CoT-TL: Low-Resource Temporal Knowledge Representation of Planning Instructions Using Chain-of-Thought Reasoning

• URL: http://arxiv.org/abs/2410.16207v1
• Date: Mon, 21 Oct 2024 17:10:43 GMT
• Title: CoT-TL: Low-Resource Temporal Knowledge Representation of Planning Instructions Using Chain-of-Thought Reasoning
• Authors: Kumar Manas, Stefan Zwicklbauer, Adrian Paschke,
• Abstract summary: CoT-TL is a data-efficient in-context learning framework for translating natural language specifications into representations. CoT-TL achieves state-of-the-art accuracy across three diverse datasets in low-data scenarios.
• Score: 0.0
• License:
• Abstract: Autonomous agents often face the challenge of interpreting uncertain natural language instructions for planning tasks. Representing these instructions as Linear Temporal Logic (LTL) enables planners to synthesize actionable plans. We introduce CoT-TL, a data-efficient in-context learning framework for translating natural language specifications into LTL representations. CoT-TL addresses the limitations of large language models, which typically rely on extensive fine-tuning data, by extending chain-of-thought reasoning and semantic roles to align with the requirements of formal logic creation. This approach enhances the transparency and rationale behind LTL generation, fostering user trust. CoT-TL achieves state-of-the-art accuracy across three diverse datasets in low-data scenarios, outperforming existing methods without fine-tuning or intermediate translations. To improve reliability and minimize hallucinations, we incorporate model checking to validate the syntax of the generated LTL output. We further demonstrate CoT-TL's effectiveness through ablation studies and evaluations on unseen LTL structures and formulas in a new dataset. Finally, we validate CoT-TL's practicality by integrating it into a QuadCopter for multi-step drone planning based on natural language instructions.

Related papers

• Boosting the Capabilities of Compact Models in Low-Data Contexts with Large Language Models and Retrieval-Augmented Generation [2.9921619703037274]
  We propose a retrieval augmented generation (RAG) framework backed by a large language model (LLM) to correct the output of a smaller model for the linguistic task of morphological glossing. We leverage linguistic information to make up for the lack of data and trainable parameters, while allowing for inputs from written descriptive grammars interpreted and distilled through an LLM. We show that a compact, RAG-supported model is highly effective in data-scarce settings, achieving a new state-of-the-art for this task and our target languages.
  arXiv  Detail & Related papers  (2024-10-01T04:20:14Z)
• Directed Exploration in Reinforcement Learning from Linear Temporal Logic [59.707408697394534]
  Linear temporal logic (LTL) is a powerful language for task specification in reinforcement learning. We show that the synthesized reward signal remains fundamentally sparse, making exploration challenging. We show how better exploration can be achieved by further leveraging the specification and casting its corresponding Limit Deterministic B"uchi Automaton (LDBA) as a Markov reward process.
  arXiv  Detail & Related papers  (2024-08-18T14:25:44Z)
• Unlocking the Potential of Model Merging for Low-Resource Languages [66.7716891808697]
  Adapting large language models to new languages typically involves continual pre-training (CT) followed by supervised fine-tuning (SFT) We propose model merging as an alternative for low-resource languages, combining models with distinct capabilities into a single model without additional training. Experiments based on Llama-2-7B demonstrate that model merging effectively endows LLMs for low-resource languages with task-solving abilities, outperforming CT-then-SFT in scenarios with extremely scarce data.
  arXiv  Detail & Related papers  (2024-07-04T15:14:17Z)
• TLINet: Differentiable Neural Network Temporal Logic Inference [10.36033062385604]
  This paper introduces TLINet, a neural-symbolic framework for learning STL formulas. In contrast to existing approaches, we introduce approximation methods for max operator designed specifically for temporal logic-based gradient techniques. Our framework not only learns the structure but also the parameters of STL formulas, allowing flexible combinations of operators and various logical structures.
  arXiv  Detail & Related papers  (2024-05-03T16:38:14Z)
• Prefix Text as a Yarn: Eliciting Non-English Alignment in Foundation Language Model [50.339632513018934]
  supervised fine-tuning (SFT) has been a straightforward approach for tailoring the output of foundation large language model (LLM) to specific preferences. We critically examine this hypothesis within the scope of cross-lingual generation tasks. We introduce a novel training-free alignment method named PreTTY, which employs minimal task-related prior tokens.
  arXiv  Detail & Related papers  (2024-04-25T17:19:36Z)
• Guiding Language Model Reasoning with Planning Tokens [122.43639723387516]
  Large language models (LLMs) have recently attracted considerable interest for their ability to perform complex reasoning tasks. We propose a hierarchical generation scheme to encourage a more structural generation of chain-of-thought steps. Our approach requires a negligible increase in trainable parameters (0.001%) and can be applied through either full fine-tuning or a more parameter-efficient scheme.
  arXiv  Detail & Related papers  (2023-10-09T13:29:37Z)
• Towards Unified Token Learning for Vision-Language Tracking [65.96561538356315]
  We present a vision-language (VL) tracking pipeline, termed textbfMMTrack, which casts VL tracking as a token generation task. Our proposed framework serializes language description and bounding box into a sequence of discrete tokens. In this new design paradigm, all token queries are required to perceive the desired target and directly predict spatial coordinates of the target.
  arXiv  Detail & Related papers  (2023-08-27T13:17:34Z)
• ParroT: Translating during Chat using Large Language Models tuned with Human Translation and Feedback [90.20262941911027]
  ParroT is a framework to enhance and regulate the translation abilities during chat. Specifically, ParroT reformulates translation data into the instruction-following style. We propose three instruction types for finetuning ParroT models, including translation instruction, contrastive instruction, and error-guided instruction.
  arXiv  Detail & Related papers  (2023-04-05T13:12:00Z)
• Data-Efficient Learning of Natural Language to Linear Temporal Logic Translators for Robot Task Specification [6.091096843566857]
  We present a learning-based approach for translating from natural language commands to specifications with very limited human-labeled training data. This is in stark contrast to existing natural-language to translators, which require large human-labeled datasets. We show that we can translate natural language commands at 75% accuracy with far less human data.
  arXiv  Detail & Related papers  (2023-03-09T00:09:58Z)
• Interactive Learning from Natural Language and Demonstrations using Signal Temporal Logic [5.88797764615148]
  Natural language (NL) is ambiguous, real world tasks and their safety requirements need to be communicated unambiguously. Signal Temporal Logic (STL) is a formal logic that can serve as a versatile, expressive, and unambiguous formal language to describe robotic tasks. We propose DIALOGUESTL, an interactive approach for learning correct and concise STL formulas from (often) ambiguous NL descriptions.
  arXiv  Detail & Related papers  (2022-07-01T19:08:43Z)
• Generalizing to New Domains by Mapping Natural Language to Lifted LTL [20.58567011476273]
  We introduce an intermediate contextual query representation which can be learned from single positive task specification examples. We compare our method to state-of-the-art CopyNet models capable of translating natural language. We demonstrate that our method outputs can be used for planning in a simulated OO-MDP environment.
  arXiv  Detail & Related papers  (2021-10-11T20:49:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.