# Semantic Diversity in Dialogue with Natural Language Inference

arXiv: https://arxiv.org/abs/2205.01497 · HTML: https://mlsanity.com/paper/2205.01497/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 37 references that are in the map.
- First posted on arXiv 3 May 2022.

## Builds on (most cited first, 26 of 26)

- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [A large annotated corpus for learning natural language inference](https://mlsanity.com/paper/1508.05326/) (2015)
- [FEVER: a large-scale dataset for Fact Extraction and VERification](https://mlsanity.com/paper/1803.05355/) (2018)
- [A Diversity-Promoting Objective Function for Neural Conversation Models](https://mlsanity.com/paper/1510.03055/) (2015)
- [SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluation](https://mlsanity.com/paper/1708.00055/) (2017)
- [DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation](https://mlsanity.com/paper/1911.00536/) (2019)
- [Adversarial NLI: A New Benchmark for Natural Language Understanding](https://mlsanity.com/paper/1910.14599/) (2019)
- [DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset](https://mlsanity.com/paper/1710.03957/) (2017)
- [Recipes for building an open-domain chatbot](https://mlsanity.com/paper/2004.13637/) (2020)
- [Texygen: A Benchmarking Platform for Text Generation Models](https://mlsanity.com/paper/1802.01886/) (2018)
- [What makes a good conversation? How controllable attributes affect human judgments](https://mlsanity.com/paper/1902.08654/) (2019)
- [Evaluating the Evaluation of Diversity in Natural Language Generation](https://mlsanity.com/paper/2004.02990/) (2020)
- [Unifying Human and Statistical Evaluation for Natural Language Generation](https://mlsanity.com/paper/1904.02792/) (2019)
- [Combining Fact Extraction and Verification with Neural Semantic Matching Networks](https://mlsanity.com/paper/1811.07039/) (2018)
- [Generating Informative and Diverse Conversational Responses via Adversarial Information Maximization](https://mlsanity.com/paper/1809.05972/) (2018)
- [Improving Dialog Evaluation with a Multi-reference Adversarial Dataset and Large Scale Pretraining](https://mlsanity.com/paper/2009.11321/) (2020)
- [Investigating Evaluation of Open-Domain Dialogue Systems With Human Generated Multiple References](https://mlsanity.com/paper/1907.10568/) (2019)
- [Approximating Interactive Human Evaluation with Self-Play for Open-Domain Dialog Systems](https://mlsanity.com/paper/1906.09308/) (2019)
- [Generating Persona Consistent Dialogues by Exploiting Natural Language Inference](https://mlsanity.com/paper/1911.05889/) (2019)
- [Outlier Detection for Improved Data Quality and Diversity in Dialog Systems](https://mlsanity.com/paper/1904.03122/) (2019)
- [Syntax-Infused Variational Autoencoder for Text Generation](https://mlsanity.com/paper/1906.02181/) (2019)
- [Latent Variable Dialogue Models and their Diversity](https://mlsanity.com/paper/1702.05962/) (2017)

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

- [Understanding the Effects of RLHF on LLM Generalisation and Diversity](https://mlsanity.com/paper/2310.06452/) (2023)
- [The Curious Decline of Linguistic Diversity: Training Language Models on Synthetic Text](https://mlsanity.com/paper/2311.09807/) (2023)
- [Evaluating Large Language Model Biases in Persona-Steered Generation](https://mlsanity.com/paper/2405.20253/) (2024)
- [Flipping the Dialogue: Training and Evaluating User Language Models](https://mlsanity.com/paper/2510.06552/) (2025)
- [What Comes Next? Evaluating Uncertainty in Neural Text Generators Against Human Production Variability](https://mlsanity.com/paper/2305.11707/) (2023)
- [Evaluating the Diversity and Quality of LLM Generated Content](https://mlsanity.com/paper/2504.12522/) (2025)
- [Benchmarking Linguistic Diversity of Large Language Models](https://mlsanity.com/paper/2412.10271/) (2024)
- [The Homogenizing Effect of Large Language Models on Human Expression and Thought](https://mlsanity.com/paper/2508.01491/) (2025)
- [How Far Can We Extract Diverse Perspectives from Large Language Models?](https://mlsanity.com/paper/2311.09799/) (2023)
- [Humor in AI: Massive Scale Crowd-Sourced Preferences and Benchmarks for Cartoon Captioning](https://mlsanity.com/paper/2406.10522/) (2024)
- [Evaluating Diversity in Automatic Poetry Generation](https://mlsanity.com/paper/2406.15267/) (2024)
- [Measuring and Improving Semantic Diversity of Dialogue Generation](https://mlsanity.com/paper/2210.05725/) (2022)
- [Lessons from the Use of Natural Language Inference (NLI) in Requirements Engineering Tasks](https://mlsanity.com/paper/2405.05135/) (2024)
- [Where does output diversity collapse in post-training?](https://mlsanity.com/paper/2604.16027/) (2026)
- [Optimizing Diversity and Quality through Base-Aligned Model Collaboration](https://mlsanity.com/paper/2511.05650/) (2025)
- [Best-k Search Algorithm for Neural Text Generation](https://mlsanity.com/paper/2211.11924/) (2022)
- [DESIGNER: Design-Logic-Guided Multidisciplinary Data Synthesis for LLM Reasoning](https://mlsanity.com/paper/2508.12726/) (2025)
- [Limited Linguistic Diversity in Embodied AI Datasets](https://mlsanity.com/paper/2601.03136/) (2026)
- [Measuring Diversity in Synthetic Datasets](https://mlsanity.com/paper/2502.08512/) (2025)
- [Exploring Continual Learning of Compositional Generalization in NLI](https://mlsanity.com/paper/2403.04400/) (2024)
- [A survey of diversity quantification in natural language processing: The why, what, where and how](https://mlsanity.com/paper/2507.20858/) (2025)
- [Interpretation modeling: Social grounding of sentences by reasoning over their implicit moral judgments](https://mlsanity.com/paper/2312.03726/) (2023)
- [An Empirical Study on Preference Tuning Generalization and Diversity Under Domain Shift](https://mlsanity.com/paper/2601.05882/) (2026)
- [For Generated Text, Is NLI-Neutral Text the Best Text?](https://mlsanity.com/paper/2302.08577/) (2023)
- [Pragmatically Appropriate Diversity for Dialogue Evaluation](https://mlsanity.com/paper/2304.02812/) (2023)
- [Vocabulary Dropout for Curriculum Diversity in LLM Co-Evolution](https://mlsanity.com/paper/2604.03472/) (2026)
- [Measuring Dataset Diversity from a Geometric Perspective](https://mlsanity.com/paper/2602.09340/) (2026)
- [Towards Scalable Data Diversification for Language Model Pretraining via Leverage Score Sampling](https://mlsanity.com/paper/2609.32484/) (2026)
- [PLDiv: Measuring Dataset Diversity and Semantic Collapse via Persistence Landscapes](https://mlsanity.com/paper/2610.14031/) (2026)

## Abstract (arXiv)

Generating diverse, interesting responses to chitchat conversations is a problem for neural conversational agents. This paper makes two substantial contributions to improving diversity in dialogue generation. First, we propose a novel metric which uses Natural Language Inference (NLI) to measure the semantic diversity of a set of model responses for a conversation. We evaluate this metric using an established framework (Tevet and Berant, 2021) and find strong evidence indicating NLI Diversity is correlated with semantic diversity. Specifically, we show that the contradiction relation is more useful than the neutral relation for measuring this diversity and that incorporating the NLI model's confidence achieves state-of-the-art results. Second, we demonstrate how to iteratively improve the semantic diversity of a sampled set of responses via a new generation procedure called Diversity Threshold Generation, which results in an average 137% increase in NLI Diversity compared to standard generation procedures.