mlsanityData to 14 Oct 2026

Enhancing User Engagement in Socially-Driven Dialogue through Interactive LLM Alignments

arXiv 2506.21497 ↗First posted 26 Jun 2025cs.CLcited by 1

On the map: LLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment

Abstract (arXiv)

Enhancing user engagement through interactions plays an essential role in socially-driven dialogues. While prior works have optimized models to reason over relevant knowledge or plan a dialogue act flow, the relationship between user engagement and knowledge or dialogue acts is subtle and does not guarantee user engagement in socially-driven dialogues. To this end, we enable interactive LLMs to learn user engagement by leveraging signals from the future development of conversations. Specifically, we adopt a more direct and relevant indicator of user engagement, i.e., the user's reaction related to dialogue intention after the interaction, as a reward to align interactive LLMs. To achieve this, we develop a user simulator to interact with target interactive LLMs and explore interactions between the user and the interactive LLM system via textiti×MCTS (textitMonte textitCarlo textitTree textitSearch for textitinteraction). In this way, we collect a dataset containing pairs of higher and lower-quality experiences using textiti×MCTS, and align interactive LLMs for high-level user engagement by direct preference optimization (DPO) accordingly. Experiments conducted on two socially-driven dialogue scenarios (emotional support conversations and persuasion for good) demonstrate that our method effectively enhances user engagement in interactive LLMs.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Human values and AI feedback alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation. Builds on 21 of its 34 references that are in the map. First posted on arXiv 26 Jun 2025.

Builds on

21 of 34 references.

References · 21

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  3. 2024LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Modelscited by 1,464
  4. 2023Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Modelscited by 574
  5. 2024ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Searchcited by 344
  6. 2021Towards Emotional Support Dialog Systemscited by 299
  7. 2023Alphazero-like Tree-Search can Guide Large Language Model Decoding and Trainingcited by 295
  8. 2024Monte Carlo Tree Search Boosts Reasoning via Iterative Preference Learningcited by 241
  9. 2021Mastering Atari Games with Limited Datacited by 237
  10. 2019Persuasion for Good: Towards a Personalized Persuasive Dialogue System for Social Goodcited by 209
  11. 2023SoulChat: Improving LLMs' Empathy, Listening, and Comfort Abilities through Fine-tuning with Multi-turn Empathy Conversationscited by 110
  12. 2021PsyQA: A Chinese Dataset for Generating Long Counseling Text for Mental Health Supportcited by 92
9 more
  1. 2023Prompt-Based Monte-Carlo Tree Search for Goal-Oriented Dialogue Policy Planningcited by 61
  2. 2023Knowledge-enhanced Mixed-initiative Dialogue System for Emotional Support Conversationscited by 41
  3. 2024PsyDT: Using LLMs to Construct the Digital Twin of Psychological Counselor with Personalized Counseling Style for Psychological Counselingcited by 38
  4. 2024Towards Self-Improvement of LLMs via MCTS: Leveraging Stepwise Knowledge with Curriculum Preference Learningcited by 30
  5. 2024Towards a Client-Centered Assessment of LLM Therapists by Client Simulationcited by 24
  6. 2024ComPeer: A Generative Conversational Agent for Proactive Peer Supportcited by 24
  7. 2019Gunrock: A Social Bot for Complex and Engaging Long Conversationscited by 14
  8. 2017Learning Conversational Systems that Interleave Task and Non-Task Contentcited by 7
  9. 2022CARE: Causality Reasoning for Empathetic Responses by Conditional Graph Generationcited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Magic, Madness, Heaven, Sin: LLM Output Diversity is Everything, Everywhere, All at Oncecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Benchmarking LLM Tool-Use in the Wild
  2. 2025Show or Tell? Modeling the evolution of request-making in Human-LLM conversations
  3. 2026Beyond the Assistant Turn: User Turn Generation as a Probe of Interaction Awareness in Language Models
  4. 2024LLM Agents in Interaction: Measuring Personality Consistency and Linguistic Alignment in Interacting Populations of Large Language Models
  5. 2025Prototypical Human-AI Collaboration Behaviors from LLM-Assisted Writing in the Wild
  6. 2024Aligning LLMs with Individual Preferences via Interaction
  7. 2025Interaction Dynamics as a Reward Signal for LLMs
  8. 2024AntEval: Evaluation of Social Interaction Competencies in LLM-Driven Agents