Improving Multi-turn Task Completion in Task-Oriented Dialog Systems via Prompt Chaining and Fine-Grained Feedback
- URL: http://arxiv.org/abs/2502.13298v1
- Date: Tue, 18 Feb 2025 21:36:19 GMT
- Title: Improving Multi-turn Task Completion in Task-Oriented Dialog Systems via Prompt Chaining and Fine-Grained Feedback
- Authors: Moghis Fereidouni, Md Sajid Ahmed, Adib Mosharrof, A. B. Siddique,
- Abstract summary: Task-oriented dialog (TOD) systems facilitate users in accomplishing complex, multi-turn tasks through natural language.<n>LLMs struggle to reliably handle multi-turn task completion.<n>We propose RealTOD, a novel framework that enhances TOD systems through prompt chaining and fine-grained feedback mechanisms.
- Score: 2.246166820363412
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Task-oriented dialog (TOD) systems facilitate users in accomplishing complex, multi-turn tasks through natural language. While traditional approaches rely on extensive fine-tuning and annotated data for each domain, instruction-tuned large language models (LLMs) offer a more flexible alternative. However, LLMs struggle to reliably handle multi-turn task completion, particularly with accurately generating API calls and adapting to new domains without explicit demonstrations. To address these challenges, we propose RealTOD, a novel framework that enhances TOD systems through prompt chaining and fine-grained feedback mechanisms. Prompt chaining enables zero-shot domain adaptation via a two-stage prompting strategy, eliminating the need for human-curated demonstrations. Meanwhile, the fine-grained feedback mechanism improves task completion by verifying API calls against domain schemas and providing precise corrective feedback when errors are detected. We conduct extensive experiments on the SGD and BiTOD benchmarks using four LLMs. RealTOD improves API accuracy, surpassing AutoTOD by 37.74% on SGD and SimpleTOD by 11.26% on BiTOD. Human evaluations further confirm that LLMs integrated with RealTOD achieve superior task completion, fluency, and informativeness compared to existing methods.
Related papers
- SUTA-LM: Bridging Test-Time Adaptation and Language Model Rescoring for Robust ASR [58.31068047426522]
Test-Time Adaptation (TTA) aims to mitigate by adjusting models during inference.<n>Recent work explores combining TTA with external language models, using techniques like beam search rescoring or generative error correction.<n>We propose SUTA-LM, a simple yet effective extension of SUTA, with language model rescoring.<n> Experiments on 18 diverse ASR datasets show that SUTA-LM achieves robust results across a wide range of domains.
arXiv Detail & Related papers (2025-06-10T02:50:20Z) - MLE-Dojo: Interactive Environments for Empowering LLM Agents in Machine Learning Engineering [57.156093929365255]
Gym-style framework for systematically reinforcement learning, evaluating, and improving autonomous large language model (LLM) agents.<n>MLE-Dojo covers diverse, open-ended MLE tasks carefully curated to reflect realistic engineering scenarios.<n>Its fully executable environment supports comprehensive agent training via both supervised fine-tuning and reinforcement learning.
arXiv Detail & Related papers (2025-05-12T17:35:43Z) - EMMOE: A Comprehensive Benchmark for Embodied Mobile Manipulation in Open Environments [11.97783742296183]
Embodied Mobile Manipulation in Open Environments is a benchmark that requires agents to interpret user instructions and execute long-horizon everyday tasks in continuous space.<n>Embodied Mobile Manipulation in Open Environments seamlessly integrates high-level and low-level embodied tasks into a unified framework, along with three new metrics for more diverse assessment.<n>We designmodel, a sophisticated agent system consists of LLM with Direct Preference Optimization (DPO), light weighted navigation and manipulation models, and multiple error detection mechanisms.
arXiv Detail & Related papers (2025-03-11T16:42:36Z) - Evaluating and Enhancing Out-of-Domain Generalization of Task-Oriented Dialog Systems for Task Completion without Turn-level Dialog Annotations [2.453775887722866]
This work explores whether large language models (LLMs) can be fine-tuned solely on natural language dialogs to perform ToD tasks, without requiring such annotations.<n>We find that models fine-tuned without turn-level annotations generate coherent and contextually appropriate responses.<n>We propose ZeroToD, a framework that incorporates a schema augmentation mechanism to enhance API call accuracy and overall task completion rates.
arXiv Detail & Related papers (2025-02-18T22:10:51Z) - Scaling Autonomous Agents via Automatic Reward Modeling And Planning [52.39395405893965]
Large language models (LLMs) have demonstrated remarkable capabilities across a range of tasks.<n>However, they still struggle with problems requiring multi-step decision-making and environmental feedback.<n>We propose a framework that can automatically learn a reward model from the environment without human annotations.
arXiv Detail & Related papers (2025-02-17T18:49:25Z) - AutoML-Agent: A Multi-Agent LLM Framework for Full-Pipeline AutoML [56.565200973244146]
Automated machine learning (AutoML) accelerates AI development by automating tasks in the development pipeline.
Recent works have started exploiting large language models (LLM) to lessen such burden.
This paper proposes AutoML-Agent, a novel multi-agent framework tailored for full-pipeline AutoML.
arXiv Detail & Related papers (2024-10-03T20:01:09Z) - Task-Distributionally Robust Data-Free Meta-Learning [99.56612787882334]
Data-Free Meta-Learning (DFML) aims to efficiently learn new tasks by leveraging multiple pre-trained models without requiring their original training data.
For the first time, we reveal two major challenges hindering their practical deployments: Task-Distribution Shift ( TDS) and Task-Distribution Corruption (TDC)
arXiv Detail & Related papers (2023-11-23T15:46:54Z) - 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) - OverPrompt: Enhancing ChatGPT through Efficient In-Context Learning [49.38867353135258]
We propose OverPrompt, leveraging the in-context learning capability of LLMs to handle multiple task inputs.
Our experiments show that OverPrompt can achieve cost-efficient zero-shot classification without causing significant detriment to task performance.
arXiv Detail & Related papers (2023-05-24T10:08:04Z) - 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) - Making Pre-trained Language Models End-to-end Few-shot Learners with
Contrastive Prompt Tuning [41.15017636192417]
We present CP-Tuning, the first end-to-end Contrastive Prompt Tuning framework for fine-tuning Language Models.
It is integrated with the task-invariant continuous prompt encoding technique with fully trainable prompt parameters.
Experiments over a variety of language understanding tasks used in IR systems and different PLMs show that CP-Tuning outperforms state-of-the-art methods.
arXiv Detail & Related papers (2022-04-01T02:24:24Z) - 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.