AAAI-2024-Papers Application Natural Language Processing 🆔 Title Repo Paper Video Frame Semantic Role Labeling Using Arbitrary-Order Conditional Random Fields ➖ DTF-AT: Decoupled Time-Frequency Audio Transformer for Event Classification ➖ WikiSQE: A Large-Scale Dataset for Sentence Quality Estimation in Wikipedia ➖ Beyond Grounding: Extracting Fine-Grained Event Hierarchies across Modalities ➖ All Should Be Equal in the Eyes of LMs: Counterfactually Aware Fair Text Generation ➖ Graph of Thoughts: Solving Elaborate Problems with Large Language Models ➖ When Do Program-of-Thought Works for Reasoning? ➖ Beyond Attention: Breaking the Limits of Transformer Context Length with Recurrent Memory ➖ MedBench: A Large-Scale Chinese Benchmark for Evaluating Medical Large Language Models ➖ CAR-Transformer: Cross-Attention Reinforcement Transformer for Cross-Lingual Summarization ➖ Compositional Generalization for Multi-Label Text Classification: A Data-Augmentation Approach ➖ Counterfactual-Enhanced Information Bottleneck for Aspect-Based Sentiment Analysis ➖ Visual Instruction Tuning with Polite Flamingo ➖ Benchmarking Large Language Models in Retrieval-Augmented Generation ➖ CIDR: A Cooperative Integrated Dynamic Refining Method for Minimal Feature Removal Problem ➖ Is a Large Language Model a Good Annotator for Event Extraction? ➖ Modeling Adaptive Inter-Task Feature Interactions via Sentiment-Aware Contrastive Learning for Joint Aspect-Sentiment Prediction ➖ From Coarse to Fine: A Distillation Method for Fine-Grained Emotion-Causal Span Pair Extraction in Conversation ➖ Divergence-Guided Simultaneous Speech Translation ➖ Benchmarking Large Language Models on Controllable Generation under Diversified Instructions ➖ Journey to the Center of the Knowledge Neurons: Discoveries of Language-Independent Knowledge Neurons and Degenerate Knowledge Neurons ➖ Talk Funny! A Large-Scale Humor Response Dataset with Chain-of-Humor Interpretation ➖ Editing Language Model-Based Knowledge Graph Embeddings ➖ Towards Multi-Intent Spoken Language Understanding via Hierarchical Attention and Optimal Transport ➖ Cooper: Coordinating Specialized Agents towards a Complex Dialogue Goal ➖ DDDM-VC: Decoupled Denoising Diffusion Models with Disentangled Representation and Prior Mixup for Verified Robust Voice Conversion ➖ How to Protect Copyright Data in Optimization of Large Language Models? ➖ Unsupervised Layer-Wise Score Aggregation for Textual OOD Detection ➖ Spanning the Spectrum of Hatred Detection: A Persian Multi-Label Hate Speech Dataset with Annotator Rationales ➖ Enhancing Bilingual Lexicon Induction via Bi-directional Translation Pair Retrieving ➖ From Retrieval to Generation: A Simple and Unified Generative Model for End-to-End Task-Oriented Dialogue ➖ How to Trade Off the Quantity and Capacity of Teacher Ensemble: Learning Categorical Distribution to Stochastically Employ a Teacher for Distillation ➖ UniCATS: A Unified Context-Aware Text-to-Speech Framework with Contextual VQ-Diffusion and Vocoding ➖ DocMSU: A Comprehensive Benchmark for Document-Level Multimodal Sarcasm Understanding ➖ AdaCCD: Adaptive Semantic Contrasts Discovery Based Cross Lingual Adaptation for Code Clone Detection ➖ Frugal LMs Trained to Invoke Symbolic Solvers Achieve Parameter-Efficient Arithmetic Reasoning ➖ Can Large Language Models Serve as Rational Players in Game Theory? A Systematic Analysis ➖ Enhancing Low-Resource Relation Representations through Multi-View Decoupling ➖ Quantum-Inspired Neural Network with Runge-Kutta Method ➖ Large Language Models Are Neurosymbolic Reasoners ➖ Combining Multiple Supervision for Robust Zero-Shot Dense Retrieval ➖ Watermarking Conditional Text Generation for AI Detection: Unveiling Challenges and a Semantic-Aware Watermark Remedy ➖ BAND: Biomedical Alert News Dataset ➖ Winnie: Task-Oriented Dialog System with Structure-Aware Contrastive Learning and Enhanced Policy Planning ➖ Confucius: Iterative Tool Learning from Introspection Feedback by Easy-to-Difficult Curriculum ➖ Customizing Language Model Responses with Contrastive In-Context Learning ➖ DA-Net: A Disentangled and Adaptive Network for Multi-Source Cross-Lingual Transfer Learning ➖ Discrepancy and Uncertainty Aware Denoising Knowledge Distillation for Zero-Shot Cross-Lingual Named Entity Recognition ➖ Who Knows the Answer? Finding the Best Model and Prompt for Each Query Using Confidence-Based Search ➖ A General Search-Based Framework for Generating Textual Counterfactual Explanations ➖ What Makes Quantization for Large Language Model Hard? An Empirical Study from the Lens of Perturbation ➖ CoPL: Contextual Prompt Learning for Vision-Language Understanding ➖ Xiezhi: An Ever-Updating Benchmark for Holistic Domain Knowledge Evaluation ➖ DINGO: Towards Diverse and Fine-Grained Instruction-Following Evaluation ➖ MM-TTS: Multi-Modal Prompt Based Style Transfer for Expressive Text-to-Speech Synthesis ➖ Mitigating Large Language Model Hallucinations via Autonomous Knowledge Graph-Based Retrofitting ➖ Detecting and Preventing Hallucinations in Large Vision Language Models ➖ MolTailor: Tailoring Chemical Molecular Representation to Specific Tasks via Text Prompts ➖ Audio Generation with Multiple Conditional Diffusion Model ➖ Small Language Model Can Self-Correct ➖ Decoupling Representation and Knowledge for Few-Shot Intent Classification and Slot Filling ➖ Multi-Modal Latent Space Learning for Chain-of-Thought Reasoning in Language Models ➖ Can Large Language Models Understand Real-World Complex Instructions? ➖ Improving Factual Error Correction by Learning to Inject Factual Errors ➖ Text2Analysis: A Benchmark of Table Question Answering with Advanced Data Analysis and Unclear Queries ➖ ParaGuide: Guided Diffusion Paraphrasers for Plug-and-Play Textual Style Transfer ➖ ShareBERT: Embeddings Are Capable of Learning Hidden Layers ➖ LLM vs Small Model? Large Language Model Based Text Augmentation Enhanced Personality Detection Model ➖ Learning Robust Rationales for Model Explainability: A Guidance-Based Approach ➖ Separate the Wheat from the Chaff: Model Deficiency Unlearning via Parameter-Efficient Module Operation ➖ Three Heads Are Better than One: Improving Cross-Domain NER with Progressive Decomposed Network ➖ Uncovering and Mitigating the Hidden Chasm: A Study on the Text-Text Domain Gap in Euphemism Identification ➖ PoetryDiffusion: Towards Joint Semantic and Metrical Manipulation in Poetry Generation ➖ Towards Equipping Transformer with the Ability of Systematic Compositionality ➖ Cross-Modal and Uni-Modal Soft-Label Alignment for Image-Text Retrieval ➖ Response Enhanced Semi-supervised Dialogue Query Generation ➖ PMRC: Prompt-Based Machine Reading Comprehension for Few-Shot Named Entity Recognition ➖ Revisiting Document-Level Relation Extraction with Context-Guided Link Prediction ➖ Enhancing Zero-Shot Multi-Speaker TTS with Negated Speaker Representations ➖ Chain-of-Thought Improves Text Generation with Citations in Large Language Models ➖ Debiasing Multimodal Sarcasm Detection with Contrastive Learning ➖ ZO-AdaMU Optimizer: Adapting Perturbation by the Momentum and Uncertainty in Zeroth-Order Optimization ➖ Unsupervised Extractive Summarization with Learnable Length Control Strategies ➖ BOK-VQA: Bilingual outside Knowledge-Based Visual Question Answering via Graph Representation Pretraining ➖ Improving Knowledge Extraction from LLMs for Task Learning through Agent Analysis ➖ On Unsupervised Domain Adaptation: Pseudo Label Guided Mixup for Adversarial Prompt Tuning ➖ A Hierarchical Network for Multimodal Document-Level Relation Extraction ➖ Large Language Models Are Clinical Reasoners: Reasoning-Aware Diagnosis Framework with Prompt-Generated Rationales ➖ Frequency Spectrum Is More Effective for Multimodal Representation and Fusion: A Multimodal Spectrum Rumor Detector ➖ LAMPAT: Low-Rank Adaption for Multilingual Paraphrasing Using Adversarial Training ➖ Continual Relation Extraction via Sequential Multi-Task Learning ➖ Labels Need Prompts Too: Mask Matching for Natural Language Understanding Tasks ➖ Harnessing Holistic Discourse Features and Triadic Interaction for Sentiment Quadruple Extraction in Dialogues ➖ Task Contamination: Language Models May Not Be Few-Shot Anymore ➖ Dialogue for Prompting: A Policy-Gradient-Based Discrete Prompt Generation for Few-Shot Learning ➖ DeepSpeed Data Efficiency: Improving Deep Learning Model Quality and Training Efficiency via Efficient Data Sampling and Routing ➖ Advancing Spatial Reasoning in Large Language Models: An In-Depth Evaluation and Enhancement Using the StepGame Benchmark ➖ Exploiting Auxiliary Caption for Video Grounding ➖ VLN-Video: Utilizing Driving Videos for Outdoor Vision-and-Language Navigation ➖ Enhancing Multi-Label Classification via Dynamic Label-Order Learning ➖ Norm Tweaking: High-Performance Low-Bit Quantization of Large Language Models ➖ Object Attribute Matters in Visual Question Answering ➖ Translate Meanings, Not Just Words: IdiomKB’s Role in Optimizing Idiomatic Translation with Language Models ➖ PMET: Precise Model Editing in a Transformer ➖ Dialogues Are Not Just Text: Modeling Cognition for Dialogue Coherence Evaluation ➖ EcomGPT: Instruction-Tuning Large Language Models with Chain-of-Task Tasks for E-commerce ➖ Turning Dust into Gold: Distilling Complex Reasoning Capabilities from LLMs by Leveraging Negative Data ➖ LatestEval: Addressing Data Contamination in Language Model Evaluation through Dynamic and Time-Sensitive Test Construction ➖ FlexKBQA: A Flexible LLM-Powered Framework for Few-Shot Knowledge Base Question Answering ➖ Machine-Created Universal Language for Cross-Lingual Transfer ➖ CFEVER: A Chinese Fact Extraction and VERification Dataset ➖ Bootstrapping Large Language Models for Radiology Report Generation ➖ Liberating Seen Classes: Boosting Few-Shot and Zero-Shot Text Classification via Anchor Generation and Classification Reframing ➖ Beyond Entities: A Large-Scale Multi-Modal Knowledge Graph with Triplet Fact Grounding ➖ Chinese Spelling Correction as Rephrasing Language Model ➖ TA&AT: Enhancing Task-Oriented Dialog with Turn-Level Auxiliary Tasks and Action-Tree Based Scheduled Sampling ➖ Hierarchical Aligned Multimodal Learning for NER on Tweet Posts ➖ Adaptive Prompt Routing for Arbitrary Text Style Transfer with Pre-trained Language Models ➖ Emotion Rendering for Conversational Speech Synthesis with Heterogeneous Graph-Based Context Modeling ➖ Robust Evaluation Measures for Evaluating Social Biases in Masked Language Models ➖ Improved Graph Contrastive Learning for Short Text Classification ➖ QuerySum: A Multi-Document Query-Focused Summarization Dataset Augmented with Similar Query Clusters ➖ Generative Multi-Modal Knowledge Retrieval with Large Language Models ➖ Synergistic Anchored Contrastive Pre-training for Few-Shot Relation Extraction ➖ STAR: Boosting Low-Resource Information Extraction by Structure-to-Text Data Generation with Large Language Models ➖ Mastering Context-to-Label Representation Transformation for Event Causality Identification with Diffusion Models ➖ Span Graph Transformer for Document-Level Named Entity Recognition ➖ Underspecification in Language Modeling Tasks: A Causality-Informed Study of Gendered Pronoun Resolution ➖ MCL-NER: Cross-Lingual Named Entity Recognition via Multi-View Contrastive Learning ➖ KAM-CoT: Knowledge Augmented Multimodal Chain-of-Thoughts Reasoning ➖ Accelerating the Global Aggregation of Local Explanations ➖ Self-Supervised Disentangled Representation Learning for Robust Target Speech Extraction ➖ READ-PVLA: Recurrent Adapter with Partial Video-Language Alignment for Parameter-Efficient Transfer Learning in Low-Resource Video-Language Modeling ➖ Code-Style In-Context Learning for Knowledge-Based Question Answering ➖ Aspect-Based Sentiment Analysis with Explicit Sentiment Augmentations ➖ Fact-Driven Logical Reasoning for Machine Reading Comprehension ➖ Preparing Lessons for Progressive Training on Language Models ➖ A Novel Energy Based Model Mechanism for Multi-Modal Aspect-Based Sentiment Analysis ➖ A Joint Framework with Heterogeneous-Relation-Aware Graph and Multi-Channel Label Enhancing Strategy for Event Causality Extraction ➖ MULTISCRIPT: Multimodal Script Learning for Supporting Open Domain Everyday Tasks ➖ Exploring Transformer Extrapolation ➖ Using Artificial Populations to Study Psychological Phenomena in Neural Models ➖ Better than Random: Reliable NLG Human Evaluation with Constrained Active Sampling ➖ VELMA: Verbalization Embodiment of LLM Agents for Vision and Language Navigation in Street View ➖ OntoFact: Unveiling Fantastic Fact-Skeleton of LLMs via Ontology-Driven Reinforcement Learning ➖ Agile-Quant: Activation-Guided Quantization for Faster Inference of LLMs on the Edge ➖ CORECODE: A Common Sense Annotated Dialogue Dataset with Benchmark Tasks for Chinese Large Language Models ➖ A Unified Knowledge Transfer Network for Generalized Category Discovery ➖ RewriteLM: An Instruction-Tuned Large Language Model for Text Rewriting ➖ Well, Now We Know! Unveiling Sarcasm: Initiating and Exploring Multimodal Conversations with Reasoning ➖ Preference Ranking Optimization for Human Alignment ➖ TACIT: A Target-Agnostic Feature Disentanglement Framework for Cross-Domain Text Classification ➖ A Dual-Way Enhanced Framework from Text Matching Point of View for Multimodal Entity Linking ➖ RoPDA: Robust Prompt-Based Data Augmentation for Low-Resource Named Entity Recognition ➖ Wikiformer: Pre-training with Structured Information of Wikipedia for Ad-Hoc Retrieval ➖ SIG: Speaker Identification in Literature via Prompt-Based Generation ➖ Collaborative Synthesis of Patient Records through Multi-Visit Health State Inference ➖ SciEval: A Multi-Level Large Language Model Evaluation Benchmark for Scientific Research ➖ UMIE: Unified Multimodal Information Extraction with Instruction Tuning ➖ InstructDoc: A Dataset for Zero-Shot Generalization of Visual Document Understanding with Instructions ➖ Graph Neural Prompting with Large Language Models ➖ Adaptive Graph Learning for Multimodal Conversational Emotion Detection ➖ Dependency Structure-Enhanced Graph Attention Networks for Event Detection ➖ ESRL: Efficient Sampling-Based Reinforcement Learning for Sequence Generation ➖ Exploring Equation as a Better Intermediate Meaning Representation for Numerical Reasoning of Large Language Models ➖ Manifold-Based Verbalizer Space Re-embedding for Tuning-Free Prompt-Based Classification ➖ Improving the Robustness of Knowledge-Grounded Dialogue via Contrastive Learning ➖ Restoring Speaking Lips from Occlusion for Audio-Visual Speech Recognition ➖ Learning from Failure: Improving Meeting Summarization without Good Samples ➖ T-SciQ: Teaching Multimodal Chain-of-Thought Reasoning via Large Language Model Signals for Science Question Answering ➖ Mitigating the Impact of False Negative in Dense Retrieval with Contrastive Confidence Regularization ➖ DenoSent: A Denoising Objective for Self-Supervised Sentence Representation Learning ➖ LLMRG: Improving Recommendations through Large Language Model Reasoning Graphs ➖ A Positive-Unlabeled Metric Learning Framework for Document-Level Relation Extraction with Incomplete Labeling ➖ Knowledge Graph Prompting for Multi-Document Question Answering ➖ STAIR: Spatial-Temporal Reasoning with Auditable Intermediate Results for Video Question Answering ➖ Video Event Extraction with Multi-View Interaction Knowledge Distillation ➖ ConsistNER: Towards Instructive NER Demonstrations for LLMs with the Consistency of Ontology and Context ➖ Mitigating Idiom Inconsistency: A Multi-Semantic Contrastive Learning Method for Chinese Idiom Reading Comprehension ➖ Improving Open-Domain Dialogue Response Generation with Multi-Source Multilingual Commonsense Knowledge ➖ On the Affinity, Rationality, and Diversity of Hierarchical Topic Modeling ➖ MindMap: Constructing Evidence Chains for Multi-Step Reasoning in Large Language Models ➖ De-biased Attention Supervision for Text Classification with Causality ➖ Get an A in Math: Progressive Rectification Prompting ➖ DIUSum: Dynamic Image Utilization for Multimodal Summarization ➖ Automated Defect Report Generation for Enhanced Industrial Quality Control ➖ ALISON: Fast and Effective Stylometric Authorship Obfuscation ➖ SECap: Speech Emotion Captioning with Large Language Model ➖ Question Calibration and Multi-Hop Modeling for Temporal Question Answering ➖ Robust Few-Shot Named Entity Recognition with Boundary Discrimination and Correlation Purification ➖ Tackling Vision Language Tasks through Learning Inner Monologues ➖ YTCommentQA: Video Question Answerability in Instructional Videos ➖ Zhongjing: Enhancing the Chinese Medical Capabilities of Large Language Model through Expert Feedback and Real-World Multi-Turn Dialogue ➖ Exploring Post-training Quantization in LLMs from Comprehensive Study to Low Rank Compensation ➖ Investigating the Effectiveness of Task-Agnostic Prefix Prompt for Instruction Following ➖ Uni-MIS: United Multiple Intent Spoken Language Understanding via Multi-View Intent-Slot Interaction ➖ TextGT: A Double-View Graph Transformer on Text for Aspect-Based Sentiment Analysis ➖ History Matters: Temporal Knowledge Editing in Large Language Model ➖ Topic-VQ-VAE: Leveraging Latent Codebooks for Flexible Topic-Guided Document Generation ➖ CK12: A Rounded K12 Knowledge Graph Based Benchmark for Chinese Holistic Cognition Evaluation ➖ Reliable Data Generation and Selection for Low-Resource Relation Extraction ➖ MELO: Enhancing Model Editing with Neuron-Indexed Dynamic LoRA ➖ SeqGPT: An Out-of-the-Box Large Language Model for Open Domain Sequence Understanding ➖ TaskLAMA: Probing the Complex Task Understanding of Language Models ➖ An Autoregressive Text-to-Graph Framework for Joint Entity and Relation Extraction ➖ Teaching Large Language Models to Translate with Comparison ➖ InterpretARA: Enhancing Hybrid Automatic Readability Assessment with Linguistic Feature Interpreter and Contrastive Learning ➖ ConsistentEE: A Consistent and Hardness-Guided Early Exiting Method for Accelerating Language Models Inference ➖ A Comprehensive Analysis of the Effectiveness of Large Language Models as Automatic Dialogue Evaluators ➖ PREFER: Prompt Ensemble Learning via Feedback-Reflect-Refine ➖ Causal Walk: Debiasing Multi-Hop Fact Verification with Front-Door Adjustment ➖ Visual Hallucination Elevates Speech Recognition ➖ Quantum Interference Model for Semantic Biases of Glosses in Word Sense Disambiguation ➖ Tree-of-Reasoning Question Decomposition for Complex Question Answering with Large Language Models ➖ What to Remember: Self-Adaptive Continual Learning for Audio Deepfake Detection ➖ A Goal Interaction Graph Planning Framework for Conversational Recommendation ➖ Personalized LoRA for Human-Centered Text Understanding ➖ StyleSinger: Style Transfer for Out-of-Domain Singing Voice Synthesis ➖ Seed-Guided Fine-Grained Entity Typing in Science and Engineering Domains ➖ LLMEval: A Preliminary Study on How to Evaluate Large Language Models ➖ Coreference Graph Guidance for Mind-Map Generation ➖ ExpeL: LLM Agents Are Experiential Learners ➖ Conditional Variational Autoencoder for Sign Language Translation with Cross-Modal Alignment ➖ Graph Reasoning Transformers for Knowledge-Aware Question Answering ➖ MultiSum: A Multi-Facet Approach for Extractive Social Summarization Utilizing Semantic and Sociological Relationships ➖ QPEN: Quantum Projection and Quantum Entanglement Enhanced Network for Cross-Lingual Aspect-Based Sentiment Analysis ➖ SENCR: A Span Enhanced Two-Stage Network with Counterfactual Rethinking for Chinese NER ➖ Reverse Multi-Choice Dialogue Commonsense Inference with Graph-of-Thought ➖ FT-GAN: Fine-Grained Tune Modeling for Chinese Opera Synthesis ➖ Layer-Wise Representation Fusion for Compositional Generalization ➖ You Only Read Once: Constituency-Oriented Relational Graph Convolutional Network for Multi-Aspect Multi-Sentiment Classification ➖ MemoryBank: Enhancing Large Language Models with Long-Term Memory ➖ Fine-Grained Distillation for Long Document Retrieval ➖ Quantifying and Analyzing Entity-Level Memorization in Large Language Models ➖ MathAttack: Attacking Large Language Models towards Math Solving Ability ➖ LimeAttack: Local Explainable Method for Textual Hard-Label Adversarial Attack ➖ Multichannel AV-wav2vec2: A Framework for Learning Multichannel Multi-Modal Speech Representation ➖ Aligner²: Enhancing Joint Multiple Intent Detection and Slot Filling via Adjustive and Forced Cross-Task Alignment ➖ Towards Explainable Joint Models via Information Theory for Multiple Intent Detection and Slot Filling ➖ Video-Context Aligned Transformer for Video Question Answering ➖
