# Enhancing User-Oriented Proactivity in Open-Domain Dialogues with Critic Guidance

arXiv: https://arxiv.org/abs/2505.12334 · HTML: https://mlsanity.com/paper/2505.12334/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 36 references that are in the map.
- First posted on arXiv 18 May 2025.

## Builds on (most cited first, 19 of 19)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [MemoryBank: Enhancing Large Language Models with Long-Term Memory](https://mlsanity.com/paper/2305.10250/) (2023)
- [BlenderBot 3: a deployed conversational agent that continually learns to responsibly engage](https://mlsanity.com/paper/2208.03188/) (2022)
- [Prompting and Evaluating Large Language Models for Proactive Dialogues: Clarification, Target-guided, and Non-collaboration](https://mlsanity.com/paper/2305.13626/) (2023)
- [MemoChat: Tuning LLMs to Use Memos for Consistent Long-Range Open-Domain Conversation](https://mlsanity.com/paper/2308.08239/) (2023)
- [Target-Guided Open-Domain Conversation](https://mlsanity.com/paper/1905.11553/) (2019)
- [A Survey on Proactive Dialogue Systems: Problems, Methods, and Prospects](https://mlsanity.com/paper/2305.02750/) (2023)
- [Confucius: Iterative Tool Learning from Introspection Feedback by Easy-to-Difficult Curriculum](https://mlsanity.com/paper/2308.14034/) (2023)
- [CharacterChat: Learning towards Conversational AI with Personalized Social Support](https://mlsanity.com/paper/2308.10278/) (2023)
- [Recent Trends in Personalized Dialogue Generation: A Review of Datasets, Methodologies, and Evaluations](https://mlsanity.com/paper/2405.17974/) (2024)
- [Towards Robust Personalized Dialogue Generation via Order-Insensitive Representation Regularization](https://mlsanity.com/paper/2305.12782/) (2023)
- [Efficient Dynamic Ensembling for Multiple LLM Experts](https://mlsanity.com/paper/2412.07448/) (2024)
- [Knowledge-Grounded Dialogue Flow Management for Social Robots and Conversational Agents](https://mlsanity.com/paper/2108.02174/) (2021)
- [Target-constrained Bidirectional Planning for Generation of Target-oriented Proactive Dialogue](https://mlsanity.com/paper/2403.06063/) (2024)
- [Dynamic Compressing Prompts for Efficient Inference of Large Language Models](https://mlsanity.com/paper/2504.11004/) (2025)
- [Towards Diverse, Relevant and Coherent Open-Domain Dialogue Generation via Hybrid Latent Variables](https://mlsanity.com/paper/2212.01145/) (2022)

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

- [Test-Time Learning for Large Language Models](https://mlsanity.com/paper/2505.20633/) (2025)
- [Beyond Fast and Slow: Cognitive-Inspired Elastic Reasoning for Large Language Models](https://mlsanity.com/paper/2512.15089/) (2025)

## Abstract (arXiv)

Open-domain dialogue systems aim to generate natural and engaging conversations, providing significant practical value in real applications such as social robotics and personal assistants. The advent of large language models (LLMs) has greatly advanced this field by improving context understanding and conversational fluency. However, existing LLM-based dialogue systems often fall short in proactively understanding the user's chatting preferences and guiding conversations toward user-centered topics. This lack of user-oriented proactivity can lead users to feel unappreciated, reducing their satisfaction and willingness to continue the conversation in human-computer interactions. To address this issue, we propose a User-oriented Proactive Chatbot (UPC) to enhance the user-oriented proactivity. Specifically, we first construct a critic to evaluate this proactivity inspired by the LLM-as-a-judge strategy. Given the scarcity of high-quality training data, we then employ the critic to guide dialogues between the chatbot and user agents, generating a corpus with enhanced user-oriented proactivity. To ensure the diversity of the user backgrounds, we introduce the ISCO-800, a diverse user background dataset for constructing user agents. Moreover, considering the communication difficulty varies among users, we propose an iterative curriculum learning method that trains the chatbot from easy-to-communicate users to more challenging ones, thereby gradually enhancing its performance. Experiments demonstrate that our proposed training method is applicable to different LLMs, improving user-oriented proactivity and attractiveness in open-domain dialogues.