Towards Zero-Shot, Controllable Dialog Planning with LLMs

2024-10-08

AI Summary

Large language models (LLMs) exhibit hallucination and poor zero-shot controllability in dialogue planning for sensitive domains (e.g., law, healthcare). Method: We propose Zero-Shot Controllable Tree Search (CTS), a prompt-engineering–based approach that constructs domain-specific dialogue graphs without reinforcement learning. CTS enables real-time LLM-guided dynamic node expansion and preference-driven pruning, ensuring goal-directedness while enhancing factual consistency. Contribution/Results: Our key innovation lies in decoupling controllable planning into graph-structured navigation and zero-shot reasoning—balancing strategic control with reliability. Experiments show CTS significantly outperforms state-of-the-art RL-based agents across all simulated tasks (p < 0.0001); user studies further confirm a statistically significant improvement in task success rate (p < 0.05).

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

Recently, Large Language Models (LLMs) have emerged as an alternative to training task-specific dialog agents, due to their broad reasoning capabilities and performance in zero-shot learning scenarios. However, many LLM-based dialog systems fall short in planning towards an overarching dialog goal and therefore cannot steer the conversation appropriately. Furthermore, these models struggle with hallucination, making them unsuitable for information access in sensitive domains, such as legal or medical domains, where correctness of information given to users is critical. The recently introduced task Conversational Tree Search (CTS) proposes the use of dialog graphs to avoid hallucination in sensitive domains, however, state-of-the-art agents are Reinforcement Learning (RL) based and require long training times, despite excelling at dialog strategy. This paper introduces a novel zero-shot method for controllable CTS agents, where LLMs guide the dialog planning through domain graphs by searching and pruning relevant graph nodes based on user interaction preferences. We show that these agents significantly outperform state-of-the-art CTS agents ($p<0.0001$; Barnard Exact test) in simulation. This generalizes to all available CTS domains. Finally, we perform user evaluation to test the agent's performance in the wild, showing that our policy significantly ($p<0.05$; Barnard Exact) improves task-success compared to the state-of-the-art RL-based CTS agent.

Problem

• LLMs lack dialog goal planning and steering capabilities
• LLMs struggle with hallucination in sensitive domains
• Current CTS agents require long RL training times

Innovation

• LLMs guide dialog planning via domain graphs
• Search and prune graph nodes based on preferences
• Zero-shot method outperforms RL-based CTS agents