# Augmenting Non-Collaborative Dialog Systems with Explicit Semantic and Strategic Dialog History

arXiv: https://arxiv.org/abs/1909.13425 · HTML: https://mlsanity.com/paper/1909.13425/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Sep 2019.

## Built on by (most cited first, 20 of 20)

- [Prompting and Evaluating Large Language Models for Proactive Dialogues: Clarification, Target-guided, and Non-collaboration](https://mlsanity.com/paper/2305.13626/) (2023)
- [Plug-and-Play Policy Planner for Large Language Model Powered Dialogue Agents](https://mlsanity.com/paper/2311.00262/) (2023)
- [A Survey on Proactive Dialogue Systems: Problems, Methods, and Prospects](https://mlsanity.com/paper/2305.02750/) (2023)
- [Improving Multi-turn Emotional Support Dialogue Generation with Lookahead Strategy Planning](https://mlsanity.com/paper/2210.04242/) (2022)
- [Let's Negotiate! A Survey of Negotiation Dialogue Systems](https://mlsanity.com/paper/2212.09072/) (2022)
- [DialoGraph: Incorporating Interpretable Strategy-Graph Networks into Negotiation Dialogues](https://mlsanity.com/paper/2106.00920/) (2021)
- [Interacting with Non-Cooperative User: A New Paradigm for Proactive Dialogue Policy](https://mlsanity.com/paper/2204.07433/) (2022)
- [Social Influence Dialogue Systems: A Survey of Datasets and Models For Social Influence Tasks](https://mlsanity.com/paper/2210.05664/) (2022)
- [Dialogue Planning via Brownian Bridge Stochastic Process for Goal-directed Proactive Dialogue](https://mlsanity.com/paper/2305.05290/) (2023)
- [Opponent Modeling in Negotiation Dialogues by Related Data Adaptation](https://mlsanity.com/paper/2205.00344/) (2022)
- [Towards Emotion-Aware Agents For Negotiation Dialogues](https://mlsanity.com/paper/2107.13165/) (2021)
- [Follow Me: Conversation Planning for Target-driven Recommendation Dialogue Systems](https://mlsanity.com/paper/2208.03516/) (2022)
- [Advancements in Scientific Controllable Text Generation Methods](https://mlsanity.com/paper/2307.05538/) (2023)
- [Target-constrained Bidirectional Planning for Generation of Target-oriented Proactive Dialogue](https://mlsanity.com/paper/2403.06063/) (2024)
- [Unsupervised Learning of Hierarchical Conversation Structure](https://mlsanity.com/paper/2205.12244/) (2022)
- [The Future of Cognitive Strategy-enhanced Persuasive Dialogue Agents: New Perspectives and Trends](https://mlsanity.com/paper/2402.04631/) (2024)
- [DialogXpert: Driving Intelligent and Emotion-Aware Conversations through Online Value-Based Reinforcement Learning with LLM Priors](https://mlsanity.com/paper/2505.17795/) (2025)
- [Towards a Neural Era in Dialogue Management for Collaboration: A Literature Survey](https://mlsanity.com/paper/2307.09021/) (2023)
- [A Personalized Utterance Style (PUS) based Dialogue Strategy for Efficient Service Requirement Elicitation](https://mlsanity.com/paper/2301.04582/) (2023)
- [Let's Negotiate! A Survey of Negotiation Dialogue Systems](https://mlsanity.com/paper/2402.01097/) (2024)

## Abstract (arXiv)

We study non-collaborative dialogs, where two agents have a conflict of interest but must strategically communicate to reach an agreement (e.g., negotiation). This setting poses new challenges for modeling dialog history because the dialog's outcome relies not only on the semantic intent, but also on tactics that convey the intent. We propose to model both semantic and tactic history using finite state transducers (FSTs). Unlike RNN, FSTs can explicitly represent dialog history through all the states traversed, facilitating interpretability of dialog structure. We train FSTs on a set of strategies and tactics used in negotiation dialogs. The trained FSTs show plausible tactic structure and can be generalized to other non-collaborative domains (e.g., persuasion). We evaluate the FSTs by incorporating them in an automated negotiating system that attempts to sell products and a persuasion system that persuades people to donate to a charity. Experiments show that explicitly modeling both semantic and tactic history is an effective way to improve both dialog policy planning and generation performance.