Hai Zhao

BoYaEval: Evaluating Multimodal Large Language Models on Understanding Ancient Chinese Musical Scores ACL 2026 Scaling LLM Speculative Decoding: Non-Autoregressive Forecasting in Large-Batch Scenarios AAAI 2026 PAR: Training-Free Positional Perturbation and Attention Recycling for Faithful OCR ACL 2026 Can Large Language Models Be Good Language Teachers? EMNLP 2025 Faster In-Context Learning for LLMs via N-Gram Trie Speculative Decoding EMNLP 2025 ToM: Leveraging Tree-oriented MapReduce for Long-Context Reasoning in Large Language Models EMNLP 2025 XQuant: Achieving Ultra-Low Bit KV Cache Quantization with Cross-Layer Compression EMNLP 2025 IAM: Efficient Inference through Attention Mapping between Different-scale LLMs ACL 2025 DAC: A Dynamic Attention-aware Approach for Task-Agnostic Prompt Compression ACL 2025 DocBench: A Benchmark for Evaluating LLM-based Document Reading Systems NAACL 2025 Unfolding the Headline: Iterative Self-Questioning for News Retrieval and Timeline Summarization NAACL 2025 MEGen: Generative Backdoor into Large Language Models via Model Editing ACL 2025 KV-Latent: Dimensional-level KV Cache Reduction with Frequency-aware Rotary Positional Embedding ACL 2025 What Limits Bidirectional Model’s Generative Capabilities? A Uni-Bi-Directional Mixture-of-Expert Method For Bidirectional Fine-tuning ICML 2025 Segment First or Comprehend First? Explore the Limit of Unsupervised Word Segmentation with Large Language Models ACL 2025 Towards Enhanced Immersion and Agency for LLM-based Interactive Drama ACL 2025 PGPO: Enhancing Agent Reasoning via Pseudocode-style Planning Guided Preference Optimization ACL 2025 Driving Chinese Spelling Correction from a Fine-Grained Perspective COLING 2025 Dialogue-RAG: Enhancing Retrieval for LLMs via Node-Linking Utterance Rewriting ACL 2025 SCANS: Mitigating the Exaggerated Safety for LLMs via Safety-Conscious Activation Steering AAAI 2025 LESA: Learnable LLM Layer Scaling-Up ACL 2025 X-TURING: Towards an Enhanced and Efficient Turing Test for Long-Term Dialogue Agents ACL 2025 Caution for the Environment: Multimodal LLM Agents are Susceptible to Environmental Distractions ACL 2025 Game Development as Human-LLM Interaction ACL 2025 Open-Theatre: An Open-Source Toolkit for LLM-based Interactive Drama EMNLP 2025 CoViPAL: Layer-wise Contextualized Visual Token Pruning for Large Vision-Language Models EMNLP 2025 Evolving Chinese Spelling Correction with Corrector-Verifier Collaboration EMNLP 2025 From Parameters to Performance: A Data-Driven Study on LLM Structure and Development EMNLP 2025 On the Robustness of Editing Large Language Models EMNLP 2024 Attack Named Entity Recognition by Entity Boundary Interference COLING 2024 AuRoRA: A One-for-all Platform for Augmented Reasoning and Refining with Task-Adaptive Chain-of-Thought Prompting COLING 2024 Mitigating Misleading Chain-of-Thought Reasoning with Selective Filtering COLING 2024 PROM: A Phrase-level Copying Mechanism with Pre-training for Abstractive Summarization COLING 2024 Unveiling Vulnerability of Self-Attention COLING 2024 Reference Trustable Decoding: A Training-Free Augmentation Paradigm for Large Language Models NIPS 2024 Chinese Spelling Correction as Rephrasing Language Model AAAI 2024 Fact-Driven Logical Reasoning for Machine Reading Comprehension AAAI 2024 A Novel Energy Based Model Mechanism for Multi-Modal Aspect-Based Sentiment Analysis AAAI 2024 Sparse is Enough in Fine-tuning Pre-trained Large Language Models ICML 2024 Generative Judge for Evaluating Alignment ICLR 2024 LaCo: Large Language Model Pruning via Layer Collapse EMNLP 2024 Head-wise Shareable Attention for Large Language Models EMNLP 2024 GoT: Effective Graph-of-Thought Reasoning in Language Models NAACL 2024 Self-Prompting Large Language Models for Zero-Shot Open-Domain QA NAACL 2024 Vript: A Video Is Worth Thousands of Words NIPS 2024 Dissecting Human and LLM Preferences ACL 2024 SirLLM: Streaming Infinite Retentive LLM ACL 2024 Hypergraph based Understanding for Document Semantic Entity Recognition ACL 2024 Selective Prefix Tuning for Pre-trained Language Models ACL 2024 The Music Maestro or The Musically Challenged, A Massive Music Evaluation Benchmark for Large Language Models ACL 2024 PyramidInfer: Pyramid KV Cache Compression for High-throughput LLM Inference ACL 2024 From Role-Play to Drama-Interaction: An LLM Solution ACL 2024 GKT: A Novel Guidance-Based Knowledge Transfer Framework For Efficient Cloud-edge Collaboration LLM Deployment ACL 2024 Chinese Spelling Corrector Is Just a Language Learner ACL 2024 CoCo-Agent: A Comprehensive Cognitive MLLM Agent for Smartphone GUI Automation ACL 2024 CMMLU: Measuring massive multitask language understanding in Chinese ACL 2024 Are LLMs Aware that Some Questions are not Open-ended? EMNLP 2024 Instruction-Driven Game Engine: A Poker Case Study EMNLP 2024 VHASR: A Multimodal Speech Recognition System With Vision Hotwords EMNLP 2024 GLaPE: Gold Label-agnostic Prompt Evaluation for Large Language Models EMNLP 2024 Decker: Double Check with Heterogeneous Knowledge for Commonsense Fact Verification ACL 2023 Learning Event-aware Measures for Event Coreference Resolution ACL 2023 Extrapolating Multilingual Understanding Models as Multilingual Generators EMNLP 2023 Self-prompted Chain-of-Thought on Large Language Models for Open-domain Multi-hop Reasoning EMNLP 2023 RefGPT: Dialogue Generation of GPT, by GPT, and for GPT EMNLP 2023 Empower Nested Boolean Logic via Self-Supervised Curriculum Learning EMNLP 2023 Query Rewriting in Retrieval-Augmented Large Language Models EMNLP 2023 iRe2f: Rethinking Effective Refinement in Language Structure Prediction via Efficient Iterative Retrospecting and Reasoning IJCAI 2023 Toward Adversarial Training on Contextualized Language Representation ICLR 2023 Bidirectional Looking with A Novel Double Exponential Moving Average to Adaptive and Non-adaptive Momentum Optimizers ICML 2023 Language Model Pre-training on True Negatives AAAI 2023 Adversarial Self-Attention for Language Understanding AAAI 2023 Towards End-to-End Open Conversational Machine Reading EACL 2023 EM Pre-training for Multi-party Dialogue Response Generation ACL 2023 Learning Better Masking for Better Language Model Pre-training ACL 2023 Pre-training Multi-party Dialogue Models with Latent Discourse Inference ACL 2023 Rethinking Masked Language Modeling for Chinese Spelling Correction ACL 2023 FSUIE: A Novel Fuzzy Span Mechanism for Universal Information Extraction ACL 2023 Encoder and Decoder, Not One Less for Pre-trained Language Model Sponsored NMT ACL 2023 Contextualized Semantic Distance between Highly Overlapped Texts ACL 2023 Sentence Representation Learning with Generative Objective rather than Contrastive Objective EMNLP 2022 Reorder and then Parse, Fast and Accurate Discontinuous Constituency Parsing EMNLP 2022 Task Compass: Scaling Multi-task Pre-training with Task Prefix EMNLP 2022 Modeling Hierarchical Reasoning Chains by Linking Discourse Units and Key Phrases for Reading Comprehension COLING 2022 Nested Named Entity Recognition as Corpus Aware Holistic Structure Parsing COLING 2022 ArT: All-round Thinker for Unsupervised Commonsense Question Answering COLING 2022 Aspect-based Sentiment Analysis as Machine Reading Comprehension COLING 2022 Instance Regularization for Discriminative Language Model Pre-training EMNLP 2022 BiBL: AMR Parsing and Generation with Bidirectional Bayesian Learning COLING 2022 Explicit Alignment Learning for Neural Machine Translation IJCAI 2022 Semantic-Preserving Adversarial Code Comprehension COLING 2022 Structural Characterization for Dialogue Disentanglement ACL 2022 Forging Multiple Training Objectives for Pre-trained Language Models via Meta-Learning EMNLP 2022 Sentence-aware Contrastive Learning for Open-Domain Passage Retrieval ACL 2022 Tracing Origins: Coreference-aware Machine Reading Comprehension ACL 2022 Lite Unified Modeling for Discriminative Reading Comprehension ACL 2022 Restricted or Not: A General Training Framework for Neural Machine Translation ACL 2022 What Works and Doesn’t Work, A Deep Decoder for Neural Machine Translation ACL 2022 Distinguishing Non-natural from Natural Adversarial Samples for More Robust Pre-trained Language Model ACL 2022 Back to the Future: Bidirectional Information Decoupling Network for Multi-turn Dialogue Modeling EMNLP 2022 Multilingual Pre-training with Universal Dependency Learning NIPS 2021 Filling the Gap of Utterance-aware and Speaker-aware Representation for Multi-turn Dialogue AAAI 2021 Topic-Aware Multi-turn Dialogue Modeling AAAI 2021 Semantics-Aware Inferential Network for Natural Language Understanding AAAI 2021 Retrospective Reader for Machine Reading Comprehension AAAI 2021 Pre-training Universal Language Representation ACL 2021 Structural Pre-training for Dialogue Comprehension ACL 2021 Code Summarization with Structure-induced Transformer ACL 2021 Dialogue-oriented Pre-training ACL 2021 Enhancing Language Generation with Effective Checkpoints of Pre-trained Language Model ACL 2021 Dialogue Graph Modeling for Conversational Machine Reading ACL 2021 Defending Pre-trained Language Models from Adversarial Word Substitution Without Performance Sacrifice ACL 2021 Grammatical Error Correction as GAN-like Sequence Labeling ACL 2021 NICT’s Neural Machine Translation Systems for the WAT21 Restricted Translation Task ACL 2021 Advances and Challenges in Unsupervised Neural Machine Translation EACL 2021 Unsupervised Neural Machine Translation with Universal Grammar EMNLP 2021 Smoothing Dialogue States for Open Conversational Machine Reading EMNLP 2021 Seeking Common but Distinguishing Difference, A Joint Aspect-based Sentiment Analysis Model EMNLP 2021 MiSS: An Assistant for Multi-Style Simultaneous Translation EMNLP 2021 Syntax in End-to-End Natural Language Processing EMNLP 2021 Span Fine-tuning for Pre-trained Language Models EMNLP 2021 Self- and Pseudo-self-supervised Prediction of Speaker and Key-utterance for Multi-party Dialogue Reading Comprehension EMNLP 2021 What If Sentence-hood is Hard to Define: A Case Study in Chinese Reading Comprehension EMNLP 2021 MiSS@WMT21: Contrastive Learning-reinforced Domain Adaptation in Neural Machine Translation EMNLP 2021 Pre-training Universal Language Representation IJCNLP 2021 Structural Pre-training for Dialogue Comprehension IJCNLP 2021 Code Summarization with Structure-induced Transformer IJCNLP 2021 Dialogue-oriented Pre-training IJCNLP 2021 Enhancing Language Generation with Effective Checkpoints of Pre-trained Language Model IJCNLP 2021 Dialogue Graph Modeling for Conversational Machine Reading IJCNLP 2021 Defending Pre-trained Language Models from Adversarial Word Substitution Without Performance Sacrifice IJCNLP 2021 Grammatical Error Correction as GAN-like Sequence Labeling IJCNLP 2021 NICT’s Neural Machine Translation Systems for the WAT21 Restricted Translation Task IJCNLP 2021 Cross-lingual Supervision Improves Unsupervised Neural Machine Translation NAACL 2021 SJTU-NICT’s Supervised and Unsupervised Neural Machine Translation Systems for the WMT20 News Translation Task EMNLP 2020 DCMN+: Dual Co-Matching Network for Multi-Choice Reading Comprehension AAAI 2020 Semantics-Aware BERT for Language Understanding AAAI 2020 SG-Net: Syntax-Guided Machine Reading Comprehension AAAI 2020 Neural Machine Translation with Universal Visual Representation ICLR 2020 Data-dependent Gaussian Prior Objective for Language Generation ICLR 2020 Bipartite Flat-Graph Network for Nested Named Entity Recognition ACL 2020 Span Model for Open Information Extraction on Accurate Corpus AAAI 2020 Hierarchical Contextualized Representation for Named Entity Recognition AAAI 2020 Global Greedy Dependency Parsing AAAI 2020 Explicit Sentence Compression for Neural Machine Translation AAAI 2020 Attention Is All You Need for Chinese Word Segmentation EMNLP 2020 Named Entity Recognition Only from Word Embeddings EMNLP 2020 High-order Semantic Role Labeling EMNLP 2020 Reference Language based Unsupervised Neural Machine Translation EMNLP 2020 Parsing All: Syntax and Semantics, Dependencies and Spans EMNLP 2020 LIMIT-BERT : Linguistics Informed Multi-Task BERT EMNLP 2020 Unsupervised Learning Helps Supervised Neural Word Segmentation AAAI 2019 Dependency or Span, End-to-End Uniform Semantic Role Labeling AAAI 2019 GAN Driven Semi-distant Supervision for Relation Extraction NAACL 2019 Lattice-Based Transformer Encoder for Neural Machine Translation ACL 2019 Head-Driven Phrase Structure Grammar Parsing on Penn Treebank ACL 2019 Open Vocabulary Learning for Neural Chinese Pinyin IME ACL 2019 SJTU at MRP 2019: A Transition-Based Multi-Task Parser for Cross-Framework Meaning Representation Parsing CONLL 2019 SJTU-NICT at MRP 2019: Multi-Task Learning for End-to-End Uniform Semantic Graph Parsing CONLL 2019 Semantic Role Labeling with Associated Memory Network NAACL 2019 Minimum Divergence vs. Maximum Margin: an Empirical Comparison on Seq2Seq Models ICLR 2019 Syntax-aware Multilingual Semantic Role Labeling IJCNLP 2019 Syntax-aware Multilingual Semantic Role Labeling EMNLP 2019 Multi-Labeled Relation Extraction with Attentive Capsule Network AAAI 2019 A Unified Syntax-aware Framework for Semantic Role Labeling EMNLP 2018 Chinese Pinyin Aided IME, Input What You Have Not Keystroked Yet EMNLP 2018 Exploring Recombination for Efficient Decoding of Neural Machine Translation EMNLP 2018 SJTU-NLP at SemEval-2018 Task 9: Neural Hypernym Discovery with Term Embeddings SEMEVAL 2018 Lingke: a Fine-grained Multi-turn Chatbot for Customer Service COLING 2018 Modeling Multi-turn Conversation with Deep Utterance Aggregation COLING 2018 Seq2seq Dependency Parsing COLING 2018 A Full End-to-End Semantic Role Labeler, Syntactic-agnostic Over Syntactic-aware? COLING 2018 Subword-augmented Embedding for Cloze Reading Comprehension COLING 2018 Deep Enhanced Representation for Implicit Discourse Relation Recognition COLING 2018 One-shot Learning for Question-Answering in Gaokao History Challenge COLING 2018 Moon IME: Neural-based Chinese Pinyin Aided Input Method with Customizable Association ACL 2018 Automatic Article Commenting: the Task and Dataset ACL 2018 Syntax for Semantic Role Labeling, To Be, Or Not To Be ACL 2018 Joint Learning of POS and Dependencies for Multilingual Universal Dependency Parsing CONLL 2018 Multilingual Universal Dependency Parsing from Raw Text with Low-Resource Language Enhancement CONLL 2018 Adversarial Connective-exploiting Networks for Implicit Discourse Relation Classification ACL 2017 Fast and Accurate Neural Word Segmentation for Chinese ACL 2017 A Transition-based System for Universal Dependency Parsing CONLL 2017 A Stacking Gated Neural Architecture for Implicit Discourse Relation Classification EMNLP 2016 Probabilistic Graph-based Dependency Parsing with Convolutional Neural Network ACL 2016 A Constituent Syntactic Parse Tree Based Discourse Parser CONLL 2016 A Bilingual Graph-Based Semantic Model for Statistical Machine Translation IJCAI 2016 Implicit Discourse Relation Recognition with Context-aware Character-enhanced Embeddings COLING 2016 Connecting Phrase based Statistical Machine Translation Adaptation COLING 2016 Shallow Discourse Parsing Using Convolutional Neural Network CONLL 2016 Learning Distributed Word Representations For Bidirectional LSTM Recurrent Neural Network NAACL 2016 Neural Word Segmentation Learning for Chinese ACL 2016 Learning Word Reorderings for Hierarchical Phrase-based Statistical Machine Translation ACL 2015 Learning Word Reorderings for Hierarchical Phrase-based Statistical Machine Translation IJCNLP 2015 Shallow Discourse Parsing Using Constituent Parsing Tree CONLL 2015 Neural Network Based Bilingual Language Model Growing for Statistical Machine Translation EMNLP 2014 A Joint Graph Model for Pinyin-to-Chinese Conversion with Typo Correction ACL 2014 Learning Hierarchical Translation Spans EMNLP 2014 Grammatical Error Detection and Correction using a Single Maximum Entropy Model CONLL 2014 KySS 1.0: a Framework for Automatic Evaluation of Chinese Input Method Engines IJCNLP 2013 Labeled Alignment for Recognizing Textual Entailment IJCNLP 2013 Grammatical Error Correction as Multiclass Classification with Single Model CONLL 2013 Converting Continuous-Space Language Models into N-Gram Language Models for Statistical Machine Translation EMNLP 2013 Improving Function Word Alignment with Frequency and Syntactic Information IJCAI 2013 Using Deep Linguistic Features for Finding Deceptive Opinion Spam COLING 2012 Chinese Coreference Resolution via Ordered Filtering CONLL 2012 System paper for CoNLL-2012 shared task: Hybrid Rule-based Algorithm for Coreference Resolution. CONLL 2012 A Machine Learning Approach to Convert CCGbank to Penn Treebank COLING 2012 Fourth-Order Dependency Parsing COLING 2012 Enhance Top-down method with Meta-Classification for Very Large-scale Hierarchical Classification IJCNLP 2011 Hedge Detection and Scope Finding by Sequence Labeling with Procedural Feature Selection CONLL 2010 Character-Level Dependencies in Chinese: Usefulness and Learning EACL 2009 Multilingual Dependency Learning: A Huge Feature Engineering Method to Semantic Dependency Parsing CONLL 2009 Cross Language Dependency Parsing using a Bilingual Lexicon ACL 2009 Improving Nominal SRL in Chinese Language with Verbal SRL Information and Automatic Predicate Recognition EMNLP 2009 Cross Language Dependency Parsing using a Bilingual Lexicon IJCNLP 2009 Multilingual Dependency Learning: Exploiting Rich Features for Tagging Syntactic and Semantic Dependencies CONLL 2009 Semantic Dependency Parsing of NomBank and PropBank: An Efficient Integrated Approach via a Large-scale Feature Selection EMNLP 2009 Parsing Syntactic and Semantic Dependencies with Two Single-Stage Maximum Entropy Models CONLL 2008 An Empirical Comparison of Goodness Measures for Unsupervised Chinese Word Segmentation with a Unified Framework IJCNLP 2008 Unsupervised Segmentation Helps Supervised Learning of Character Tagging for Word Segmentation and Named Entity Recognition IJCNLP 2008