# Modeling the One-to-Many Property in Open-Domain Dialogue with LLMs

arXiv: https://arxiv.org/abs/2506.15131 · HTML: https://mlsanity.com/paper/2506.15131/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 43 references that are in the map.
- First posted on arXiv 18 Jun 2025.

## Builds on (most cited first, 27 of 27)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [WebGPT: Browser-assisted question-answering with human feedback](https://mlsanity.com/paper/2112.09332/) (2021)
- [A Diversity-Promoting Objective Function for Neural Conversation Models](https://mlsanity.com/paper/1510.03055/) (2015)
- [DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset](https://mlsanity.com/paper/1710.03957/) (2017)
- [Contrastive Learning with Hard Negative Samples](https://mlsanity.com/paper/2010.04592/) (2020)
- [TinyLlama: An Open-Source Small Language Model](https://mlsanity.com/paper/2401.02385/) (2024)
- [Towards a Unified Multi-Dimensional Evaluator for Text Generation](https://mlsanity.com/paper/2210.07197/) (2022)
- [Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders](https://mlsanity.com/paper/1703.10960/) (2017)
- [Human Evaluation of Conversations is an Open Problem: comparing the sensitivity of various methods for evaluating dialogue agents](https://mlsanity.com/paper/2201.04723/) (2022)
- [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)
- [DialogWAE: Multimodal Response Generation with Conditional Wasserstein Auto-Encoder](https://mlsanity.com/paper/1805.12352/) (2018)
- [Chain of Thought Prompting Elicits Knowledge Augmentation](https://mlsanity.com/paper/2307.01640/) (2023)
- [Generating Relevant and Coherent Dialogue Responses using Self-separated Conditional Variational AutoEncoders](https://mlsanity.com/paper/2106.03410/) (2021)
- [A Conditional Variational Framework for Dialog Generation](https://mlsanity.com/paper/1705.00316/) (2017)
- [Improving Contextual Coherence in Variational Personalized and Empathetic Dialogue Agents](https://mlsanity.com/paper/2202.05971/) (2022)
- [Think Twice: A Human-like Two-stage Conversational Agent for Emotional Response Generation](https://mlsanity.com/paper/2301.04907/) (2023)
- [An Empirical Bayes Framework for Open-Domain Dialogue Generation](https://mlsanity.com/paper/2311.10945/) (2023)
- [A Systematic Evaluation of Response Selection for Open Domain Dialogue](https://mlsanity.com/paper/2208.04379/) (2022)
- [Dial-MAE: ConTextual Masked Auto-Encoder for Retrieval-based Dialogue Systems](https://mlsanity.com/paper/2306.04357/) (2023)
- [Generate, Evaluate, and Select: A Dialogue System with a Response Evaluator for Diversity-Aware Response Generation](https://mlsanity.com/paper/2206.04937/) (2022)

## Built on by (most cited first, 3 of 3)

- [Multi-Dimensional Prompt Chaining to Improve Open-Domain Dialogue Generation](https://mlsanity.com/paper/2601.01037/) (2026)
- [ToSCA: Leveraging Hierarchical Reinforcement Learning on Temporal and Strategic Abstractions of Conversational Agents](https://mlsanity.com/paper/2608.21969/) (2026)
- [Multi-Expert Conformal Risk Control for Pairwise LLM Judging in Open-Ended Dialogue](https://mlsanity.com/paper/2608.26529/) (2026)

## Abstract (arXiv)

Open-domain Dialogue (OD) exhibits a one-to-many (o2m) property, whereby multiple appropriate responses exist for a single dialogue context. Despite prior research showing that modeling this property boosts response diversity, most modern LLM-based dialogue agents do not explicitly do so. In this work, we model the o2m property of OD in LLMs by decomposing OD generation into two key tasks: Multi-Response Generation (MRG) and Preference-based Selection (PS), which entail generating a set of n semantically and lexically diverse high-quality responses for a given dialogue context, followed by selecting a single response based on human preference, respectively. To facilitate MRG and PS, we introduce o2mDial, a dialogue corpus explicitly designed to capture the o2m property by featuring multiple plausible responses for each context. Leveraging o2mDial, we propose new in-context learning and instruction-tuning strategies, as well as novel evaluation metrics for MRG, alongside a model-based approach for PS. Empirical results demonstrate that applying the proposed two-stage framework to smaller LLMs for OD generation enhances overall response diversity while maintaining contextual coherence, improving response quality by up to 90%, bringing them closer to the performance of larger models.