| BeautifulPrompt: Towards Automatic Prompt Engineering for Text-to-Image Synthesis | 
 | 
 | :heavy_minus_sign: |
| Enhancing Language Model with Unit Test Techniques for Efficient Regular Expression Generation | :heavy_minus_sign: | | :heavy_minus_sign: |
| A Comparative Analysis of Task-Agnostic Distillation Methods for Compressing Transformer Language Models | :heavy_minus_sign: |
 | :heavy_minus_sign: |
| Towards Effective Automatic Debt Collection with Persona Awareness | :heavy_minus_sign: | | :heavy_minus_sign: |
| Gatekeeper to Save COGS and Improve Efficiency of Text Prediction | :heavy_minus_sign: | | :heavy_minus_sign: |
| Efficient Transformer Knowledge Distillation: A Performance Review | :heavy_minus_sign: |
 | :heavy_minus_sign: |
| CDD: A Large Scale Dataset for Legal Intelligence Research | :heavy_minus_sign: | | :heavy_minus_sign: |
| MUST&P-SRL: Multi-Lingual and Unified Syllabification in Text and Phonetic Domains for Speech Representation Learning |  |
 | :heavy_minus_sign: |
| Personalized Dense Retrieval on Global Index for Voice-Enabled Conversational Systems | :heavy_minus_sign: | | :heavy_minus_sign: |
| Text2Topic: Multi-Label Text Classification System for Efficient Topic Detection in User Generated Content with Zero-Shot Capabilities | :heavy_minus_sign: |
 | :heavy_minus_sign: |
| Deep Metric Learning to Hierarchically Rank - An Application in Product Retrieval | :heavy_minus_sign: | | :heavy_minus_sign: |
| A Pretrained Language Model for Cyber Threat Intelligence | :heavy_minus_sign: | | :heavy_minus_sign: |
| SAMP: A Model Inference Toolkit of Post-Training Quantization for Text Processing via Self-Adaptive Mixed-Precision | :heavy_minus_sign: | | :heavy_minus_sign: |
| KD-Boost: Boosting Real-Time Semantic Matching in E-Commerce with Knowledge Distillation | :heavy_minus_sign: | | :heavy_minus_sign: |
| Multi-Teacher Distillation for Multilingual Spelling Correction | :heavy_minus_sign: |
 | :heavy_minus_sign: |
| Does Named Entity Recognition Truly Not Scale Up to Real-World Product Attribute Extraction? | :heavy_minus_sign: | | :heavy_minus_sign: |
| Investigating Table-to-Text Generation Capabilities of Large Language Models in Real-World Information Seeking Scenarios |  |
 | :heavy_minus_sign: |
| TMID: A Comprehensive Real-World Dataset for Trademark Infringement Detection in E-Commerce | :heavy_minus_sign: | | :heavy_minus_sign: |
| Joint Dialogue Topic Segmentation and Categorization: A Case Study on Clinical Spoken Conversations | :heavy_minus_sign: | | :heavy_minus_sign: |
| AdapterDistillation: Non-Destructive Task Composition with Knowledge Distillation | :heavy_minus_sign: | | :heavy_minus_sign: |
| PROMINET: Prototype-based Multi-View Network for Interpretable Email Response Prediction | :heavy_minus_sign: |
 | :heavy_minus_sign: |
| Retrieval-Enhanced Dual Encoder Training for Product Matching | :heavy_minus_sign: | | :heavy_minus_sign: |
| WordArt Designer: User-Driven Artistic Typography Synthesis using Large Language Models | :heavy_minus_sign: |
 |  |
| Lattice Path Edit Distance: A Romanization-Aware Edit Distance for Extracting Misspelling-Correction Pairs from Japanese Search Query Logs | :heavy_minus_sign: | | :heavy_minus_sign: |
| Learning Multilingual Sentence Representations with Cross-Lingual Consistency Regularization |  |
 | :heavy_minus_sign: |
| Unveiling Identity Biases in Toxicity Detection: A Game-Focused Dataset and Reactivity Analysis Approach | :heavy_minus_sign: | | :heavy_minus_sign: |
| ORANGE: Text-Video Retrieval via Watch-Time-Aware Heterogeneous Graph Contrastive Learning | :heavy_minus_sign: | | :heavy_minus_sign: |
| Compute-Efficient Churn Reduction for Conversational Agents | :heavy_minus_sign: | | :heavy_minus_sign: |
| Empower Large Language Model to Perform Better on Industrial Domain-Specific Question Answering |  |
 | :heavy_minus_sign: |
| Enhancing Extreme Multi-Label Text Classification: Addressing Challenges in Model, Data, and Evaluation | :heavy_minus_sign: | | :heavy_minus_sign: |
| Query-Aware Multi-Modal based Ranking Relevance in Video Search | :heavy_minus_sign: | | :heavy_minus_sign: |
| Coordinated Replay Sample Selection for Continual Federated Learning | :heavy_minus_sign: |
 | :heavy_minus_sign: |
| Building Real-World Meeting Summarization Systems using Large Language Models: A Practical Perspective | :heavy_minus_sign: |
 | :heavy_minus_sign: |
| Creator Context for Tweet Recommendation | :heavy_minus_sign: |
 | :heavy_minus_sign: |
| AdaBERT-CTC: Leveraging BERT-CTC for Text-Only Domain Adaptation in ASR | :heavy_minus_sign: | | :heavy_minus_sign: |
| Conversing with Databases: Practical Natural Language Querying | :heavy_minus_sign: | | :heavy_minus_sign: |
| AART: AI-Assisted Red-Teaming with Diverse Data Generation for New LLM-powered Applications |  |
 | :heavy_minus_sign: |
| Speakerly: A Voice-based Writing Assistant for Text Composition | :heavy_minus_sign: |
 | :heavy_minus_sign: |
| Are ChatGPT and GPT-4 General-Purpose Solvers for Financial Text Analytics? A Study on Several Typical Tasks | :heavy_minus_sign: |
 | :heavy_minus_sign: |
| CL-QR: Cross-Lingual Enhanced Query Reformulation for Multi-Lingual Conversational AI Agents | :heavy_minus_sign: | | :heavy_minus_sign: |
| Improving Contextual Query Rewrite for Conversational AI Agents through User-Preference Feedback Learning | :heavy_minus_sign: | | :heavy_minus_sign: |
| Scaling Neural ITN for Numbers and Temporal Expressions in Tamil: Findings for an Agglutinative Low-Resource Language | :heavy_minus_sign: | | :heavy_minus_sign: |
| EELBERT: Tiny Models through Dynamic Embeddings | :heavy_minus_sign: |
 | :heavy_minus_sign: |
| Gold Standard Bangla OCR Dataset: An In-Depth Look at Data Preprocessing and Annotation Processes | :heavy_minus_sign: | | :heavy_minus_sign: |
| PILLOW: Enhancing Efficient Instruction Fine-Tuning via Prompt Matching | :heavy_minus_sign: | | :heavy_minus_sign: |
| Welcome to the Real World: Efficient, Incremental and Scalable Key Point Analysis | :heavy_minus_sign: | | :heavy_minus_sign: |
| Automatic Linking of Judgements to UK Supreme Court Hearings | :heavy_minus_sign: | | :heavy_minus_sign: |
| Automatic Marketing Theme and Commodity Construction System for E-Commerce | :heavy_minus_sign: | | :heavy_minus_sign: |
| Towards Safer Operations: An Expert-Involved Dataset of High-Pressure Gas Incidents for Preventing Future Failures |  |
 | :heavy_minus_sign: |
| An Auxiliary Task Boosted Multi-Task Learning Method for Service Account Retrieval with Limited Human Annotation | :heavy_minus_sign: | | :heavy_minus_sign: |
| VKIE: The Application of Key Information Extraction on Video Text | :heavy_minus_sign: |
 | :heavy_minus_sign: |
| Investigating the Role and Impact of Disfluency on Summarization | :heavy_minus_sign: | | :heavy_minus_sign: |
| InsightNet: Structured Insight Mining from Customer Feedback | :heavy_minus_sign: | | :heavy_minus_sign: |
| E2E Spoken Entity Extraction for Virtual Agents | :heavy_minus_sign: |
 | :heavy_minus_sign: |
| Generative Models for Product Attribute Extraction | :heavy_minus_sign: | | :heavy_minus_sign: |
| CarExpert: Leveraging Large Language Models for In-Car Conversational Question Answering | :heavy_minus_sign: |
 | :heavy_minus_sign: |
| BUSTER: A ''BUSiness Transaction Entity Recognition'' Dataset | :heavy_minus_sign: | | :heavy_minus_sign: |
| Multi-Word Tokenization for Sequence Compression | 
 | | :heavy_minus_sign: |
| JarviX: A LLM no Code Platform for Tabular Data Analysis and Optimization | :heavy_minus_sign: |
 | :heavy_minus_sign: |
| Retrieve and Copy: Scaling ASR Personalization to Large Catalogs | :heavy_minus_sign: |
 | :heavy_minus_sign: |
| STEER: Semantic Turn Extension-Expansion Recognition for Voice Assistants | :heavy_minus_sign: |
 | :heavy_minus_sign: |
| Self-Criticism: Aligning Large Language Models with their Understanding of Helpfulness, Honesty, and Harmlessness | :heavy_minus_sign: | | :heavy_minus_sign: |
| InstructPTS: Instruction-Tuning LLMs for Product Title Summarization | :heavy_minus_sign: |
 | :heavy_minus_sign: |
| LLM4Vis: Explainable Visualization Recommendation using ChatGPT |  |
 | :heavy_minus_sign: |
| DUBLIN: Visual Document Understanding By Language-Image Network | :heavy_minus_sign: | | :heavy_minus_sign: |
| DocumentNet: Bridging the Data Gap in Document Pre-Training | :heavy_minus_sign: |
 | :heavy_minus_sign: |
| Relevance-Assisted Generation for Robust Zero-Shot Retrieval |  | | :heavy_minus_sign: |
| Too Much of Product Information: Don't Worry, Let's Look for Evidence! | :heavy_minus_sign: | | :heavy_minus_sign: |
| Harnessing LLMs for Temporal Data - A Study on Explainable Financial Time Series Forecasting | :heavy_minus_sign: | | :heavy_minus_sign: |
| ViGPTQA - State-of-the-Art LLMs for Vietnamese Question Answering: System Overview, Core Models Training, and Evaluations | :heavy_minus_sign: | | :heavy_minus_sign: |
| An Integrated Search System for Korea Weather Data | :heavy_minus_sign: | | :heavy_minus_sign: |
| Adaptive Hyper-Parameter Learning for Deep Semantic Retrieval | :heavy_minus_sign: | | :heavy_minus_sign: |
| On Sample-Efficient Code Generation | :heavy_minus_sign: | | :heavy_minus_sign: |
| Batch Prompting: Efficient Inference with Large Language Model APIs |  |
 | :heavy_minus_sign: |
| Graph Meets LLM: A Novel Approach to Collaborative Filtering for Robust Conversational Understanding | :heavy_minus_sign: |
 | :heavy_minus_sign: |
| DELPHI: Data for Evaluating LLMs' Performance in Handling Controversial Issues |  |
 | :heavy_minus_sign: |
| Angel: Enterprise Search System for the Non-Profit Industry |  | | :heavy_minus_sign: |
