Papers by Hao Fang

Dual Adversarial Neural Transfer for Low-Resource Named Entity Recognition (P19-1)

Challenge:	Existing dialogue models struggle to interpret context accurately due to irrelevant or misclassified knowledge, limiting their effectiveness in real-world scenarios.
Approach:	They propose a framework that dynamically filters relevant commonsense knowledge and extracts personalized information to improve empathetic dialogue generation.
Outcome:	The proposed framework outperforms existing models in coherence, emotional understanding, and response relevance on the ESConv dataset.

Copied to clipboard

Joey Tianyi Zhou, Hao Zhang, Di Jin, Hongyuan Zhu, Meng Fang, Rick Siow Mong Goh, Kenneth Kwok

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

Challenge:	Named entity recognition (NER) is an important step in most natural language processing (NLP) applications.
Approach:	They propose a dual-adversarial neural transfer method for addressing low-resource Named Entity Recognition (NER) they propose 'Generalized Resource-Adversarial Discriminator' and 'accidental training'
Outcome:	The proposed method improves on low-resource Named Entity Recognition (NER) with two variants, i.e., DATNet-F and DATNET-P, and adversarial training is adopted to boost model generalization.

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

Multimodality

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 .

DevEval: A Manually-Annotated Code Generation Benchmark Aligned with Real-World Code Repositories (2024.findings-acl)

Copied to clipboard

Jia Li, Ge Li, Yunfei Zhao, Yongmin Li, Huanyu Liu, Hao Zhu, Lecheng Wang, Kaibo Liu, Zheng Fang, Lanshen Wang, Jiazheng Ding, Xuanming Zhang, Yuqi Zhu, Yihong Dong, Zhi Jin, Binhua Li, Fei Huang, Yongbin Li, Bin Gu, Mengfei Yang

A Survey of Ontology Expansion for Conversational Understanding (2024.emnlp-main)

Challenge:	Existing benchmarks are poorly aligned with real-world code repositories and are insufficient to evaluate the coding abilities of Large Language Models (LLMs).
Approach:	They propose a repository-level benchmark named DevEval to evaluate LLMs' coding abilities in real-world code repositories.
Outcome:	The proposed benchmarks show that the LLMs perform better in real-world code repositories than existing benchmarks.

Copied to clipboard

Jinggui Liang, Yuxia Wu, Yuan Fang, Hao Fei, Lizi Liao

Natural Language Interfaces

Challenge:	Current methods for conversational understanding rely on static ontologies, limiting their ability to handle new and unforeseen user needs.
Approach:	They propose to review the state-of-the-art techniques in OnExp for conversational understanding and highlight emerging frontiers . they categorize existing literature into three main areas: (1) New Intent Discovery, (2) New Slot-Value Discovery, and (3) Joint OnExp.
Outcome:	The proposed methods highlight several emerging frontiers in OnExp to improve agent performance in real-world scenarios and discuss their corresponding challenges.

Language-to-Code Translation with a Single Labeled Example (2024.emnlp-main)

Copied to clipboard

Kaj Bostrom, Harsh Jhamtani, Hao Fang, Sam Thomson, Richard Shin, Patrick Xia, Benjamin Van Durme, Jason Eisner, Jacob Andreas

Text Generation

Challenge:	In-Context Inverse Programming (ICIP) bootstraps a language-to-code system using mostly unlabeled programs written using a potentially unfamiliar library or API.
Approach:	They propose a method for bootstrapping a language-to-code system using mostly unlabeled programs written using a potentially unfamiliar library or API.
Outcome:	The proposed method outperforms baselines across nine domains and 100 examples in a “nearly unsupervised” setting.

The Whole Truth and Nothing But the Truth: Faithful and Controllable Dialogue Response Generation with Dataflow Transduction and Constrained Decoding (2023.findings-acl)

Copied to clipboard

Hao Fang, Anusha Balakrishnan, Harsh Jhamtani, John Bufe, Jean Crawford, Jayant Krishnamurthy, Adam Pauls, Jason Eisner, Jacob Andreas, Dan Klein

Learning Auxiliary Tasks Improves Reference-Free Hallucination Detection in Open-Domain Long-Form Generation (2025.acl-short)

Challenge:	In a task-oriented dialogue system, response generation is a conditional language model, but effective dialogue agents must balance fluent generation with stricter constraints.
Approach:	They propose a rule-based content selection model that transduces a dialogue agent’s actions and their results into context-free grammars representing the space of contextually acceptable responses.
Outcome:	The proposed architecture outperforms both rule-based and learned approaches in human evaluations of fluency, relevance, and truthfulness.

Copied to clipboard

Chengwei Qin, Wenxuan Zhou, Karthik Abinav Sankararaman, Nanshu Wang, Tengyu Xu, Alexander Radovic, Eryk Helenowski, Arya Talebzadeh, Aditya Tayade, Sinong Wang, Shafiq Joty, Han Fang, Hao Ma

Reasoning

Challenge:	Existing methods for detecting hallucination in long-form tasks focus on limited domains or rely heavily on external fact-checking tools, which may not always be available.
Approach:	They propose a new paradigm that augments fine-tuning with an auxiliary task for the model to jointly learn with the main task of hallucination detection.
Outcome:	The proposed method outperforms existing methods for detecting hallucination in open-domain long-form generation and is more accurate than random guessing.

Retrievals Can Be Detrimental: Unveiling the Backdoor Vulnerability of Retrieval-Augmented Diffusion Models (2026.acl-long)

Copied to clipboard

Hao Fang, Xiaohang Sui, Hongyao Yu, Kuofeng Gao, Jiawei Kong, Sijin Yu, Bin Chen, Shu-Tao Xia

Compositional Generalization for Neural Semantic Parsing via Span-level Supervised Attention (2021.naacl-main)

Challenge:	Retrieval-augmented diffusion models (RDMs) have been developed to enhance performance with reduced parameters.
Approach:	They propose to integrate retrieval-augmented diffusion models with Retrieval-augmented generation (RAG) that enhances performance with reduced parameters.
Outcome:	The proposed framework achieves outstanding attack effects while maintaining benign utility.

Copied to clipboard

Pengcheng Yin, Hao Fang, Graham Neubig, Adam Pauls, Emmanouil Antonios Platanios, Yu Su, Sam Thomson, Jacob Andreas

Semantic Text Processing

Challenge:	Existing approaches to compositional generalization in semantic parsers focus on word-level alignments, but they focus on spans.
Approach:	They propose a span-level supervised attention loss that improves compositional generalization in semantic parsers by focusing on spans.
Outcome:	The proposed method improves on three benchmarks of compositional generalization.

DualGuard: Dual-stream Large Language Model Watermarking Defense against Paraphrase and Spoofing Attack (2026.findings-acl)

Copied to clipboard

Hao Li, Yubing Ren, Yanan Cao, Yingjie Li, Fang Fang, Shi Wang, Li Guo

Robustness in NLP

Challenge:	Existing watermarking algorithms focus on defending against paraphrase and piggyback spoofing attacks, which can inject harmful content, compromise reliability, and undermine trust in attribution.
Approach:	They propose an algorithm capable of defending against paraphrase and spoofing attacks.
Outcome:	Experiments on large language models and language models show that DualGuard is the first watermarking algorithm capable of defending against both paraphrase and spoofing attacks.

Beyond Coarse Labels: Fine-Grained Problem Augmentation and Multi-Dimensional Feedback for Emotional Support Conversation (2025.findings-emnlp)

Copied to clipboard

Yuanchen Shi, Jiawang Hao, Fang Kong

DIDS: Domain Impact-aware Data Sampling for Large Language Model Training (2025.emnlp-main)

Challenge:	Existing ESC datasets often use coarse-grained problem categories, limiting models’ ability to address users’ complex, overlapping challenges.
Approach:	They propose a generalizable fine-grained problem enhancement method that augments problem types, user scenarios, and profiles, enabling the construction of richer and more diverse ESC corpora.
Outcome:	The proposed method improves both automatic and human evaluation metrics across different models.

Copied to clipboard

Weijie Shi, Jipeng Zhang, Yaguang Wu, Jingzhi Fang, Shibo Zhang, Yao Zhao, Hao Chen, Ruiyuan Zhang, Yue Cui, Jia Zhu, Sirui Han, Jiajie Xu, Xiaofang Zhou

Task-Aware Specialization for Efficient and Robust Dense Retrieval for Open-Domain Question Answering (2023.acl-short)

Challenge:	Existing approaches for optimizing domain-level sampling strategies struggle with maintaining intra-domain consistency and accurately measuring domain impact.
Approach:	They propose to use a Fisher-Information Matrix-guided metric to measure domain impact to ensure intra-domain consistency and accuracy.
Outcome:	The proposed model achieves 3.4% higher average performance while maintaining comparable training efficiency.

Copied to clipboard

Hao Cheng, Hao Fang, Xiaodong Liu, Jianfeng Gao

Beyond Hard Masks: Progressive Token Evolution for Diffusion Language Models (2026.acl-long)

Challenge:	Existing dense retrieval models are parameter-inefficient and underperform sparse counterparts.
Approach:	They propose a task-aware specialization for dEnse Retrieval architecture that enables parameter sharing by interleaving shared and specialized blocks in a single encoder.
Outcome:	The proposed architecture surpasses BM25 on questions and passages using 60% of the parameters as bi-encoder dense retrievers.

Copied to clipboard

Linhao Zhong, Linyu Wu, Bozhen Fang, Tianjian Feng, Chenchen Jing, Wen Wang, Jiaheng Zhang, Hao Chen, Chunhua Shen

MPL: Multiple Programming Languages with Large Language Models for Information Extraction (2025.findings-acl)

Challenge:	Existing Diffusion Language Models rely on hard binary masking and discrete token assignments, which hinder the revision of early decisions.
Approach:	They propose a diffusion-based language modeling approach that replaces hard binary masks with evolving soft token distributions.
Outcome:	The proposed approach outperforms existing DLMs on multiple benchmarks.

Copied to clipboard

Bo Li, Gexiang Fang, Wei Ye, Zhenghua Xu, Jinglei Zhang, Hao Cheng, Shikun Zhang

Semantic Text Processing

Challenge:	Existing research focuses on Python for code-style simulation, overlooking the potential of other widely-used PLs during the supervised fine-tuning phase.
Approach:	They propose a framework that incorporates programming languages into IE tasks . they introduce function-prompt with virtual running to simulate code-style inputs .
Outcome:	The proposed framework exploits the potential of different programming languages during the supervised fine-tuning phase.

Scalable-DSC: A Structural Template Prompt Approach to Scalable Dialogue State Correction (2023.emnlp-main)

Copied to clipboard

Haoxiang Su, Hongyan Xie, Hao Huang, Shuangyong Song, Ruiyu Fang, Xiaomeng Huang, Sijie Feng

When Efficiency Meets Safety: A Benchmark Security Analysis of KV Cache Compression in Large Language Models (2026.acl-long)

Challenge:	Existing approaches to correct wrong slot values in dialogue state tracking are intertwined with specific DST models, limiting their applicability to other DSTs.
Approach:	They propose a Scalable Dialogue State Correction model that corrects wrong slot values in predicted dialogue states by using a structural template prompt.
Outcome:	The proposed model achieves state-of-the-art results on MultiWOZ 2.0-2.4.

Copied to clipboard

Xiaoxiao Ma, Kuofeng Gao, Zeyi Lu, Wenxi Jiang, Hao Fang, Hao Wu, Bin Chen, Shu-Tao Xia

TLM: Token-Level Masking for Transformers (2023.emnlp-main)

Challenge:	Key-Value (KV) caching is widely used in large language models to enable long-context inference efficiently, yet its security implications remain underexplored.
Approach:	They propose a history-aware, per-head feedback merging strategy that prevents safety degradation while maintaining efficiency.
Outcome:	The proposed strategy prevents safety degradation while maintaining efficiency.

Copied to clipboard

Yangjun Wu, Kebin Fang, Dongxiang Zhang, Han Wang, Hao Zhang, Gang Chen

Benchmarking Commonsense Knowledge Base Population with an Effective Evaluation Dataset (2021.emnlp-main)

Challenge:	Structured dropout approaches have been investigated to regularize the multi-head attention mechanism in Transformers.
Approach:	They propose a new regularization scheme based on token-level rather than structure-level to reduce overfitting by manipulating the connections between tokens in the multi-head attention via masking.
Outcome:	The proposed regularization scheme outperforms attention dropout and DropHead on 18 datasets and can establish a new record on the data-to-text benchmark Rotowire (18.93 BLEU).

Copied to clipboard

Tianqing Fang, Weiqi Wang, Sehyun Choi, Shibo Hao, Hongming Zhang, Yangqiu Song, Bin He

Reasoning

Challenge:	Existing evaluations on the population task are either not accurate (automatic evaluation with randomly sampled negative examples) or of small scale (human annotation).
Approach:	They propose a reasoning over commonsense knowledge bases (CSKBs) that are free-text and have a human annotation set to probe commonsensical reasoning.
Outcome:	The proposed model is based on a human-annotated evaluation set and is compared with existing models on the population task.

DEIE: Benchmarking Document-level Event Information Extraction with a Large-scale Chinese News Dataset (2024.lrec-main)

Copied to clipboard

Yubing Ren, Yanan Cao, Hao Li, Yingjie Li, Zixuan ZM Ma, Fang Fang, Ping Guo, Wei Ma

Information Extraction & Text Mining

Challenge:	Existing event-based datasets mainly target sentence-level tasks . current models struggle with "document" annotation, a key feature of the current model .
Approach:	They propose a large-scale document-level event information extraction dataset with over 56,000+ events and 242,000+ arguments.
Outcome:	The proposed dataset has over 56,000+ events and 242,000+ arguments.

Intra-Event and Inter-Event Dependency-Aware Graph Network for Event Argument Extraction (2023.findings-emnlp)

Copied to clipboard

Hao Li, Yanan Cao, Yubing Ren, Fang Fang, Lanxue Zhang, Yingjie Li, Shi Wang

Multimodality

Challenge:	Existing models do not build dependency information among event argument roles . Existing methods do not learn the interactions between different roles based on event structure .
Approach:	They propose an intra-event and inter-e event dependency-aware graph network to model dependencies between roles . they use event structure as the fundamental unit to construct role dependencies within events .
Outcome:	The proposed model improves on the ACE05, RAMS, and WikiEvents datasets.

Multi-Defendant Legal Judgment Prediction via Hierarchical Reasoning (2023.findings-emnlp)

Copied to clipboard

Yougang Lyu, Jitai Hao, Zihan Wang, Kai Zhao, Shen Gao, Pengjie Ren, Zhumin Chen, Fang Wang, Zhaochun Ren

Reasoning

Challenge:	Existing methods for predicting judgment results for multiple defendants are ineffective.
Approach:	They propose a method to predict the judgment results for each defendant in multi-defendant cases . they formalize the multi-diffendant judgment process as hierarchical reasoning chains .
Outcome:	The proposed method can predict the judgment results for multiple defendants in multi-defendant cases.

Effective Long-Context Scaling of Foundation Models (2024.naacl-long)

Copied to clipboard

Wenhan Xiong, Jingyu Liu, Igor Molybog, Hejia Zhang, Prajjwal Bhargava, Rui Hou, Louis Martin, Rashi Rungta, Karthik Abinav Sankararaman, Barlas Oguz, Madian Khabsa, Han Fang, Yashar Mehdad, Sharan Narang, Kshitiz Malik, Angela Fan, Shruti Bhosale, Sergey Edunov, Mike Lewis, Sinong Wang, Hao Ma

Do Vision-Language Models Have Internal World Models? Towards an Atomic Evaluation (2025.findings-acl)

Challenge:	Large language models (LLMs) are rapidly deployed and continue to evolve through scaling.
Approach:	They propose a method to train strong long-context LLMs that are capable of utilizing massive context windows of up to 32,000 tokens.
Outcome:	The proposed model can surpass gpt-3.5-turbo-16k's overall performance on long-context benchmarks with a cost-effective instruction tuning procedure that is free of expensive annotations.

Copied to clipboard

Qiyue Gao, Xinyu Pi, Kevin Liu, Junrong Chen, Ruolan Yang, Xinqi Huang, Xinyu Fang, Lu Sun, Gautham Kishore, Bo Ai, Stone Tao, Mengyang Liu, Jiaxi Yang, Chao-Jung Lai, Chuanyang Jin, Jiannan Xiang, Benhao Huang, Zeming Chen, David Danks, Hao Su, Tianmin Shu, Ziqiao Ma, Lianhui Qin, Zhiting Hu

When More Data Hurts: A Troubling Quirk in Developing Broad-Coverage Natural Language Understanding Systems (2022.emnlp-main)

Challenge:	Recent studies have evaluated and shown limitations in specific capabilities such as visual understanding, but a systematic evaluation of VLMs’ fundamental WM abilities remains absent.
Approach:	They propose a framework that assesses perception and prediction to provide an atomic evaluation of VLMs as WMs.
Outcome:	The proposed framework assesses perception and prediction abilities on 15 latest VLMs and compares them to human-level models.

Copied to clipboard

Elias Stengel-Eskin, Emmanouil Antonios Platanios, Adam Pauls, Sam Thomson, Hao Fang, Benjamin Van Durme, Jason Eisner, Yu Su

Challenge:	In natural language understanding systems, users’ evolving needs necessitate the addition of new features over time, indexed by new symbols added to the meaning representation space.
Approach:	They propose to use a small set of new symbols to build broad-coverage NLU systems.
Outcome:	The proposed model is based on two prototypical NLU tasks: intent recognition and semantic parsing.

Infinite Babble: Inflating 3D Vision-Language Model Inference Overhead via Adversarial Geometric Perturbation (2026.findings-acl)

Copied to clipboard

Shuoyang Sun, Jiaxin Hong, Yv Zhang, Kuofeng Gao, Hao Fang, Fan Mo, Bin Chen, Shu-Tao Xia

Robustness in NLP

Challenge:	3D Vision-Language Models (VLMs) are critical cognitive backbone for spatial intelligence, but their reliance on autoregressive decoding introduces a fundamental vulnerability regarding inference efficiency.
Approach:	They propose a framework that triggers computational and economic exhaustion in 3D-VLMs by injecting imperceptible noise that forces the model into a state of pathological verbosity.
Outcome:	The proposed framework amplifies output length and energy consumption by up to 6.45, demonstrating a potent capability to drain system resources.

LLMs in the Imaginarium: Tool Learning through Simulated Trial and Error (2024.acl-long)

Copied to clipboard

Boshi Wang, Hao Fang, Jason Eisner, Benjamin Van Durme, Yu Su

GLiM: Integrating Graph Transformer and LLM for Document-Level Biomedical Relation Extraction with Incomplete Labeling (2025.findings-acl)

Challenge:	Existing work on tool-augmented LLMs focuses on the broad coverage of tools and the flexibility of adding new tools.
Approach:	They propose a biologically inspired method for tool-augmented LLMs that orchestrates three key mechanisms for successful tool use behaviors in the biological system: trial and error, imagination, and memory.
Outcome:	The proposed method improves tool learning for LLMs under both in-context learning and fine-tuning settings, bringing a boost of 46.7% to Mistral-Instruct-7B and outperforms GPT-4.

Copied to clipboard

Hao Fang, Yuejie Zhang, Rui Feng, Yingwen Wang, Qing Wang, Wen He, Xiaobo Zhang, Tao Zhang, Shang Gao

Information Extraction & Text Mining

Challenge:	Document-level relation extraction (DocRE) solves problems of document quality . number of entities and entity-pair relations increases, causing incomplete annotations .
Approach:	a framework that reduces the problem space using a graph-enhanced Transformer-based model is proposed . GLiM leverages large language models for reasoning to reduce the problem-space .
Outcome:	GLiM boosts average recall and F1 scores on biomedical datasets . compared with existing models, GLim outperforms existing models on biomedicine benchmarks compared to existing models .

INT: Establishing Information Transfer for Multilingual Intent Detection and Slot Filling (2025.findings-acl)

Copied to clipboard

Di Wu, Liting Jiang, Bohui Mao, Hongyan Xie, Haoxiang Su, Zhongjiang He, Ruiyu Fang, Shuangyong Song, Hao Huang, Xuelong Li

Sentiment Analysis

Challenge:	Existing studies struggle to achieve performance comparable to that on high-resource languages due to inherent linguistic diversity of multilingual SLU tasks.
Approach:	They propose a multilingual information transfer network to solve these challenges . they propose to reformulate SF as a span prediction problem and introduce a slot-matching attention mechanism to achieve slot alignment across languages.
Outcome:	The proposed model outperforms baseline models on the MASSIVE and MASSIV-UG datasets in overall accuracy across all languages.

Sounding Board: A User-Centric and Content-Driven Social Chatbot (N18-5)

Copied to clipboard

Hao Fang, Hao Cheng, Maarten Sap, Elizabeth Clark, Ari Holtzman, Yejin Choi, Noah A. Smith, Mari Ostendorf

A Dynamic Speaker Model for Conversational Interactions (N19-1)

Challenge:	Sounding Board is a social chatbot that can hold a coherent conversation with humans . the system is user-centric in that users can control the topic of conversation, while the system adapts to the user's needs.
Approach:	They present Sounding Board, a social chatbot that won the 2017 Amazon Alexa Prize.
Outcome:	The system is user-centric in that users can control the topic of conversation, while the system adapts to the user's needs.

Copied to clipboard

Hao Cheng, Hao Fang, Mari Ostendorf

OpenRLHF: A Ray-based Easy-to-use, Scalable and High-performance RLHF Framework (2025.emnlp-demos)

Challenge:	a neural model for characterizing individual differences in speakers is shown to be useful in human-computer interaction and dialog act prediction.
Approach:	They propose a neural model for learning a dynamically updated speaker embedding in a conversational context.
Outcome:	The proposed model is used for content ranking and dialog act prediction in human-human conversations.

Copied to clipboard

Jian Hu, Xibin Wu, Wei Shen, Jason Klein Liu, Weixun Wang, Songlin Jiang, Haoran Wang, Hao Chen, Bin Chen, Wenkai Fang, null Xianyu, Yu Cao, Haotian Xu, Yiming Liu