SGP-TOD: Building Task Bots Effortlessly via Schema-Guided LLM Prompting

• URL: http://arxiv.org/abs/2305.09067v1
• Date: Mon, 15 May 2023 23:29:56 GMT
• Title: SGP-TOD: Building Task Bots Effortlessly via Schema-Guided LLM Prompting
• Authors: Xiaoying Zhang, Baolin Peng, Kun Li, Jingyan Zhou, Helen Meng
• Abstract summary: Large language models (LLMs) have demonstrated exceptional proficiency in conversational engagement. We introduce SGP-TOD,Guided Prompting for building Task-Oriented Dialog systems effortlessly. SGP-TOD comprises three components: a LLM for engaging with users, a DST Prompter to aid the LLM with dialog state tracking, and a Policy Prompter to elicit proper responses adhering to the provided dialog policy.
• Score: 43.02058641501056
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Building end-to-end task bots and maintaining their integration with new functionalities using minimal human efforts is a long-standing challenge in dialog research. Recently large language models (LLMs) have demonstrated exceptional proficiency in conversational engagement and adherence to instructions across various downstream tasks. In this work, we introduce SGP-TOD, Schema-Guided Prompting for building Task-Oriented Dialog systems effortlessly based on LLMs. Utilizing the symbolic knowledge -- task schema, we instruct fixed LLMs to generate appropriate responses on novel tasks, circumventing the need for training data. Specifically, SGP-TOD comprises three components: a LLM for engaging with users, a DST Prompter to aid the LLM with dialog state tracking, which is then used to retrieve database items, and a Policy Prompter to elicit proper responses adhering to the provided dialog policy. Experimental results on Multiwoz, RADDLE and STAR datasets show that our training-free strategy SGP-TOD, without any task-specific data, yields state-of-the-art (SOTA) zero-shot performance, greatly surpasses the few-shot approaches. In a domain-extension setting, SGP-TOD aptly adapts to new functionalities by merely adding supplementary schema rules. We make our code and data publicly available.

Related papers

• Synergizing In-context Learning with Hints for End-to-end Task-oriented Dialog Systems [25.14460456391397]
  Large language model (LLM) based TOD systems can excel even with limited data due to their ability to learn tasks through in-context exemplars. We propose SyncTOD that synergizes LLMs with task-specific hints to improve alignment in low-data settings. With ChatGPT, SyncTOD achieves superior performance compared to LLM-based baselines and SoTA models in low-data settings.
  arXiv  Detail & Related papers  (2024-05-24T14:13:54Z)
• Sub-goal Distillation: A Method to Improve Small Language Agents [21.815417165548187]
  Large Language Models (LLMs) have demonstrated significant promise as agents in interactive tasks. We propose a method for transferring the performance of an LLM with billions of parameters to a much smaller language model. In ScienceWorld, a challenging and multi-task interactive text environment, our method surpasses standard imitation learning based solely on elementary actions by 16.7%.
  arXiv  Detail & Related papers  (2024-05-04T20:34:06Z)
• Symbolic Planning and Code Generation for Grounded Dialogue [78.48668501764385]
  Large language models (LLMs) excel at processing and generating both text and code. We present a modular and interpretable grounded dialogue system that addresses shortcomings by composing LLMs with a symbolic planner and grounded code execution. Our system substantially outperforms the previous state-of-the-art, including improving task success in human evaluations from 56% to 69% in the most challenging setting.
  arXiv  Detail & Related papers  (2023-10-26T04:22:23Z)
• InstructTODS: Large Language Models for End-to-End Task-Oriented Dialogue Systems [60.53276524369498]
  Large language models (LLMs) have been used for diverse tasks in natural language processing (NLP) We present InstructTODS, a novel framework for zero-shot end-to-end task-oriented dialogue systems. InstructTODS generates a proxy belief state that seamlessly translates user intentions into dynamic queries.
  arXiv  Detail & Related papers  (2023-10-13T06:36:26Z)
• Task-Optimized Adapters for an End-to-End Task-Oriented Dialogue System [0.0]
  We propose an End-to-end TOD system with Task-d Adapters which learn independently per task, adding only small number of parameters after fixed layers of pre-trained network. Our method is a model-agnostic approach and does not require prompt-tuning as only input data without a prompt.
  arXiv  Detail & Related papers  (2023-05-04T00:17:49Z)
• Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedback [127.75419038610455]
  Large language models (LLMs) are able to generate human-like, fluent responses for many downstream tasks. This paper proposes a LLM-Augmenter system, which augments a black-box LLM with a set of plug-and-play modules.
  arXiv  Detail & Related papers  (2023-02-24T18:48:43Z)
• Decomposed Prompting: A Modular Approach for Solving Complex Tasks [55.42850359286304]
  We propose Decomposed Prompting to solve complex tasks by decomposing them (via prompting) into simpler sub-tasks. This modular structure allows each prompt to be optimized for its specific sub-task. We show that the flexibility and modularity of Decomposed Prompting allows it to outperform prior work on few-shot prompting.
  arXiv  Detail & Related papers  (2022-10-05T17:28:20Z)
• CINS: Comprehensive Instruction for Few-shot Learning in Task-oriented Dialog Systems [56.302581679816775]
  This paper proposes Comprehensive Instruction (CINS) that exploits PLMs with task-specific instructions. We design a schema (definition, constraint, prompt) of instructions and their customized realizations for three important downstream tasks in ToD. Experiments are conducted on these ToD tasks in realistic few-shot learning scenarios with small validation data.
  arXiv  Detail & Related papers  (2021-09-10T03:23:06Z)

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.