Invocable APIs derived from NL2SQL datasets for LLM Tool-Calling Evaluation

• URL: http://arxiv.org/abs/2506.11266v1
• Date: Thu, 12 Jun 2025 20:17:52 GMT
• Title: Invocable APIs derived from NL2SQL datasets for LLM Tool-Calling Evaluation
• Authors: Benjamin Elder, Anupama Murthi, Jungkoo Kang, Ankita Rajaram Naik, Kiran Kate, Kinjal Basu, Danish Contractor,
• Abstract summary: Large language models (LLMs) are routinely deployed as agentic systems with access to tools that interact with live environments to accomplish tasks.<n>In order to create datasets with such characteristics, we explore how existing NL2 datasets can be used to automatically create NL2API datasets.<n>We apply this pipeline to one of the largest NL2 datasets, BIRD, to create a collection of over 2500 APIs that can be served as invocable tools or REST-endpoints.
• Score: 7.260113022127256
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Large language models (LLMs) are routinely deployed as agentic systems, with access to tools that interact with live environments to accomplish tasks. In enterprise deployments these systems need to interact with API collections that can be extremely large and complex, often backed by databases. In order to create datasets with such characteristics, we explore how existing NL2SQL (Natural Language to SQL query) datasets can be used to automatically create NL2API datasets. Specifically, this work describes a novel data generation pipeline that exploits the syntax of SQL queries to construct a functionally equivalent sequence of API calls. We apply this pipeline to one of the largest NL2SQL datasets, BIRD-SQL to create a collection of over 2500 APIs that can be served as invocable tools or REST-endpoints. We pair natural language queries from BIRD-SQL to ground-truth API sequences based on this API pool. We use this collection to study the performance of 10 public LLMs and find that all models struggle to determine the right set of tools (consisting of tasks of intent detection, sequencing with nested function calls, and slot-filling). We find that models have extremely low task completion rates (7-47 percent - depending on the dataset) which marginally improves to 50 percent when models are employed as ReACT agents that interact with the live API environment. The best task completion rates are far below what may be required for effective general-use tool-calling agents, suggesting substantial scope for improvement in current state-of-the-art tool-calling LLMs. We also conduct detailed ablation studies, such as assessing the impact of the number of tools available as well as the impact of tool and slot-name obfuscation. We compare the performance of models on the original SQL generation tasks and find that current models are sometimes able to exploit SQL better than APIs.

Related papers

• Querying Databases with Function Calling [1.3329663974869035]
  We propose a tool definition for database querying that unifies accessing data with search queries, filters, or a combination both.<n>We present a novel pipeline adapting the Gorilla LLM framework to create synthetic database schemas and queries.<n>We find that LLMs are highly effective at utilizing operators on properties, but struggle with text property filters.
  arXiv  Detail & Related papers  (2025-01-23T23:09:13Z)
• 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)
• APIGen: Automated Pipeline for Generating Verifiable and Diverse Function-Calling Datasets [99.8988504388011]
  APIGen is an automated data generation pipeline designed to synthesize verifiable high-quality datasets for function-calling applications. We leverage APIGen and collect 3,673 executable APIs across 21 different categories to generate diverse function-calling datasets. We release a dataset containing 60,000 high-quality entries, aiming to advance the field of function-calling agent domains.
  arXiv  Detail & Related papers  (2024-06-26T17:49:11Z)
• UQE: A Query Engine for Unstructured Databases [71.49289088592842]
  We investigate the potential of Large Language Models to enable unstructured data analytics. We propose a new Universal Query Engine (UQE) that directly interrogates and draws insights from unstructured data collections.
  arXiv  Detail & Related papers  (2024-06-23T06:58:55Z)
• From Summary to Action: Enhancing Large Language Models for Complex Tasks with Open World APIs [62.496139001509114]
  We introduce a novel tool invocation pipeline designed to control massive real-world APIs. This pipeline mirrors the human task-solving process, addressing complicated real-life user queries. Empirical evaluations of our Sum2Act pipeline on the ToolBench benchmark show significant performance improvements.
  arXiv  Detail & Related papers  (2024-02-28T08:42:23Z)
• API-BLEND: A Comprehensive Corpora for Training and Benchmarking API LLMs [28.840207102132286]
  We focus on the task of identifying, curating, and transforming existing datasets. We introduce API-BLEND, a large corpora for training and systematic testing of tool-augmented LLMs. We demonstrate the utility of the API-BLEND dataset for both training and benchmarking purposes.
  arXiv  Detail & Related papers  (2024-02-23T18:30:49Z)
• MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQL [47.120862170230566]
  Recent Text-to-yourself methods usually suffer from significant performance degradation on "huge" databases.<n>We introduce MAC, a novel Text-to-yourself LLM-based multi-agent collaborative framework.<n>In our framework, we leverage GPT-4 as the strong backbone for all agent tasks to determine the upper bound of our framework.<n>We then fine-tune an open-sourced instruction-followed model,sql-Llama, by leveraging Code 7B, to accomplish all tasks as GPT-4 does.
  arXiv  Detail & Related papers  (2023-12-18T14:40:20Z)
• Fine-Tuning Language Models for Context-Specific SQL Query Generation [0.0]
  This paper presents a novel approach to fine-tuning open-source large language models (LLMs) for the task of transforming natural language intosql queries. We introduce models specialized in generatingsql queries, trained on synthetic datasets tailored to the Snowflake SQL and Google dialects. Our methodology involves generating a context-specific dataset using GPT-4, then fine-tuning three open-source LLMs(Starcoder Plus, Code-Llama, and Mistral) employing the LoRa technique to optimize for resource constraints. The fine-tuned models demonstrate superior performance in zero-shot settings compared to the baseline GP
  arXiv  Detail & Related papers  (2023-12-04T18:04:27Z)
• CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsets [75.64181719386497]
  We present CRAFT, a tool creation and retrieval framework for large language models (LLMs) It creates toolsets specifically curated for the tasks and equips LLMs with a component that retrieves tools from these sets to enhance their capability to solve complex tasks. Our method is designed to be flexible and offers a plug-and-play approach to adapt off-the-shelf LLMs to unseen domains and modalities, without any finetuning.
  arXiv  Detail & Related papers  (2023-09-29T17:40:26Z)
• On the Effectiveness of Pretrained Models for API Learning [8.788509467038743]
  Developers frequently use APIs to implement certain functionalities, such as parsing Excel Files, reading and writing text files line by line, etc. Developers can greatly benefit from automatic API usage sequence generation based on natural language queries for building applications in a faster and cleaner manner. Existing approaches utilize information retrieval models to search for matching API sequences given a query or use RNN-based encoder-decoder to generate API sequences.
  arXiv  Detail & Related papers  (2022-04-05T20:33:24Z)
• Compositional Generalization for Natural Language Interfaces to Web APIs [26.851998759793453]
  This paper presents Okapi, a new dataset for Natural Language to executable web Application Programming Interfaces (NL2API) This dataset is in English and contains 22,508 questions and 9,019 unique API calls, covering three domains. We define new compositional generalization tasks for NL2API which explore the models' ability to extrapolate from simple API calls in the training set to new and more complex API calls in the inference phase.
  arXiv  Detail & Related papers  (2021-12-09T20:49:01Z)

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.