# Improving Neural Response Diversity with Frequency-Aware Cross-Entropy Loss

arXiv: https://arxiv.org/abs/1902.09191 · HTML: https://mlsanity.com/paper/1902.09191/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Feb 2019.

## Built on by (most cited first, 29 of 29)

- [CEM: Commonsense-aware Empathetic Response Generation](https://mlsanity.com/paper/2109.05739/) (2021)
- [Pretraining Data Detection for Large Language Models: A Divergence-based Calibration Method](https://mlsanity.com/paper/2409.14781/) (2024)
- [Rethinking and Refining the Distinct Metric](https://mlsanity.com/paper/2202.13587/) (2022)
- [Diversifying Dialog Generation via Adaptive Label Smoothing](https://mlsanity.com/paper/2105.14556/) (2021)
- [Empathetic Dialogue Generation via Sensitive Emotion Recognition and Sensible Knowledge Selection](https://mlsanity.com/paper/2210.11715/) (2022)
- [A Simple Contrastive Learning Objective for Alleviating Neural Text Degeneration](https://mlsanity.com/paper/2205.02517/) (2022)
- [On the Complementarity between Pre-Training and Random-Initialization for Resource-Rich Machine Translation](https://mlsanity.com/paper/2209.03316/) (2022)
- [An Unsupervised Method for Building Sentence Simplification Corpora in Multiple Languages](https://mlsanity.com/paper/2109.00165/) (2021)
- [RecInDial: A Unified Framework for Conversational Recommendation with Pretrained Language Models](https://mlsanity.com/paper/2110.07477/) (2021)
- [Frequency-Aware Contrastive Learning for Neural Machine Translation](https://mlsanity.com/paper/2112.14484/) (2021)
- [DiffusEmp: A Diffusion Model-Based Framework with Multi-Grained Control for Empathetic Response Generation](https://mlsanity.com/paper/2306.01657/) (2023)
- [DialoGPS: Dialogue Path Sampling in Continuous Semantic Space for Data Augmentation in Multi-Turn Conversations](https://mlsanity.com/paper/2306.16770/) (2023)
- [Diversifying Neural Dialogue Generation via Negative Distillation](https://mlsanity.com/paper/2205.02795/) (2022)
- [Bilingual Mutual Information Based Adaptive Training for Neural Machine Translation](https://mlsanity.com/paper/2105.12523/) (2021)
- [Wish I Can Feel What You Feel: A Neural Approach for Empathetic Response Generation](https://mlsanity.com/paper/2212.02000/) (2022)
- [Switching to Discriminative Image Captioning by Relieving a Bottleneck of Reinforcement Learning](https://mlsanity.com/paper/2212.03230/) (2022)
- [Diversifying Neural Text Generation with Part-of-Speech Guided Softmax and Sampling](https://mlsanity.com/paper/2105.03641/) (2021)
- [Similarity Based Label Smoothing For Dialogue Generation](https://mlsanity.com/paper/2107.11481/) (2021)
- [Perception and Semantic Aware Regularization for Sequential Confidence Calibration](https://mlsanity.com/paper/2305.19498/) (2023)
- [Multilingual Lexical Simplification via Paraphrase Generation](https://mlsanity.com/paper/2307.15286/) (2023)
- [Partially Randomizing Transformer Weights for Dialogue Response Diversity](https://mlsanity.com/paper/2311.10943/) (2023)
- [Relative Overfitting and Accept-Reject Framework](https://mlsanity.com/paper/2505.07783/) (2025)
- [InferEM: Inferring the Speaker's Intention for Empathetic Dialogue Generation](https://mlsanity.com/paper/2212.06373/) (2022)
- [Sentence Simplification Using Paraphrase Corpus for Initialization](https://mlsanity.com/paper/2305.19754/) (2023)
- [Data Augmentation for Improving Tail-traffic Robustness in Skill-routing for Dialogue Systems](https://mlsanity.com/paper/2306.04823/) (2023)
- [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)
- [Assessing the Impact of the Quality of Textual Data on Feature Representation and Machine Learning Models](https://mlsanity.com/paper/2502.08669/) (2025)
- [Dynamic Commonsense Coordination for Empathetic Response Generation](https://mlsanity.com/paper/2607.22136/) (2026)

## Abstract (arXiv)

Sequence-to-Sequence (Seq2Seq) models have achieved encouraging performance on the dialogue response generation task. However, existing Seq2Seq-based response generation methods suffer from a low-diversity problem: they frequently generate generic responses, which make the conversation less interesting. In this paper, we address the low-diversity problem by investigating its connection with model over-confidence reflected in predicted distributions. Specifically, we first analyze the influence of the commonly used Cross-Entropy (CE) loss function, and find that the CE loss function prefers high-frequency tokens, which results in low-diversity responses. We then propose a Frequency-Aware Cross-Entropy (FACE) loss function that improves over the CE loss function by incorporating a weighting mechanism conditioned on token frequency. Extensive experiments on benchmark datasets show that the FACE loss function is able to substantially improve the diversity of existing state-of-the-art Seq2Seq response generation methods, in terms of both automatic and human evaluations.