AI

AI Papers

LLM

• CMMLU: Measuring massive multitask language understanding in Chinese
• CodeFuse-13B: A Pretrained Multi-lingual Code Large Language Model
• CrossCodeEval: A Diverse and Multilingual Benchmark for Cross-File Code Completion
• CRUXEval-X: A Benchmark for Multilingual Code Reasoning, Understanding and Execution
• CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution
• DeepSeek-Coder: When the Large Language Model Meets Programming – The Rise of Code Intelligence
• DemoCraft: Using In-Context Learning to Improve Code Generation in Large Language Models
• Efficient Training of Language Models to Fill in the Middle
• Evaluating Large Language Models Trained on Code
• Evaluation of LLMs on Syntax-Aware Code Fill-in-the-Middle Tasks
• InterTrans: Leveraging Transitive Intermediate Translations to Enhance LLM-based Code Translation
• LLM-Eval: Unified Multi-Dimensional Automatic Evaluation for Open-Domain Conversations with Large Language Models
• McEval: Massively Multilingual Code Evaluation
• Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism
• Qwen2.5-Coder Technical Report
• SGLang: Efficient Execution of Structured Language Model Programs
• The Illusion of Thinking
• The Ultimate Guide to Fine-Tuning LLMs from Basics to Breakthroughs: An Exhaustive Review of Technologies, Research, Best Practices, Applied Research Challenges and Opportunities

Natural Language Processing

• A Context-Aware Hierarchical BERT Fusion Network for Multi-turn Dialog Act Detection
• A Label-Aware BERT Attention Network for Zero-Shot Multi-Intent Detection in Spoken Language Understanding
• Application of the transformer model algorithm in Chinese word sense disambiguation: a case study in Chinese language
• Are Pre-trained Transformers Robust in Intent Classification? A Missing Ingredient in Evaluation of Out-of-Scope Intent Detection
• Balancing Accuracy and Efficiency in Multi-Turn Intent Classification for LLM-Powered Dialog Systems in Production
• Benchmarking Zero-shot Text Classification: Datasets, Evaluation and Entailment Approach
• Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data
• Continual Few-shot Intent Detection
• Dual-Objective Fine-Tuning of BERT for Entity Matching
• Effective and Efficient Conversation Retrieval for Dialogue State Tracking with Implicit Text Summaries
• Few-Shot Contrastive Learning-Based Multi-Round Dialog Intent Classification Method
• Few-Shot Intent Detection via Contrastive Pre-Training and Fine-Tuning
• Infusing Context and Knowledge Awareness in Multi-turn Dialog Understanding
• Intent-Aware Dialogue Generation and Multi-Task Contrastive Learning for Multi-Turn Intent Classification
• Intent detection for task-oriented conversational agents: A comparative study of recurrent neural networks and transformer models
• Joint Multiple Intent Detection and Slot Labeling for Goal-Oriented Dialog
• Knowledge Augmented BERT Mutual Network in Multi-turn Spoken Dialogues
• LARA: Lingustic-Adaptive Retrieval-Augmentation for Multi-Turn Intent Classification
• Learning to Bridge Metric Spaces: Few-shot Joint Learning of Intent Detection and Slot Filling
• Long Dialog Summarization: An Analysis
• MIDAS: Multi-level Intent, Domain, And Slot Knowledge Distillation for Multi-turn NLU
• MIDLM: Multi-Intent Detection with Bidirectional Large Language Models
• Multi-turn intent determination and slot filling with neural networks and regular expressions
• MTSI-BERT: A Session-aware Knowledge-based Conversational Agent
• Multi-turn QA: A RNN Contextualized Approach to Intent Classification for Goal-oriented Systems
• Out-of-Domain Intent Detection Considering Multi-Turn Dialogue Contexts
• RoBERTa: A Robustly Optimized BERT Pretraining Approach
• Robust Zero-Shot Intent Detection via Contrastive Transfer Learning
• SELF-ICL: Zero-Shot In-Context Learning with Self-Generated Demonstrations
• Z-ICL: Zero-Shot In-Context Learning with Pseudo-Demonstrations
• 基于多任务蒸馏的意图识别和槽位填充
• 基于小样本学习的意图识别与槽位填充方法 (数据集)

Neural Network

• Intention Recognition with Recurrent Neural Networks for Dynamic Human-Robot Collaboration

Transformer Model

• Attention is All You Need (Reading Notes)
• BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
• Transformed-based Map Matching Model with Limited Ground-Truth Data using Transfer-Learning Approach
• Transformer++
• Transformers: State-of-the-Art Natural Language Processing