Neural Networks (D18-1)

Challenge:	Social media is an easy-to-access platform providing timely updates about societal trends and events.
Approach:	They propose a framework to extract epidemic-related events from social media posts to provide early warnings.
Outcome:	The proposed framework can detect epidemic events for three unseen epidemics of Monkeypox, Zika, and Dengue while existing models fail miserably.

Copied to clipboard

Congying Xia, Chenwei Zhang, Xiaohui Yan, Yi Chang, Philip Yu

Sentiment Analysis

Challenge:	Existing methods to classify intents are labor-intensive and time-consuming as intents will be diverse and new intents may be involved.
Approach:	They propose a zero-shot intent detection problem which aims to detect emerging user intents where no labeled utterances are currently available.
Outcome:	The proposed model can discriminate emerging intents when no labeled utterances are available in training data.

Non-Sequential Graph Script Induction via Multimedia Grounding (2023.acl-long)

Copied to clipboard

Yu Zhou, Sha Li, Manling Li, Xudong Lin, Shih-Fu Chang, Mohit Bansal, Heng Ji

Learning Semantic Textual Similarity via Topic-informed Discrete Latent Variables (2022.emnlp-main)

Challenge:	Existing scripts for everyday tasks are presented in a linear manner, which does not reflect the flexibility displayed by people executing tasks in real life.
Approach:	They propose to use loosely aligned videos to train a non-sequential graph script induction task by using a multimodal framework to ground procedural videos to WikiHow textual steps.
Outcome:	The proposed model outperforms the WikiHow linear baseline by 48.76% . it can predict future steps given a partial step sequence and generate explicit graph scripts .

Copied to clipboard

Erxin Yu, Lan Du, Yuan Jin, Zhepei Wei, Yi Chang

KIEval: A Knowledge-grounded Interactive Evaluation Framework for Large Language Models (2024.acl-long)

Challenge:	Recent discrete latent variable models have received a surge of interest in both NLP and CV . they are comparable to the continuous counterparts in representation learning, but are more interpretable in their predictions.
Approach:	They develop a topic-informed discrete latent variable model for semantic textual similarity . they inject the quantized representation into a transformer-based language model .
Outcome:	The proposed model outperforms strong baselines in semantic textual similarity tasks.

Copied to clipboard

Zhuohao Yu, Chang Gao, Wenjin Yao, Yidong Wang, Wei Ye, Jindong Wang, Xing Xie, Yue Zhang, Shikun Zhang

FreeEval: A Modular Framework for Trustworthy and Efficient Evaluation of Large Language Models (2024.emnlp-demo)

Challenge:	Existing methods to detect contaminated texts focus on quantifying contamination status instead of accurately gauging model performance.
Approach:	They propose a Knowledge-grounded Interactive Evaluation framework which incorporates an LLM-powered “interactor” role for the first time to accomplish a dynamic contamination-resilient evaluation.
Outcome:	The proposed framework is based on a question in a standard LLM benchmark and can be used to evaluate models in real-world conversations.

Copied to clipboard

Zhuohao Yu, Chang Gao, Wenjin Yao, Yidong Wang, Zhengran Zeng, Wei Ye, Jindong Wang, Yue Zhang, Shikun Zhang

Towards Unified Representations of Knowledge Graph and Expert Rules for Machine Learning and Reasoning (2022.aacl-main)

Challenge:	Large language models (LLMs) have revolutionized natural language processing with impressive performance across various tasks.
Approach:	They propose a framework for automated evaluations of large language models . they open-source their code at https://github.com/WisdomShell/FreeEval .
Outcome:	The framework is open-source and can be used to develop and validate new evaluation methods.

Copied to clipboard

Zhepei Wei, Yue Wang, Jinnan Li, Zhining Liu, Erxin Yu, Yuan Tian, Xin Wang, Yi Chang