[TOC]

  1. Title: TIC: Translate-Infer-Compile for accurate “text to plan” using LLMs and logical intermediate representations
  2. Author: Sudhir Agarwal et. al.
  3. Publish Year: Jan 2024
  4. Review Date: Sat, Feb 17, 2024
  5. url: https://arxiv.org/pdf/2402.06608.pdf

Summary of paper

image-20240217125703052

Motivation

Contribution

The approach described focuses on bridging the gap between natural language understanding and classical planning. It combines the strengths of large language models (LLMs) for natural language processing and classical planning tools for task planning. Unlike previous methods that directly use LLMs for generating Planning Domain Definition Language (PDDL) representations, this approach involves three steps:

  1. Translate: LLMs are used to generate a logically interpretable intermediate representation of natural language task descriptions.
  2. Infer: Additional logically dependent information is derived from the intermediate representation using a logic reasoner, such as an Answer Set Programming solver.
  3. Compile: The target task PDDL is generated from the base and inferred information.

By only using LLMs to output the intermediate representation, errors are significantly reduced. This approach, known as the TIC approach, achieves high accuracy in generating task PDDLs for all evaluated domains, leveraging the strengths of both LLMs and classical planning tools.

Some key terms

Intermediate Representation

comments from sukai

Results

image-20240217133757067

Summary

The core idea of the paper is that directly outputting PDDL from LLMs is challenging due to their inability to handle very concrete information, such as enumerating every facts to every objects, leading to error-prone translations. Instead, the paper suggests having LLMs translate to intermediate semi-formal representations that can represent higher level rules. This approach addresses the issue of LLMs having to explicitly enumerate all objects to state facts by allowing them to output more abstract representations (high level declaration and high level rules) and then they manually implemented ASP rules and ASP solvers to infer materialised representation. ASP refers to answer set programming.

Potential future work

Can we just replace the whole ASP section to asking LLMs to ask python code to handle the “object and fact enumeration” things. In this case, we do not need to manually writing ASP rules which were stated in Section 3.3. Translating to both PDDL and Python code… Well, it leads to the hybrid modelling topic.