Papers by Hongfei Lin

Exploring the Capability of Multimodal LLMs with Yonkoma Manga: The YManga Dataset and Its Challenging Tasks (2024.findings-emnlp)

Challenge:	Existing methods for unlearning large language models struggle to balance effective forgetting with maintaining model utility.
Approach:	They propose a human-inspired unlearning framework that simulates forgetting on fuzzy data and represents them in hyperbolic and Euclidean spaces.
Outcome:	The proposed framework is able to forget sensitive content while maintaining the model’s language understanding, fluency, and benchmark performance.

Copied to clipboard

Qi Yang, Jingjie Zeng, Liang Yang, Zhihao Yang, Hongfei Lin

Sarcasm-R1: Enhancing Sarcasm Detection through Focused Reasoning (2025.findings-emnlp)

Challenge:	YManga dataset is the first specifically designed for yonkoma manga understanding .
Approach:	They propose to use a dataset of 1,015 yonkoma strips with 10,150 human annotations to define three tasks for panel sequence detection, intent generation and description generation for masked panels.
Outcome:	The proposed dataset contains 1,015 high-quality yonkoma strips with 10,150 human annotations.

Copied to clipboard

Qi Yang, Jingjie Zeng, Liang Yang, Kai Ma, Hongfei Lin

MultiCMET: A Novel Chinese Benchmark for Understanding Multimodal Metaphor (2023.findings-emnlp)

Challenge:	Existing methods for sarcasm detection are limited by supervised learning or prompt engineering . a new approach decomposes sarcasm detection into three dimensions: language, context, and emotion .
Approach:	They propose a method that decomposes sarcasm detection into three dimensions: language, context, and emotion.
Outcome:	The proposed method outperforms state-of-the-art methods in most cases.

Copied to clipboard

Dongyu Zhang, Jingwei Yu, Senyuan Jin, Liang Yang, Hongfei Lin

Beyond Linguistic Cues: Fine-grained Conversational Emotion Recognition via Belief-Desire Modelling (2024.lrec-main)

Challenge:	Existing research on multimodal metaphors does not address categorizing the source and target domains in metaphors beyond the English language.
Approach:	They propose a Cascading Domain Knowledge Integration benchmark to detect metaphors by introducing domain-specific lexical features.
Outcome:	The proposed dataset includes 13,820 text-image pairs of advertisements with manual annotations of the occurrence of metaphors, domain categories, and sentiments metaphors convey.

Copied to clipboard

Bo Xu, Longjiao Li, Wei Luo, Mehdi Naseriparsa, Zhehuan Zhao, Hongfei Lin, Feng Xia

OD-RTE: A One-Stage Object Detection Framework for Relational Triple Extraction (2023.acl-long)

Challenge:	Emotion recognition in conversation (ERC) is essential for dialogue systems to identify the emotions expressed by speakers.
Approach:	They propose a method that incorporates both belief and desire to accurately identify emotions by extracting emotion-eliciting events from utterances and construct graphs that represent beliefs and desires in conversations.
Outcome:	The proposed model outperforms existing models on four popular ERC datasets and validates its performance with multiple state-of-the-art models.

Copied to clipboard

Jinzhong Ning, Zhihao Yang, Yuanyuan Sun, Zhizheng Wang, Hongfei Lin

Information Extraction & Text Mining

Challenge:	Existing pipelines for relational triple extraction are underutilizing regional information of triple.
Approach:	They propose a one-stage Object Detection framework for Relational Triple Extraction . framework uses vertices-based bounding box detection and global relational triple region detection .
Outcome:	The proposed framework could extract all types of triples on two widely used datasets.

It’s Not Bragging If You Can Back It Up: Can LLMs Understand Braggings? (2025.acl-long)

Copied to clipboard

Jingjie Zeng, Huayang Li, Liang Yang, Yuanyuan Sun, Hongfei Lin

Challenge:	Bragging is a pervasive social-linguistic phenomenon that reflects complex human interaction patterns.
Approach:	They propose to use bragging recognition, bragging explanation, and bragging generation tasks to examine bragging in large language models (LLMs) .
Outcome:	The proposed models can identify bragging intent, social appropriateness, and account for context sensitivity and provide new insights into how LLMs process bragging.

PclGPT: A Large Language Model for Patronizing and Condescending Language Detection (2024.findings-emnlp)

Copied to clipboard

Hongbo Wang, LiMingDa LiMingDa, Junyu Lu, Hebin Xia, Liang Yang, Bo Xu, Ruizhu Liu, Hongfei Lin

Joint Entity and Relation Extraction for Legal Documents with Legal Feature Enhancement (2020.coling-main)

Challenge:	Patronizing and condescending language is an essential branch of toxic language . pre-trained language models perform poorly in detecting PCL due to its implicit toxicity traits .
Approach:	They propose a novel LLM benchmark for patronizing and condescending language . they use a dataset to analyze the toxicity of patronizing condescending languages .
Outcome:	The proposed model can detect patronizing and condescending language (PCL) the model can be used to analyze the toxicity of the language and to improve the detection.

Copied to clipboard

Yanguang Chen, Yuanyuan Sun, Zhihao Yang, Hongfei Lin

Information Extraction & Text Mining

Challenge:	Existing methods for information extraction are based on pipelining to extract entities from unstructured judgment documents . a large number of judgment documents are released on China Judgments Online .
Approach:	They propose a legal triplet extraction system for drug-related criminal judgment documents . they annotate a dataset for Named Entity Recognition and Relation Extraction in Chinese legal domain .
Outcome:	The proposed system extracts entities and semantic relations jointly and benefits from the proposed legal lexicon feature and multi-task learning framework.

Just Like a Human Would, Direct Access to Sarcasm Augmented with Potential Result and Reaction (2023.acl-long)

Copied to clipboard

Changrong Min, Ximing Li, Liang Yang, Zhilin Wang, Bo Xu, Hongfei Lin

Leveraging Social Context for Humor Recognition and Sense of Humor Evaluation in Social Media with a New Chinese Humor Corpus - HumorWB (2024.lrec-main)

Challenge:	sarcasm is a form of irony conveying mockery and contempt . social media has become increasingly popular for identifying sarcasm .
Approach:	They develop a method to detect sarcasm from social media using augmented potentials.
Outcome:	The proposed method outperforms baselines on benchmark datasets.

Copied to clipboard

Zeyuan Zeng, Zefeng Li, Liang Yang, Hongfei Lin

Reasoning

Challenge:	Existing humor computing research focuses on content while neglecting interaction relationships in social media.
Approach:	They propose a dataset which introduces social context information from social media . they propose 'humor recognition' task and 'horror evaluation task'
Outcome:	The proposed model incorporates social context information from social media . it shows that it is efficient and can be used to evaluate humor in real life .

Is LLM an Overconfident Judge? Unveiling the Capabilities of LLMs in Detecting Offensive Language with Annotation Disagreement (2025.findings-acl)

Copied to clipboard

Junyu Lu, Kai Ma, Kaichun Wang, Kelaiti Xiao, Roy Ka-Wei Lee, Bo Xu, Liang Yang, Hongfei Lin

Telling the Whole Story: A Manually Annotated Chinese Dataset for the Analysis of Humor in Jokes (D19-1)

Challenge:	Existing studies focus on evaluating large language models' ability to handle disagreement cases.
Approach:	They evaluate the performance of large language models in detecting offensive language at varying levels of agreement.
Outcome:	The proposed model improves detection accuracy and model alignment with human judgment by using disagreement samples in training.

Copied to clipboard

Dongyu Zhang, Heting Zhang, Xikai Liu, Hongfei Lin, Feng Xia

Reasoning

Challenge:	Humor plays important role in human communication, which makes it important problem for natural language processing.
Approach:	They propose a novel annotation scheme to give scenarios of how humor arises in text . they report reasonable agreement between annotators and analyze the dataset .
Outcome:	The proposed scheme gives scenarios of how humor arises in text . it contains key words that trigger humor, character relationship, scene, and humor categories .

CogEvolve: A Multimodal Benchmark for Evaluating Relational Reasoning in Semantic Extension (2026.acl-long)

Copied to clipboard

Jingjie Zeng, Huayang Li, Liang Yang, Yuanyuan Sun, Shaowu Zhang, Hongfei Lin

RealMedDial: A Real Telemedical Dialogue Dataset Collected from Online Chinese Short-Video Clips (2022.coling-1)

Challenge:	a gap exists between human embodied logic and machine statistical learning . authors: models internalize statistical patterns or mimic static recognition .
Approach:	They propose a cognitive linguistic benchmark to test whether large language models internalize statistical logic or not . they find that models function as "Super-Associators" expert at static recognition yet fail at causal reasoning .
Outcome:	The proposed model fails at causal reasoning and has a high-fidelity concept representation but lacks transformational operators essential for true relational understanding.

Copied to clipboard

Bo Xu, Hongtong Zhang, Jian Wang, Xiaokun Zhang, Dezhi Hao, Linlin Zong, Hongfei Lin, Fenglong Ma

Dialogue Systems & Conversational Agents

Challenge:	Existing medical dialogue systems are limited by the lack of corpora and data from real scenarios.
Approach:	They construct a Chinese medical dialogue dataset based on real medical consultations.
Outcome:	The proposed dataset is applicable to a wide range of NLP tasks with respect to medical dialogue.

STATE ToxiCN: A Benchmark for Span-level Target-Aware Toxicity Extraction in Chinese Hate Speech Detection (2025.findings-acl)

Copied to clipboard

Zewen Bai, Liang Yang, Shengdi Yin, Junyu Lu, Jingjie Zeng, Haohao Zhu, Yuanyuan Sun, Hongfei Lin

Ethical NLP

Challenge:	Existing studies on Chinese hate speech detection lack span-level fine-grained annotations.
Approach:	They construct a Span-level target-aware Toxicity Extraction dataset and evaluate existing models for Chinese hateful slang.
Outcome:	The proposed dataset is the first span-level Chinese hate speech dataset and evaluates the ability of existing models to understand hate semantics.

Prototype Tuning: A Meta-Learning Approach for Few-Shot Document-Level Relation Extraction with Large Language Models (2025.findings-naacl)

Copied to clipboard

Dinghao Pan, Yuanyuan Sun, Bo Xu, Jiru Li, Zhihao Yang, Ling Luo, Hongfei Lin, Jian Wang

HyperHatePrompt: A Hypergraph-based Prompting Fusion Model for Multimodal Hate Detection (2025.coling-main)

Challenge:	Few-Shot Document-Level Relation Extraction (FSDLRE) aims to develop models capable of generalizing to new categories with minimal support examples.
Approach:	They propose a meta-training approach to train Large Language Models to improve their ICL capabilities . they construct simulated episodes using relation types that do not overlap with test corpus .
Outcome:	Experimental results show that the proposed approach outperforms baseline models on few-shot tasks.

Copied to clipboard

Bo Xu, Erchen Yu, Jiahui Zhou, Hongfei Lin, Linlin Zong

Breaking the Boundaries: A Unified Framework for Chinese Named Entity Recognition Across Text and Speech (2024.findings-emnlp)

Challenge:	Existing models for multimodal hate detection lack implicit hateful cues, cross-modal-induced hate, and diversity of hate target groups.
Approach:	They propose a hypergraph-based prompting fusion model that uses LLMs to generate hate cue prompts and hypergraph learning to merge multimodal hate features.
Outcome:	The proposed model outperforms state-of-the-art models on two benchmark datasets showing that it can detect hate content across multiple modalities.

Copied to clipboard

Jinzhong Ning, Yuanyuan Sun, Bo Xu, Zhihao Yang, Ling Luo, Hongfei Lin

“Barking up the Right Tree”, a GAN-Based Pun Generation Model through Semantic Pruning (2024.lrec-main)

Challenge:	Existing approaches to Named Entity Recognition (NER) tasks are limited by the complexity of the data and the potential connections between tasks.
Approach:	They propose a task to break the boundaries between different modal NER tasks by using a unified data format for inputs from different modalités.
Outcome:	The proposed task breaks the boundaries between different modal NER tasks and is a unified implementation of them.

Copied to clipboard

JingJie Zeng, Liang Yang, Jiahao Kang, Yufeng Diao, Zhihao Yang, Hongfei Lin

LLM-Driven Implicit Target Augmentation and Fine-Grained Contextual Modeling for Zero-Shot and Few-Shot Stance Detection (2025.emnlp-main)

Challenge:	Existing methods for generating humorous puns are limited and require a broad spectrum of commonsense and worldly skills.
Approach:	They propose a GAN-based approach that employs semantic pruning and contrastive learning to generate humorous puns using a model that captures the semantic nuances of puns.
Outcome:	The proposed model produces semantically coherent and humorous puns while ensuring both correctness and humor.

Copied to clipboard

Yanxu Ji, Jinzhong Ning, Yijia Zhang, Zhi Liu, Hongfei Lin

MultiMET: A Multimodal Dataset for Metaphor Understanding (2021.acl-long)

Challenge:	Recent studies on zero-shot and few-shot stance detection neglect implicit yet semantically important targets.
Approach:	They propose a framework that uses Large Language Models to annotate implicit targets . they also propose 'DyMCA' to dynamically adjust text-target contributions based on context .
Outcome:	The proposed framework achieves state-of-the-art on a benchmark dataset.

Copied to clipboard

Dongyu Zhang, Minghao Zhang, Heting Zhang, Liang Yang, Hongfei Lin

Construction of a Chinese Corpus for the Analysis of the Emotionality of Metaphorical Expressions (P18-2)

Challenge:	Metaphor is a linguistic phenomenon and a cognitive phenomenon structuring human thought, authors say . previous studies focused on texts, partly due to the unavailability of ground truth labels of multimodal metaphor .
Approach:	They propose a multimodal metaphor dataset that integrates multimodal text and image . it contains 10,437 text-image pairs with multimodal annotations of occurrences .
Outcome:	The proposed dataset examines multimodal cues and their interplay.

Copied to clipboard

Dongyu Zhang, Hongfei Lin, Liang Yang, Shaowu Zhang, Bo Xu

E2E-GMNER: End-to-End Generative Grounded Multimodal Named Entity Recognition (2026.findings-acl)

Challenge:	a corpus of 5,605 manually annotated sentences in Chinese is described . emotion is an abstract and vague conception, which is often described by metaphor .
Approach:	They propose to construct a corpus of metaphors annotated with emotion in Chinese . they use an annotation scheme to include linguistic metaphors, emotional categories and intensity .
Outcome:	The proposed corpus contains 5,605 manually annotated sentences in Chinese . the authors show that the corpus is large enough to analyze emotions .

Copied to clipboard

Meng Zhang, Jinzhong Ning, Xiaolong Wu, Hongfei Lin, Yijia Zhang

GLA: Grounding Large Language Models in Molecular Hierarchy for Chemical Understanding (2026.findings-acl)

Challenge:	Existing approaches decouple textual entity recognition and visual grounding, leading to error accumulation and suboptimal joint optimization.
Approach:	They propose a fully end-to-end generative framework that unifies recognition, semantic typing, visual grounding and implicit knowledge reasoning within a single multimodal large language model.
Outcome:	The proposed framework achieves highly competitive performance compared with state-of-the-art methods.

Copied to clipboard

Yingxu Li, Jingjie Zeng, Zekun Wang, Hongfei Lin, Liang Yang

Breakthrough from Nuance and Inconsistency: Enhancing Multimodal Sarcasm Detection with Context-Aware Self-Attention Fusion and Word Weight Calculation. (2024.lrec-main)

Challenge:	Existing molecule-language models obscure the hierarchical organization of chemical semantics . Existing models rely on linear or uniform encodings, causing structural distortion .
Approach:	They propose a framework that integrates intrinsic molecular topology into large language models.
Outcome:	The proposed framework improves on cross-modal retrieval, captioning, and property prediction benchmarks.

Copied to clipboard

Hongfei Xue, Linyan Xu, Yu Tong, Rui Li, Jiali Lin, Dazhi Jiang

Mechanistic Insights into Deferred Semantic Drift in LLMs (2026.findings-acl)

Challenge:	Existing methods for sarcasm detection rely on feature concatenation to fuse different modalities or model inconsistencies among modalités.
Approach:	They propose to use Context-Aware Self-Attention Fusion to integrate local and momentary multimodal information into specific words to illustrate the inconsistencies between connotation and denotation.
Outcome:	The proposed method achieves an accuracy of 76.9 and an F1 score of 76.1 on the MUStARD dataset, surpassing the current state-of-the-art IWAN model by 1.7 and 1.6 respectively.

Copied to clipboard

Jingjie Zeng, Huayang Li, Liang Yang, Shaowu Zhang, Yuanyuan Sun, Hongfei Lin

Challenge:	Large Language Models (LLMs) face a fundamental challenge with delayed disambiguation: how can a model update the meaning of an early, ambiguous token when clarifying context only appears later in the sequence?
Approach:	They propose a method to defer semantic re-evaluation to subsequent tokens in a process they call "Deferred Semantic Drift" they demonstrate this mechanism in metaphor comprehension and provide causal validation by steering model outputs towards literal or metaphorical meanings via targeted activation interventions.
Outcome:	The proposed model can update the meaning of an ambiguous word when clarifying context arrives only after it has been processed.

Two Languages Are Better than One: Bilingual Enhancement for Chinese Named Entity Recognition (2022.coling-1)

Copied to clipboard

Jinzhong Ning, Zhihao Yang, Zhizheng Wang, Yuanyuan Sun, Hongfei Lin, Jian Wang

Information Extraction & Text Mining

Challenge:	Existing studies focus on internal features of Chinese named entity recognition, but neglect other lingual modalities.
Approach:	They propose a bilingual enhancement module for Chinese Named Entity Recognition . they integrate rich English information into Chinese representation and use it to learn the interaction between bilinguals and dependent information within Chinese.
Outcome:	The proposed model can learn the interaction of bilinguals and dependent information within Chinese.

Cultural Bias Matters: A Cross-Cultural Benchmark Dataset and Sentiment-Enriched Model for Understanding Multimodal Metaphors (2025.acl-long)

Copied to clipboard

Senqi Yang, Dongyu Zhang, Jing Ren, Ziqi Xu, Xiuzhen Zhang, Yiliao Song, Hongfei Lin, Feng Xia

Sheep’s Skin, Wolf’s Deeds: Are LLMs Ready for Metaphorical Implicit Hate Speech? (2025.acl-long)

Challenge:	Metaphors are pervasive in communication, making them crucial for natural language processing.
Approach:	They propose a multicultural multimodal metaphor dataset designed for cross-cultural studies of metaphor in Chinese and English.
Outcome:	The proposed model improves metaphor comprehension across cultural backgrounds and cultural domains.

Copied to clipboard

Jingjie Zeng, Liang Yang, Zekun Wang, Yuanyuan Sun, Hongfei Lin

Locality Preserving Sentence Encoding (2021.findings-emnlp)

Challenge:	specialized models fail to detect implicit hate speech due to its indirectly expressed hateful intent . advanced LLMs often misinterpret metaphorical implicit hate content, resulting in its propagation .
Approach:	They propose a Jailbreaking strategy and Energy-based Constrained Decoding techniques to detect implicit hate speech in large language models.
Outcome:	The proposed model can generate metaphorical implicit hate speech, but it fails to detect it effectively.

Copied to clipboard

Changrong Min, Yonghe Chu, Liang Yang, Bo Xu, Hongfei Lin

Commonality and Individuality! Integrating Humor Commonality with Speaker Individuality for Humor Recognition (2025.naacl-long)

Challenge:	Existing word embeddings can be used to learn sentence embedds on the sentence level.
Approach:	They propose a sentence embedding method that uses the inner product to compute semantic similarity between sentences.
Outcome:	The proposed method encodes sentences better in the sense of semantic structures.

Copied to clipboard

Haohao Zhu, Xiaokun Zhang, Zeyuan Zeng, Junyu Lu, Zewen Bai, Liang Yang, Hongfei Lin

Commonsense Reasoning

Challenge:	Current methods for humor recognition focus on one aspect of humor commonalities, ignoring the multifaceted nature of humor.
Approach:	They propose a commonality and individuality incorporated network for humor recognition that integrates multifaceted humor commonalities with speaker individuality.
Outcome:	The proposed model integrates multifaceted humor commonalities with speaker individuality to deepen the understanding of humor expressions.

Take Its Essence, Discard Its Dross! Debiasing for Toxic Language Detection via Counterfactual Causal Effect (2024.lrec-main)

Copied to clipboard

Junyu Lu, Bo Xu, Xiaokun Zhang, Kaiyuan Liu, Dongyu Zhang, Liang Yang, Hongfei Lin

LOTUS: Evolving Multimodal Unlearning via Hyperbolic Entailment and Lorentz Transport (2026.acl-long)

Challenge:	Existing methods to mitigate lexical bias in toxic language detection (TLD) do not exploit the “useful” and “misleading” impact of the bias.
Approach:	They propose a counterfactual Causal Debiasing Framework to mitigate lexical bias in toxic language detection (TLD) it preserves the “useful impact” of lexical bias and eliminates the "misleading impact" they propose to use the same framework to analyze the causal effect of a sentence and bias tokens .
Outcome:	The proposed framework preserves the “useful impact” of lexical bias and eliminates the ‘misleading impact’ Empirical evaluations show that the proposed model outperforms current debiased models for out-of-distribution data.

Copied to clipboard

Zekun Wang, Jingjie Zeng, Yingxu Li, Hongfei Lin, Liang Yang

Label-Enhanced Hierarchical Contextualized Representation for Sequential Metaphor Identification (2021.emnlp-main)

Challenge:	Existing unlearning methods suffer from a geometric mismatch, causing catastrophic forgetting or unsafe substitution.
Approach:	They propose a framework for surgical semantic pruning within the Lorentz manifold.
Outcome:	Experiments on MLLMU-Bench show that LOTUS significantly outperforms baselines while maintaining general utility.

Copied to clipboard

Shuqun Li, Liang Yang, Weidong He, Shiqi Zhang, Jingjie Zeng, Hongfei Lin

Representation Learning

Challenge:	Recent approaches to identify metaphors ignore extra information from data, such as contextual information and broader discourse information.
Approach:	They propose a model augmented with hierarchical contextualized representation to extract more information from both sentence-level and discourse-level.
Outcome:	The proposed model outperforms state-of-the-art methods on two tasks using a VUA dataset.

WildFeedback: Aligning LLMs With In-situ User Interactions And Feedback (2026.acl-long)

Copied to clipboard

Taiwei Shi, Zhuoer Wang, Longqi Yang, Ying-Chun Lin, Zexue He, Mengting Wan, Pei Zhou, Sujay Kumar Jauhar, Sihao Chen, Shan Xia, Hongfei Zhang, Jieyu Zhao, Xiaofeng Xu, Xia Song, Jennifer Neville

Challenge:	Traditional alignment methods rely on human annotations and are subjective and misalignment with real-world user preferences.
Approach:	They propose a framework that leverages in-situ user feedback during conversations with LLMs to create preference datasets automatically.
Outcome:	The proposed framework identifies and classifies user feedback to LLM responses between conversation turns and creates examples of preferred and dispreferred responses according to user preferences.

Hate Speech Detection Based on Sentiment Knowledge Sharing (2021.acl-long)

Copied to clipboard

Xianbing Zhou, Yang Yong, Xiaochao Fan, Ge Ren, Yunfeng Song, Yufeng Diao, Liang Yang, Hongfei Lin

Facilitating Fine-grained Detection of Chinese Toxic Language: Hierarchical Taxonomy, Resources, and Benchmarks (2023.acl-long)

Challenge:	Existing methods for hate speech detection are stereotyped and biased . et al., a paper examining the effectiveness of multitask learning in hate speech recognition tasks .
Approach:	They propose a hate speech detection framework based on sentiment knowledge sharing . they extract affective features of the target sentence and use sentiment features from external resources .
Outcome:	The proposed model can detect hate speech over two public datasets.

Copied to clipboard

Junyu Lu, Bo Xu, Xiaokun Zhang, Changrong Min, Liang Yang, Hongfei Lin

Challenge:	Existing datasets suffer from a lack of fine-grained annotations, such as the toxic type and expressions with indirect toxicity.
Approach:	They propose a benchmark model to detect toxic language by incorporating lexical features into a Chinese dataset to facilitate fine-grained annotations.
Outcome:	The proposed model is based on insulting vocabulary containing implicit profanity and is able to detect toxic language with lexical features.

WECA: A WordNet-Encoded Collocation-Attention Network for Homographic Pun Recognition (D18-1)

Copied to clipboard

Yufeng Diao, Hongfei Lin, Di Wu, Liang Yang, Kan Xu, Zhihao Yang, Jian Wang, Shaowu Zhang, Bo Xu, Dongyu Zhang