Papers by Fei Yuan

Text Diffusion Model with Encoder-Decoder Transformers for Sequence-to-Sequence Generation (2024.naacl-long)

Challenge:	Existing benchmarks and MLLMs focus on single-image input scenarios, leaving performance of ML models when handling multiple images underexplored.
Approach:	They propose a benchmark to evaluate fine-grained abilities of multimodal large language models in multi-image scenarios.
Outcome:	The proposed benchmark categorizes the multi-image abilities into three scenarios: MII, MKS and MIC.

Copied to clipboard

Hongyi Yuan, Zheng Yuan, Chuanqi Tan, Fei Huang, Songfang Huang

Extrapolating Multilingual Understanding Models as Multilingual Generators (2023.findings-emnlp)

Challenge:	Existing diffusion models are applied to continuous feature space while texts are sequences of discrete categorical tokens.
Approach:	They propose to use an encoder-decoder Transformer architecture to approach sequence-to-sequence text generation.
Outcome:	The proposed model improves on five sequence-to-sequence generation tasks compared to other diffusion-based models regarding text quality and inference time.

Copied to clipboard

Bohong Wu, Fei Yuan, Hai Zhao, Lei Li, Jingjing Xu

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

Challenge:	Existing multilingual understanding models are not capable of generating high-quality text compared with decoder-based causal language models.
Approach:	They propose a method to adapt a multilingual encoder to a language generator with a small number of additional parameters.
Outcome:	The proposed approach outperforms initialization-based methods with 9.4 BLEU on machine translation, 8.1 Rouge-L on question generation, and 5.5 METEOR on story generation.

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.

Robustness via Referencing: Defending against Prompt Injection Attacks by Referencing the Executed Instruction (2026.findings-acl)

Copied to clipboard

Yulin Chen, Haoran Li, Yuan Sui, Yue Liu, Yufei He, Xiaoling Bai, Chi Fei, Li Yabo, Haozhe Ma, Yangqiu Song, Bryan Hooi

Responsible & Trustworthy NLP

Challenge:	Prompt injection attacks manipulate large language models (LLMs) by misleading them to deviate from the original input instructions and execute maliciously injected instructions.
Approach:	They propose a prompt injection defense method that suppresses the model's instruction-following tendencies rather than suppressing them.
Outcome:	The proposed method outperforms prompt-engineering-based approaches and fine-tuning methods and reduces the ASR to nearly 0% in some scenarios.

LJPCheck: Functional Tests for Legal Judgment Prediction (2024.findings-acl)

Copied to clipboard

Yuan Zhang, Wanhong Huang, Yi Feng, Chuanyi Li, Zhiwei Fei, Jidong Ge, Bin Luo, Vincent Ng

Responsible & Trustworthy NLP

Challenge:	Existing LJP models fail to evaluate specific aspects of their performance, such as legal fairness and judicial fairness.
Approach:	They propose a suite of functional tests for LJP models to comprehend LJp models’ behaviors and offer diagnostic insights.
Outcome:	Extensive tests reveal weaknesses in LJP models and provide diagnostic insights.

Enhancing Answer Boundary Detection for Multilingual Machine Reading Comprehension (2020.acl-main)

Copied to clipboard

Fei Yuan, Linjun Shou, Xuanyu Bai, Ming Gong, Yaobo Liang, Nan Duan, Yan Fu, Daxin Jiang

From Multimodal LLM to Human-level AI: Modality, Instruction, Reasoning, Efficiency and beyond (2024.lrec-tutorials)

Challenge:	Existing approaches to improve machine reading comprehension performance on low resource languages are limited due to the lack of sufficient training data.
Approach:	They propose to use a mixed MRC task to translate the question to other languages and build cross-lingual question-passage pairs.
Outcome:	The proposed task improves on two cross-lingual MRC datasets.

Copied to clipboard

Hao Fei, Yuan Yao, Zhuosheng Zhang, Fuxiao Liu, Ao Zhang, Tat-Seng Chua

Responsible & Trustworthy NLP

Challenge:	This tutorial aims to deliver a comprehensive review of cutting-edge research in MLLMs.
Approach:	This tutorial will review cutting-edge research in MLLMs and examine the impact of ML in learning and reasoning.
Outcome:	This course will review cutting-edge research in MLLMs and examine the impact of ML models on learning, learning, and multimodal reasoning.

MPTc-Bench: Measuring Cross-market Generative Ability of Vision-Language Models via Movie Poster Transcreation (2026.findings-acl)

Copied to clipboard

Youyuan Lin, Yuan Li, Yahan Yu, Fei Cheng, Shin’ya Nishida, Chenhui Chu

Multimodality

Challenge:	Recent work adapts textual transcreation to image editing and formulates image transcreations to better match a target audience while preserving meaning.
Approach:	They propose a two-stage planner-editor pipeline in which an VLM planner specifies executable edits and an image editor renders them.
Outcome:	The proposed model can transcreate a visual asset for a different market while preserving its identity while matching market-specific design preferences and multilingual typography.

Memp: Exploring Agent Procedural Memory (2026.findings-acl)

Copied to clipboard

Runnan Fang, Yuan Liang, Xiaobin Wang, Jialong Wu, Shuofei Qiao, Pengjun Xie, Fei Huang, Huajun Chen, Ningyu Zhang

Challenge:	Large Language Models (LLMs) based agents suffer from brittle procedural memory that is manually engineered or entangled in static parameters.
Approach:	They propose a procedural-memory repository that distills past agent trajectories into fine-grained, step-by-step instructions and higher-level, script-like abstractions.
Outcome:	The proposed repository can be used to improve agents' performance on travelplanner and Alfworld.

KS-Lottery: Finding Certified Lottery Tickets for Multilingual Transfer in Large Language Models (2025.naacl-long)

Copied to clipboard

Fei Yuan, Chang Ma, Shuai Yuan, Qiushi Sun, Lei Li

LLaMAX: Scaling Linguistic Horizons of LLM by Enhancing Translation Capabilities Beyond 100 Languages (2024.findings-emnlp)

Challenge:	Existing studies have shown that a small subset of parameters is highly effective in fine-tuning . prior work shows that there are a few additional parameters corresponding to an intrinsic dimension in a well-trained Large Language Model.
Approach:	They propose a method to identify a small subset of LLM parameters highly effective in multilingual fine-tuning.
Outcome:	The proposed method can find the certified winning tickets in the embedding layer, and fine-tuning on the found parameters is guaranteed to perform as well as full fine- tuning.

Copied to clipboard

Yinquan Lu, Wenhao Zhu, Lei Li, Yu Qiao, Fei Yuan

Unifying Latent and Lexicon Representations for Effective Video-Text Retrieval (2024.lrec-main)

Challenge:	Large Language Models (LLMs) exhibit exceptional translation capabilities in high-resource language tasks, yet their effectiveness in low-resourced languages is suboptimal.
Approach:	They conduct extensive multilingual continual pre-training on the LLaMA series models and develop LLiMAX for translation support across more than 100 languages.
Outcome:	The proposed model achieves higher translation performance than existing open-source models and performs on-par with specialized translation model on the Flores-101 benchmark.

Copied to clipboard

Haowei Liu, Yaya Shi, Haiyang Xu, Chunfeng Yuan, Qinghao Ye, Chenliang Li, Ming Yan, Ji Zhang, Fei Huang, Bing Li, Weiming Hu

Semantics-enhanced Cross-modal Masked Image Modeling for Vision-Language Pre-training (2024.lrec-main)

Challenge:	Existing methods for video-text retrieval capture fine-grained semantic concepts . however, they lack the ability to capture finer-grain concepts such as objects and actions.
Approach:	They propose a dual-encoder architecture for fast video-text retrieval that learns lexicon representations to capture fine-grained semantics.
Outcome:	The proposed framework outperforms existing methods with 4.8% and 8.2% improvement on MSR-VTT and DiDeMo respectively.

Copied to clipboard

Haowei Liu, Yaya Shi, Haiyang Xu, Chunfeng Yuan, Qinghao Ye, Chenliang Li, Ming Yan, Ji Zhang, Fei Huang, Bing Li, Weiming Hu

Multimodality

Challenge:	Existing methods for vision-language pre-training lack high-level semantics and text is not sufficiently involved in masked modeling.
Approach:	They propose a semantics-enhanced cross-modal MIM framework for vision-language representation learning that harvests high-level semantics from global image features via self-supervised agreement learning and transfers them to local patch encodings by sharing the encode space.
Outcome:	The proposed model achieves state-of-the-art or competitive performance on multiple vision-language tasks.

Lego-MT: Learning Detachable Models for Massively Multilingual Machine Translation (2023.findings-acl)

Copied to clipboard

Fei Yuan, Yinquan Lu, Wenhao Zhu, Lingpeng Kong, Lei Li, Yu Qiao, Jingjing Xu

Cross-Document Cross-Lingual NLI via RST-Enhanced Graph Fusion and Interpretability Prediction (2025.emnlp-main)

Challenge:	Existing monolithic models for multilingual neural machine translation encounter parameter interference and inefficient inference for large models.
Approach:	They propose a detachable multi-way model that assigns each language to an individual branch . they use data from OPUS to build a translation benchmark covering 433 languages .
Outcome:	The proposed model outperforms existing models in OPUS and is faster than existing models.

Copied to clipboard

Mengying Yuan, WenHao Wang, Zixuan Wang, Yujie Huang, Kangli Wei, Fei Li, Chong Teng, Donghong Ji

Explainability & Interpretability in NLP

Challenge:	Despite the development of many subdirections, Cross-Document Cross-Lingual NLI remains largely unexplored.
Approach:	They propose a novel paradigm that extends traditional NLI capabilities to multi-document, multilingual scenarios by integrating RST-enhanced graph fusion with interpretability-aware prediction.
Outcome:	The proposed method improves on existing models and document-level NLI to multi-document, multilingual scenarios.

Speculative Contrastive Decoding (2024.acl-short)

Copied to clipboard

Hongyi Yuan, Keming Lu, Fei Huang, Zheng Yuan, Chang Zhou

How Vocabulary Sharing Facilitates Multilingualism in LLaMA? (2024.findings-acl)

Challenge:	Large language models (LLMs) exhibit exceptional performance in language tasks, yet their auto-regressive inference is limited due to high computational requirements and is sub-optimal due to the exposure bias.
Approach:	They propose a decoding approach that leverages predictions from smaller language models to achieve both decoding acceleration and quality improvement.
Outcome:	The proposed method achieves both decoding acceleration and quality improvement on four diverse language tasks.

Copied to clipboard

Fei Yuan, Shuai Yuan, Zhiyong Wu, Lei Li

InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviews (2024.acl-long)

Challenge:	Large Language Models (LLMs) show strong performance on English tasks, but their performance in other languages is limited.
Approach:	They conducted an exhaustive analysis of the multilingual capability of LLMs by examining the performance gap before and after embedding fine-tuning across 101 languages.
Outcome:	The proposed model improves on the attributes of four quadrants in the model and provides actionable and efficient guidelines for tuning these languages.

Copied to clipboard

Xintao Wang, Yunze Xiao, Jen-tse Huang, Siyu Yuan, Rui Xu, Haoran Guo, Quan Tu, Yaying Fei, Ziang Leng, Wei Wang, Jiangjie Chen, Cheng Li, Yanghua Xiao

Challenge:	Existing methods focus on knowledge and linguistic patterns of characters.
Approach:	They propose to evaluate character fidelity of role-playing agents with psychological scales . they propose to use psychological scale to measure personality traits of RPAs based on personality traits.
Outcome:	The proposed model reproduces character fidelity with psychological scales and shows that it is effective in measuring personality traits.

HyPe: Better Pre-trained Language Model Fine-tuning with Hidden Representation Perturbation (2023.acl-long)

Copied to clipboard

Hongyi Yuan, Zheng Yuan, Chuanqi Tan, Fei Huang, Songfang Huang

Symbol-LLM: Towards Foundational Symbol-centric Interface For Large Language Models (2024.acl-long)

Challenge:	Existing techniques to fine-tune pre-trained language models on downstream tasks are inadequate.
Approach:	They propose a technique to perturb hidden Transformers representations by enhancing generalization of hidden representations from different layers.
Outcome:	The proposed technique outperforms vanilla fine-tuning and enhances generalization of hidden representations from different layers.

Copied to clipboard

Fangzhi Xu, Zhiyong Wu, Qiushi Sun, Siyu Ren, Fei Yuan, Shuai Yuan, Qika Lin, Yu Qiao, Jun Liu

Question Translation Training for Better Multilingual Reasoning (2024.findings-acl)

Challenge:	Large Language Models (LLMs) have limitations when it comes to comprehending and expressing world knowledge that extends beyond the boundaries of natural language.
Approach:	They propose a model that integrates symbolic data into LLM training without loss of generality ability.
Outcome:	The proposed model performs better on symbol- and NL-centric tasks.

Copied to clipboard

Wenhao Zhu, Shujian Huang, Fei Yuan, Shuaijie She, Jiajun Chen, Alexandra Birch

Predicting Rewards Alongside Tokens: Non-disruptive Parameter Insertion for Efficient Inference Intervention in Large Language Model (2024.emnlp-main)

Challenge:	Large language models have shown compelling performance on reasoning tasks but they tend to perform much worse in languages other than English.
Approach:	They propose to train a model to translate reasoning questions into English by fine tuning on X-English parallel question data.
Outcome:	The proposed approach improves on LLaMA2-13B on the MGSM and MSVAMP multilingual reasoning benchmarks.

Copied to clipboard

Chenhan Yuan, Fei Huang, Ru Peng, Keming Lu, Bowen Yu, Chang Zhou, Jingren Zhou

Fusing Heterogeneous Factors with Triaffine Mechanism for Nested Named Entity Recognition (2022.findings-acl)

Challenge:	Existing approaches to fine tune LLMs produce unsafe responses and unreliable reasoning, but this solution introduces substantial time and space overhead due to the separate models required.
Approach:	They propose to insert extra parameters into transformer architecture to predict calibration signals along with original LLM output.
Outcome:	The proposed model reduces time and space costs while enabling seamless online deployment.

Copied to clipboard

Zheng Yuan, Chuanqi Tan, Songfang Huang, Fei Huang

Information Extraction & Text Mining

Challenge:	Named entity recognition (NER) is a fundamental natural language processing task that extracts entities from texts.
Approach:	They propose a triaffine mechanism which integrates heterogeneous factors into a single model to fuse these factors into one model to achieve better span representation.
Outcome:	The proposed method outperforms previous span-based methods and achieves state-of-the-art F1 scores on nested NER datasets GENIA and KBP2017.

Reverse Constitutional AI: A Framework for Controllable Toxic Data Generation via Probability-Clamped RLAIF (2026.findings-acl)

Copied to clipboard

Yuan Fang, Yiming Luo, Aimin Zhou, Fei Tan

Robustness in NLP

Challenge:	Existing approaches to red teaming focus on searching for individual adversarial inputs.
Approach:	They propose a framework for automated adversarial data generation that inverts harmless constitution into constitution of toxicity and iteratively refining model outputs through critique–revision pipeline.
Outcome:	The proposed framework generates diverse, high-quality toxic data without human annotation and significantly improves semantic coherence without sacrificing adversarial strength.

CorefQA: Coreference Resolution as Query-based Span Prediction (2020.acl-main)

Copied to clipboard

Wei Wu, Fei Wang, Arianna Yuan, Fei Wu, Jiwei Li

Information Extraction & Text Mining

Challenge:	Existing coreference resolution models suffer from mention proposal.
Approach:	They propose a query-based span prediction task that can retrieve mentions left out at the mention proposal stage.
Outcome:	The proposed model can retrieve mentions left out at the mention proposal stage and improve generalization capability using existing question answering datasets.

LegoMT2: Selective Asynchronous Sharded Data Parallel Training for Massive Neural Machine Translation (2025.findings-acl)

Copied to clipboard

Fei Yuan, Yinquan Lu, Lei Li, Jingjing Xu

Machine Translation

Challenge:	Existing methods to train a single model for massive languages have huge communication overheads and parameter interference.
Approach:	They propose an efficient training approach with an asymmetric multi-way model architecture for massive multilingual neural machine translation.
Outcome:	The proposed model is 16.2 faster than the distributed training method for M2M-100-12B while improving the translation performance by an average of 2.2 BLEU on Flores-101.

GlotEval: A Test Suite for Massively Multilingual Evaluation of Large Language Models (2025.emnlp-demos)

Copied to clipboard

Hengyu Luo, Zihao Li, Joseph Attieh, Sawal Devkota, Ona de Gibert, Xu Huang, Shaoxiong Ji, Peiqin Lin, Bhavani Sai Praneeth Varma Mantina, Ananda Sreenidhi, Raúl Vázquez, Mengjie Wang, Samea Yusofi, Fei Yuan, Jörg Tiedemann

BenchMAX: A Comprehensive Multilingual Evaluation Suite for Large Language Models (2025.findings-emnlp)

Challenge:	Existing evaluation frameworks focus on English and a handful of high-resource languages, thereby overlooking the realistic performance of large language models in multilingual and lower-resourced scenarios.
Approach:	They propose a unified and lightweight framework that integrates 27 benchmarks under a standard ISO 639-3 language identifier system to enable seamless incorporation of new benchmarks.
Outcome:	The proposed framework integrates 27 benchmarks under a standard ISO 639-3 language identifier system, allowing for seamless incorporation of new benchmarks.

Copied to clipboard

Xu Huang, Wenhao Zhu, Hanxu Hu, Conghui He, Lei Li, Shujian Huang, Fei Yuan