# Diversifying Neural Dialogue Generation via Negative Distillation

arXiv: https://arxiv.org/abs/2205.02795 · HTML: https://mlsanity.com/paper/2205.02795/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 41 references that are in the map.
- First posted on arXiv 5 May 2022.

## Builds on (most cited first, 29 of 29)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [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)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [TinyBERT: Distilling BERT for Natural Language Understanding](https://mlsanity.com/paper/1909.10351/) (2019)
- [A Diversity-Promoting Objective Function for Neural Conversation Models](https://mlsanity.com/paper/1510.03055/) (2015)
- [What Does BERT Look At? An Analysis of BERT's Attention](https://mlsanity.com/paper/1906.04341/) (2019)
- [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)
- [Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders](https://mlsanity.com/paper/1703.10960/) (2017)
- [A Neural Conversational Model](https://mlsanity.com/paper/1506.05869/) (2015)
- [Poly-encoders: Transformer Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoring](https://mlsanity.com/paper/1905.01969/) (2019)
- [NLNL: Negative Learning for Noisy Labels](https://mlsanity.com/paper/1908.07387/) (2019)
- [Neural Responding Machine for Short-Text Conversation](https://mlsanity.com/paper/1503.02364/) (2015)
- [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)
- [Adversarial Learning for Neural Dialogue Generation](https://mlsanity.com/paper/1701.06547/) (2017)
- [Importance of Search and Evaluation Strategies in Neural Dialogue Modeling](https://mlsanity.com/paper/1811.00907/) (2018)
- [Improving Neural Conversational Models with Entropy-Based Data Filtering](https://mlsanity.com/paper/1905.05471/) (2019)
- [Improving Neural Response Diversity with Frequency-Aware Cross-Entropy Loss](https://mlsanity.com/paper/1902.09191/) (2019)
- [Diversifying Dialog Generation via Adaptive Label Smoothing](https://mlsanity.com/paper/2105.14556/) (2021)
- [Negative Training for Neural Dialogue Response Generation](https://mlsanity.com/paper/1903.02134/) (2019)
- [Diversifying Dialogue Generation with Non-Conversational Text](https://mlsanity.com/paper/2005.04346/) (2020)
- [Implicit Unlikelihood Training: Improving Neural Text Generation with Reinforcement Learning](https://mlsanity.com/paper/2101.04229/) (2021)
- [Learning from Perturbations: Diverse and Informative Dialogue Generation with Inverse Adversarial Training](https://mlsanity.com/paper/2105.15171/) (2021)
- [SENT: Sentence-level Distant Relation Extraction via Negative Training](https://mlsanity.com/paper/2106.11566/) (2021)
- [Strategy of the Negative Sampling for Training Retrieval-Based Dialogue Systems](https://mlsanity.com/paper/1811.09785/) (2018)

## Built on by (most cited first, 6 of 6)

- [Contrastive Learning Reduces Hallucination in Conversations](https://mlsanity.com/paper/2212.10400/) (2022)
- [Focused Large Language Models are Stable Many-Shot Learners](https://mlsanity.com/paper/2408.13987/) (2024)
- [Multi-level Adaptive Contrastive Learning for Knowledge Internalization in Dialogue Generation](https://mlsanity.com/paper/2310.08943/) (2023)
- [Modeling Complex Dialogue Mappings via Sentence Semantic Segmentation Guided Conditional Variational Auto-Encoder](https://mlsanity.com/paper/2212.00231/) (2022)
- [Heterogeneous-Branch Collaborative Learning for Dialogue Generation](https://mlsanity.com/paper/2303.11621/) (2023)
- [Learning to Diversify Neural Text Generation via Degenerative Model](https://mlsanity.com/paper/2309.12619/) (2023)

## Abstract (arXiv)

Generative dialogue models suffer badly from the generic response problem, limiting their applications to a few toy scenarios. Recently, an interesting approach, namely negative training, has been proposed to alleviate this problem by reminding the model not to generate high-frequency responses during training. However, its performance is hindered by two issues, ignoring low-frequency but generic responses and bringing low-frequency but meaningless responses. In this paper, we propose a novel negative training paradigm, called negative distillation, to keep the model away from the undesirable generic responses while avoiding the above problems. First, we introduce a negative teacher model that can produce query-wise generic responses, and then the student model is required to maximize the distance with multi-level negative knowledge. Empirical results show that our method outperforms previous negative training methods significantly.