# Multi-level Adaptive Contrastive Learning for Knowledge Internalization in Dialogue Generation

arXiv: https://arxiv.org/abs/2310.08943 · HTML: https://mlsanity.com/paper/2310.08943/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 42 references that are in the map.
- First posted on arXiv 13 Oct 2023.

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

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation](https://mlsanity.com/paper/1911.00536/) (2019)
- [Personalizing Dialogue Agents: I have a dog, do you have pets too?](https://mlsanity.com/paper/1801.07243/) (2018)
- [Recipes for building an open-domain chatbot](https://mlsanity.com/paper/2004.13637/) (2020)
- [Wizard of Wikipedia: Knowledge-Powered Conversational agents](https://mlsanity.com/paper/1811.01241/) (2018)
- [Neural Text Generation with Unlikelihood Training](https://mlsanity.com/paper/1908.04319/) (2019)
- [How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation](https://mlsanity.com/paper/1603.08023/) (2016)
- [Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models](https://mlsanity.com/paper/1610.02424/) (2016)
- [A Contrastive Framework for Neural Text Generation](https://mlsanity.com/paper/2202.06417/) (2022)
- [Don't Say That! Making Inconsistent Dialogue Unlikely with Unlikelihood Training](https://mlsanity.com/paper/1911.03860/) (2019)
- [Why Exposure Bias Matters: An Imitation Learning Perspective of Error Accumulation in Language Generation](https://mlsanity.com/paper/2204.01171/) (2022)
- [A Dataset for Document Grounded Conversations](https://mlsanity.com/paper/1809.07358/) (2018)
- [Sequential Latent Knowledge Selection for Knowledge-Grounded Dialogue](https://mlsanity.com/paper/2002.07510/) (2020)
- [Towards Exploiting Background Knowledge for Building Conversation Systems](https://mlsanity.com/paper/1809.08205/) (2018)
- [CoNT: Contrastive Neural Text Generation](https://mlsanity.com/paper/2205.14690/) (2022)
- [Straight to the Gradient: Learning to Use Novel Tokens for Neural Text Generation](https://mlsanity.com/paper/2106.07207/) (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)
- [Implicit Unlikelihood Training: Improving Neural Text Generation with Reinforcement Learning](https://mlsanity.com/paper/2101.04229/) (2021)
- [Generative Knowledge Selection for Knowledge-Grounded Dialogues](https://mlsanity.com/paper/2304.04836/) (2023)
- [Difference-aware Knowledge Selection for Knowledge-grounded Conversation Generation](https://mlsanity.com/paper/2009.09378/) (2020)
- [You Truly Understand What I Need: Intellectual and Friendly Dialogue Agents grounding Knowledge and Persona](https://mlsanity.com/paper/2301.02401/) (2023)
- [TLDR: Token Loss Dynamic Reweighting for Reducing Repetitive Utterance Generation](https://mlsanity.com/paper/2003.11963/) (2020)
- [Diversifying Neural Dialogue Generation via Negative Distillation](https://mlsanity.com/paper/2205.02795/) (2022)
- [CorefDiffs: Co-referential and Differential Knowledge Flow in Document Grounded Conversations](https://mlsanity.com/paper/2210.02223/) (2022)
- [There Is No Standard Answer: Knowledge-Grounded Dialogue Generation with Adversarial Activated Multi-Reference Learning](https://mlsanity.com/paper/2210.12459/) (2022)

## Built on by (most cited first, 4 of 4)

- [System 1&2 Synergy via Dynamic Model Interpolation](https://mlsanity.com/paper/2601.21414/) (2026)
- [Breaking the Trade-Off Between Faithfulness and Expressiveness for Large Language Models](https://mlsanity.com/paper/2508.18651/) (2025)
- [A Factuality and Diversity Reconciled Decoding Method for Knowledge-Grounded Dialogue Generation](https://mlsanity.com/paper/2407.05718/) (2024)
- [Qsnail: A Questionnaire Dataset for Sequential Question Generation](https://mlsanity.com/paper/2402.14272/) (2024)

## Abstract (arXiv)

Knowledge-grounded dialogue generation aims to mitigate the issue of text degeneration by incorporating external knowledge to supplement the context. However, the model often fails to internalize this information into responses in a human-like manner. Instead, it simply inserts segments of the provided knowledge into generic responses. As a result, the generated responses tend to be tedious, incoherent, and in lack of interactivity which means the degeneration problem is still unsolved. In this work, we first find that such copying-style degeneration is primarily due to the weak likelihood objective, which allows the model to "cheat" the objective by merely duplicating knowledge segments in a superficial pattern matching based on overlap. To overcome this challenge, we then propose a Multi-level Adaptive Contrastive Learning (MACL) framework that dynamically samples negative examples and subsequently penalizes degeneration behaviors at both the token-level and sequence-level. Extensive experiments on the WoW dataset demonstrate the effectiveness of our approach across various pre-trained models.