Xiaodong Liu

Towards Consistent Natural-Language Explanations via Explanation-Consistency Finetuning COLING 2025 Iterative Self-Tuning LLMs for Enhanced Jailbreaking Capabilities NAACL 2025 ProMEA: Prompt-driven Expansion and Alignment for Single Domain Generalization IJCAI 2025 SWEA: Updating Factual Knowledge in Large Language Models via Subject Word Embedding Altering AAAI 2025 Towards Verifiable Text Generation with Generative Agent AAAI 2025 Diversifying the Expert Knowledge for Task-Agnostic Pruning in Sparse Mixture-of-Experts ACL 2025 Generative Adapter: Contextualizing Language Models in Parameters with A Single Forward Pass ICLR 2025 Stand on The Shoulders of Giants: Building JailExpert from Previous Attack Experience EMNLP 2025 Fast-ELECTRA for Efficient Pre-training ICLR 2024 Language Models as Inductive Reasoners EACL 2024 Tell Your Model Where to Attend: Post-hoc Attention Steering for LLMs ICLR 2024 ReEval: Automatic Hallucination Evaluation for Retrieval-Augmented Large Language Models via Transferable Adversarial Attacks NAACL 2024 Optimal Auction Design with User Coupons in Advertising Systems IJCAI 2024 Task-Aware Specialization for Efficient and Robust Dense Retrieval for Open-Domain Question Answering ACL 2023 Deep Generative Modeling on Limited Data with Regularization by Nontransferable Pre-trained Models ICLR 2023 Pre-training Multi-task Contrastive Learning Models for Scientific Literature Understanding EMNLP 2023 Visually-Augmented Language Modeling ICLR 2023 Auto-bidding with Budget and ROI Constrained Buyers IJCAI 2023 Understand and Modularize Generator Optimization in ELECTRA-style Pretraining ICML 2023 Bridging Discrete and Backpropagation: Straight-Through and Beyond NIPS 2023 Augmenting Language Models with Long-Term Memory NIPS 2023 Chain-of-Skills: A Configurable Model for Open-Domain Question Answering ACL 2023 Model-Generated Pretraining Signals Improves Zero-Shot Generalization of Text-to-Text Transformers ACL 2023 AutoMoE: Heterogeneous Mixture-of-Experts with Adaptive Computation for Efficient Neural Machine Translation ACL 2023 Taming Sparsely Activated Transformer with Stochastic Experts ICLR 2022 AdaMix: Mixture-of-Adaptations for Parameter-efficient Model Tuning EMNLP 2022 Knowledge-Rich Self-Supervision for Biomedical Entity Linking EMNLP 2022 Open-domain Question Answering via Chain of Reasoning over Heterogeneous Knowledge EMNLP 2022 LiST: Lite Prompted Self-training Makes Parameter-efficient Few-shot Learners NAACL 2022 Human Parity on CommonsenseQA: Augmenting Self-Attention with External Attention IJCAI 2022 Few-shot Task-agnostic Neural Architecture Search for Distilling Large Language Models NIPS 2022 Open Domain Question Answering with A Unified Knowledge Interface ACL 2022 PTSEFormer: Progressive Temporal-Spatial Enhanced TransFormer towards Video Object Detection ECCV 2022 No Parameters Left Behind: Sensitivity Guided Adaptive Learning Rate for Training Large Transformer Models ICLR 2022 Token-wise Curriculum Learning for Neural Machine Translation EMNLP 2021 Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer NIPS 2021 UnitedQA: A Hybrid Approach for Open Domain Question Answering ACL 2021 Generation-Augmented Retrieval for Open-Domain Question Answering ACL 2021 Super Tickets in Pre-Trained Language Models: From Model Compression to Improving Generalization ACL 2021 Reader-Guided Passage Reranking for Open-Domain Question Answering ACL 2021 Adversarial Regularization as Stackelberg Game: An Unrolled Optimization Approach EMNLP 2021 HittER: Hierarchical Transformers for Knowledge Graph Embeddings EMNLP 2021 ARCH: Efficient Adversarial Regularized Training with Caching EMNLP 2021 DEBERTA: DECODING-ENHANCED BERT WITH DISENTANGLED ATTENTION ICLR 2021 UnitedQA: A Hybrid Approach for Open Domain Question Answering IJCNLP 2021 Generation-Augmented Retrieval for Open-Domain Question Answering IJCNLP 2021 Super Tickets in Pre-Trained Language Models: From Model Compression to Improving Generalization IJCNLP 2021 Reader-Guided Passage Reranking for Open-Domain Question Answering IJCNLP 2021 Posterior Differential Regularization with f-divergence for Improving Model Robustness NAACL 2021 Targeted Adversarial Training for Natural Language Understanding NAACL 2021 RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parsers ACL 2020 SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization ACL 2020 On the Variance of the Adaptive Learning Rate and Beyond ICLR 2020 A Tale of Two Linkings: Dynamically Gating between Schema Linking and Structural Linking for Text-to-SQL Parsing COLING 2020 UniLMv2: Pseudo-Masked Language Models for Unified Language Model Pre-Training ICML 2020 The Microsoft Toolkit of Multi-Task Deep Neural Networks for Natural Language Understanding ACL 2020 Understanding the Difficulty of Training Transformers EMNLP 2020 Adversarial Training for Commonsense Inference ACL 2020 Unified Language Model Pre-training for Natural Language Understanding and Generation NIPS 2019 Multi-Task Deep Neural Networks for Natural Language Understanding ACL 2019 Cyclical Annealing Schedule: A Simple Approach to Mitigating KL Vanishing NAACL 2019 Unsupervised Deep Structured Semantic Models for Commonsense Reasoning NAACL 2019 DoubleTransfer at MEDIQA 2019: Multi-Source Transfer Learning for Natural Language Understanding in the Medical Domain ACL 2019 Conversing by Reading: Contentful Neural Conversation with On-demand Machine Reading ACL 2019 Adversarial Domain Adaptation for Machine Reading Comprehension EMNLP 2019 A Hybrid Neural Network Model for Commonsense Reasoning EMNLP 2019 Adversarial Domain Adaptation for Machine Reading Comprehension IJCNLP 2019 Multi-task Learning with Sample Re-weighting for Machine Reading Comprehension NAACL 2019 Language-Based Image Editing With Recurrent Attentive Models CVPR 2018 Stochastic Answer Networks for Machine Reading Comprehension ACL 2018 Navigating with Graph Representations for Fast and Scalable Decoding of Neural Language Models NIPS 2018 Lexical Simplification with the Deep Structured Similarity Model IJCNLP 2017 An Empirical Analysis of Multiple-Turn Reasoning Strategies in Reading Comprehension Tasks IJCNLP 2017 Representation Learning Using Multi-Task Deep Neural Networks for Semantic Classification and Information Retrieval NAACL 2015 Topic Models + Word Alignment = A Flexible Framework for Extracting Bilingual Dictionary from Comparable Corpus CONLL 2013