Xian Li

ALERT: An LLM-powered Benchmark for Automatic Evaluation of Recommendation Explanations NAACL 2025 Learning to Plan & Reason for Evaluation with Thinking-LLM-as-a-Judge ICML 2025 DORM: Preference Data Weights Optimization for Reward Modeling in LLM Alignment EMNLP 2025 Train a Unified Multimodal Data Quality Classifier with Synthetic Data EMNLP 2025 Forensics-Bench: A Comprehensive Forgery Detection Benchmark Suite for Large Vision Language Models CVPR 2025 UniConv: Unifying Retrieval and Response Generation for Large Language Models in Conversations ACL 2025 MEMORYLLM: Towards Self-Updatable Large Language Models ICML 2024 Self-Alignment with Instruction Backtranslation ICLR 2024 To the Globe (TTG): Towards Language-Driven Guaranteed Travel Planning EMNLP 2024 Branch-Solve-Merge Improves Large Language Model Evaluation and Generation NAACL 2024 Better Alignment with Instruction Back-and-Forth Translation EMNLP 2024 Data Diversity Matters for Robust Instruction Tuning EMNLP 2024 Shopping MMLU: A Massive Multi-Task Online Shopping Benchmark for Large Language Models NIPS 2024 Chain-of-Verification Reduces Hallucination in Large Language Models ACL 2024 Stronger, Lighter, Better: Towards Life-Long Attribute Value Extraction for E-Commerce Products ACL 2024 Self-Rewarding Language Models ICML 2024 Knowledge-Selective Pretraining for Attribute Value Extraction EMNLP 2023 Towards Open-World Product Attribute Mining: A Lightly-Supervised Approach ACL 2023 Tab-Cleaner: Weakly Supervised Tabular Data Cleaning via Pre-training for E-commerce Catalog ACL 2023 PV2TEA: Patching Visual Modality to Textual-Established Information Extraction ACL 2023 Concept2Box: Joint Geometric Embeddings for Learning Two-View Knowledge Graphs ACL 2023 Methods for Measuring, Updating, and Visualizing Factual Beliefs in Language Models EACL 2023 Towards A Unified View of Sparse Feed-Forward Network in Pretraining Large Language Model EMNLP 2023 Generative Models for Product Attribute Extraction EMNLP 2023 Few-shot Learning with Multilingual Generative Language Models EMNLP 2022 Efficient Large Scale Language Modeling with Mixtures of Experts EMNLP 2022 Ask-and-Verify: Span Candidate Generation and Verification for Attribute Value Extraction EMNLP 2022 Prototype-Representations for Training Data Filtering in Weakly-Supervised Information Extraction EMNLP 2022 Unified Speech-Text Pre-training for Speech Translation and Recognition ACL 2022 ATST: Audio Representation Learning with Teacher-Student Transformer INTERSPEECH 2022 Lifting the Curse of Multilinguality by Pre-training Modular Transformers NAACL 2022 ToKen: Task Decomposition and Knowledge Infusion for Few-Shot Hate Speech Detection EMNLP 2022 FST: the FAIR Speech Translation System for the IWSLT21 Multilingual Shared Task ACL 2021 Multilingual Neural Machine Translation with Deep Encoder and Multiple Shallow Decoders EACL 2021 Recipes for Adapting Pre-trained Monolingual and Multilingual Models to Machine Translation EACL 2021 Distributionally Robust Multilingual Machine Translation EMNLP 2021 Pay Better Attention to Attention: Head Selection in Multilingual and Multi-Domain Sequence Modeling NIPS 2021 Improving Speech Translation by Understanding and Learning from the Auxiliary Text Translation Task ACL 2021 Improving Zero-Shot Translation by Disentangling Positional Information ACL 2021 Multilingual Speech Translation from Efficient Finetuning of Pretrained Models ACL 2021 Adaptive Label Noise Cleaning With Meta-Supervision for Deep Face Recognition ICCV 2021 Robust Optimization for Multilingual Translation with Imbalanced Data NIPS 2021 Multilingual Speech Translation from Efficient Finetuning of Pretrained Models IJCNLP 2021 Improving Zero-Shot Translation by Disentangling Positional Information IJCNLP 2021 Improving Speech Translation by Understanding and Learning from the Auxiliary Text Translation Task IJCNLP 2021 Gender bias amplification during Speed-Quality optimization in Neural Machine Translation IJCNLP 2021 Multilingual Translation from Denoising Pre-Training IJCNLP 2021 FST: the FAIR Speech Translation System for the IWSLT21 Multilingual Shared Task IJCNLP 2021 Towards Understanding the Behaviors of Optimal Deep Active Learning Algorithms AISTATS 2021 Multilingual Translation from Denoising Pre-Training ACL 2021 Gender bias amplification during Speed-Quality optimization in Neural Machine Translation ACL 2021 Cross-lingual Retrieval for Iterative Self-Supervised Training NIPS 2020 Deep Transformers with Latent Depth NIPS 2020 Global-Local GCN: Large-Scale Label Noise Cleansing for Face Recognition CVPR 2020 Findings of the WMT 2020 Shared Task on Machine Translation Robustness EMNLP 2020 Findings of the Fourth Workshop on Neural Generation and Translation ACL 2020 Addressing Posterior Collapse with Mutual Information for Improved Variational Neural Machine Translation ACL 2020 Findings of the First Shared Task on Machine Translation Robustness ACL 2019 On Evaluation of Adversarial Perturbations for Sequence-to-Sequence Models NAACL 2019 FlowSeq: Non-Autoregressive Conditional Sequence Generation with Generative Flow IJCNLP 2019 FlowSeq: Non-Autoregressive Conditional Sequence Generation with Generative Flow EMNLP 2019 Deep Voice: Real-time Neural Text-to-Speech ICML 2017 CVTE at IJCNLP-2017 Task 1: Character Checking System for Chinese Grammatical Error Diagnosis Task IJCNLP 2017