Papers by Lijie Hu

Automatic Table Union Search with Tabular Representation Learning (2023.findings-acl)

Challenge:	Existing methods for relation extraction use heuristics or distant-supervised annotations, but distant supervised methods make strong assumptions on entity cooccurrence without sufficient contexts.
Approach:	They propose a framework that exploits weak, self-supervised signals by leveraging large pretrained language models for adaptive clustering on contextualized relational features.
Outcome:	The proposed framework exploits weak, self-supervised signals on open-domain Relation Extraction . it bootstraps the self-supervised signals by improving contextualized features in relation classification .

Copied to clipboard

Xuming Hu, Shen Wang, Xiao Qin, Chuan Lei, Zhengyuan Shen, Christos Faloutsos, Asterios Katsifodimos, George Karypis, Lijie Wen, Philip S. Yu

Flattery in Motion: Benchmarking and Analyzing Sycophancy in Video-LLMs (2026.acl-long)

Challenge:	Existing methods to identify uniability based on column representations are insufficient to reveal latent relational features to describe column relation between pair of columns.
Approach:	They propose a self-supervised table union search framework called AutoTUS to learn column relational representations in a multi-stage manner.
Outcome:	The proposed framework improves on the SOTA baseline and on real-world datasets.

Copied to clipboard

Wenrui Zhou, Mohamed Hendy, Shu Yang, Qingsong Yang, Zikun Guo, Yuyu Luo, Lijie Hu, Di Wang

Multimodality

Challenge:	Current sycophancy research has largely overlooked its specific manifestations in the video-language domain.
Approach:	They propose a video-LLM sycophancy benchmarking and evaluation to evaluate scophancies in video-LLMs.
Outcome:	The proposed benchmark evaluates sycophantic behavior in state-of-the-art Video-LLMs across diverse question formats, prompt biases, and visual reasoning tasks.

CHEF: A Pilot Chinese Dataset for Evidence-Based Fact-Checking (2022.naacl-main)

Copied to clipboard

Xuming Hu, Zhijiang Guo, GuanYu Wu, Aiwei Liu, Lijie Wen, Philip Yu

Responsible & Trustworthy NLP

Challenge:	CHEF dataset provides evidence retrieval over non-English claims . e-fact-checking is a time-consuming task, which can take journalists several hours or days.
Approach:	They construct a dataset of 10K real-world claims that is based on annotated evidence retrieved from the Internet.
Outcome:	The proposed dataset provides evidence retrieval as a latent variable and can be used to train and reason over non-English claims.

HiURE: Hierarchical Exemplar Contrastive Learning for Unsupervised Relation Extraction (2022.naacl-main)

Copied to clipboard

Shuliang Liu, Xuming Hu, Chenwei Zhang, Shu’ang Li, Lijie Wen, Philip Yu

Understanding How Value Neurons Shape the Generation of Specified Values in LLMs (2025.findings-emnlp)

Challenge:	Existing methods to extract relational feature signals from natural language sentences use self-supervised clustering and classification that cause gradual drift problems.
Approach:	They propose a framework that derives hierarchical signals from relational feature space using cross hierarchy attention and effectively optimizes relation representation of sentences under exemplar-wise contrastive learning.
Outcome:	The proposed framework can extract the relationship between entities from natural language sentences without prior knowledge on relation scope or distribution.

Copied to clipboard

Yi Su, Jiayi Zhang, Shu Yang, Xinhai Wang, Lijie Hu, Di Wang

Explainability & Interpretability in NLP

Challenge:	Current approaches to interpret value representations are limited by superficial judgments over mechanistic analysis.
Approach:	They propose a mechanistic interpretability framework that uses the Schwartz Values Survey to interpret value . they use a dataset that operationalizes four dimensions of universal value through behavioral contexts .
Outcome:	The proposed method bridges psychological value frameworks with neuron analysis in large language models.

Visual Self-Fulfilling Alignment: Shaping Safety-Oriented Personas via Threat-Related Images (2026.acl-long)

Copied to clipboard

Qishun Yang, Shu Yang, Lijie Hu, Di Wang

Visual Data in NLP

Challenge:	Existing methods require explicit safety labels or contrastive data, yet visual inputs enable harmful outputs.
Approach:	They propose a visual self-fulfilling alignment mechanism that fine-tunes vision-language models on neutral VQA tasks without any safety labels.
Outcome:	The proposed approach reduces attack success rate, improves response quality, and mitigates over-refusal while preserving general capabilities.

Character-level White-Box Adversarial Attacks against Transformers via Attachable Subwords Substitution (2022.emnlp-main)

Copied to clipboard

Aiwei Liu, Honghai Yu, Xuming Hu, Shu’ang Li, Li Lin, Fukun Ma, Yawen Yang, Lijie Wen

Robustness in NLP

Challenge:	Existing methods to attack transformer models are not effective at character level, but they are a natural attack scenario.
Approach:	They propose a character-level adversarial attack method against transformer models . they use a gradient-based method to find the most vulnerable words in a sentence .
Outcome:	The proposed method outperforms previous methods on sentence-level and token-level tasks.

Private Language Models via Truncated Laplacian Mechanism (2024.emnlp-main)

Copied to clipboard

Tianhao Huang, Tao Yang, Ivan Habernal, Lijie Hu, Di Wang

COMPKE: Complex Question Answering under Knowledge Editing (2025.findings-acl)

Challenge:	Existing methods for word embedding are prone to privacy leakage, resulting in weaker relaxations of DP that are inferior to the canonical DP in terms of privacy strength.
Approach:	They propose a method for private word embedding that uses a non-trivial extension of the truncated Laplacian mechanism and propose to test its effectiveness.
Outcome:	The proposed method has lower variance compared to the previous methods.

Copied to clipboard

Keyuan Cheng, Zijian Kan, Zhuoran Zhang, Muhammad Asif Ali, Lijie Hu, Di Wang

Natural Language Interfaces

Challenge:	Existing benchmarks for knowledge editing do not accurately evaluate how well models apply knowledge in real-life situations.
Approach:	They propose a benchmark to evaluate how well updated models apply new knowledge in real-life situations.
Outcome:	The proposed method achieves 39.47 accuracy on GPT-4o-mini but drops significantly to 3.83 on Qwen2.5-3B.

Gradient Imitation Reinforcement Learning for Low Resource Relation Extraction (2021.emnlp-main)

Copied to clipboard

Xuming Hu, Chenwei Zhang, Yawen Yang, Xiaohe Li, Li Lin, Lijie Wen, Philip S. Yu

Low-Resource NLP

Challenge:	Existing methods to extract relation facts from limited labeled corpora are laborintensive to obtain . Existing approaches use self-training to generate pseudo labels that will cause gradual drift problem or leverage meta-learning scheme which does not solicit feedback explicitly.
Approach:	They propose a Gradient Imitation Reinforcement Learning method to encourage pseudo label data to imitate gradient descent direction on labeled data and bootstrap its optimization capability through trial and error.
Outcome:	The proposed method handles two major scenarios in low-resource relation extraction when no unlabeled data is available.

Entity-to-Text based Data Augmentation for various Named Entity Recognition Tasks (2023.findings-acl)

Copied to clipboard

Xuming Hu, Yong Jiang, Aiwei Liu, Zhongqiang Huang, Pengjun Xie, Fei Huang, Lijie Wen, Philip S. Yu

CODEMENV: Benchmarking Large Language Models on Code Migration (2025.findings-acl)

Challenge:	Existing augmentation techniques manipulate words in the original text that break the semantic coherence of the text, or exploit generative models that ignore preserving entities in the text.
Approach:	They propose a novel Entity-to-Text based data augmentation technique called EnTDA to add, delete, replace or swap entities in the original text.
Outcome:	The proposed technique generates semantically coherent and entity preserving texts on thirteen NER tasks and two settings.

Copied to clipboard

Keyuan Cheng, Xudong Shen, Yihao Yang, TengyueWang TengyueWang, Yang Cao, Muhammad Asif Ali, Hanbin Wang, Lijie Hu, Di Wang

Deciphering Cultural Representations in Large Language Models via Sparse Autoencoders (2026.findings-acl)

Challenge:	Large language models (LLMs) have demonstrated remarkable proficiency in handling a wide range of tasks within the software engineering domain, but their ability to perform code migration—adapting code to different environments—remains underexplored.
Approach:	They propose a benchmark to evaluate large language models’ performance in handling code migration tasks.
Outcome:	The proposed benchmark comprises 922 data points across 19 Python and Java packages and offers three tasks to systematically evaluate code migration: identifying version-incompatible functions, determining function changes, and adapting code to target environments.

Copied to clipboard

Chenye Zou, Difan Jiao, Lijie Hu

On the Robustness of Document-Level Relation Extraction Models to Entity Name Variations (2024.findings-acl)

Challenge:	Prior work has identified so-called cultural neurons, but individual neurons are often polysemous, conflating abstract cultural knowledge with surface-level lexical cues due to superposition.
Approach:	They apply Sparse Autoencoders to decompose LLM activations into sparse, interpretable feature representations that disentangle culturally selective features.
Outcome:	The proposed model disentangles culturally selective features from paraphrasing and task formats, indicating abstraction beyond lexical correlations.

Copied to clipboard

Shiao Meng, Xuming Hu, Aiwei Liu, Fukun Ma, Yawen Yang, Shuang Li, Lijie Wen

Can LLM Watermarks Robustly Prevent Unauthorized Knowledge Distillation? (2025.acl-long)

Challenge:	Existing DocRE models which perform well may make more mistakes when merely changing the entity names in the document, hindering the generalization to novel entity names.
Approach:	They propose a pipeline to generate entity-renamed documents by replacing the original entity names with names from Wikidata.
Outcome:	The proposed pipeline generates entity-renamed documents by replacing the original entity names with names from Wikidata.

Copied to clipboard

Leyi Pan, Aiwei Liu, Shiyu Huang, Yijian Lu, Xuming Hu, Lijie Wen, Irwin King, Philip S. Yu

Responsible & Trustworthy NLP

Challenge:	Large Language Model (LLM) watermarking is radioactive and enables the detection of watermarks inherited by student models when trained on the outputs of watermarked teacher models.
Approach:	They propose two types of watermark removal attacks that allow student models to perform untraceable knowledge distillation while avoiding watermark inheritance.
Outcome:	The proposed attacks eliminate inherited watermarks while maintaining knowledge transfer efficiency and low computational overhead.

Fraud-R1 : A Multi-Round Benchmark for Assessing the Robustness of LLM Against Augmented Fraud and Phishing Inducements (2025.findings-acl)

Copied to clipboard

Shu Yang, Shenzhe Zhu, Zeyu Wu, Keyu Wang, Junchi Yao, Junchao Wu, Lijie Hu, Mengdi Li, Derek F. Wong, Di Wang

Robustness in NLP

Challenge:	Existing fraud detection benchmarks focus on single-turn classification tasks, failing to capture dynamic nature of real-world fraud attempts.
Approach:	They propose a bilingual benchmark to assess LLMs' ability to resist fraud and phishing attacks across five key fraud categories: Fraudulent Services, Impersonation, Phishing Scams, Fake Job Postings, and Online Relationships.
Outcome:	The proposed model improves in role-play settings and in e-commerce and recommendation systems.

Differentially Private Natural Language Models: Recent Advances and Future Directions (2024.findings-eacl)

Copied to clipboard

Lijie Hu, Ivan Habernal, Lei Shen, Di Wang

Responsible & Trustworthy NLP

Challenge:	Recent advances in deep learning have led to great success in various natural language processing tasks.
Approach:	They propose a systematic review of recent advances in DP deep learning models . they discuss some differences and additional challenges of DP-NLP .
Outcome:	The proposed method can prevent reconstruction attacks and protect against potential side knowledge while maintaining the privacy of sensitive data.

RAPL: A Relation-Aware Prototype Learning Approach for Few-Shot Document-Level Relation Extraction (2023.emnlp-main)

Copied to clipboard

Shiao Meng, Xuming Hu, Aiwei Liu, Shuang Li, Fukun Ma, Yawen Yang, Lijie Wen

Dissecting Fine-Tuning Unlearning in Large Language Models (2024.emnlp-main)

Challenge:	Existing methods to identify semantic relations between entities are time-consuming and labor-intensive.
Approach:	They propose a relation-aware prototype learning method for document-level relation extraction (FSDLRE) they propose RAPL, which judiciously leverages relation descriptions and real NOTA instances as guidance .
Outcome:	The proposed method outperforms state-of-the-art approaches by 2.61% F1 . it generates task-specific NOTA prototypes and refines relation prototypes .

Copied to clipboard

Yihuai Hong, Yuelin Zou, Lijie Hu, Ziqian Zeng, Di Wang, Haiqin Yang

Understanding the Repeat Curse in Large Language Models from a Feature Perspective (2025.findings-acl)

Challenge:	Existing methods for fine-tuning-based unlearning are ineffective at completely erasing model-embedded knowledge, but their true effectiveness remains unclear.
Approach:	They propose to use activation patching and parameter restoration experiments to examine the limitations of fine-tuning-based unlearning methods for erasing harmful, sensitive, or copyrighted information within large language models.
Outcome:	The proposed methods alter the model’s knowledge retrieval process rather than genuinely erasing the problematic knowledge embedded in the model parameters.

Copied to clipboard

Junchi Yao, Shu Yang, Jianhua Xu, Lijie Hu, Mengdi Li, Di Wang

MarkLLM: An Open-Source Toolkit for LLM Watermarking (2024.emnlp-demo)

Challenge:	Large language models suffer from repetitive text generation, a phenomenon we refer to as the ”Repeat Curse”.
Approach:	They propose a method to induce and analyze the Repeat Curse in large language models by using mechanistic interpretability.
Outcome:	The proposed method induces and analyzes the Repeat Curse in large language models using mechanistic interpretability.

Copied to clipboard

Leyi Pan, Aiwei Liu, Zhiwei He, Zitian Gao, Xuandong Zhao, Yijian Lu, Binglin Zhou, Shuliang Liu, Xuming Hu, Lijie Wen, Irwin King, Philip Yu

LLMArena: Assessing Capabilities of Large Language Models in Dynamic Multi-Agent Environments (2024.acl-long)

Challenge:	Large Language Models (LLMs) embed imperceptible yet algorithmically detectable signals in outputs to identify LLM-generated text.
Approach:	They propose to develop an open-source toolkit for LLM watermarking that embeds imperceptible yet algorithmically detectable signals in model outputs to identify LLM-generated text.
Outcome:	MarkLLM provides a unified framework for implementing LLM watermarking algorithms, while providing user-friendly interfaces to ensure ease of access.

Copied to clipboard

Junzhe Chen, Xuming Hu, Shuodi Liu, Shiyu Huang, Wei-Wei Tu, Zhaofeng He, Lijie Wen

AMR-based Network for Aspect-based Sentiment Analysis (2023.acl-long)

Challenge:	Existing benchmarks for evaluating large language models use static datasets, leading to data leakage or overlooking the complexities of multi-agent interactions.
Approach:	They propose a framework that evaluates the diverse capabilities of LLM agents in multi-agent dynamic environments.
Outcome:	The proposed framework assesses the diverse capabilities of LLM agents in multi-agent dynamic environments.

Copied to clipboard

Fukun Ma, Xuming Hu, Aiwei Liu, Yawen Yang, Shuang Li, Philip S. Yu, Lijie Wen

Can Large Language Models Identify Implicit Suicidal Ideation? An Empirical Evaluation (2025.findings-emnlp)

Challenge:	Recent studies have used dependency trees to extract relation between aspects and contexts, but there is a potential mismatch between the dependency tree and sentiment classification as a semantic task.
Approach:	They propose to replace the syntactic dependency tree with a semantic structure to capture the relation between an aspect and a context.
Outcome:	The proposed model improves ABSA on four public datasets with 1.13% improvement over baselines.

Copied to clipboard

Tong Li, Shu Yang, Junchao Wu, Jiyao Wei, Lijie Hu, Mengdi Li, Derek F. Wong, Joshua R. Oltmanns, Di Wang

Evaluating Robustness of Generative Search Engine on Adversarial Factoid Questions (2024.findings-acl)

Challenge:	Existing data on suicidal ideation in private conversations are limited . a new dataset of 1,200 test cases is presented to address this gap .
Approach:	They propose a dataset of 1,200 test cases simulating implicit suicidal ideation in private contexts.
Outcome:	The proposed dataset includes 1,200 test cases simulating implicit suicidal ideation in dialogue scenarios.

Copied to clipboard

Xuming Hu, Xiaochuan Li, Junzhe Chen, Yinghui Li, Yangning Li, Xiaoguang Li, Yasheng Wang, Qun Liu, Lijie Wen, Philip Yu, Zhijiang Guo

Robustness in NLP

Challenge:	Existing large language models (LLMs)-backed generative search engines may not always be accurate.
Approach:	They propose to evaluate the robustness of retrieval-augmented generation in a realistic and high-risk setting where adversaries have only black-box system access.
Outcome:	The proposed model exhibits higher susceptibility to factual errors compared to LLMs without retrieval.

Enhancing Cross-lingual Natural Language Inference by Soft Prompting with Multilingual Verbalizer (2023.findings-acl)

Copied to clipboard

Shuang Li, Xuming Hu, Aiwei Liu, Yawen Yang, Fukun Ma, Philip S. Yu, Lijie Wen

Low-Resource NLP

Challenge:	Existing approaches to cross-lingual natural language inference lack annotated parallel corpora.
Approach:	They propose a new prompt learning framework with the Multilingual Verbalizer for XNLI that uses a multilingual verbalizer to align the representations of original and augmented multilingual questions into a unified semantic space with consistency regularization.
Outcome:	The proposed framework outperforms existing methods under few-shot and full-shot cross-lingual transfer settings.

Scene Graph Modification as Incremental Structure Expanding (2022.coling-1)

Copied to clipboard

Xuming Hu, Zhijiang Guo, Yu Fu, Lijie Wen, Philip S. Yu

Multimodality

Challenge:	Scene graphs are used in cross-modal tasks such as image retrieval, image captioning, and visual question answering.
Approach:	They propose a model that iterates between nodes prediction and edges prediction . they frame scene graph modification as a graph expansion task by introducing incremental structure expanding .
Outcome:	The proposed model surpasses the state-of-the-art model by large margins on four benchmarks.

Semi-supervised Relation Extraction via Incremental Meta Self-Training (2021.findings-emnlp)

Copied to clipboard

Xuming Hu, Chenwei Zhang, Fukun Ma, Chenyao Liu, Lijie Wen, Philip S. Yu

UniMEEC: Towards Unified Multimodal Emotion Recognition and Emotion Cause (2024.findings-emnlp)

Challenge:	Existing methods suffer from the gradual drift problem, where noisy pseudo labels are incorporated during training.
Approach:	They propose a method that uses pseudo labels to assess quality on unlabeled samples . they use a relation label generation network to learn from successful and failed attempts .
Outcome:	Experimental results show the proposed method can improve on two public datasets.

Copied to clipboard

Guimin Hu, Zhihong Zhu, Daniel Hershcovich, Lijie Hu, Hasti Seifi, Jiayuan Xie