ToolFlow: Boosting LLM Tool-Calling Through Natural and Coherent Dialogue Synthesis

• URL: http://arxiv.org/abs/2410.18447v1
• Date: Thu, 24 Oct 2024 05:45:04 GMT
• Title: ToolFlow: Boosting LLM Tool-Calling Through Natural and Coherent Dialogue Synthesis
• Authors: Zezhong Wang, Xingshan Zeng, Weiwen Liu, Liangyou Li, Yasheng Wang, Lifeng Shang, Xin Jiang, Qun Liu, Kam-Fai Wong,
• Abstract summary: We propose a Graph-based Sampling strategy to sample more relevant tool combinations, and a Planned-generation strategy to create plans that guide the synthesis of coherent dialogues. We apply SFT on LLaMA-3.1-8B using 8,000 synthetic dialogues generated with ToolFlow. Results show that the model achieves tool-calling performance comparable to or even surpassing GPT-4, while maintaining strong general capabilities.
• Score: 80.34000499166648
• License:
• Abstract: Supervised fine-tuning (SFT) is a common method to enhance the tool calling capabilities of Large Language Models (LLMs), with the training data often being synthesized. The current data synthesis process generally involves sampling a set of tools, formulating a requirement based on these tools, and generating the call statements. However, tools sampled randomly lack relevance, making them difficult to combine and thus reducing the diversity of the data. Additionally, current work overlooks the coherence between turns of dialogues, leading to a gap between the synthesized data and real-world scenarios. To address these issues, we propose a Graph-based Sampling strategy to sample more relevant tool combinations, and a Planned-generation strategy to create plans that guide the synthesis of coherent dialogues. We integrate these two strategies and enable multiple agents to synthesize the dialogue data interactively, resulting in our tool-calling data synthesis pipeline ToolFlow. Data quality assessments demonstrate improvements in the naturalness and coherence of our synthesized dialogues. Finally, we apply SFT on LLaMA-3.1-8B using 8,000 synthetic dialogues generated with ToolFlow. Results show that the model achieves tool-calling performance comparable to or even surpassing GPT-4, while maintaining strong general capabilities.

Related papers

• Generating Realistic Tabular Data with Large Language Models [49.03536886067729]
  Large language models (LLM) have been used for diverse tasks, but do not capture the correct correlation between the features and the target variable. We propose a LLM-based method with three important improvements to correctly capture the ground-truth feature-class correlation in the real data. Our experiments show that our method significantly outperforms 10 SOTA baselines on 20 datasets in downstream tasks.
  arXiv  Detail & Related papers  (2024-10-29T04:14:32Z)
• DiaSynth: Synthetic Dialogue Generation Framework for Low Resource Dialogue Applications [18.378069426713]
  Existing research is constrained by general or niche datasets that lack sufficient scale for training dialogue systems. We introduce Dia Synth - a synthetic dialogue generation framework capable of generating high-quality, contextually rich dialogues. We perform our experiments by generating synthetic data using different LLMs and few-shot examples from DialogSum and SAMSum.
  arXiv  Detail & Related papers  (2024-09-25T07:03:31Z)
• ToolACE: Winning the Points of LLM Function Calling [139.07157814653638]
  ToolACE is an automatic agentic pipeline designed to generate accurate, complex, and diverse tool-learning data. We demonstrate that models trained on our synthesized data, even with only 8B parameters, achieve state-of-the-art performance on the Berkeley Function-Calling Leaderboard.
  arXiv  Detail & Related papers  (2024-09-02T03:19:56Z)
• Self-Directed Synthetic Dialogues and Revisions Technical Report [16.587350874099638]
  We introduce Self Directed Synthetic Dialogues (SDSD), an experimental dataset consisting of guided conversations of language models talking to themselves. SDSD consists of multi-turn conversations generated with DBRX, Llama 2 70B, and Mistral Large, all instructed to follow a conversation plan generated prior to the conversation.
  arXiv  Detail & Related papers  (2024-07-25T22:42:36Z)
• Towards Completeness-Oriented Tool Retrieval for Large Language Models [60.733557487886635]
  Real-world systems often incorporate a wide array of tools, making it impractical to input all tools into Large Language Models. Existing tool retrieval methods primarily focus on semantic matching between user queries and tool descriptions. We propose a novel modelagnostic COllaborative Learning-based Tool Retrieval approach, COLT, which captures not only the semantic similarities between user queries and tool descriptions but also takes into account the collaborative information of tools.
  arXiv  Detail & Related papers  (2024-05-25T06:41:23Z)
• Fake it to make it: Using synthetic data to remedy the data shortage in joint multimodal speech-and-gesture synthesis [21.210982054134686]
  Methods for joint and unified synthesis of speech audio and co-speech 3D gesture motion from text are a new and emerging field. Existing methods are trained on parallel data from all constituent modalities. Inspired by student-teacher methods, we propose a straightforward solution to the data shortage, by simply synthesising additional training material.
  arXiv  Detail & Related papers  (2024-04-30T15:22:19Z)
• Simulating Task-Oriented Dialogues with State Transition Graphs and Large Language Models [16.94819621353007]
  SynTOD is a new synthetic data generation approach for developing end-to-end Task-Oriented Dialogue (TOD) systems. It generates diverse, structured conversations through random walks and response simulation using large language models. In our experiments, using graph-guided response simulations leads to significant improvements in intent classification, slot filling and response relevance.
  arXiv  Detail & Related papers  (2024-04-23T06:23:34Z)
• Turning Flowchart into Dialog: Augmenting Flowchart-grounded Troubleshooting Dialogs via Synthetic Data Generation [50.06143883455979]
  Flowchart-grounded troubleshooting dialogue (FTD) systems follow the instructions of a flowchart to diagnose users' problems in specific domains. We propose a plan-based synthetic data generation approach that generates diverse synthetic dialog data at scale.
  arXiv  Detail & Related papers  (2023-05-02T11:08:27Z)
• TRoVE: Transforming Road Scene Datasets into Photorealistic Virtual Environments [84.6017003787244]
  This work proposes a synthetic data generation pipeline to address the difficulties and domain-gaps present in simulated datasets. We show that using annotations and visual cues from existing datasets, we can facilitate automated multi-modal data generation.
  arXiv  Detail & Related papers  (2022-08-16T20:46:08Z)

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.