# Improving the Robustness of Knowledge-Grounded Dialogue via Contrastive Learning

arXiv: https://arxiv.org/abs/2401.04361 · HTML: https://mlsanity.com/paper/2401.04361/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 50 references that are in the map.
- First posted on arXiv 9 Jan 2024.

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [A Diversity-Promoting Objective Function for Neural Conversation Models](https://mlsanity.com/paper/1510.03055/) (2015)
- [Effective Approaches to Attention-based Neural Machine Translation](https://mlsanity.com/paper/1508.04025/) (2015)
- [A Survey on Contrastive Self-supervised Learning](https://mlsanity.com/paper/2011.00362/) (2020)
- [Is ChatGPT a Good NLG Evaluator? A Preliminary Study](https://mlsanity.com/paper/2303.04048/) (2023)
- [On the Robustness of ChatGPT: An Adversarial and Out-of-distribution Perspective](https://mlsanity.com/paper/2302.12095/) (2023)
- [Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models](https://mlsanity.com/paper/1507.04808/) (2015)
- [A Knowledge-Grounded Neural Conversation Model](https://mlsanity.com/paper/1702.01932/) (2017)
- [Towards Conversational Recommendation over Multi-Type Dialogs](https://mlsanity.com/paper/2005.03954/) (2020)
- [Proactive Human-Machine Conversation with Explicit Conversation Goals](https://mlsanity.com/paper/1906.05572/) (2019)
- [Sequential Latent Knowledge Selection for Knowledge-Grounded Dialogue](https://mlsanity.com/paper/2002.07510/) (2020)
- [Learning to Select Knowledge for Response Generation in Dialog Systems](https://mlsanity.com/paper/1902.04911/) (2019)
- [Increasing Faithfulness in Knowledge-Grounded Dialogue with Controllable Features](https://mlsanity.com/paper/2107.06963/) (2021)
- [KdConv: A Chinese Multi-domain Dialogue Dataset Towards Multi-turn Knowledge-driven Conversation](https://mlsanity.com/paper/2004.04100/) (2020)
- [Knowledge-Grounded Dialogue Generation with a Unified Knowledge Representation](https://mlsanity.com/paper/2112.07924/) (2021)
- [Attribute-Consistent Knowledge Graph Representation Learning for Multi-Modal Entity Alignment](https://mlsanity.com/paper/2304.01563/) (2023)
- [When to Pre-Train Graph Neural Networks? From Data Generation Perspective!](https://mlsanity.com/paper/2303.16458/) (2023)
- [TRIPS: Efficient Vision-and-Language Pre-training with Text-Relevant Image Patch Selection](https://mlsanity.com/paper/2305.04474/) (2023)
- [On the Robustness of Intent Classification and Slot Labeling in Goal-oriented Dialog Systems to Real-world Noise](https://mlsanity.com/paper/2104.07149/) (2021)
- [Enhancing Visual Dialog Questioner with Entity-based Strategy Learning and Augmented Guesser](https://mlsanity.com/paper/2109.02297/) (2021)
- [AspectMMKG: A Multi-modal Knowledge Graph with Aspect-aware Entities](https://mlsanity.com/paper/2308.04992/) (2023)
- [DialAug: Mixing up Dialogue Contexts in Contrastive Learning for Robust Conversational Modeling](https://mlsanity.com/paper/2204.07679/) (2022)
- [RT-KGD: Relation Transition Aware Knowledge-Grounded Dialogue Generation](https://mlsanity.com/paper/2207.08212/) (2022)
- [Snowman: A Million-scale Chinese Commonsense Knowledge Graph Distilled from Foundation Model](https://mlsanity.com/paper/2306.10241/) (2023)

## Built on by (most cited first, 2 of 2)

- [Resilience in Knowledge Graph Embeddings](https://mlsanity.com/paper/2410.21163/) (2024)
- [FALCON: Fine-grained Activation Manipulation by Contrastive Orthogonal Unalignment for Large Language Model](https://mlsanity.com/paper/2502.01472/) (2025)

## Abstract (arXiv)

Knowledge-grounded dialogue (KGD) learns to generate an informative response based on a given dialogue context and external knowledge (e.g., knowledge graphs; KGs). Recently, the emergence of large language models (LLMs) and pre-training techniques has brought great success to knowledge-grounded dialogue. However, when building KGD systems in real applications, there are various real-world noises that are inevitable to face. For example, the dialogue context might involve perturbations such as misspellings and abbreviations. In addition, KGs typically suffer from incompletion and also might contain erroneous and outdated facts. Such real-world noises pose a challenge to the robustness of KGD systems and hinder their applications in the real world. In this paper, we propose an entity-based contrastive learning framework for improving the robustness of KGD. Specifically, we make use of the entity information in a KGD sample to create both its positive and negative samples which involve semantic-irrelevant and semantic-relevant perturbations, respectively. The contrastive learning framework ensures the KGD model is aware of these two types of perturbations, thus generating informative responses with the potentially noisy inputs in real applications. Experimental results on three benchmark datasets show that our method achieves new state-of-the-art performance in terms of automatic evaluation scores, verifying its effectiveness and potentiality. Furthermore, we show that our method can generate better responses than comparison models in both the noisy and the few-shot settings.