Sujian Li

KNN-SSD: Enabling Dynamic Self-Speculative Decoding via Nearest Neighbor Layer Set Optimization EACL 2026 DocLens: A Tool-Augmented Multi-Agent Framework for Long Visual Document Understanding ACL 2026 Exploring Fine-Grained Human Motion Video Captioning COLING 2025 VL-RewardBench: A Challenging Benchmark for Vision-Language Generative Reward Models CVPR 2025 EERPD: Leveraging Emotion and Emotion Regulation for Improving Personality Detection COLING 2025 LongAttn: Selecting Long-context Training Data via Token-level Attention ACL 2025 More Tokens, Lower Precision: Towards the Optimal Token-Precision Trade-off in KV Cache Compression EMNLP 2025 MPO: Boosting LLM Agents with Meta Plan Optimization EMNLP 2025 Chain-of-Thought Matters: Improving Long-Context Language Models with Reasoning Path Supervision EMNLP 2025 Realistic Training Data Generation and Rule Enhanced Decoding in LLM for NameGuess EMNLP 2025 FinRAGBench-V: A Benchmark for Multimodal RAG with Visual Citation in the Financial Domain EMNLP 2025 The Good, The Bad, and The Greedy: Evaluation of LLMs Should Not Ignore Non-Determinism NAACL 2025 ISR: Self-Refining Referring Expressions for Entity Grounding ACL 2025 Hierarchical Memory Organization for Wikipedia Generation ACL 2025 WIKIGENBENCH:Exploring Full-length Wikipedia Generation under Real-World Scenario COLING 2025 Trial and Error: Exploration-Based Trajectory Optimization of LLM Agents ACL 2024 CoUDA: Coherence Evaluation via Unified Data Augmentation NAACL 2024 Selecting Large Language Model to Fine-tune via Rectified Scaling Law ICML 2024 PoSE: Efficient Context Window Extension of LLMs via Positional Skip-wise Training ICLR 2024 AgentBank: Towards Generalized LLM Agents via Fine-Tuning on 50000+ Interaction Trajectories EMNLP 2024 Watch Every Step! LLM Agent Learning via Iterative Step-level Process Refinement EMNLP 2024 LongEmbed: Extending Embedding Models for Long Context Retrieval EMNLP 2024 FaGANet: An Evidence-Based Fact-Checking Model with Integrated Encoder Leveraging Contextual Information COLING 2024 InstructEval: Instruction-Tuned Text Evaluator from Human Preference ACL 2024 Debiasing Generative Named Entity Recognition by Calibrating Sequence Likelihood ACL 2023 KBioXLM: A Knowledge-anchored Biomedical Multilingual Pretrained Language Model EMNLP 2023 InfoCL: Alleviating Catastrophic Forgetting in Continual Text Classification from An Information Theoretic Perspective EMNLP 2023 WeCheck: Strong Factual Consistency Checker via Weakly Supervised Learning ACL 2023 Contrastive Bootstrapping for Label Refinement ACL 2023 Rationale-Enhanced Language Models are Better Continual Relation Learners EMNLP 2023 Exploring In-Context Learning for Knowledge Grounded Dialog Generation EMNLP 2023 ConFiguRe: Exploring Discourse-level Chinese Figures of Speech COLING 2022 Promoting Pre-trained LM with Linguistic Features on Automatic Readability Assessment AACL 2022 Premise-based Multimodal Reasoning: Conditional Inference on Joint Textual and Visual Clues ACL 2022 Learn and Review: Enhancing Continual Named Entity Recognition via Reviewing Synthetic Samples ACL 2022 A Transition-based Method for Complex Question Understanding COLING 2022 Learning Robust Representations for Continual Relation Extraction via Adversarial Class Augmentation EMNLP 2022 Precisely the Point: Adversarial Augmentations for Faithful and Informative Text Generation EMNLP 2022 FRSUM: Towards Faithful Abstractive Summarization via Enhancing Factual Robustness EMNLP 2022 Consecutive Question Generation via Dynamic Multitask Learning EMNLP 2022 Promoting Pre-trained LM with Linguistic Features on Automatic Readability Assessment IJCNLP 2022 Low Resource Style Transfer via Domain Adaptive Meta Learning NAACL 2022 Semi-Automatic Construction of Text-to-SQL Data for Domain Transfer ACL 2021 Cross-Lingual Leveled Reading Based on Language-Invariant Features EMNLP 2021 Do It Once: An Embarrassingly Simple Joint Matching Approach to Response Selection ACL 2021 BASS: Boosting Abstractive Summarization with Unified Semantic Graph ACL 2021 Guiding the Growth: Difficulty-Controllable Question Generation through Step-by-Step Rewriting ACL 2021 Semi-Automatic Construction of Text-to-SQL Data for Domain Transfer IJCNLP 2021 Do It Once: An Embarrassingly Simple Joint Matching Approach to Response Selection IJCNLP 2021 BASS: Boosting Abstractive Summarization with Unified Semantic Graph IJCNLP 2021 Guiding the Growth: Difficulty-Controllable Question Generation through Step-by-Step Rewriting IJCNLP 2021 Composing Elementary Discourse Units in Abstractive Summarization ACL 2020 A Robust Adversarial Training Approach to Machine Reading Comprehension AAAI 2020 Syntax-Aware Graph Attention Network for Aspect-Level Sentiment Classification COLING 2020 Research on Discourse Parsing: from the Dependency View AACL 2020 Do NLP Models Know Numbers? Probing Numeracy in Embeddings IJCNLP 2019 Denoising based Sequence-to-Sequence Pre-training for Text Generation IJCNLP 2019 Text Level Graph Neural Network for Text Classification IJCNLP 2019 Text Level Graph Neural Network for Text Classification EMNLP 2019 Denoising based Sequence-to-Sequence Pre-training for Text Generation EMNLP 2019 Do NLP Models Know Numbers? Probing Numeracy in Embeddings EMNLP 2019 Tree-structured Decoding for Solving Math Word Problems IJCNLP 2019 Beyond Word Attention: Using Segment Attention in Neural Relation Extraction IJCAI 2019 Enhancing Pre-Trained Language Representations with Rich Knowledge for Machine Reading Comprehension ACL 2019 Exploring Sequence-to-Sequence Learning in Aspect Term Extraction ACL 2019 Tree-structured Decoding for Solving Math Word Problems EMNLP 2019 Multi-Perspective Context Aggregation for Semi-supervised Cloze-style Reading Comprehension COLING 2018 Query and Output: Generating Words by Querying Distributed Word Representations for Paraphrase Generation NAACL 2018 Auto-Dialabel: Labeling Dialogue Data with Unsupervised Learning EMNLP 2018 Toward Fast and Accurate Neural Discourse Segmentation EMNLP 2018 Joint Learning for Targeted Sentiment Analysis EMNLP 2018 SciDTB: Discourse Dependency TreeBank for Scientific Abstracts ACL 2018 Multi-Passage Machine Reading Comprehension with Cross-Passage Answer Verification ACL 2018 Retrieve, Rerank and Rewrite: Soft Template Based Neural Summarization ACL 2018 Adaptations of ROUGE and BLEU to Better Evaluate Machine Reading Comprehension Task ACL 2018 Interactive Attention Networks for Aspect-Level Sentiment Classification IJCAI 2017 A Two-Stage Parsing Method for Text-Level Discourse Analysis ACL 2017 PKU_ICL at SemEval-2017 Task 10: Keyphrase Extraction with Model Ensemble and External Knowledge SEMEVAL 2017 Tag-Enhanced Tree-Structured Neural Networks for Implicit Discourse Relation Classification IJCNLP 2017 Cascading Multiway Attentions for Document-level Sentiment Classification IJCNLP 2017 Learning to Rank Semantic Coherence for Topic Segmentation EMNLP 2017 AttSum: Joint Learning of Focusing and Summarization with Neural Attention COLING 2016 Reading and Thinking: Re-read LSTM Unit for Textual Entailment Recognition COLING 2016 Recognizing Implicit Discourse Relations via Repeated Reading: Neural Networks with Multi-Level Attention EMNLP 2016 News Stream Summarization using Burst Information Networks EMNLP 2016 Joint Learning Templates and Slots for Event Schema Induction NAACL 2016 Towards Time-Aware Knowledge Graph Completion COLING 2016 RBPB: Regularization-Based Pattern Balancing Method for Event Extraction ACL 2016 Capturing Argument Relationship for Chinese Semantic Role Labeling EMNLP 2016 Encoding Temporal Information for Time-Aware Link Prediction EMNLP 2016 Component-Enhanced Chinese Character Embeddings EMNLP 2015 Learning Summary Prior Representation for Extractive Summarization ACL 2015 A Hierarchical Knowledge Representation for Expert Finding on Social Media ACL 2015 A Dependency-Based Neural Network for Relation Classification ACL 2015 Context-aware Entity Morph Decoding ACL 2015 Bring you to the past: Automatic Generation of Topically Relevant Event Chronicles ACL 2015 Bring you to the past: Automatic Generation of Topically Relevant Event Chronicles IJCNLP 2015 Context-aware Entity Morph Decoding IJCNLP 2015 A Dependency-Based Neural Network for Relation Classification IJCNLP 2015 A Hierarchical Knowledge Representation for Expert Finding on Social Media IJCNLP 2015 Learning Summary Prior Representation for Extractive Summarization IJCNLP 2015 Recognizing Textual Entailment Using Probabilistic Inference EMNLP 2015 Why Read if You Can Scan? Trigger Scoping Strategy for Biographical Fact Extraction NAACL 2015 Joint Learning of Chinese Words, Terms and Keywords EMNLP 2014 Query-focused Multi-Document Summarization: Combining a Topic Model with Graph-based Semi-supervised Learning COLING 2014 Text-level Discourse Dependency Parsing ACL 2014 Constructing Information Networks Using One Single Model EMNLP 2014 Event-Based Time Label Propagation for Automatic Dating of News Articles EMNLP 2013 Evolutionary Hierarchical Dirichlet Process for Timeline Summarization ACL 2013 TopicSpam: a Topic-Model based approach for spam detection ACL 2013 Constructing Chinese Abbreviation Dictionary: A Stacked Approach COLING 2012 Joint Learning for Coreference Resolution with Markov Logic CONLL 2012 Update Summarization using a Multi-level Hierarchical Dirichlet Process Model COLING 2012 Implicit Discourse Relation Recognition by Selecting Typical Training Examples COLING 2012 Joint Learning for Coreference Resolution with Markov Logic EMNLP 2012 A Semi-Supervised Key Phrase Extraction Approach: Learning from Title Phrases through a Document Semantic Network ACL 2010 Experiments of Ontology Construction with Formal Concept Analysis IJCNLP 2005