# Controlling Dialogue Generation with Semantic Exemplars

arXiv: https://arxiv.org/abs/2008.09075 · HTML: https://mlsanity.com/paper/2008.09075/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Aug 2020.

## Built on by (most cited first, 25 of 25)

- [A Survey on Retrieval-Augmented Text Generation](https://mlsanity.com/paper/2202.01110/) (2022)
- [Controllable Neural Dialogue Summarization with Personal Named Entity Planning](https://mlsanity.com/paper/2109.13070/) (2021)
- [Personalized Large Language Model Assistant with Evolving Conditional Memory](https://mlsanity.com/paper/2312.17257/) (2023)
- [Prompt-Based Length Controlled Generation with Multiple Control Types](https://mlsanity.com/paper/2406.10278/) (2024)
- [Synthesizing Adversarial Negative Responses for Robust Response Ranking and Evaluation](https://mlsanity.com/paper/2106.05894/) (2021)
- [Recent Advances in Neural Text Generation: A Task-Agnostic Survey](https://mlsanity.com/paper/2203.03047/) (2022)
- [Prompt-Based Length Controlled Generation with Reinforcement Learning](https://mlsanity.com/paper/2308.12030/) (2023)
- [A Double-Graph Based Framework for Frame Semantic Parsing](https://mlsanity.com/paper/2206.09158/) (2022)
- [TegTok: Augmenting Text Generation via Task-specific and Open-world Knowledge](https://mlsanity.com/paper/2203.08517/) (2022)
- [AARGH! End-to-end Retrieval-Generation for Task-Oriented Dialog](https://mlsanity.com/paper/2209.03632/) (2022)
- [Local Explanation of Dialogue Response Generation](https://mlsanity.com/paper/2106.06528/) (2021)
- [Controllable Dialogue Generation with Disentangled Multi-grained Style Specification and Attribute Consistency Reward](https://mlsanity.com/paper/2109.06717/) (2021)
- [Long-term Control for Dialogue Generation: Methods and Evaluation](https://mlsanity.com/paper/2205.07352/) (2022)
- [Dynamic Demonstration Retrieval and Cognitive Understanding for Emotional Support Conversation](https://mlsanity.com/paper/2404.02505/) (2024)
- [Distilling the Knowledge of Large-scale Generative Models into Retrieval Models for Efficient Open-domain Conversation](https://mlsanity.com/paper/2108.12582/) (2021)
- [Understanding and Improving the Exemplar-based Generation for Open-domain Conversation](https://mlsanity.com/paper/2112.06723/) (2021)
- [CogIntAc: Modeling the Relationships between Intention, Emotion and Action in Interactive Process from Cognitive Perspective](https://mlsanity.com/paper/2205.03540/) (2022)
- [Multi-Step Dialogue Workflow Action Prediction](https://mlsanity.com/paper/2311.09593/) (2023)
- [CORAL: Contextual Response Retrievability Loss Function for Training Dialog Generation Models](https://mlsanity.com/paper/2205.10558/) (2022)
- [Frugal Prompting for Dialog Models](https://mlsanity.com/paper/2305.14919/) (2023)
- [Length Representations in Large Language Models](https://mlsanity.com/paper/2507.20398/) (2025)
- [Controllable Response Generation for Assistive Use-cases](https://mlsanity.com/paper/2112.02246/) (2021)
- [Use of a Taxonomy of Empathetic Response Intents to Control and Interpret Empathy in Neural Chatbots](https://mlsanity.com/paper/2305.10096/) (2023)
- [Towards Optimizing a Retrieval Augmented Generation using Large Language Model on Academic Data](https://mlsanity.com/paper/2411.08438/) (2024)
- [PRCCF: A Persona-guided Retrieval and Causal-aware Cognitive Filtering Framework for Emotional Support Conversation](https://mlsanity.com/paper/2604.01671/) (2026)

## Abstract (arXiv)

Dialogue systems pretrained with large language models generate locally coherent responses, but lack the fine-grained control over responses necessary to achieve specific goals. A promising method to control response generation is exemplar-based generation, in which models edit exemplar responses that are retrieved from training data, or hand-written to strategically address discourse-level goals, to fit new dialogue contexts. But, current exemplar-based approaches often excessively copy words from the exemplar responses, leading to incoherent replies. We present an Exemplar-based Dialogue Generation model, EDGE, that uses the semantic frames present in exemplar responses to guide generation. We show that controlling dialogue generation based on the semantic frames of exemplars, rather than words in the exemplar itself, improves the coherence of generated responses, while preserving semantic meaning and conversation goals present in exemplar responses.