FLAP: Flow-Adhering Planning with Constrained Decoding in LLMs
Roy, Shamik, Sengupta, Sailik, Bonadiman, Daniele, Mansour, Saab, Gupta, Arshit
–arXiv.org Artificial Intelligence
Planning is a crucial task for agents in task oriented dialogs (TODs). Human agents typically resolve user issues by following predefined workflows, decomposing workflow steps into actionable items, and performing actions by executing APIs in order; all of which require reasoning and planning. With the recent advances in LLMs, there have been increasing attempts to use them for task planning and API usage. However, the faithfulness of the plans to predefined workflows and API dependencies, is not guaranteed with LLMs. Moreover, workflows in real life are often custom-defined and prone to changes; hence, adaptation is desirable. To study this, we propose the problem of faithful planning in TODs that needs to resolve user intents by following predefined flows and preserving API dependencies. To solve this problem, we propose FLAP, a Flow-Adhering Planning algorithm based on constrained decoding with lookahead heuristic for LLMs. Our algorithm alleviates the need for finetuning LLMs using domain specific (plan/dependency) data, enables quick adaptation to predefined flows, and outperforms other decoding and prompting-based baselines. Further, our algorithm empowers smaller LLMs (7B) to perform at par larger LLMs (30B-40B).
arXiv.org Artificial Intelligence
Jun-4-2024
- Country:
- North America
- United States
- District of Columbia > Washington (0.04)
- Nevada > Clark County
- Las Vegas (0.04)
- Minnesota > Hennepin County
- Minneapolis (0.04)
- Louisiana > Orleans Parish
- New Orleans (0.04)
- Illinois > Cook County
- Chicago (0.05)
- Florida > Broward County
- Fort Lauderdale (0.04)
- California
- San Francisco County > San Francisco (0.04)
- Los Angeles County > Los Angeles (0.04)
- San Diego County > San Diego (0.04)
- Canada > Ontario
- Toronto (0.04)
- United States
- Asia
- Singapore (0.04)
- Myanmar > Tanintharyi Region
- Dawei (0.04)
- North America
- Genre:
- Workflow (1.00)
- Research Report > New Finding (0.46)
- Industry:
- Consumer Products & Services > Travel (0.46)
- Technology: