# Diversifying Dialog Generation via Adaptive Label Smoothing

arXiv: https://arxiv.org/abs/2105.14556 · HTML: https://mlsanity.com/paper/2105.14556/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 49 references that are in the map.
- First posted on arXiv 30 May 2021.

## Builds on (most cited first, 30 of 36)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [A Diversity-Promoting Objective Function for Neural Conversation Models](https://mlsanity.com/paper/1510.03055/) (2015)
- [When Does Label Smoothing Help?](https://mlsanity.com/paper/1906.02629/) (2019)
- [Sequence-Level Knowledge Distillation](https://mlsanity.com/paper/1606.07947/) (2016)
- [DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset](https://mlsanity.com/paper/1710.03957/) (2017)
- [Neural Text Generation with Unlikelihood Training](https://mlsanity.com/paper/1908.04319/) (2019)
- [Regularizing Neural Networks by Penalizing Confident Output Distributions](https://mlsanity.com/paper/1701.06548/) (2017)
- [Calibrating Deep Neural Networks using Focal Loss](https://mlsanity.com/paper/2002.09437/) (2020)
- [OpenNMT: Open-source Toolkit for Neural Machine Translation](https://mlsanity.com/paper/1709.03815/) (2017)
- [Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders](https://mlsanity.com/paper/1703.10960/) (2017)
- [Challenges in Building Intelligent Open-domain Dialog Systems](https://mlsanity.com/paper/1905.05709/) (2019)
- [Generating Informative and Diverse Conversational Responses via Adversarial Information Maximization](https://mlsanity.com/paper/1809.05972/) (2018)
- [Don't Say That! Making Inconsistent Dialogue Unlikely with Unlikelihood Training](https://mlsanity.com/paper/1911.03860/) (2019)
- [Deep Encoder, Shallow Decoder: Reevaluating Non-autoregressive Machine Translation](https://mlsanity.com/paper/2006.10369/) (2020)
- [Multilingual Neural Machine Translation with Knowledge Distillation](https://mlsanity.com/paper/1902.10461/) (2019)
- [Understanding and Improving Knowledge Distillation](https://mlsanity.com/paper/2002.03532/) (2020)
- [Comparison of Diverse Decoding Methods from Conditional Language Models](https://mlsanity.com/paper/1906.06362/) (2019)
- [A Large-Scale Chinese Short-Text Conversation Dataset](https://mlsanity.com/paper/2008.03946/) (2020)
- [A Pre-training Based Personalized Dialogue Generation Model with Persona-sparse Data](https://mlsanity.com/paper/1911.04700/) (2019)
- [Calibration of Encoder Decoder Models for Neural Machine Translation](https://mlsanity.com/paper/1903.00802/) (2019)
- [Importance of Search and Evaluation Strategies in Neural Dialogue Modeling](https://mlsanity.com/paper/1811.00907/) (2018)
- [Data Manipulation: Towards Effective Instance Learning for Neural Dialogue Generation via Learning to Augment and Reweight](https://mlsanity.com/paper/2004.02594/) (2020)
- [Improving Neural Response Diversity with Frequency-Aware Cross-Entropy Loss](https://mlsanity.com/paper/1902.09191/) (2019)
- [How Decoding Strategies Affect the Verifiability of Generated Text](https://mlsanity.com/paper/1911.03587/) (2019)

## Built on by (most cited first, 25 of 25)

- [Duplex Conversation: Towards Human-like Interaction in Spoken Dialogue Systems](https://mlsanity.com/paper/2205.15060/) (2022)
- [Rethinking and Refining the Distinct Metric](https://mlsanity.com/paper/2202.13587/) (2022)
- [Measuring and Improving Semantic Diversity of Dialogue Generation](https://mlsanity.com/paper/2210.05725/) (2022)
- [An Equal-Size Hard EM Algorithm for Diverse Dialogue Generation](https://mlsanity.com/paper/2209.14627/) (2022)
- [Teacher Forcing Recovers Reward Functions for Text Generation](https://mlsanity.com/paper/2210.08708/) (2022)
- [Estimating Soft Labels for Out-of-Domain Intent Detection](https://mlsanity.com/paper/2211.05561/) (2022)
- [SimOAP: Improve Coherence and Consistency in Persona-based Dialogue Generation via Over-sampling and Post-evaluation](https://mlsanity.com/paper/2305.11130/) (2023)
- [Prompt Conditioned VAE: Enhancing Generative Replay for Lifelong Learning in Task-Oriented Dialogue](https://mlsanity.com/paper/2210.07783/) (2022)
- [An Empirical Study on the Overlapping Problem of Open-Domain Dialogue Datasets](https://mlsanity.com/paper/2201.06219/) (2022)
- [Diversifying Neural Dialogue Generation via Negative Distillation](https://mlsanity.com/paper/2205.02795/) (2022)
- [EZInterviewer: To Improve Job Interview Performance with Mock Interview Generator](https://mlsanity.com/paper/2301.00972/) (2023)
- [Diversifying Question Generation over Knowledge Base via External Natural Questions](https://mlsanity.com/paper/2309.14362/) (2023)
- [Taming Repetition in Dialogue Generation](https://mlsanity.com/paper/2112.08657/) (2021)
- [Targeted Augmentation for Low-Resource Event Extraction](https://mlsanity.com/paper/2405.08729/) (2024)
- [For Better or For Worse? Learning Minimum Variance Features With Label Augmentation](https://mlsanity.com/paper/2402.06855/) (2024)
- [Similarity Based Label Smoothing For Dialogue Generation](https://mlsanity.com/paper/2107.11481/) (2021)
- [Adversarial Ensemble Training by Jointly Learning Label Dependencies and Member Models](https://mlsanity.com/paper/2206.14477/) (2022)
- [CORAL: Contextual Response Retrievability Loss Function for Training Dialog Generation Models](https://mlsanity.com/paper/2205.10558/) (2022)
- [Partially Randomizing Transformer Weights for Dialogue Response Diversity](https://mlsanity.com/paper/2311.10943/) (2023)
- [Accuracy on In-Domain Samples Matters When Building Out-of-Domain detectors: A Reply to Marek et al. (2021)](https://mlsanity.com/paper/2205.11887/) (2022)
- [Hi Model, generating 'nice' instead of 'good' is not as bad as generating 'rice'! Towards Context and Semantic Infused Dialogue Generation Loss Function and Evaluation Metric](https://mlsanity.com/paper/2309.05804/) (2023)
- [Learning to Diversify Neural Text Generation via Degenerative Model](https://mlsanity.com/paper/2309.12619/) (2023)
- [Multi-party Response Generation with Relation Disentanglement](https://mlsanity.com/paper/2403.10827/) (2024)
- [Bridge the Gap between Past and Future: Siamese Model Optimization for Context-Aware Document Ranking](https://mlsanity.com/paper/2505.14180/) (2025)
- [Label Smoothing is a Pragmatic Information Bottleneck](https://mlsanity.com/paper/2508.14077/) (2025)

## Abstract (arXiv)

Neural dialogue generation models trained with the one-hot target distribution suffer from the over-confidence issue, which leads to poor generation diversity as widely reported in the literature. Although existing approaches such as label smoothing can alleviate this issue, they fail to adapt to diverse dialog contexts. In this paper, we propose an Adaptive Label Smoothing (AdaLabel) approach that can adaptively estimate a target label distribution at each time step for different contexts. The maximum probability in the predicted distribution is used to modify the soft target distribution produced by a novel light-weight bi-directional decoder module. The resulting target distribution is aware of both previous and future contexts and is adjusted to avoid over-training the dialogue model. Our model can be trained in an end-to-end manner. Extensive experiments on two benchmark datasets show that our approach outperforms various competitive baselines in producing diverse responses.