# SimOAP: Improve Coherence and Consistency in Persona-based Dialogue Generation via Over-sampling and Post-evaluation

arXiv: https://arxiv.org/abs/2305.11130 · HTML: https://mlsanity.com/paper/2305.11130/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 37 references that are in the map.
- First posted on arXiv 18 May 2023.

## Builds on (most cited first, 30 of 31)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Hierarchical Neural Story Generation](https://mlsanity.com/paper/1805.04833/) (2018)
- [A Diversity-Promoting Objective Function for Neural Conversation Models](https://mlsanity.com/paper/1510.03055/) (2015)
- [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)
- [Plug and Play Language Models: A Simple Approach to Controlled Text Generation](https://mlsanity.com/paper/1912.02164/) (2019)
- [Recipes for building an open-domain chatbot](https://mlsanity.com/paper/2004.13637/) (2020)
- [Towards a Human-like Open-Domain Chatbot](https://mlsanity.com/paper/2001.09977/) (2020)
- [PLATO: Pre-trained Dialogue Generation Model with Discrete Latent Variable](https://mlsanity.com/paper/1910.07931/) (2019)
- [Dialogue Natural Language Inference](https://mlsanity.com/paper/1811.00671/) (2018)
- [Don't Say That! Making Inconsistent Dialogue Unlikely with Unlikelihood Training](https://mlsanity.com/paper/1911.03860/) (2019)
- [Improving Coherence and Consistency in Neural Sequence Models with Dual-System, Neuro-Symbolic Reasoning](https://mlsanity.com/paper/2107.02794/) (2021)
- [Personalizing Dialogue Agents via Meta-Learning](https://mlsanity.com/paper/1905.10033/) (2019)
- [BoB: BERT Over BERT for Training Persona-based Dialogue Models from Limited Personalized Data](https://mlsanity.com/paper/2106.06169/) (2021)
- [Controllable Natural Language Generation with Contrastive Prefixes](https://mlsanity.com/paper/2202.13257/) (2022)
- [A Pre-training Based Personalized Dialogue Generation Model with Persona-sparse Data](https://mlsanity.com/paper/1911.04700/) (2019)
- [Generate, Delete and Rewrite: A Three-Stage Framework for Improving Persona Consistency of Dialogue Generation](https://mlsanity.com/paper/2004.07672/) (2020)
- [Generating Persona Consistent Dialogues by Exploiting Natural Language Inference](https://mlsanity.com/paper/1911.05889/) (2019)
- [Achieving Reliable Human Assessment of Open-Domain Dialogue Systems](https://mlsanity.com/paper/2203.05899/) (2022)
- [Diversifying Dialog Generation via Adaptive Label Smoothing](https://mlsanity.com/paper/2105.14556/) (2021)
- [DEAM: Dialogue Coherence Evaluation using AMR-based Semantic Manipulations](https://mlsanity.com/paper/2203.09711/) (2022)
- [A Model-Agnostic Data Manipulation Method for Persona-based Dialogue Generation](https://mlsanity.com/paper/2204.09867/) (2022)
- [Profile Consistency Identification for Open-domain Dialogue Agents](https://mlsanity.com/paper/2009.09680/) (2020)
- [Towards Quantifiable Dialogue Coherence Evaluation](https://mlsanity.com/paper/2106.00507/) (2021)
- [Thinking Clearly, Talking Fast: Concept-Guided Non-Autoregressive Generation for Open-Domain Dialogue Systems](https://mlsanity.com/paper/2109.04084/) (2021)
- [Pretrained Language Models for Dialogue Generation with Multiple Input Sources](https://mlsanity.com/paper/2010.07576/) (2020)
- [Large Scale Multi-Actor Generative Dialog Modeling](https://mlsanity.com/paper/2005.06114/) (2020)
- [REAMsharp: An Enhancement Approach to Reference-based Evaluation Metrics for Open-domain Dialog Generation](https://mlsanity.com/paper/2105.14488/) (2021)

## Built on by (most cited first, 11 of 11)

- [Evaluating LLM-based Agents for Multi-Turn Conversations: A Survey](https://mlsanity.com/paper/2503.22458/) (2025)
- [Recent Trends in Personalized Dialogue Generation: A Review of Datasets, Methodologies, and Evaluations](https://mlsanity.com/paper/2405.17974/) (2024)
- [Exploring and Controlling Diversity in LLM-Agent Conversation](https://mlsanity.com/paper/2412.21102/) (2024)
- [The Imperative of Conversation Analysis in the Era of LLMs: A Survey of Tasks, Techniques, and Trends](https://mlsanity.com/paper/2409.14195/) (2024)
- [Exploring Persona Sentiment Sensitivity in Personalized Dialogue Generation](https://mlsanity.com/paper/2502.11423/) (2025)
- [Post Persona Alignment for Multi-Session Dialogue Generation](https://mlsanity.com/paper/2506.11857/) (2025)
- [Enhancing Goal-oriented Proactive Dialogue Systems via Consistency Reflection and Correction](https://mlsanity.com/paper/2506.13366/) (2025)
- [From Persona to Person: Enhancing the Naturalness with Multiple Discourse Relations Graph Learning in Personalized Dialogue Generation](https://mlsanity.com/paper/2506.11557/) (2025)
- [Score Before You Speak: Improving Persona Consistency in Dialogue Generation using Response Quality Scores](https://mlsanity.com/paper/2508.06886/) (2025)
- [Persona-Aware Alignment Framework for Personalized Dialogue Generation](https://mlsanity.com/paper/2511.10215/) (2025)
- [Qsnail: A Questionnaire Dataset for Sequential Question Generation](https://mlsanity.com/paper/2402.14272/) (2024)

## Abstract (arXiv)

Language models trained on large-scale corpora can generate remarkably fluent results in open-domain dialogue. However, for the persona-based dialogue generation task, consistency and coherence are also key factors, which are great challenges for language models. Existing works mainly focus on valuable data filtering, model structure modifying, or objective function designing, while their improvements are limited and hard to generalize to all types of pre-trained language models. However, we find that language models can produce consistent and coherent responses if we consider enough generations. Thus, the problems lay in large-scale response generation and target response selection. In this work, a simple but effective two-stage SimOAP strategy is proposed, i.e., over-sampling and post-evaluation. The over-sampling stage takes large-scale responses from existing trained models efficiently via off-the-shelf distilling and compressing methods, and the post-evaluation stage selects a good response based on multiple well-designed evaluation metrics from large-scale candidates. Experimental results show that the proposed plug-in SimOAP strategy improves the backbone models and outperforms the baseline strategies in both automatic and human evaluations.