Kehai Chen

Lost in Benchmarks? Rethinking Large Language Model Benchmarking with Item Response Theory AAAI 2026 Long-form RewardBench: Evaluating Reward Models for Long-form Generation AAAI 2026 Diagnosing and Remedying Representation Deficiencies for Deterministic Reasoning in KGQA ACL 2026 SAT: Balancing Reasoning Accuracy and Efficiency with Stepwise Adaptive Thinking ACL 2026 DUAL RM: Beyond Rule-based Preference Reward Modeling via Meta-Reward ACL 2026 WSDPO: A Generative Word Sense Disambiguation Framework with Chain-of-Thought and Preference Optimization ACL 2026 Exploiting Prompt-induced Confidence for Black-Box Attacks on LLMs EMNLP 2025 Look Before You Leap: Enhance Attention and Vigilance Regarding Harmful Content with GuidelineLLM AAAI 2025 Make Imagination Clearer! Stable Diffusion-based Visual Imagination for Multimodal Machine Translation ACL 2025 Generative Reward Modeling via Synthetic Criteria Preference Learning ACL 2025 Benchmarking and Improving Large Vision-Language Models for Fundamental Visual Graph Understanding and Reasoning ACL 2025 Efficient Safety Alignment of Large Language Models via Preference Re-ranking and Representation-based Reward Modeling ACL 2025 From Awareness to Adaptability: Enhancing Tool Utilization for Scientific Reasoning ACL 2025 MDIT-Bench: Evaluating the Dual-Implicit Toxicity in Large Multimodal Models ACL 2025 The Rise of Darkness: Safety-Utility Trade-Offs in Role-Playing Dialogue Agents ACL 2025 LLM-based Translation Inference with Iterative Bilingual Understanding ACL 2025 InImageTrans: Multimodal LLM-based Text Image Machine Translation ACL 2025 Memory-augmented Query Reconstruction for LLM-based Knowledge Graph Reasoning ACL 2025 Tool learning via Inference-time Scaling and Cycle Verifier ACL 2025 HITSZ’s End-To-End Speech Translation Systems Combining Sequence-to-Sequence Auto Speech Recognition Model and Indic Large Language Model for IWSLT 2025 in Indic Track ACL 2025 ZigZagKV: Dynamic KV Cache Compression for Long-context Modeling based on Layer Uncertainty COLING 2025 Understanding the RoPE Extensions of Long-Context LLMs: An Attention Perspective COLING 2025 Merge then Realign: Simple and Effective Modality-Incremental Continual Learning for Multimodal LLMs EMNLP 2025 Generator-Assistant Stepwise Rollback Framework for Large Language Model Agent EMNLP 2025 ORPP: Self-Optimizing Role-playing Prompts to Enhance Language Model Capabilities EMNLP 2025 Benchmarking LLMs for Translating Classical Chinese Poetry: Evaluating Adequacy, Fluency, and Elegance EMNLP 2025 A Survey on the Feedback Mechanism of LLM-based AI Agents IJCAI 2025 MoDification: Mixture of Depths Made Easy NAACL 2025 Question-guided Knowledge Graph Re-scoring and Injection for Knowledge Graph Question Answering EMNLP 2024 Adaptive Feature-based Low-Rank Compression of Large Language Models via Bayesian Optimization EMNLP 2024 Dynamic Planning for LLM-based Graphical User Interface Automation EMNLP 2024 Efficient Domain Adaptation for Non-Autoregressive Machine Translation ACL 2024 On the Hallucination in Simultaneous Machine Translation ACL 2024 DUAL-REFLECT: Enhancing Large Language Models for Reflective Translation through Dual Learning Feedback Mechanisms ACL 2024 Context Consistency between Training and Inference in Simultaneous Machine Translation ACL 2024 Unsupervised Sign Language Translation and Generation ACL 2024 Speech Sense Disambiguation: Tackling Homophone Ambiguity in End-to-End Speech Translation ACL 2024 Paying More Attention to Source Context: Mitigating Unfaithful Translations from Large Language Model ACL 2024 Improving Low-resource Question Answering by Augmenting Question Information EMNLP 2023 PromptST: Abstract Prompt Learning for End-to-End Speech Translation EMNLP 2023 Improving Translation Quality Estimation with Bias Mitigation ACL 2023 A Closer Look at Transformer Attention for Multilingual Translation EMNLP 2023 INFORM : Information eNtropy based multi-step reasoning FOR large language Models EMNLP 2023 Effective Graph Context Representation for Document-level Machine Translation IJCAI 2022 Document-Level Relation Extraction with Sentences Importance Estimation and Focusing NAACL 2022 Synchronous Refinement for Neural Machine Translation ACL 2022 Discriminative Reasoning for Document-level Relation Extraction ACL 2021 Syntax in End-to-End Natural Language Processing EMNLP 2021 Discriminative Reasoning for Document-level Relation Extraction IJCNLP 2021 Self-Training for Unsupervised Neural Machine Translation in Unbalanced Training Data Scenarios NAACL 2021 Document-Level Relation Extraction with Reconstruction AAAI 2021 Robust Unsupervised Neural Machine Translation with Adversarial Denoising Training COLING 2020 Content Word Aware Neural Machine Translation ACL 2020 Knowledge Distillation for Multilingual Unsupervised Neural Machine Translation ACL 2020 SJTU-NICT’s Supervised and Unsupervised Neural Machine Translation Systems for the WMT20 News Translation Task EMNLP 2020 Robust Machine Reading Comprehension by Learning Soft labels COLING 2020 Explicit Sentence Compression for Neural Machine Translation AAAI 2020 Data-dependent Gaussian Prior Objective for Language Generation ICLR 2020 Neural Machine Translation with Universal Visual Representation ICLR 2020 Neural Machine Translation with Reordering Embeddings ACL 2019 Unsupervised Bilingual Word Embedding Agreement for Unsupervised Neural Machine Translation ACL 2019 NICT’s Supervised Neural Machine Translation Systems for the WMT19 News Translation Task ACL 2019 English-Myanmar Supervised and Unsupervised NMT: NICT’s Machine Translation Systems at WAT-2019 EMNLP 2019 Recurrent Positional Embedding for Neural Machine Translation EMNLP 2019 Recurrent Positional Embedding for Neural Machine Translation IJCNLP 2019 Lattice-Based Transformer Encoder for Neural Machine Translation ACL 2019 Sentence-Level Agreement for Neural Machine Translation ACL 2019 NICT’s Unsupervised Neural and Statistical Machine Translation Systems for the WMT19 News Translation Task ACL 2019 Neural Machine Translation with Source Dependency Representation EMNLP 2017 Context-Aware Smoothing for Neural Machine Translation IJCNLP 2017 Instance Weighting for Neural Machine Translation Domain Adaptation EMNLP 2017