Papers by Dan Yu

Rethinking LLM Uncertainty: A Multi-Agent Approach to Estimating Black-Box Model Uncertainty (2025.findings-emnlp)

Challenge:	Large Audio Language Models (LALMs) exhibit a degradation in knowledge and reasoning capabilities . empirical results show that CORD significantly bridges the audio–text performance gap .
Approach:	They propose a framework that performs online cross-modal self-distillation to bridge the acoustic-semantic gap between LALMs and text-based models.
Outcome:	The proposed framework bridges the acoustic-semantic gap between LALMs and text-based models . it employs on-policy reverse KL divergence with importance-aware weighting .

Copied to clipboard

Yu Feng, Phu Mon Htut, Zheng Qi, Wei Xiao, Manuel Mager, Nikolaos Pappas, Kishaloy Halder, Yang Li, Yassine Benajiba, Dan Roth

Challenge:	Existing methods to gauge model’s uncertainty through self-consistency in responses to the target query are misleading: an LLM may confidently provide an incorrect answer to a target query, yet give a confident and accurate answer to that same query when answering a knowledge-preserving perturbation of the query.
Approach:	They propose a method that uses multi-agent interaction to estimate black-box LLMs' uncertainty.
Outcome:	The proposed method outperforms existing self-consistency based methods and improves hallucination detection.

Domain Generalization via Switch Knowledge Distillation for Robust Review Representation (2023.findings-acl)

Copied to clipboard

You Zhang, Jin Wang, Liang-Chih Yu, Dan Xu, Xuejie Zhang

Event Linking: Grounding Event Mentions to Wikipedia (2023.eacl-main)

Challenge:	Existing models for review representations of unseen or anonymous users are limited by their in-domain nature.
Approach:	They propose to use in-domain user and product information to generalize reviews . they use switch knowledge distillation to learn review representations for unseen users .
Outcome:	The proposed model performs well for existing or anonymous unseen users.

Copied to clipboard

Xiaodong Yu, Wenpeng Yin, Nitish Gupta, Dan Roth

Challenge:	a new task for natural language understanding is called Event Linking . the context where an event is mentioned lacks the details of this event .
Approach:	They propose a new task to link an article's event mention to the most appropriate Wikipedia page . they collect a training set from Wikipedia and evaluate two models to test the task .
Outcome:	The proposed model is based on a dataset and a real-world news domain . it is expected that the most appropriate Wikipedia page will provide rich knowledge about the mention .

Event Semantic Classification in Context (2024.findings-eacl)

Copied to clipboard

Haoyu Wang, Hongming Zhang, Kaiqiang Song, Dong Yu, Dan Roth

Information Extraction & Text Mining

Challenge:	In this work, we focus on the semantic classification of events in context to help machines gain a deeper understanding of events.
Approach:	They propose to integrate event semantics into downstream tasks to help machines understand events better.
Outcome:	The proposed model improves the understanding of events in context.

On the Strength of Character Language Models for Multilingual Named Entity Recognition (D18-1)

Copied to clipboard

Xiaodong Yu, Stephen Mayhew, Mark Sammons, Dan Roth

Task-Oriented Dialogue as Dataflow Synthesis (2020.tacl-1)

Challenge:	Character-level patterns have been widely used in English Named Entity Recognition systems.
Approach:	They propose to use corpus-agnostic character-level language models to capture name tokens . they demonstrate they can capture name and non-name tokens in a diverse set of languages .
Outcome:	The proposed model improves the performance of an off-the-shelf NER system for multiple languages.

Copied to clipboard

Jacob Andreas, John Bufe, David Burkett, Charles Chen, Josh Clausman, Jean Crawford, Kate Crim, Jordan DeLoach, Leah Dorner, Jason Eisner, Hao Fang, Alan Guo, David Hall, Kristin Hayes, Kellie Hill, Diana Ho, Wendy Iwaszuk, Smriti Jha, Dan Klein, Jayant Krishnamurthy, Theo Lanman, Percy Liang, Christopher H. Lin, Ilya Lintsbakh, Andy McGovern, Aleksandr Nisnevich, Adam Pauls, Dmitrij Petters, Brent Read, Dan Roth, Subhro Roy, Jesse Rusak, Beth Short, Div Slomin, Ben Snyder, Stephon Striplin, Yu Su, Zachary Tellman, Sam Thomson, Andrei Vorobev, Izabela Witoszko, Jason Wolfe, Abby Wray, Yuchen Zhang, Alexander Zotov

Sub-Sentence Encoder: Contrastive Learning of Propositional Semantic Representations (2024.naacl-long)

Challenge:	Existing approaches to task-oriented dialogue represent dialogue state as a dataflow graph . microsoft's SMCalFlow dataset features complex dialogues about events, weather, places, and people .
Approach:	They propose a dataflow graph-based dialogue agent that maps each user utterance to a program that extends this graph.
Outcome:	The proposed framework improves representability and predictability in natural dialogues . it uses dataflow graphs and metacomputation to map user intents to a program .

Copied to clipboard

Sihao Chen, Hongming Zhang, Tong Chen, Ben Zhou, Wenhao Yu, Dian Yu, Baolin Peng, Hongwei Wang, Dan Roth, Dong Yu

ReEval: Automatic Hallucination Evaluation for Retrieval-Augmented Large Language Models via Transferable Adversarial Attacks (2024.findings-naacl)

Challenge:	Sentence embeddings are typically learned to recognize the semantic relation between two text inputs.
Approach:	They introduce a contrastively-learned contextual embedding model for fine-grained semantic representation of text.
Outcome:	The proposed model is able to produce contextual embeddings corresponding to different atomic propositions, i.e. semantic equivalence between propositions across different text sequences.

Copied to clipboard

Xiaodong Yu, Hao Cheng, Xiaodong Liu, Dan Roth, Jianfeng Gao

Responsible & Trustworthy NLP

Challenge:	Existing static benchmarks do not guarantee that models can use the provided evidence for answering, which is essential to avoid hallucination when the required knowledge is new or private.
Approach:	They propose to automatically perturb existing static one for dynamic evaluation by using a chatGPT framework and a set of open-domain QA datasets.
Outcome:	The proposed framework generates new test cases on two open-domain QA datasets and is human-readable and useful to trigger hallucination in LLMs.

Pairwise Representation Learning for Event Coreference (2022.starsem-1)

Copied to clipboard

Xiaodong Yu, Wenpeng Yin, Dan Roth

Information Extraction & Text Mining

Challenge:	Existing work induces mention representations independently by extracting features from the sentence that contains the mention, without using the context of the other mention.
Approach:	They propose a Pairwise Representation Learning scheme for the event mention pairs that jointly encodes a pair of text snippets so that the representation of each mention in the pair is induced in the context of the other one.
Outcome:	The proposed scheme outperforms state-of-the-art representations on cross-document and within-document benchmarks.

Capturing the Content of a Document through Complex Event Identification (2022.starsem-1)

Copied to clipboard

Zheng Qi, Elior Sulem, Haoyu Wang, Xiaodong Yu, Dan Roth

Challenge:	Recent work grouped granular events into more general events, called complex events . however, this approach assumes that a given complex event is always described in consecutive sentences .
Approach:	They propose a context-augmented representation learning approach that uses contextual information to model pairwise relation between granular events.
Outcome:	The proposed approach outperforms baselines on the complex event identification task.

Multi-hop Question Generation with Graph Convolutional Network (2020.findings-emnlp)

Copied to clipboard

Dan Su, Yan Xu, Wenliang Dai, Ziwei Ji, Tiezheng Yu, Pascale Fung

Text Generation

Challenge:	Existing studies on text-based QG focus on generating SQuAD-style questions.
Approach:	They propose a multi-hop question generation model that does context encoding in multiple hops with Graph Convolutional Network and encoder fusion via an Encoder Reasoning Gate.
Outcome:	Empirical results show that the proposed model generates fluent questions with high completeness and outperforms baselines on automatic evaluation metrics.

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

Copied to clipboard

Ruiqi Zhong, Tao Yu, Dan Klein

Programming Languages in NLP

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.

Affect inTweets: A Transfer Learning Approach (2020.lrec-1)

Copied to clipboard

Linrui Zhang, Hsin-Lun Huang, Yang Yu, Dan Moldovan

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

Challenge:	Existing machine learning models require considerable effort to design task specific features to understand affectual states of people.
Approach:	They propose a transfer-learning based approach to infer the affectual state of a person from tweets.
Outcome:	The proposed model ranks 2nd, 4th and 6th in four of the four subtasks on SemEval-2018 task 1: Affect in Tweets.

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.

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

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

Information Extraction & Text Mining

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.

NusaCrowd: Open Source Initiative for Indonesian NLP Resources (2023.findings-acl)

Copied to clipboard

Samuel Cahyawijaya, Holy Lovenia, Alham Fikri Aji, Genta Winata, Bryan Wilie, Fajri Koto, Rahmad Mahendra, Christian Wibisono, Ade Romadhony, Karissa Vincentio, Jennifer Santoso, David Moeljadi, Cahya Wirawan, Frederikus Hudi, Muhammad Satrio Wicaksono, Ivan Parmonangan, Ika Alfina, Ilham Firdausi Putra, Samsul Rahmadani, Yulianti Oenang, Ali Septiandri, James Jaya, Kaustubh Dhole, Arie Suryani, Rifki Afina Putri, Dan Su, Keith Stevens, Made Nindyatama Nityasya, Muhammad Adilazuarda, Ryan Hadiwijaya, Ryandito Diandaru, Tiezheng Yu, Vito Ghifari, Wenliang Dai, Yan Xu, Dyah Damapuspita, Haryo Wibowo, Cuk Tho, Ichwanul Karo Karo, Tirana Fatyanosa, Ziwei Ji, Graham Neubig, Timothy Baldwin, Sebastian Ruder, Pascale Fung, Herry Sujaini, Sakriani Sakti, Ayu Purwarianti

Challenge:	Existing NLP research in Indonesian languages has been held back by factors such as language diversity, orthographic variation, resource limitation and other societal challenges.
Approach:	They present a collaborative initiative to collect and unify existing resources for Indonesian languages and open access to previously non-public resources.
Outcome:	The results show that the datasets are highly reliable and can be used to generate the first zero-shot benchmarks for natural language understanding and generation in Indonesian and the local languages of Indonesia.

Budget-Aware Anytime Reasoning with LLM-Synthesized Preference Data (2026.findings-acl)

Copied to clipboard

Xuanming Zhang, Shwan Ashrafi, Aziza Mirsaidova, Amir H. Rezaeian, Miguel Ballesteros, Lydia Chilton, Zhou Yu, Dan Roth

Hyperbolic Geometry is Not Necessary: Lightweight Euclidean-Based Models for Low-Dimensional Knowledge Graph Embeddings (2021.findings-emnlp)

Challenge:	Recent work has explored reasoning efficiency via test-time scaling and early exit strategies.
Approach:	They propose an anytime reasoning framework and the Anytime Index to improve model quality . they also propose an inference-time self-improvement method to produce better intermediate solutions .
Outcome:	The proposed method improves on NaturalPlan, AIME, and GPQA datasets and improves reasoning quality and efficiency under budget constraints.

Copied to clipboard

Kai Wang, Yu Liu, Dan Lin, Michael Sheng

Design Challenges in Low-resource Cross-lingual Entity Linking (2020.emnlp-main)

Challenge:	Recent knowledge graph embedding models based on hyperbolic geometry are complicated than Euclidean operations.
Approach:	They propose to use hyperbolic geometry to generate high-fidelity and parsimonious representations of hierarchical patterns in knowledge graphs.
Outcome:	The proposed models achieve state-of-the-art performance on two widely-used datasets and cost less than RotH.

Copied to clipboard

Xingyu Fu, Weijia Shi, Xiaodong Yu, Zian Zhao, Dan Roth

Low-Resource NLP

Challenge:	Existing techniques for grounding mentions of entities in a foreign language do not rise to the challenges introduced by text in low-resource languages (LRL) and fail to generalize to text not taken from Wikipedia, on which they are usually trained.
Approach:	They propose a cross-lingual XEL technique that uses search engines to locate and search for foreign language entries in Wikipedia.
Outcome:	The proposed system shows an increase of 25% in gold candidate recall and 13% in end-to-end linking accuracy over state-of-the-art baselines.

Generative Pre-trained Speech Language Model with Efficient Hierarchical Transformer (2024.acl-long)

Copied to clipboard

Yongxin Zhu, Dan Su, Liqiang He, Linli Xu, Dong Yu

Speech & Audio in NLP

Challenge:	Experimental results indicate that GPST significantly outperforms the existing speech language models in terms of word error rate, speech quality, and speaker similarity.
Approach:	They propose a hierarchical transformer that quantizes audio waveforms into two distinct types of discrete speech representations and integrates them within a transformer architecture.
Outcome:	The proposed model outperforms existing speech language models in word error rate, speech quality, and speaker similarity.

Learning to Decompose: Hypothetical Question Decomposition Based on Comparable Texts (2022.emnlp-main)

Copied to clipboard

Ben Zhou, Kyle Richardson, Xiaodong Yu, Dan Roth

Responsible & Trustworthy NLP

Challenge:	Existing approaches to end-to-end questionanswering assume that pre-trained language can decompose complex tasks into more straightforward sub-tasks.
Approach:	They propose to use distant supervision to train decomposition-based transformers for large-scale parallel news.
Outcome:	The proposed model improves on semantic parsing and on hotpotQA and strategyQA datasets by 20% to 30%.

MoE Adapter for Large Audio Language Models: Sparsity, Disentanglement, and Gradient-Conflict-Free (2026.findings-acl)

Copied to clipboard

Yishu Lei, Shuwei He, Hu Jing, Dan Zhang, Xianlong Luo, Danxiang Zhu, Shikun Feng, Rui Liu, Jingzhou HE, Yu Sun, Hua Wu, Haifeng Wang

AndroidLab: Training and Systematic Benchmarking of Android Autonomous Agents (2025.acl-long)

Challenge:	Existing research on Large Language Models (LLMs) limited to textual input modality . acoustic information is intrinsically heterogeneous, entangling attributes such as speech, music, and environmental context.
Approach:	They propose a sparse Mixture-of-Experts architecture to decouple acoustic information by routing audio tokens to specialized experts.
Outcome:	The proposed architecture outperforms existing models on audio semantic and paralinguistic tasks while retaining shared experts for global context.

Copied to clipboard

Yifan Xu, Xiao Liu, Xueqiao Sun, Siyi Cheng, Hao Yu, Hanyu Lai, Shudan Zhang, Dan Zhang, Jie Tang, Yuxiao Dong

Improve Query Focused Abstractive Summarization by Incorporating Answer Relevance (2021.findings-acl)

Challenge:	Existing studies on Android agents lack systematic research on open-source and closed-source models.
Approach:	They propose a framework for Android agents that includes an operation environment and a reproducible benchmark.
Outcome:	The proposed framework lifts the success rate of open-source LLMs and LMMs from 4.59% to 21.50% for LLM and 1.93% to 13.28% for LMM.

Copied to clipboard

Dan Su, Tiezheng Yu, Pascale Fung

Summarization

Challenge:	Query focused summarization models aim to generate summaries from source documents that can answer the given query.
Approach:	They propose a QFS-BART model that incorporates the explicit answer relevance of the source documents given the query via a question answering model.
Outcome:	Empirical results show that the proposed model achieves the new state-of-the-art performance.

Generic Temporal Reasoning with Differential Analysis and Explanation (2023.acl-long)

Copied to clipboard

Yu Feng, Ben Zhou, Haoyu Wang, Helen Jin, Dan Roth

Responsible & Trustworthy NLP

Challenge:	Existing temporal reasoning models drop to random guessing on TODAY, suggesting that they heavily rely on spurious information rather than proper reasoning for temporal predictions.
Approach:	They propose a task called TODAY that evaluates whether systems can correctly understand the effect of incremental changes in temporal relation distributions.
Outcome:	The proposed task outperforms existing models, including GPT-3.5, on in-domain benchmarks while allowing for more appropriate annotations.

ConEC: Earnings Call Dataset with Real-world Contexts for Benchmarking Contextual Speech Recognition (2024.lrec-main)

Copied to clipboard

Ruizhe Huang, Mahsa Yarmohammadi, Jan Trmal, Jing Liu, Desh Raj, Leibny Paola Garcia, Alexei V. Ivanov, Patrick Ehlen, Mingzhi Yu, Dan Povey, Sanjeev Khudanpur

Auto-Instruct: Automatic Instruction Generation and Ranking for Black-Box Language Models (2023.findings-emnlp)

Challenge:	Existing work on contextual speech recognition (ASR) systems focuses on recognizing words that are not frequently seen in training data, such as rare words, but word error rate on rare words remains over 20%.
Approach:	They propose to use public-domain earnings calls and supplementary materials to evaluate contextual ASR approaches grounded on real-world applications.
Outcome:	The proposed frameworks are noisier than artificially synthesized contexts that contain the ground truth, yet still make great room for future improvement of contextual ASR technology.

Copied to clipboard

Zhihan Zhang, Shuohang Wang, Wenhao Yu, Yichong Xu, Dan Iter, Qingkai Zeng, Yang Liu, Chenguang Zhu, Meng Jiang

HumT DumT: Measuring and controlling human-like language in LLMs (2025.acl-long)

Challenge:	Large language models can perform a wide range of tasks by following natural language instructions without task-specific fine-tuning.
Approach:	They propose a method to automatically improve the quality of LLM instructions . they leverage the generative ability of LMS to generate diverse candidate instructions based on a scoring model trained on 575 existing NLP tasks.
Outcome:	The proposed method surpasses human-written and LLM-generated instructions on 118 out-of-domain tasks.

Copied to clipboard

Myra Cheng, Sunny Yu, Dan Jurafsky

Challenge:	Human-like language might improve user experience, but might also lead to deception, overreliance, and stereotyping.
Approach:	They introduce HumT and SocioT, metrics for human-like tone in LLM outputs . HumT measures human-type tone and other dimensions of social perceptions in text data .
Outcome:	The proposed method reduces human-like tone while preserving model performance.

Generation of Patient After-Visit Summaries to Support Physicians (2022.coling-1)

Copied to clipboard

Pengshan Cai, Fei Liu, Adarsha Bajracharya, Joe Sills, Alok Kapoor, Weisong Liu, Dan Berlowitz, David Levy, Richeek Pradhan, Hong Yu

Challenge:	After-visit summary is a summary note given to patients after their clinical visit.
Approach:	They propose to automate the generation of after-visit summaries and introduce a feedback mechanism that alerts physicians when an automatic summary fails to capture important details of the clinical notes.
Outcome:	The proposed system improves on a large clinical dataset that contains electronic health record (EHR) notes and their associated summaries.

Federated Retrieval Augmented Generation for Multi-Product Question Answering (2025.coling-industry)

Copied to clipboard

Parshin Shojaee, Sai Sree Harsha, Dan Luo, Akash Maharaj, Tong Yu, Yunyao Li

Information Retrieval

Challenge:	Existing multi-domain RAG-QA approaches query all domains indiscriminately or rely on rigid resource selection.
Approach:	They propose a multi-product knowledge-augmented QA framework with probabilistic federated search across domains and relevant knowledge.
Outcome:	The proposed framework improves multi-product knowledge-augmented QA performance on Adobe products.

MM-LLMs: Recent Advances in MultiModal Large Language Models (2024.findings-acl)

Copied to clipboard

Duzhen Zhang, Yahan Yu, Jiahua Dong, Chenxing Li, Dan Su, Chenhui Chu, Dong Yu

Intention Knowledge Graph Construction for User Intention Relation Modeling (2026.eacl-long)

Challenge:	MultiModal Large Language Models (MM-LLMs) have undergone significant advances in the past year . traditional MM models incur substantial computational costs, especially when trained from scratch .
Approach:	They propose a taxonomy encompassing 126 MM-LLMs and summarize key training recipes to enhance their potency.
Outcome:	The proposed models preserve the reasoning and decision-making capabilities of LLMs and empower diverse range of MM tasks.

Copied to clipboard

Jiaxin Bai, Zhaobo Wang, Junfei Cheng, Dan Yu, Zerui Huang, Weiqi Wang, Xin Liu, Chen Luo, Yanming Zhu, Bo Li, Yangqiu Song

Improving Personalized Sentiment Representation with Knowledge-enhanced and Parameter-efficient Layer Normalization (2024.lrec-main)

Challenge:	Existing knowledge graphs focus on connecting intentions but lacks the ability to model the relationships between different intentions.
Approach:	They propose a framework to automatically generate an intention knowledge graph, capturing connections between user intentions.
Outcome:	The proposed model outperforms state-of-the-art methods and shows its utility.

Copied to clipboard

You Zhang, Jin Wang, Liang-Chih Yu, Dan Xu, Xuejie Zhang