# Generating High-Quality and Informative Conversation Responses with Sequence-to-Sequence Models

arXiv: https://arxiv.org/abs/1701.03185 · HTML: https://mlsanity.com/paper/1701.03185/

## Key facts

- Cited by 42 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Jan 2017.

## Built on by (most cited first, 30 of 42)

- [StarVector: Generating Scalable Vector Graphics Code from Images and Text](https://mlsanity.com/paper/2312.11556/) (2023)
- [Amortizing intractable inference in large language models](https://mlsanity.com/paper/2310.04363/) (2023)
- [On Decoding Strategies for Neural Text Generators](https://mlsanity.com/paper/2203.15721/) (2022)
- [TalkToModel: Explaining Machine Learning Models with Interactive Natural Language Conversations](https://mlsanity.com/paper/2207.04154/) (2022)
- [Attention, please! A survey of Neural Attention Models in Deep Learning](https://mlsanity.com/paper/2103.16775/) (2021)
- [RevCore: Review-augmented Conversational Recommendation](https://mlsanity.com/paper/2106.00957/) (2021)
- [Long Text Generation by Modeling Sentence-Level and Discourse-Level Coherence](https://mlsanity.com/paper/2105.08963/) (2021)
- [Weight Ensembling Improves Reasoning in Language Models](https://mlsanity.com/paper/2504.10478/) (2025)
- [Adaptive Contrastive Search: Uncertainty-Guided Decoding for Open-Ended Text Generation](https://mlsanity.com/paper/2407.18698/) (2024)
- [Evaluating Mixed-initiative Conversational Search Systems via User Simulation](https://mlsanity.com/paper/2204.08046/) (2022)
- [Stealing the Decoding Algorithms of Language Models](https://mlsanity.com/paper/2303.04729/) (2023)
- [OpenViDial 2.0: A Larger-Scale, Open-Domain Dialogue Generation Dataset with Visual Contexts](https://mlsanity.com/paper/2109.12761/) (2021)
- [Waterfall: Framework for Robust and Scalable Text Watermarking and Provenance for LLMs](https://mlsanity.com/paper/2407.04411/) (2024)
- [Knowledge Infused Decoding](https://mlsanity.com/paper/2204.03084/) (2022)
- [EIPE-text: Evaluation-Guided Iterative Plan Extraction for Long-Form Narrative Text Generation](https://mlsanity.com/paper/2310.08185/) (2023)
- [FLAP: Flow-Adhering Planning with Constrained Decoding in LLMs](https://mlsanity.com/paper/2403.05766/) (2024)
- [Learning from flowsheets: A generative transformer model for autocompletion of flowsheets](https://mlsanity.com/paper/2208.00859/) (2022)
- [Towards Efficiently Diversifying Dialogue Generation via Embedding Augmentation](https://mlsanity.com/paper/2103.01534/) (2021)
- [Conversational Semantic Role Labeling](https://mlsanity.com/paper/2104.04947/) (2021)
- [Investigating Regularization of Self-Play Language Models](https://mlsanity.com/paper/2404.04291/) (2024)
- [Improving Diversity in Language Models: When Temperature Fails, Change the Loss](https://mlsanity.com/paper/2508.09654/) (2025)
- [Towards Standard Criteria for human evaluation of Chatbots: A Survey](https://mlsanity.com/paper/2105.11197/) (2021)
- [Applying Automatic Text Summarization for Fake News Detection](https://mlsanity.com/paper/2204.01841/) (2022)
- [Grounding in social media: An approach to building a chit-chat dialogue model](https://mlsanity.com/paper/2206.05696/) (2022)
- [Muscles in Time: Learning to Understand Human Motion by Simulating Muscle Activations](https://mlsanity.com/paper/2411.00128/) (2024)
- [Language Model Evaluation in Open-ended Text Generation](https://mlsanity.com/paper/2108.03578/) (2021)
- [Bootstrapping Multilingual Semantic Parsers using Large Language Models](https://mlsanity.com/paper/2210.07313/) (2022)
- [HU at SemEval-2024 Task 8A: Can Contrastive Learning Learn Embeddings to Detect Machine-Generated Text?](https://mlsanity.com/paper/2402.11815/) (2024)
- [Explicit Diversity Conditions for Effective Question Answer Generation with Large Language Models](https://mlsanity.com/paper/2406.17990/) (2024)
- [Finch: Prompt-guided Key-Value Cache Compression](https://mlsanity.com/paper/2408.00167/) (2024)

## Abstract (arXiv)

Sequence-to-sequence models have been applied to the conversation response generation problem where the source sequence is the conversation history and the target sequence is the response. Unlike translation, conversation responding is inherently creative. The generation of long, informative, coherent, and diverse responses remains a hard task. In this work, we focus on the single turn setting. We add self-attention to the decoder to maintain coherence in longer responses, and we propose a practical approach, called the glimpse-model, for scaling to large datasets. We introduce a stochastic beam-search algorithm with segment-by-segment reranking which lets us inject diversity earlier in the generation process. We trained on a combined data set of over 2.3B conversation messages mined from the web. In human evaluation studies, our method produces longer responses overall, with a higher proportion rated as acceptable and excellent as length increases, compared to baseline sequence-to-sequence models with explicit length-promotion. A back-off strategy produces better responses overall, in the full spectrum of lengths.