Papers by Mingyang Wang

When Evolution Strategy Meets Language Models Tuning (2025.coling-main)

Challenge:	Existing methods to overcome catastrophic forgetting are rehearsal-based and parameter isolation-based.
Approach:	They propose a rehearsal-free framework which continuously adds new modules to language models and composes them with existing modules.
Outcome:	Experiments on benchmarks show that MoCL outperforms state-of-the-art and effectively facilitates knowledge transfer.

Copied to clipboard

Bo Huang, Yuxin Jiang, Mingyang Chen, Yi Wang, Hongyang Chen, Wei Wang

From Allies to Adversaries: Manipulating LLM Tool-Calling through Adversarial Injection (2025.naacl-long)

Challenge:	Autoregressive language models with pretraining often display limited capability in effectively following instructions.
Approach:	They propose an on-policy approach to optimize models by harnessing the principle of biological evolution, namely survival of the fittest.
Outcome:	The proposed method can achieve superior performance in various tasks and comparable performance in the human alignment task.

Copied to clipboard

Rupeng Zhang, Haowei Wang, Junjie Wang, Mingyang Li, Yuekai Huang, Dandan Wang, Qing Wang

Repairing Catastrophic-Neglect in Text-to-Image Diffusion Models via Attention-Guided Feature Enhancement (2024.findings-emnlp)

Challenge:	Toolcalling has changed Large Language Model (LLM) applications by integrating external tools, but it also introduces new security vulnerabilities, particularly in the tool scheduling mechanisms of LLM, which have not been extensively studied.
Approach:	They propose a framework that exploits vulnerabilities in Large Language Models through adversarial tool injection to execute privacy theft, launch denial-of-service attacks, and manipulate business competition.
Outcome:	The proposed framework exploits vulnerabilities in LLM tool-calling systems through adversarial tool injection.

Copied to clipboard

Zhiyuan Chang, Mingyang Li, Junjie Wang, Yi Liu, Qing Wang, Yang Liu

Better Call SAUL: Fluent and Consistent Language Model Editing with Generation Regularization (2024.findings-emnlp)

Challenge:	Text-to-Image Diffusion models generate high-quality images from textual descriptions, but they often produce images that do not fully align with the input prompts, resulting in semantic inconsistencies.
Approach:	They propose an automated repair approach to address catastrophic-neglect in T2I DMs.
Outcome:	The proposed model achieves 10.1%-16.3% higher Correct Rate in image generation compared to baselines.

Copied to clipboard

Mingyang Wang, Lukas Lange, Heike Adel, Jannik Strötgen, Hinrich Schuetze

Lost in Multilinguality: Dissecting Cross-lingual Factual Inconsistency in Transformer Language Models (2025.acl-long)

Challenge:	State-of-the-art methods for updating large language models require computational overhead and lack theoretical validation.
Approach:	They propose a model editing method that uses sentence concatenation with augmented random facts for generation regularization.
Outcome:	The proposed method outperforms state-of-the-art methods while maintaining generation quality and reducing computational overhead.

Copied to clipboard

Mingyang Wang, Heike Adel, Lukas Lange, Yihong Liu, Ercong Nie, Jannik Strötgen, Hinrich Schuetze

Learning to Plan for Retrieval-Augmented Large Language Models from Knowledge Graphs (2024.findings-emnlp)

Challenge:	Multilingual language models store factual knowledge across languages but struggle to provide consistent responses to semantically equivalent prompts in different languages.
Approach:	They propose a linear shortcut method that bypasses computations in the final layers . this method improves accuracy and cross-lingual consistency .
Outcome:	The proposed method improves prediction accuracy and cross-lingual consistency.

Copied to clipboard

Junjie Wang, Mingyang Chen, Binbin Hu, Dan Yang, Ziqi Liu, Yue Shen, Peng Wei, Zhiqiang Zhang, Jinjie Gu, Jun Zhou, Jeff Pan, Wen Zhang, Huajun Chen

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models (2026.findings-acl)

Challenge:	Recent studies have attempted to enhance the performance of large language models (LLMs) in complex question-answering (QA) tasks by combining step-wise planning with external retrieval.
Approach:	They propose a framework for enhancing LLMs’ planning capabilities by using planning data derived from knowledge graphs (KGs).
Outcome:	The proposed framework improves LLMs’ planning capabilities by using knowledge graphs (KGs) the proposed framework is compared with existing frameworks on multiple datasets and shows that it is effective for large language models.

Copied to clipboard

Hengyuan Zhang, Zhihao Zhang, Ercong Nie, Mingyang Wang, Zunhai Su, Yiwei Wang, Qianli Wang, Shuzhou Yuan, Xufeng Duan, Qibo Xue, Zeping Yu, Chenming Shang, Xiao Liang, Jing Xiong, Hui Shen, Chaofan Tao, Zhengwu Liu, Senjie Jin, Zhiheng Xi, Dongdong Zhang, Sophia Ananiadou, Tao Gui, Ruobing Xie, Hayden Kwok-Hay So, Hinrich Schuetze, Xuanjing Huang, Qi Zhang, Ngai Wong

Explainability & Interpretability in NLP

Challenge:	Existing literature on mechanistic interpretation (MI) treats it as an observational science, leaving practical applications underexplored.
Approach:	They propose a survey structured around the pipeline to identify and improve MI models.
Outcome:	The proposed framework enables tangible improvements in Alignment, Capability, and Efficiency.

PFDial: A Structured Dialogue Instruction Fine-tuning Method Based on UML Flowcharts (2025.findings-acl)

Copied to clipboard

Ming Zhang, Yuhui Wang, Yujiong Shen, Tingyi Yang, Changhao Jiang, Yilong Wu, Shihan Dou, Qinhao Chen, Zhiheng Xi, Zhihao Zhang, Yi Dong, Zhen Wang, Zhihui Fei, Mingyang Wan, Tao Liang, Guojun Ma, Qi Zhang, Tao Gui, Xuanjing Huang

Dialogue Systems & Conversational Agents

Challenge:	Large Language Models (LLMs) have shown remarkable progress in dialogue and reasoning, but they struggle to solve strictly constrained dialogue tasks.
Approach:	They construct a dataset that contains 12,705 high-quality Chinese dialogue instructions from 440 flowcharts containing 5,055 process nodes.
Outcome:	The proposed model outperforms GPT-4o models on backward transitions and outperformed GPT-42 models on the same dataset.

GradSim: Gradient-Based Language Grouping for Effective Multilingual Training (2023.emnlp-main)

Copied to clipboard

Mingyang Wang, Heike Adel, Lukas Lange, Jannik Strötgen, Hinrich Schuetze

How Transliterations Improve Crosslingual Alignment (2025.coling-main)

Challenge:	Existing studies show that not all languages positively influence each other . multilingual training can help in those cases by sharing knowledge across languages .
Approach:	They propose a gradient similarity-based language grouping method for multilingual training that is better correlated with cross-lingual model performance.
Outcome:	The proposed method leads to the largest performance gains on a multilingual dataset and is better correlated with cross-lingual model performance.

Copied to clipboard

Yihong Liu, Mingyang Wang, Amir Hossein Kargaran, Ayyoob ImaniGooghari, Orgest Xhelili, Haotian Ye, Chunlan Ma, François Yvon, Hinrich Schütze

Multilinguality

Challenge:	Recent studies show that post-aligning multilingual pretrained language models improve crosslingual alignment, but it is unclear how and why this is achieved.
Approach:	They propose to explicitly evaluate crosslingual alignment by adding transliterations to models using original and transliterated data.
Outcome:	The proposed approach improves crosslingual alignment even for random sentences.

Towards Knowledge-Intensive Text-to-SQL Semantic Parsing with Formulaic Knowledge (2022.emnlp-main)

Copied to clipboard

Longxu Dou, Yan Gao, Xuqi Liu, Mingyang Pan, Dingzirui Wang, Wanxiang Che, Dechen Zhan, Min-Yen Kan, Jian-Guang Lou

Programming Languages in NLP

Challenge:	Existing approaches to text-to-SQL require domain knowledge to parse expert questions into SQL queries.
Approach:	They propose a framework to leverage domain knowledge during parsing by building a new benchmark KnowSQL with domain-specific questions.
Outcome:	The proposed framework improves the performance of the proposed benchmark by 28.2%.

Play Guessing Game with LLM: Indirect Jailbreak Attack with Implicit Clues (2024.findings-acl)

Copied to clipboard

Zhiyuan Chang, Mingyang Li, Yi Liu, Junjie Wang, Qing Wang, Yang Liu

OFA: A Framework of Initializing Unseen Subword Embeddings for Efficient Large-scale Multilingual Continued Pretraining (2024.findings-naacl)

Challenge:	Existing jailbreak attacks primarily utilize scenario camouflage techniques, however their explicit mention of malicious intent will be easily recognized and defended by LLMs.
Approach:	They propose an indirect jailbreak attack approach, Puzzler, which can bypass LLM’s defensive strategies and obtain malicious response by implicitly providing LLMs with some clues about the original malicious query.
Outcome:	The proposed approach can bypass the LLM’s defensive strategies and obtain malicious response by implicitly providing LLMs with some clues about the original malicious query.

Copied to clipboard

Yihong Liu, Peiqin Lin, Mingyang Wang, Hinrich Schuetze

SAD: A Large-Scale Strategic Argumentative Dialogue Dataset (2026.acl-long)

Challenge:	Existing methods to pretrain multilingual models are limited by the number of embedding parameters and the complexity of the model.
Approach:	They propose a framework that initializes the embeddings of unseen subwords and can adapt a model to multiple languages.
Outcome:	The proposed framework can adapt a pre-trained model to multiple languages efficiently and effectively.

Copied to clipboard

YongKang Liu, Jiayang Yu, Mingyang Wang, Yiqun Zhang, Ercong Nie, Shi Feng, Daling Wang, Kaisong Song, Hinrich Schuetze

Dialogue Systems & Conversational Agents

Challenge:	Argumentation is a key part of human reasoning and decision-making . existing argumentative corpora focus on single-turn settings, but multi-turn dialogues are often realized as multi-turned dialogues .
Approach:	They present a dataset for strategic multi-turn argumentation dialogues . they annotate each utterance with five strategy types, allowing multiple strategies per utterrance .
Outcome:	The proposed dataset shows that explicit prompting improves fluency, stylistic coherence and persuasiveness.

Lion: Adversarial Distillation of Proprietary Large Language Models (2023.emnlp-main)

Copied to clipboard

Yuxin Jiang, Chunkit Chan, Mingyang Chen, Wei Wang

Mimicking the Familiar: Dynamic Command Generation for Information Theft Attacks in LLM Tool-Learning System (2025.acl-long)

Challenge:	Existing methods for transferring knowledge from a proprietary large language model to an open-source LLM have been criticized for not incorporating any feedback to boost student model's proficiency iteratively.
Approach:	They propose a novel adversarial distillation framework that integrates feedback to identify challenging instructions where the student model’s performance falls short.
Outcome:	The proposed framework surpasses existing state-of-the-art LLMs by 55.4% in challenging zero-shot reasoning benchmarks and 16.7% on AGIEval.

Copied to clipboard

Ziyou Jiang, Mingyang Li, Guowei Yang, Junjie Wang, Yuekai Huang, Zhiyuan Chang, Qing Wang

Robustness in NLP

Challenge:	Existing approaches to attack Large Language Model (LLM) tool-learning systems are black-box oriented and rely on static commands that cannot adapt flexibly to the changes in user queries and the invocation chain.
Approach:	They propose a dynamic attack comment generation approach for information theft attacks in LLM tool-learning systems that mimics the familiar by inferring the information utilized by upstream tools.
Outcome:	The proposed approach outperforms baselines with +13.2% ASRTheft and can be generalized to new tool-learning systems to expose their information leakage risks.

The Impact of Demonstrations on Multilingual In-Context Learning: A Multidimensional Analysis (2024.findings-acl)

Copied to clipboard

Miaoran Zhang, Vagrant Gautam, Mingyang Wang, Jesujoba Alabi, Xiaoyu Shen, Dietrich Klakow, Marius Mosbach

BMIKE-53: Investigating Cross-Lingual Knowledge Editing with In-Context Learning (2025.acl-long)

Challenge:	In-context learning is a popular inference strategy where large language models solve a task using only a few labeled demonstrations without updating the model parameters.
Approach:	They conduct multidimensional analysis of multilingual in-context learning using 5 models from different model families and 9 datasets covering classification and generation tasks.
Outcome:	The results show that demonstrations vary significantly across models, tasks, and languages.

Copied to clipboard

Ercong Nie, Bo Shao, Mingyang Wang, Zifeng Ding, Helmut Schmid, Hinrich Schuetze

MultiFinBen: Benchmarking Large Language Models for Multilingual and Multimodal Financial Application (2026.acl-long)

Challenge:	Using a benchmark for cross-lingual knowledge editing, knowledge editing is underexplored.
Approach:	They propose a benchmark for cross-lingual in-context knowledge editing that spans 53 languages and three KE datasets.
Outcome:	The proposed benchmark systematically evaluates cross-lingual knowledge editing (IKE) under zero-shot, one-shot and few-shot setups.

Copied to clipboard

Xueqing Peng, Lingfei Qian, Yan Wang, Ruoyu Xiang, Yueru He, Yang Ren, Mingyang Jiang, Vincent Jim Zhang, Yuqing Guo, Jeff Zhao, Huan He, Yi Han, Yun Feng, Yuechen Jiang, Yupeng Cao, Haohang Li, Yangyang Yu, Xiaoyu Wang, Penglei Gao, Shengyuan Lin, Keyi Wang, Shanshan Yang, Yilun Zhao, Zhiwei Liu, Peng Lu, Jerry Huang, Suyuchen Wang, Triantafillos Papadopoulos, Polydoros Giannouris, Efstathia Soufleri, Nuo Chen, Zhiyang Deng, Heming Fu, Yijia Zhao, Mingquan Lin, Meikang Qiu, Kaleb E Smith, Arman Cohan, Xiao-Yang Liu, Jimin Huang, Guojun Xiong, Alejandro Lopez-Lira, Xi Chen, Junichi Tsujii, Jian-Yun Nie, Sophia Ananiadou, Qianqian Xie

On Relation-Specific Neurons in Large Language Models (2025.emnlp-main)

Challenge:	Existing evaluations of LLMs in finance are text-only, monolingual, and largely saturated by current models.
Approach:	They propose a multilingual and multimodal benchmark for evaluating LLMs in real financial contexts.
Outcome:	The first expert-annotated multilingual and multimodal benchmark is released . it evaluates 21 leading LLMs and shows they perform better in multilingual settings .

Copied to clipboard

Yihong Liu, Runsheng Chen, Lea Hirlimann, Ahmad Dawar Hakimi, Mingyang Wang, Amir Hossein Kargaran, Sascha Rothe, François Yvon, Hinrich Schuetze

LangSAMP: Language-Script Aware Multilingual Pretraining (2025.acl-long)

Challenge:	In large language models, certain neurons can store distinct pieces of knowledge learned during pretraining.
Approach:	They hypothesize that relation-specific neurons detect relation in input text and guide generation involving such a relation.
Outcome:	The proposed model can handle facts involving relation r and facts containing a different relation .

Copied to clipboard

Yihong Liu, Haotian Ye, Chunlan Ma, Mingyang Wang, Hinrich Schuetze

One Shot Dominance: Knowledge Poisoning Attack on Retrieval-Augmented Generation Systems (2025.findings-emnlp)

Challenge:	Recent multilingual pretrained language models often avoid using language embeddings, which places a significant burden on token representations to encode all language-specific information.
Approach:	They propose a method that incorporates both language and script embeddings into the output of Transformer blocks before passing the final representations to the language modeling head for prediction.
Outcome:	The proposed method outperforms the baseline model in zero-shot crosslingual transfer across diverse downstream tasks.

Copied to clipboard

Zhiyuan Chang, Mingyang Li, Xiaojun Jia, Junjie Wang, Yuekai Huang, Ziyou Jiang, Yang Liu, Qing Wang

Robustness in NLP

Challenge:	Existing knowledge poisoning attacks against RAG systems require multiple poisoned documents or can only function effectively on simplistic queries.
Approach:	They propose a more realistic knowledge poisoning attack that poisons only a single document while remaining effective for complex multi-hop questions involving complex relationships between multiple elements.
Outcome:	The proposed attack achieves success by poisoning only a single document while remaining effective for complex multi-hop questions involving complex relationships between multiple elements.

Tracing Multilingual Factual Knowledge Acquisition in Pretraining (2025.findings-emnlp)

Copied to clipboard

Yihong Liu, Mingyang Wang, Amir Hossein Kargaran, Felicia Körner, Ercong Nie, Barbara Plank, François Yvon, Hinrich Schuetze

All Changes May Have Invariant Principles: Improving Ever-Shifting Harmful Meme Detection via Design Concept Reproduction (2026.acl-long)

Challenge:	Large Language Models are capable of recalling multilingual factual knowledge, but most studies evaluate only the final model, leaving the development of factual recall and crosslingual consistency unexplored.
Approach:	They trace how factual recall and crosslingual consistency evolve during pretraining, focusing on OLMo-7B as a case study.
Outcome:	The results show that fact frequency is the key to a better recall of multilingual facts, regardless of language, and some low-frequency facts in non-English languages can still be correctly recalled.

Copied to clipboard

Ziyou Jiang, Mingyang Li, Junjie Wang, Yuekai Huang, Jie Huang, Zhiyuan Chang, Zhaoyang Li, Qing Wang

Know Thy Enemy: Securing LLMs Against Prompt Injection via Diverse Data Synthesis and Instruction-Level Chain-of-Thought Learning (2026.findings-acl)

Challenge:	Existing methods for harmful meme detection only learn the combination of harmful elements and lack understanding of these implicit expressions.
Approach:	They propose a method that detects harmful memes by replicating the design concept of malicious users.
Outcome:	The proposed method achieves the highest accuracy with 81.1% and has slight accuracy decreases when generalized to type-shifting and temporal-evolving memes.

Copied to clipboard

Zhiyuan Chang, Mingyang Li, Yuekai Huang, Ziyou Jiang, Xiaojun Jia, Qian Xiong, Junjie Wang, Zhaoyang Li, Qing Wang

SAGE: Synergistic Adaptive Gating of Experts for Hateful Video Detection (2026.acl-long)

Challenge:	Large language model (LLM)-integrated applications face security vulnerabilities from prompt injection (PI) attacks.
Approach:	They propose a model enhancement method that synthesizes diverse training data and employs instruction-level chain-of-thought fine-tuning to enable LLMs to effectively identify and reject malicious instructions regardless of their source or position in the context.
Outcome:	The proposed method outperforms baselines in three critical dimensions while maintaining utility performance without degradation.

Copied to clipboard

Jie Huang, Xin Liao, Junjie Wang, Mingyang Li, Wenshuo Wang, Ziyou Jiang, Shoubin Li, Qing Wang

Visual Data in NLP

Challenge:	Existing methods for hateful video detection rely on multimodal feature fusion . existing methods rely only on blind feature mixing, which leads to feature dilution .
Approach:	They propose a framework that shifts from blind feature mixing to decision-level arbitration . it instantiates disentangled experts to rigorously preserve modality-specific semantics .
Outcome:	The proposed framework outperforms state-of-the-art methods on HateMM and MultiHateClip benchmarks.

PlaM: Training-Free Plateau-Guided Model Merging for Better Visual Grounding in MLLMs (2026.findings-acl)

Copied to clipboard

Zijing Wang, YongKang Liu, Mingyang Wang, Ercong Nie, Deyuan Chen, Zhengjie Zhao, Shi Feng, Daling Wang, Xiaocui Yang, Yifei Zhang, Hinrich Schuetze

Explainable Recommendation with Personalized Review Retrieval and Aspect Learning (2023.acl-long)

Challenge:	Multimodal instruction fine-tuning degrades textual reasoning capability, undermining multimodal performance.
Approach:	They propose a plateau-guided model merging method that selectively injects base language model parameters into MLLMs to mitigate this degradation.
Outcome:	The proposed framework reduces multimodal instruction fine-tuning degradation by incorporating a plateau-guided model merging method into MLLMs.

Copied to clipboard

Hao Cheng, Shuo Wang, Wensheng Lu, Wei Zhang, Mingyang Zhou, Kezhong Lu, Hao Liao

Explainability & Interpretability in NLP

Challenge:	Recent years have witnessed a growing interest in the development of explainable recommendation models.
Approach:	They propose a model that combines prediction and generation tasks to produce more persuasive explanations by obtaining additional information from the training sets.
Outcome:	The proposed model outperforms state-of-the-art models on three datasets and shows that it is more persuasive than previous models.

Language Mixing in Reasoning Language Models: Patterns, Impact, and Internal Causes (2025.emnlp-main)

Copied to clipboard

Mingyang Wang, Lukas Lange, Heike Adel, Yunpu Ma, Jannik Strötgen, Hinrich Schuetze

On Temperature-Constrained Non-Deterministic Machine Translation: Potential and Evaluation (2026.findings-acl)

Challenge:	Reasoning language models (RLMs) excel at complex tasks by leveraging a chain-of-thought process to generate structured intermediate steps.
Approach:	They present the first systematic study of language mixing in reasoning language models, examining its patterns, impact, and internal causes across 15 languages, 7 task difficulty levels, and 18 subject areas.
Outcome:	The proposed model generates reasoning steps that include a mixture of languages when prompted in one language, and this improves accuracy.

Copied to clipboard

Weichuan Wang, Mingyang Liu, Chen Ma, Linqi Song

Machine Translation

Challenge:	Recent studies have focused on the non-deterministic properties of language models, but these properties remain under-explored in machine translation.
Approach:	They propose a method that evaluates MT systems and identifies temperature-constrained non-deterministic MT as a distinct phenomenon.
Outcome:	The proposed framework provides higher-quality candidates than Deterministic MT under temperature constraints.

Logical Structure as Knowledge: Enhancing LLM Reasoning via Structured Logical Knowledge Density Estimation (2026.findings-acl)

Copied to clipboard

Zhen Bi, Zhenlin Hu, Xueshu Chen, Mingyang Chen, Cheng Deng, Yida Xue, Zhen Wang, Qing Shen, Ningyu Zhang, Jungang Lou

Reasoning

Challenge:	Existing data-centric paradigms equate quality with factuality or diversity and ignore the internal logical complexity of training samples.
Approach:	They propose a density-aware re-cognizing optimization strategy that prioritizes high-density logical samples to align training with the model's reasoning boundary.
Outcome:	The proposed metric outperforms existing methods and improves reasoning performance without increasing total data volume.

SSR-Zero: Simple Self-Rewarding Reinforcement Learning for Machine Translation (2026.findings-acl)

Copied to clipboard

Wenjie Yang, Mao Zheng, Mingyang Song, Zheng Li, Sitong Wang

Machine Translation

Challenge:	Large language models (LLMs) have demonstrated remarkable capabilities in machine translation, but most MT-specific LLMs rely heavily on external supervision during training.
Approach:	They propose a reinforcement learning framework for machine translation that is reference-free and relies solely on self-judging rewards.
Outcome:	The proposed framework outperforms existing LLMs and larger general LLM models on English Chinese translation benchmarks and performs competitively with leading closed-source systems.

Route Sparse Autoencoder to Interpret Large Language Models (2025.emnlp-main)

Copied to clipboard

Wei Shi, Sihang Li, Tao Liang, Mingyang Wan, Guojun Ma, Xiang Wang, Xiangnan He

Explainability & Interpretability in NLP

Challenge:	Sparse autoencoders (SAEs) extract interpretable and monosemantic features in large language models . prior work focused on feature extraction from a single layer, failing to capture activations that span multiple layers.
Approach:	They propose a framework that integrates a routing mechanism with a shared SAE to efficiently extract features from multiple layers.
Outcome:	The proposed framework extracts features from multiple layers while incurring minimal parameter overhead while achieving high interpretability and flexibility.

Do LVLMs Understand Charts? Analyzing and Correcting Factual Errors in Chart Captioning (2024.findings-acl)

Copied to clipboard

Kung-Hsiang Huang, Mingyang Zhou, Hou Pong Chan, Yi Fung, Zhenhailong Wang, Lingyu Zhang, Shih-Fu Chang, Heng Ji

AdapThink: Adaptive Thinking Preferences for Reasoning Language Models (2026.findings-acl)

Challenge:	LVLMs are known for producing text that is factually inconsistent with visual input . factuality of generated captions for structured visuals has not been studied as much .
Approach:	They propose a typology of factual errors in captions generated by large vision-language models . they propose CHOCOLATE, a visual entailment model that outperforms current models based on this analysis .
Outcome:	The proposed model outperforms current models in evaluating caption factuality.

Copied to clipboard

Wenyue Xu, Xu Wan, Wei Wang, Wenqi Huang, Wotao Yin, Shengjie Zhao, Mingyang Sun