Chat-Ghosting: A Comparative Study of Methods for Auto-Completion in Dialog Systems
Not on the map. Why?
Abstract (arXiv)
Ghosting, the ability to predict a user's intended text input for inline query auto-completion, is an invaluable feature for modern search engines and chat interfaces, greatly enhancing user experience. By suggesting completions to incomplete queries (or prefixes), ghosting aids users with slow typing speeds, disabilities, or limited language proficiency. Ghosting is a challenging problem and has become more important with the ubiquitousness of chat-based systems like ChatGPT, Copilot, etc. Despite the increasing prominence of chat-based systems utilizing ghosting, this challenging problem of Chat-Ghosting has received little attention from the NLP/ML research community. There is a lack of standardized benchmarks and relative performance analysis of deep learning and non-deep learning methods. We address this through an open and thorough study of this problem using four publicly available dialog datasets: two human-human (DailyDialog and DSTC7-Ubuntu) and two human-bot (Open Assistant and ShareGPT). We experiment with various existing query auto-completion methods (using tries), n-gram methods and deep learning methods, with and without dialog context. We also propose a novel entropy-based dynamic early stopping strategy. Our analysis finds that statistical n-gram models and tries outperform deep learning based models in terms of both model performance and inference efficiency for seen prefixes. For unseen queries, neural models like T5 and Phi-2 lead to better results. Adding conversational context leads to significant improvements in ghosting quality, especially for Open-Assistant and ShareGPT. We make code and data publicly available
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 43 of its 86 references that are in the map. First posted on arXiv 8 Jul 2025.
Builds on
43 of 86 references.
References · 43
- 2020Language Models are Few-Shot Learnerscited by 32,199
- 2023GPT-4 Technical Reportcited by 18,132
- 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
- 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
- 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
- 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,291
- 2022GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformerscited by 1,838
- 2023AWQ: Activation-aware Weight Quantization for LLM Compression and Accelerationcited by 1,234
- 2019DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generationcited by 842
- 2023OpenAssistant Conversations -- Democratizing Large Language Model Alignmentcited by 712
- 2017DailyDialog: A Manually Labelled Multi-turn Dialogue Datasetcited by 649
- 2020Recipes for building an open-domain chatbotcited by 593
31 more
- 2020Towards a Human-like Open-Domain Chatbotcited by 467
- 2021DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Expertscited by 434
- 2022Quark: Controllable Text Generation with Reinforced Unlearningcited by 236
- 2017Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoderscited by 222
- 2021Internet-Augmented Dialogue Generationcited by 217
- 2015Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Modelscited by 207
- 2016A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialoguescited by 174
- 2015The Ubuntu Dialogue Corpus: A Large Dataset for Research in Unstructured Multi-Turn Dialogue Systemscited by 172
- 2019Poly-encoders: Transformer Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoringcited by 164
- 2019PLATO: Pre-trained Dialogue Generation Model with Discrete Latent Variablecited by 145
- 2024DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inferencecited by 106
- 2019Gmail Smart Compose: Real-Time Assisted Writingcited by 97
- 2019ConveRT: Efficient and Accurate Conversational Representations from Transformerscited by 95
- 2015A Hierarchical Recurrent Encoder-Decoder For Generative Context-Aware Query Suggestioncited by 68
- 2020Compression of Deep Learning Models for Text: A Surveycited by 64
- 2020Do Response Selection Models Really Know What's Next? Utterance Manipulation Strategies for Multi-turn Response Selectioncited by 36
- 2020Learning an Effective Context-Response Matching Model with Self-Supervised Tasks for Retrieval-based Dialoguescited by 34
- 2017Learning to Attend, Copy, and Generate for Session-Based Query Suggestioncited by 22
- 2020Compiling ONNX Neural Network Models Using MLIRcited by 18
- 2017A Conditional Variational Framework for Dialog Generationcited by 16
- 2020Hierarchical Transformer for Task Oriented Dialog Systemscited by 14
- 2018Personalized neural language models for real-world query auto completioncited by 10
- 2020Efficient Neural Query Auto Completioncited by 10
- 2022An Empirical Study on the Overlapping Problem of Open-Domain Dialogue Datasetscited by 8
- 2019Sequential Attention-based Network for Noetic End-to-End Response Selectioncited by 6
- 2020Faster Transformer Decoding: N-gram Masked Self-Attentioncited by 6
- 2019Subword Language Model for Query Auto-Completioncited by 4
- 2020Efficient and Effective Query Auto-Completioncited by 4
- 2021Improving Text Auto-Completion with Next Phrase Predictioncited by 4
- 2021Representation Learning for Conversational Data using Discourse Mutual Information Maximizationcited by 4
- 2024ChaI-TeA: A Benchmark for Evaluating Autocompletion of Interactions with LLM-based Chatbotscited by 1
Built on by
Citing papers per year: 2026: 1.
1 paper.