Papers by Mo Yu

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

Reasoning

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.

TVShowGuess: Character Comprehension in Stories as Speaker Guessing (2022.naacl-main)

Copied to clipboard

Yisi Sang, Xiangyang Mou, Mo Yu, Shunyu Yao, Jing Li, Jeffrey Stanton

Challenge:	Our proposed task, TVShowGuess, builds on the scripts of TV series and takes the form of guessing the anonymous main characters based on the backgrounds of the scenes and the dialogues.
Approach:	They propose a task that takes the form of guessing the anonymous main characters based on the backgrounds of the scenes and the dialogues.
Outcome:	The proposed models outperform baselines, yet lag behind human performance.

Multilingual BERT Post-Pretraining Alignment (2021.naacl-main)

Copied to clipboard

Lin Pan, Chung-Wei Hang, Haode Qi, Abhishek Shah, Saloni Potdar, Mo Yu

ReFreeKV: Towards Threshold-Free KV Cache Compression (2026.findings-acl)

Challenge:	Recent work improves on the success of monolingual pretrained language models by adding cross-lingual tasks that always involve English.
Approach:	They propose a method to align multilingual contextual embeddings as a post-pretraining step for improved cross-lingual transferability of pretrained language models.
Outcome:	The proposed model outperforms XLM-R_Base on translation-train tasks while using less parallel data and fewer parameters.

Copied to clipboard

Xuanfan Ni, Liyan Xu, Chenyang Lyu, Longyue Wang, Mo Yu, Lemao Liu, Fandong Meng, Jie Zhou, Piji Li

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

Challenge:	Towards the KV cache efficiency, we propose a new objective that lifts the threshold constraints for robust KV compression.
Approach:	They propose a method that adjusts KV cache budgets while preserving full-cache performance.
Outcome:	The proposed method can reduce memory consumption while preserving full-cache performance.

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

Leveraging Dependency Forest for Neural Medical Relation Extraction (D19-1)

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

Linfeng Song, Yue Zhang, Daniel Gildea, Mo Yu, Zhiguo Wang, Jinsong Su

Benchmarking Commercial Intent Detection Services with Practice-Driven Evaluations (2021.naacl-industry)

Challenge:	Existing methods for medical relation extraction use dependency syntax as a source of features.
Approach:	They propose a method to extract relational information from medical literature by using dependency forests.
Outcome:	The proposed method outperforms the standard tree-based methods in the medical domain.

Copied to clipboard

Haode Qi, Lin Pan, Atin Sood, Abhishek Shah, Ladislav Kunc, Mo Yu, Saloni Potdar

Sentiment Analysis

Challenge:	Intent detection models require large amounts of labeled data to achieve high accuracy, and in practical scenarios it is more common to find small, unbalanced, and noisy datasets.
Approach:	They benchmark intent detection methods on a variety of datasets and found that Watson Assistant's model outperforms other commercial solutions.
Outcome:	The proposed model outperforms pretrained language models on a variety of datasets while requiring only a fraction of computational resources and training data.

It is AI’s Turn to Ask Humans a Question: Question-Answer Pair Generation for Children’s Story Books (2022.acl-long)

Copied to clipboard

Bingsheng Yao, Dakuo Wang, Tongshuang Wu, Zheng Zhang, Toby Li, Mo Yu, Ying Xu

JECC: Commonsense Reasoning Tasks Derived from Interactive Fictions (2023.findings-acl)

Challenge:	Existing question answering (QA) techniques are created mainly to answer questions asked by humans, but in educational applications, teachers often need to decide what questions to ask .
Approach:	They propose to use a fairytale-themed storybook as input to generate QA pairs that can test a student's comprehension skills.
Outcome:	The proposed system outperforms state-of-the-art QAG baseline systems and builds an interactive story-telling application for the future real-world deployment.

Copied to clipboard

Mo Yu, Yi Gu, Xiaoxiao Guo, Yufei Feng, Xiaodan Zhu, Michael Greenspan, Murray Campbell, Chuang Gan

Reasoning

Challenge:	Existing benchmarks focus on a single reasoning type and ask human annotators to write candidate statements related to the particular type of commonsense.
Approach:	They propose a new commonsense reasoning dataset based on human’s Interactive Fiction (IF) gameplaywalkthroughs.
Outcome:	The proposed dataset is challenging to previous machine reading models and large language models with a significant 20%performance gap compared to human experts.

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

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.

Do Multi-hop Readers Dream of Reasoning Chains? (D19-58)

Copied to clipboard

Haoyu Wang, Mo Yu, Xiaoxiao Guo, Rajarshi Das, Wenhan Xiong, Tian Gao

Identifying Factual Inconsistencies in Summaries: Grounding LLM Inference via Task Taxonomy (2024.findings-emnlp)

Challenge:	Existing models for multihop reasoning are limited in their performance . multi-hop reasoning requires the ability to gather information from multiple passages .
Approach:	They propose a method that provides the full reasoning chain of multiple passages instead of just one final passage where the answer appears.
Outcome:	The proposed model improves on existing models by providing the full reasoning chain of multiple passages instead of just one final passage where the answer appears.

Copied to clipboard

Liyan Xu, Zhenlin Su, Mo Yu, Jin Xu, Jinho Choi, Jie Zhou, Fei Liu

Fantastic Questions and Where to Find Them: FairytaleQA – An Authentic Dataset for Narrative Comprehension (2022.acl-long)

Challenge:	Existing studies have focused on specialized BERT-variants and recent LLMs to reason inconsistencies.
Approach:	They propose to incorporate task-specific taxonomy into inferences to facilitate both zero-shot and supervised paradigms.
Outcome:	The proposed model outperforms specialized non-LLM and recent LLM models in a number of domains.

Copied to clipboard

Ying Xu, Dakuo Wang, Mo Yu, Daniel Ritchie, Bingsheng Yao, Tongshuang Wu, Zheng Zhang, Toby Li, Nora Bradford, Branda Sun, Tran Hoang, Yisi Sang, Yufang Hou, Xiaojuan Ma, Diyi Yang, Nanyun Peng, Zhou Yu, Mark Warschauer

Rethinking the Evaluation of In-Context Learning for LLMs (2024.emnlp-main)

Challenge:	Existing QA datasets rarely distinguish fine-grained reading skills, such as the understanding of varying narrative elements.
Approach:	They propose to use FairytaleQA to generate 10,580 questions based on 278 children-friendly stories to assess model's fine-grained learning skills.
Outcome:	The proposed dataset consists of 10,580 questions derived from 278 children-friendly stories, covering seven types of narrative elements or relations.

Copied to clipboard

Guoxin Yu, Lemao Liu, Mo Yu, Yue Yu, Xiang Ao

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

Challenge:	Existing studies evaluate In-context learning methods based on task performance . however, this evaluation protocol overlooks the significant cost associated with the demonstration configuration process .
Approach:	They propose a two-dimensional evaluation paradigm that considers both configuration costs and task performance.
Outcome:	The proposed evaluation paradigm can be applied to any ICL method as a plugin.

Copied to clipboard

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

FaithDial: A Faithful Benchmark for Information-Seeking Dialogue (2022.tacl-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

Nouha Dziri, Ehsan Kamalloo, Sivan Milton, Osmar Zaiane, Mo Yu, Edoardo M. Ponti, Siva Reddy

Dialogue Systems & Conversational Agents

Challenge:	a new benchmark for hallucination-free dialogues is based on knowledge-based conversational models that generate unsupported utterances . a recent study shows that models that are trustworthy generate unverifiable or factually incorrect statements .
Approach:	They propose a data-centric solution to edit hallucinated responses in the Wizard of Wikipedia benchmark.
Outcome:	The proposed model improves on the Wizard of Wikipedia benchmark while maintaining engaging conversations.

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

Copied to clipboard

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

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

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

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

CDT: A Comprehensive Capability Framework for Large Language Models Across Cognition, Domain, and Task (2025.findings-emnlp)

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

Haosi Mo, Xinyu Ma, Xuebo Liu, Derek F. Wong, Yu Li, Jie Liu, Min Zhang

Multi-step Entity-centric Information Retrieval for Multi-Hop Question Answering (D19-58)

Challenge:	Existing benchmarks focus on isolated abilities, lacking a holistic framework for assessing LLM capabilities.
Approach:	They propose a Cognition-Domain-Task framework which measures a model’s capabilities across three dimensions.
Outcome:	The proposed framework improves performance on dataset evaluation and data selection, while achieving higher scores on general and specific benchmarks.

Copied to clipboard

Rajarshi Das, Ameya Godbole, Dilip Kavarthapu, Zhiyu Gong, Abhishek Singhal, Mo Yu, Xiaoxiao Guo, Tian Gao, Hamed Zamani, Manzil Zaheer, Andrew McCallum

On Large Language Models’ Hallucination with Regard to Known Facts (2024.naacl-long)

Challenge:	Multi-hop question answering (QA) requires an information retrieval system that can find multiple supporting evidence needed to answer the question.
Approach:	They propose a technique that uses information of entities present in the initial retrieved evidence to learn to ‘hop’ onto other relevant evidence.
Outcome:	The proposed method boosts retrieval performance on a multi-hop question answering dataset with 5 million Wikipedia paragraphs and a model without training increases its performance by 10.59 F1.

Copied to clipboard

Che Jiang, Biqing Qi, Xiangyu Hong, Dayuan Fu, Yang Cheng, Fandong Meng, Mo Yu, Bowen Zhou, Jie Zhou

Unsupervised Information Refinement Training of Large Language Models for Retrieval-Augmented Generation (2024.acl-long)

Challenge:	Large language models are successful in answering factoid questions but are also prone to hallucination.
Approach:	They propose self-reporting to the model when faced with such limitations.
Outcome:	The proposed classifier can detect hallucinations with an 88% success rate and can be used to answer factoid questions with correct answer knowledge.

Copied to clipboard

Shicheng Xu, Liang Pang, Mo Yu, Fandong Meng, Huawei Shen, Xueqi Cheng, Jie Zhou

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

Challenge:	Existing studies show that LLMs face challenges in effectively using retrieved information . authors propose a method that considers LLM as "Information Refiner"
Approach:	They propose a method that considers LLMs as "Information Refiners" they propose INFO-RAG, which is low-cost and general across various tasks .
Outcome:	The proposed method improves performance of LLaMA2 by 9.39% relative points . it is low-cost and general across various tasks, and is robust and in-context learning is possible .

Copied to clipboard

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

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

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.

Copied to clipboard

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

Narrative Question Answering with Cutting-Edge Open-Domain QA Techniques: A Comprehensive Study (2021.tacl-1)

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

Xiangyang Mou, Chenghao Yang, Mo Yu, Bingsheng Yao, Xiaoxiao Guo, Saloni Potdar, Hui Su

The Essence of Contextual Understanding in Theory of Mind: A Study on Question Answering with Story Characters (2025.acl-long)

Challenge:	Recent advances in open-domain question answering (ODQA) have led to human-level performance on many datasets.
Approach:	They provide a comprehensive and quantitative analysis about the difficulty of book QA . they compare the results of their research with extensive ODQA experiments .
Outcome:	The proposed model outperforms existing models on event-oriented questions on the NarrativeQA dataset.

Copied to clipboard

Chulun Zhou, Qiujing Wang, Mo Yu, Xiaoqian Yue, Rui Lu, Jiangnan Li, Yifan Zhou, Shunchi Zhang, Jie Zhou, Wai Lam

The Art of Prompting: Event Detection based on Type Specific Prompts (2023.acl-short)

Challenge:	Theory-of-Mind (ToM) is a psychological capability that allows humans to understand and interpret the mental states of others.
Approach:	They propose a CharToM-QA benchmark to assess the importance of comprehensive contextual understanding about personal backgrounds in ToM.
Outcome:	The proposed model outperforms existing models on 1,035 ToM questions based on classic novels and shows that educated participants perform better when they have read the novels than non-educated participants.

Copied to clipboard

Sijia Wang, Mo Yu, Lifu Huang

Low-Resource NLP

Challenge:	Experimental results show that a well-defined and comprehensive description of event types can significantly improve event detection performance when the annotations are limited.
Approach:	They propose a unified framework to integrate event type specific prompts for supervised, few-shot and zero-shot event detection.
Outcome:	The proposed framework shows up to 22.2% gain over the prior state-of-the-art frameworks.

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

The Stochastic Parrot on LLM’s Shoulder: A Summative Assessment of Physical Concept Understanding (2025.naacl-long)

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.

Copied to clipboard

Mo Yu, Lemao Liu, Junjie Wu, Tsz Ting Chung, Shunchi Zhang, Jiangnan Li, Dit-Yan Yeung, Jie Zhou

Challenge:	Recent years have witnessed remarkable advancements in large language models (LLMs) many researchers argue that LLMs may not * Equal contribution.
Approach:	They propose a task that summarises the memorization issue by using grid inputs that abstractly describe physical phenomena.
Outcome:	The proposed task alleviates the memorization issue by using grid-format inputs that abstractly describe physical phenomena.

DivLogicEval: A Framework for Benchmarking Logical Reasoning Evaluation in Large Language Models (2025.findings-emnlp)

Copied to clipboard

Tsz Ting Chung, Lemao Liu, Mo Yu, Dit-Yan Yeung

Timeline Summarization based on Event Graph Compression via Time-Aware Optimal Transport (2021.emnlp-main)

Challenge:	Existing logic reasoning benchmarks are limited in language diversity and their distributions are deviated from ideal distributions, which may lead to biased evaluation results.
Approach:	They propose a new logic benchmark DivLogicEval that uses natural sentences to evaluate logical reasoning .
Outcome:	The proposed evaluation metric mitigates bias and randomness inherent in LLMs.

Copied to clipboard

Manling Li, Tengfei Ma, Mo Yu, Lingfei Wu, Tian Gao, Heng Ji, Kathleen McKeown

Multimodality

Challenge:	Existing methods for timeline summarization ignore the events’ intra-structures and inter-structure connections.
Approach:	They propose to represent news articles as an event-graph, thus compressing the whole graph to its salient sub-graph.
Outcome:	The proposed method significantly improves on the state-of-the-art on three real-world datasets, including two public benchmarks and a Timeline100 dataset.

MCMH: Learning Multi-Chain Multi-Hop Rules for Knowledge Graph Reasoning (2020.findings-emnlp)

Copied to clipboard

Lu Zhang, Mo Yu, Tian Gao, Yue Yu

Knowledge Representation

Challenge:	Existing work on knowledge graphs infers a missing relationship between entities with a multi-hop rule . Empirical results show that our multi-chain multi-homing (MCMH) rules yield superior results compared to the standard single-chain approaches.
Approach:	They propose to use a generalized form of multi-hop rules to learn generalized rules efficiently . they propose to select a small set of relation chains as a rule and evaluate confidence .
Outcome:	The proposed method outperforms the existing methods and the existing frameworks.

On the token distance modeling ability of higher RoPE attention dimension (2024.findings-emnlp)

Copied to clipboard

Xiangyu Hong, Che Jiang, Biqing Qi, Fandong Meng, Mo Yu, Bowen Zhou, Jie Zhou

Representation Learning

Challenge:	Existing work on extending the context length of language models based on Rotary position embedding (RoPE) has shown promising results in capturing longer-range contextual information.
Approach:	They propose to use a hidden dimension of an attention head to investigate its contribution to capturing long-distance dependencies.
Outcome:	The proposed model can capture long-distance dependencies by extending the attention of a particular dimension of an attention head.

Educational Question Generation of Children Storybooks via Question Type Distribution Learning and Event-centric Summarization (2022.acl-long)

Copied to clipboard

Zhenjie Zhao, Yufang Hou, Dakuo Wang, Mo Yu, Chengzhong Liu, Xiaojuan Ma

Text Generation

Challenge:	Existing methods to generate educational questions of fairytales or storybooks are difficult to implement due to adults lacking the skills or time to integrate such interactive opportunities.
Approach:	They propose a question generation method that first learns the question type distribution of an input story paragraph, and then summarizes salient events which can be used to generate high-cognitive-demand questions.
Outcome:	The proposed method performs well on automatic and human evaluation metrics on a newly proposed educational question-answering dataset FairytaleQA.

Fine-Grained Modeling of Narrative Context: A Coherence Perspective via Retrospective Questions (2024.acl-long)

Copied to clipboard

Liyan Xu, Jiangnan Li, Mo Yu, Jie Zhou

Multimodality

Challenge:	a novel graph for narrative comprehension captures coherence between passages in narratives . end-to-end paradigms are effective for comprehension tasks, but may not be sufficient for all comprehension scenarios.
Approach:	They propose a graph dubbed NarCo which explicitly depicts task-agnostic coherence dependencies that are ready to be consumed by downstream tasks.
Outcome:	The proposed graph is practically instantiated by LLMs without human annotations.

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

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.

Explicit Planning Helps Language Models in Logical Reasoning (2023.emnlp-main)

Copied to clipboard

Hongyu Zhao, Kangrui Wang, Mo Yu, Hongyuan Mei

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

Challenge:	Existing systems that use pre-trained large language models to perform multi-step logical reasoning have been unable to perform this task.
Approach:	They propose a system that uses language models to perform multi-step logical reasoning and incorporates explicit planning into the inference procedure.
Outcome:	The proposed system outperforms other competing methods on multiple datasets and significantly outperformed chain-of-thought prompting on the PrOntoQA dataset.

Copied to clipboard

Tszhang Guo, Shiyu Chang, Mo Yu, Kun Bai

Multimodality

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.

Understanding LLMs’ Fluid Intelligence Deficiency: An Analysis of the ARC Task (2025.naacl-long)

Copied to clipboard

Junjie Wu, Mo Yu, Lemao Liu, Dit-Yan Yeung, Jie Zhou

Challenge:	Recent research on fluid intelligence assessments has highlighted significant deficiencies in LLMs’ abilities.
Approach:	They analyze the challenges LLMs face in demonstrating fluid intelligence through controlled experiments using the most representative ARC task as an example.
Outcome:	The proposed model shows that it lacks the ability to combine skill composition and abstract input formats and lacks left-to-right decoding.

Personality Understanding of Fictional Characters during Book Reading (2023.acl-long)

Copied to clipboard

Mo Yu, Jiangnan Li, Shunyu Yao, Wenjie Pang, Xiaochen Zhou, Zhou Xiao, Fandong Meng, Jie Zhou

Challenge:	Existing methods to predict characters' personalities have not been studied in the NLP field due to the lack of appropriate datasets mimicking the process of book reading.
Approach:	They propose a dataset to predict characters' personalities that uses an exhaustive vocabulary of personality traits as targets.
Outcome:	The proposed dataset is efficient and accurate and relies on long-term context to achieve accurate predictions for both machines and humans.

Question-Interlocutor Scope Realized Graph Modeling over Key Utterances for Dialogue Reading Comprehension (2023.findings-acl)

Copied to clipboard

Jiangnan Li, Mo Yu, Fandong Meng, Zheng Lin, Peng Fu, Weiping Wang, Jie Zhou

Deriving Machine Attention from Human Rationales (D18-1)

Challenge:	Compared to standard RC tasks, dialogue reading comprehension (DRC) has raised challenges because of the complex speaker information and noisy dialogue context.
Approach:	They propose a new method for dialogue reading comprehension that extracts answers from dialogues by using key-utterances-extracting methods and a Question-Interlocutor Scope Realized Graph.
Outcome:	The proposed method achieves state-of-the-art performance against previous works.

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

Reasoning

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.

WXImpactBench: A Disruptive Weather Impact Understanding Benchmark for Evaluating Large Language Models (2025.findings-acl)

Copied to clipboard

Yongan Yu, Qingchen Hu, Xianda Du, Jiayin Wang, Fengran Mo, Renée Sieber

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

Challenge:	Climate change adaptation requires the understanding of disruptive weather impacts on society.
Approach:	They propose a large language model to evaluate the capacity of LLMs on disruptive weather impacts by using a four-stage construction pipeline.
Outcome:	The proposed model is based on a four-stage well-crafted construction pipeline and requires two evaluation tasks, multi-label classification and ranking-based question answering.

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)

On the Origin of Hallucinations in Conversational Models: Is it the Datasets or the Models? (2022.naacl-main)

Copied to clipboard

Nouha Dziri, Sivan Milton, Mo Yu, Osmar Zaiane, Siva Reddy

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

Challenge:	Existing knowledge-grounded conversational benchmarks produce factually invalid statements, a phenomenon commonly called hallucination.
Approach:	They conduct a human study on knowledge-grounded conversational benchmarks and state-of-the-art models.
Outcome:	The findings raise important questions on the quality of existing datasets and models.

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.

Exploiting Rich Syntactic Information for Semantic Parsing with Graph-to-Sequence Model (D18-1)

Copied to clipboard

Kun Xu, Lingfei Wu, Zhiguo Wang, Mo Yu, Liwei Chen, Vadim Sheinin

MBTI Personality Prediction for Fictional Characters Using Movie Scripts (2022.findings-emnlp)

Challenge:	Existing neural semantic parsers extract word order features while neglecting other valuable syntactic information.
Approach:	They propose to use syntactic graph to represent three types of syntaktic information . they then employ a graph-to-sequence model to encode the syntastic graph and decode a logical form .
Outcome:	The proposed model is comparable to the state-of-the-art on Jobs640, ATIS, and Geo880.

Copied to clipboard

Yisi Sang, Xiangyang Mou, Mo Yu, Dakuo Wang, Jing Li, Jeffrey Stanton

Challenge:	Existing NLP models cannot predict character's personality types based on text classifications . character comprehension is the cornerstone of understanding stories in psychology and education.
Approach:	They propose a benchmark to predict movie character's MBTI or Big 5 personality types based on the narratives of the character.
Outcome:	The proposed model outperforms existing models in the task and is more accurate than random guesses.

Dense Retrievers Can Fail on Simple Queries: Revealing The Granularity Dilemma of Embeddings (2025.findings-emnlp)

Copied to clipboard

Liyan Xu, Zhenlin Su, Mo Yu, Jiangnan Li, Fandong Meng, Jie Zhou

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

Challenge:	a limited number of text encoders are able to recognize fine-grained entities or events within encoded semantics.
Approach:	They propose a new evaluation dataset to examine embeddings' ability to recognize fine-grained entities or events within encoded semantics.
Outcome:	The proposed dataset shows embeddings struggle with fine-grained matching . the proposed encoder outperforms the state-of-the-art 7B model in a small sample .

Copied to clipboard

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

Revisiting the Roles of “Text” in Text Games (2022.findings-emnlp)

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 .

Copied to clipboard

Yi Gu, Shunyu Yao, Chuang Gan, Josh Tenenbaum, Mo Yu

Challenge:	Recent work has shown that random text hashes could be complementary rather than contrasting in text games.
Approach:	They propose a scheme to extract contextual information into an approximate state hash as extra input for an RNN-based text agent.
Outcome:	The proposed scheme achieves competitive performance with state-of-the-art text agents using advanced NLU techniques such as knowledge graph and passage retrieval.

Plot Retrieval as an Assessment of Abstract Semantic Association (2024.acl-srw)

Copied to clipboard

Shicheng Xu, Liang Pang, Jiangnan Li, Mo Yu, Fandong Meng, Huawei Shen, Xueqi Cheng, Jie Zhou

Information Retrieval

Challenge:	Existing information retrieval datasets cannot capture abstract semantic associations well.
Approach:	They propose a task that retrieves relevant plots from the book for a query using a labeled dataset.
Outcome:	The proposed task can be used to evaluate the performance of IR models on the novel task Plot Retrieval.

Situated Embedding Models for Context-Aware Dense Retrieval (2026.acl-short)

Copied to clipboard

Junjie Wu, Jiangnan Li, Yuqing Li, Lemao Liu, Liyan Xu, Jiwei Li, Dit-Yan Yeung, Jie Zhou, Mo Yu

Representation Learning

Challenge:	Existing embedding models are not well-equipped to encode situated context effectively, i.e., situating a chunk’s meaning within its context.
Approach:	They propose to represent short chunks in a way that is conditioned on a broader context window to enhance retrieval performance.
Outcome:	The proposed model outperforms state-of-the-art embedding models on a book-plot retrieval dataset.

Cross-lingual Knowledge Graph Alignment via Graph Matching Neural Network (P19-1)

Copied to clipboard

Kun Xu, Liwei Wang, Mo Yu, Yansong Feng, Yan Song, Zhiguo Wang, Dong Yu

Structured Data in NLP

Challenge:	Existing approaches to cross-lingual knowledge graph (KG) alignment rely on entity embeddings derived from monolingual KG structural information.
Approach:	They propose a topic entity graph to represent entities with contextual information in KGs.
Outcome:	The proposed model outperforms state-of-the-art methods by a large margin.

Learning as Conversation: Dialogue Systems Reinforced for Information Acquisition (2022.naacl-main)

Copied to clipboard

Pengshan Cai, Hui Wan, Fei Liu, Mo Yu, Hong Yu, Sachindra Joshi