Deyi Xiong

Finding the Translation Switch: Discovering and Exploiting the Task-Initiation Features in LLMs AAAI 2026 Thesis Proposal: Diagnosing and Mitigating Semantic Interference in Script-Sharing Low-Resource Language Models: A Case Study on Square Bai Script ACL 2026 From Curated Data to Scalable Models: Continual Pre-training of Dense and MoE Large Language Models for Tibetan ACL 2026 Why Does Reinforcement Learning Generalize? A Feature-Level Mechanistic Study of Post-Training in Large Language Models ACL 2026 AdaDPI: Document-level Translation Adaptive Agent via Dynamic Parametric Internalization ACL 2026 EvoSci: A Bio-Inspired Multi-Agent Framework for the Evolution of Scientific Discovery ACL 2026 From Insight to Action: A Novel Framework for Interpretability-Guided Data Selection in Large Language Models ACL 2026 DVMap: Fine-Grained Pluralistic Value Alignment via High-Consensus Demographic-Value Mapping ACL 2026 Beyond Value Benchmarks: Measuring Value-Structure Alignment in Large Language Models via Symmetric Q-Sorts ACL 2026 Incentivizing Parametric Knowledge via Reinforcement Learning with Verifiable Rewards for Cross-Cultural Entity Translation ACL 2026 APPSI-139: A Parallel Corpus of English Application Privacy Policy Summarization and Interpretation ACL 2026 Praetor: A Fine-Grained Generative LLM Evaluator with Instance-Level Customizable Evaluation Criteria ACL 2025 CRiskEval: A Chinese Multi-Level Risk Evaluation Benchmark Dataset for Large Language Models ACL 2025 Automated Progressive Red Teaming COLING 2025 HighMATH: Evaluating Math Reasoning of Large Language Models in Breadth and Depth EMNLP 2025 Think-Search-Patch: A Retrieval-Augmented Reasoning Framework for Repository-Level Code Repair EMNLP 2025 DecEx-RAG: Boosting Agentic Retrieval-Augmented Generation with Decision and Execution Optimization via Process Supervision EMNLP 2025 Towards a Unified Paradigm of Concept Editing in Large Language Models EMNLP 2025 DCIS: Efficient Length Extrapolation of LLMs via Divide-and-Conquer Scaling Factor Search EMNLP 2025 Towards Optimal Evaluation Efficiency for Large Language Models EMNLP 2025 DiplomacyAgent: Do LLMs Balance Interests and Ethical Principles in International Events? EMNLP 2025 CONTRANS: Weak-to-Strong Alignment Engineering via Concept Transplantation COLING 2025 BackMATH: Towards Backward Reasoning for Solving Math Problems Step by Step COLING 2025 Empirical Study on Data Attributes Insufficiency of Evaluation Benchmarks for LLMs COLING 2025 ReproHum #0067-01: A Reproduction of the Evaluation of Cross-Lingual Summarization ACL 2025 C²RBench: A Chinese Complex Reasoning Benchmark for Large Language Models ACL 2025 Debate4MATH: Multi-Agent Debate for Fine-Grained Reasoning in Math ACL 2025 ChatSOP: An SOP-Guided MCTS Planning Framework for Controllable LLM Dialogue Agents ACL 2025 MLAS-LoRA: Language-Aware Parameters Detection and LoRA-Based Knowledge Transfer for Multilingual Machine Translation ACL 2025 Evaluating and Improving Graph to Text Generation with Large Language Models NAACL 2025 Self-Pluralising Culture Alignment for Large Language Models NAACL 2025 Towards Understanding Multi-Task Learning (Generalization) of LLMs via Detecting and Exploring Task-Specific Neurons COLING 2025 Do Large Language Models Mirror Cognitive Language Processing? COLING 2025 Evaluating Multimodal Large Language Models on Video Captioning via Monte Carlo Tree Search ACL 2025 Towards Robust In-Context Learning for Machine Translation with Large Language Models COLING 2024 LHMKE: A Large-scale Holistic Multi-subject Knowledge Evaluation Benchmark for Chinese Large Language Models COLING 2024 IRCAN: Mitigating Knowledge Conflicts in LLM Generation via Identifying and Reweighting Context-Aware Neurons NIPS 2024 An Empirical Study on the Robustness of Massively Multilingual Neural Machine Translation COLING 2024 Can Large Language Models Learn Translation Robustness from Noisy-Source In-context Demonstrations? COLING 2024 CBBQ: A Chinese Bias Benchmark Dataset Curated with Human-AI Collaboration for Large Language Models COLING 2024 Decoding at the Speed of Thought: Harnessing Parallel Decoding of Lexical Units for LLMs COLING 2024 IT2ACL Learning Easy-to-Hard Instructions via 2-Phase Automated Curriculum Learning for Large Language Models COLING 2024 LFED: A Literary Fiction Evaluation Dataset for Large Language Models COLING 2024 Exploring Multilingual Concepts of Human Values in Large Language Models: Is Value Alignment Consistent, Transferable and Controllable across Languages? EMNLP 2024 FuxiTranyu: A Multilingual Large Language Model Trained with Balanced Data EMNLP 2024 Star-Agents: Automatic Data Optimization with LLM Agents for Instruction Tuning NIPS 2024 Watermarking Conditional Text Generation for AI Detection: Unveiling Challenges and a Semantic-Aware Watermark Remedy AAAI 2024 CORECODE: A Common Sense Annotated Dialogue Dataset with Benchmark Tasks for Chinese Large Language Models AAAI 2024 LANDeRMT: Dectecting and Routing Language-Aware Neurons for Selectively Finetuning LLMs to Machine Translation ACL 2024 OpenEval: Benchmarking Chinese LLMs across Capability, Alignment and Safety ACL 2024 Mitigating Privacy Seesaw in Large Language Models: Augmented Privacy Neuron Editing via Activation Patching ACL 2024 Efficiently Exploring Large Language Models for Document-Level Machine Translation with In-context Learning ACL 2024 CMoralEval: A Moral Evaluation Benchmark for Chinese Large Language Models ACL 2024 A Comprehensive Evaluation of Quantization Strategies for Large Language Models ACL 2024 CToolEval: A Chinese Benchmark for LLM-Powered Agent Evaluation in Real-World API Interactions ACL 2024 Evaluating Chinese Large Language Models on Discipline Knowledge Acquisition via Memorization and Robustness Assessment ACL 2024 Rewiring the Transformer with Depth-Wise LSTMs COLING 2024 CKDST: Comprehensively and Effectively Distill Knowledge from Machine Translation to End-to-End Speech Translation ACL 2023 X-RiSAWOZ: High-Quality End-to-End Multilingual Dialogue Datasets and Few-shot Agents ACL 2023 Tab-CQA: A Tabular Conversational Question Answering Dataset on Financial Reports ACL 2023 PEIT: Bridging the Modality Gap with Pre-trained Models for End-to-End Image Translation ACL 2023 Inverse Reinforcement Learning for Text Summarization EMNLP 2023 CCSRD: Content-Centric Speech Representation Disentanglement Learning for End-to-End Speech Translation EMNLP 2023 MMNMT: Modularizing Multilingual Neural Machine Translation with Flexibly Assembled MoE and Dense Blocks EMNLP 2023 CS2W: A Chinese Spoken-to-Written Style Conversion Dataset with Multiple Conversion Types EMNLP 2023 Language Representation Projection: Can We Transfer Factual Knowledge across Languages in Multilingual Language Models? EMNLP 2023 DEPN: Detecting and Editing Privacy Neurons in Pretrained Language Models EMNLP 2023 Is Robustness Transferable across Languages in Multilingual Neural Machine Translation? EMNLP 2023 Towards a Deep Understanding of Multilingual End-to-End Speech Translation EMNLP 2023 TJUNLP:System Description for the WMT23 Literary Task in Chinese to English Translation Direction EMNLP 2023 SCoMoE: Efficient Mixtures of Experts with Structured Communication ICLR 2023 Unsupervised and Few-Shot Parsing from Pretrained Language Models (Extended Abstract) IJCAI 2023 GhostRNN: Reducing State Redundancy in RNN with Cheap Operations INTERSPEECH 2023 HuaSLIM: Human Attention Motivated Shortcut Learning Identification and Mitigation for Large Language models ACL 2023 TGEA 2.0: A Large-Scale Diagnostically Annotated Dataset with Benchmark Tasks for Text Generation of Pretrained Language Models NIPS 2022 Bridging between Cognitive Processing Signals and Linguistic Features via a Unified Attentional Network AAAI 2022 Adversarially Improving NMT Robustness to ASR Errors with Confusion Sets AACL 2022 KaFSP: Knowledge-Aware Fuzzy Semantic Parsing for Conversational Question Answering over a Large-Scale Knowledge Base ACL 2022 CogTaskonomy: Cognitively Inspired Task Taxonomy Is Beneficial to Transfer Learning in NLP ACL 2022 Learning Disentangled Semantic Representations for Zero-Shot Cross-Lingual Transfer in Multilingual Machine Reading Comprehension ACL 2022 Efficient Cluster-Based k-Nearest-Neighbor Machine Translation ACL 2022 Adaptive Differential Privacy for Language Model Training ACL 2022 ParaZh-22M: A Large-Scale Chinese Parabank via Machine Translation COLING 2022 Language Branch Gated Multilingual Neural Machine Translation COLING 2022 Informative Language Representation Learning for Massively Multilingual Neural Machine Translation COLING 2022 CoDoNMT: Modeling Cohesion Devices for Document-Level Neural Machine Translation COLING 2022 Evaluating Discourse Cohesion in Pre-trained Language Models COLING 2022 Long Text Generation with Topic-aware Discrete Latent Variable Model EMNLP 2022 Recovering Gold from Black Sand: Multilingual Dense Passage Retrieval with Hard and False Negative Samples EMNLP 2022 GEMv2: Multilingual NLG Benchmarking in a Single Line of Code EMNLP 2022 CoCoID: Learning Contrastive Representations and Compact Clusters for Semi-Supervised Intent Discovery EMNLP 2022 Adversarially Improving NMT Robustness to ASR Errors with Confusion Sets IJCNLP 2022 Learning Structural Information for Syntax-Controlled Paraphrase Generation NAACL 2022 Modeling Task-Aware MIMO Cardinality for Efficient Multilingual Neural Machine Translation IJCNLP 2021 Efficient Object-Level Visual Context Modeling for Multimodal Machine Translation: Masking Irrelevant Objects Helps Grounding AAAI 2021 Autocorrect in the Process of Translation — Multi-task Learning Improves Dialogue Machine Translation NAACL 2021 Probing Word Translations in the Transformer and Trading Decoder for Encoder Layers NAACL 2021 Domain-Aware Self-Attention for Multi-Domain Neural Machine Translation INTERSPEECH 2021 Integrating Pre-trained Model into Rule-based Dialogue Management AAAI 2021 Enhancing Chinese Word Segmentation via Pseudo Labels for Practicability IJCNLP 2021 AdaST: Dynamically Adapting Encoder States in the Decoder for End-to-End Speech-to-Text Translation IJCNLP 2021 An Empirical Study on Adversarial Attack on NMT: Languages and Positions Matter IJCNLP 2021 Syntactically-Informed Unsupervised Paraphrasing with Non-Parallel Data EMNLP 2021 Re-embedding Difficult Samples via Mutual Information Constrained Semantically Oversampling for Imbalanced Text Classification EMNLP 2021 Chinese WPLC: A Chinese Dataset for Evaluating Pretrained Language Models on Word Prediction Given Long-Range Context EMNLP 2021 Learning Hard Retrieval Decoder Attention for Transformers EMNLP 2021 Secoco: Self-Correcting Encoding for Neural Machine Translation EMNLP 2021 TGEA: An Error-Annotated Dataset and Benchmark Tasks for TextGeneration from Pretrained Language Models IJCNLP 2021 CogAlign: Learning to Align Textual Neural Representations to Cognitive Language Processing Signals IJCNLP 2021 Multi-Head Highly Parallelized LSTM Decoder for Neural Machine Translation IJCNLP 2021 Enhancing Chinese Word Segmentation via Pseudo Labels for Practicability ACL 2021 AdaST: Dynamically Adapting Encoder States in the Decoder for End-to-End Speech-to-Text Translation ACL 2021 An Empirical Study on Adversarial Attack on NMT: Languages and Positions Matter ACL 2021 Modeling Task-Aware MIMO Cardinality for Efficient Multilingual Neural Machine Translation ACL 2021 TGEA: An Error-Annotated Dataset and Benchmark Tasks for TextGeneration from Pretrained Language Models ACL 2021 CogAlign: Learning to Align Textual Neural Representations to Cognitive Language Processing Signals ACL 2021 Multi-Head Highly Parallelized LSTM Decoder for Neural Machine Translation ACL 2021 The Box is in the Pen: Evaluating Commonsense Reasoning in Neural Machine Translation EMNLP 2020 Learning Source Phrase Representations for Neural Machine Translation ACL 2020 Balanced Joint Adversarial Training for Robust Intent Detection and Slot Filling COLING 2020 Efficient Context-Aware Neural Machine Translation with Layer-Wise Weighting and Input-Aware Gating IJCAI 2020 Exploring Bilingual Parallel Corpora for Syntactically Controllable Paraphrase Generation IJCAI 2020 Dynamically Adjusting Transformer Batch Size by Monitoring Gradient Direction Change ACL 2020 Modeling Long Context for Task-Oriented Dialogue State Generation ACL 2020 A Test Suite for Evaluating Discourse Phenomena in Document-level Neural Machine Translation AACL 2020 Lipschitz Constrained Parameter Initialization for Deep Transformers ACL 2020 Cycle-Consistent Adversarial Autoencoders for Unsupervised Text Style Transfer COLING 2020 A Learning-Exploring Method to Generate Diverse Paraphrases with Multi-Objective Deep Reinforcement Learning COLING 2020 RiSAWOZ: A Large-Scale Multi-Domain Wizard-of-Oz Dataset with Rich Semantic Annotations for Task-Oriented Dialogue Modeling EMNLP 2020 TED-CDB: A Large-Scale Chinese Discourse Relation Dataset on TED Talks EMNLP 2020 Proceedings of the Fourth Workshop on Discourse in Machine Translation (DiscoMT 2019) EMNLP 2019 GECOR: An End-to-End Generative Ellipsis and Co-reference Resolution Model for Task-Oriented Dialogue IJCNLP 2019 Generating Highly Relevant Questions IJCNLP 2019 BiPaR: A Bilingual Parallel Dataset for Multilingual and Cross-lingual Reading Comprehension on Novels IJCNLP 2019 Hierarchical Modeling of Global Context for Document-Level Neural Machine Translation IJCNLP 2019 Towards Linear Time Neural Machine Translation with Capsule Networks IJCNLP 2019 Towards Linear Time Neural Machine Translation with Capsule Networks EMNLP 2019 Hierarchical Modeling of Global Context for Document-Level Neural Machine Translation EMNLP 2019 BiPaR: A Bilingual Parallel Dataset for Multilingual and Cross-lingual Reading Comprehension on Novels EMNLP 2019 GECOR: An End-to-End Generative Ellipsis and Co-reference Resolution Model for Task-Oriented Dialogue EMNLP 2019 Generating Highly Relevant Questions EMNLP 2019 Modeling Coherence for Neural Machine Translation with Dynamic and Topic Caches COLING 2018 Encoding Gated Translation Memory into Neural Machine Translation EMNLP 2018 Simplifying Neural Machine Translation with Addition-Subtraction Twin-Gated Recurrent Networks EMNLP 2018 Accelerating Neural Transformer via an Average Attention Network ACL 2018 Attention Focusing for Neural Machine Translation by Bridging Source and Target Embeddings ACL 2018 Sentence Weighting for Neural Machine Translation Domain Adaptation COLING 2018 Neural Machine Translation with Decoding History Enhanced Attention COLING 2018 Fusing Recency into Neural Machine Translation with an Inter-Sentence Gate Model COLING 2018 Modeling Source Syntax for Neural Machine Translation ACL 2017 Translating Phrases in Neural Machine Translation EMNLP 2017 Improving Translation Selection with Supersenses COLING 2016 Variational Neural Discourse Relation Recognizer EMNLP 2016 Variational Neural Machine Translation EMNLP 2016 Learning Event Expressions via Bilingual Structure Projection COLING 2016 Bilingual Autoencoders with Global Descriptors for Modeling Parallel Sentences COLING 2016 Improving Statistical Machine Translation with Selectional Preferences COLING 2016 Convolution-Enhanced Bilingual Recursive Neural Network for Bilingual Semantic Modeling COLING 2016 Bilingual Correspondence Recursive Autoencoder for Statistical Machine Translation EMNLP 2015 A Context-Aware Topic Model for Statistical Machine Translation IJCNLP 2015 Shallow Convolutional Neural Network for Implicit Discourse Relation Recognition EMNLP 2015 Learning Semantic Representations for Nonterminals in Hierarchical Phrase-Based Translation EMNLP 2015 A Context-Aware Topic Model for Statistical Machine Translation ACL 2015 Graph-Based Collective Lexical Selection for Statistical Machine Translation EMNLP 2015 Discriminative Reordering Model Adaptation via Structural Learning IJCAI 2015 Modeling Term Translation for Document-informed Machine Translation EMNLP 2014 A Sense-Based Translation Model for Statistical Machine Translation ACL 2014 Semantics, Discourse and Statistical Machine Translation ACL 2014 Max-Margin Synchronous Grammar Induction for Machine Translation EMNLP 2013 Modeling Lexical Cohesion for Document-Level Machine Translation IJCAI 2013 Lexical Chain Based Cohesion Models for Document-Level Statistical Machine Translation EMNLP 2013 Bilingual Lexical Cohesion Trigger Model for Document-Level Machine Translation ACL 2013 Modeling the Translation of Predicate-Argument Structure for SMT ACL 2012 A Topic Similarity Model for Hierarchical Phrase-based Translation ACL 2012 Unsupervised Discriminative Induction of Synchronous Grammar for Machine Translation COLING 2012 Enhancing Language Models in Statistical Machine Translation with Backward N-grams and Mutual Information Triggers ACL 2011 Error Detection for Statistical Machine Translation Using Linguistic Features ACL 2010 Learning Translation Boundaries for Phrase-Based Decoding NAACL 2010 A Syntax-Driven Bracketing Model for Phrase-Based Translation IJCNLP 2009 A Syntax-Driven Bracketing Model for Phrase-Based Translation ACL 2009 Linguistically Annotated BTG for Statistical Machine Translation COLING 2008 A Linguistically Annotated Reordering Model for BTG-based Statistical Machine Translation ACL 2008 Refinements in BTG-based Statistical Machine Translation IJCNLP 2008 Maximum Entropy Based Phrase Reordering Model for Statistical Machine Translation ACL 2006 Maximum Entropy Based Phrase Reordering Model for Statistical Machine Translation COLING 2006 Parsing the Penn Chinese Treebank with Semantic Knowledge IJCNLP 2005