Expert Curated Dataset 2026
Collection
The dataset is used for fine-tuning and aligning LLMs with Kazakh culture. • 13 items • Updated
🇰🇿 Kazakh Tool Output Interpretation and Financial Action Dataset
Dataset Summary
Kazakh Tool Output Interpretation and Financial Action Dataset is a Kazakh-language dataset designed for training and evaluating Large Language Models (LLMs) in tool-augmented agentic workflows that require interpreting structured tool outputs and generating grounded final responses.
The dataset focuses on scenarios where an assistant must understand a Kazakh user request, call the appropriate tools, read structured outputs, and summarize the result accurately. Many samples involve sensitive or action-oriented domains, such as banking, account balance checking, transfers, and financial status reporting.
This dataset is useful for studying how Kazakh-language AI agents interpret tool responses, combine outputs from multiple tools, preserve numerical accuracy, and produce concise user-facing answers based on simulated external APIs.
📊 Dataset Statistics
General Metrics
| Metric | Count |
|---|---|
| Total Samples | 3,568 |
| Total Words (approx.) | 1,079,862 |
| Avg. Words per Sample | 302 |
Word Count Distribution Per Field
The following table details the distribution of word counts across different fields in the dataset.
| Field | Mean | Median | Min | Max | Total Words |
|---|---|---|---|---|---|
| answers | 29.3 | 26.0 | 8 | 137 | 104,465 |
| category | 1.0 | 1.0 | 1 | 1 | 3,568 |
| difficulty | 1.0 | 1.0 | 1 | 1 | 3,568 |
| id | 1.0 | 1.0 | 1 | 1 | 3,568 |
| query | 15.3 | 15.0 | 3 | 38 | 54,731 |
| tools | 88.7 | 86.0 | 30 | 160 | 316,565 |
| turns | 166.3 | 160.0 | 66 | 369 | 593,397 |
Dataset Structure
Each dataset instance represents a complete tool-use interaction. A sample usually includes a Kazakh user query, available tool schemas, expected tool calls, simulated tool responses, and a final assistant answer.
Data Fields
id: A unique identifier for the sample.query: The original user request in Kazakh. The query may involve checking information, performing a simulated action, or asking the assistant to interpret structured tool results.category: The task category. For example,07_tool_output_interpretationindicates that the sample focuses on understanding and summarizing tool outputs correctly.tools: A list of tools available to the assistant. Each tool contains:name: the tool name;description: the tool’s purpose;parameters: the required or optional input schema;mock_response: the expected response structure.
difficulty: The difficulty level of the sample.answers: The expected tool calls. This field may contain one or more function calls with serialized JSON arguments.turns: The complete interaction trace, including:- user request;
- assistant planning;
- assistant tool calls;
- mock tool responses;
- final answer grounded in the tool outputs.
Data Instance
Below is one representative example from the dataset.
{
"id": "dastan_07_1",
"query": "Менің 123456789 шотымдағы ақшаны 987654321 шотына 10000 теңге аударшы.",
"category": "07_tool_output_interpretation",
"tools": [
{
"name": "bank.balance",
"description": "Get bank account balance",
"parameters": {
"account": {
"type": "string",
"description": "Account number",
"required": true
},
"api_key": {
"type": "string",
"description": "Auth key",
"required": false
}
},
"mock_response": {
"account": "",
"balance": null,
"currency": ""
}
},
{
"name": "bank.transfer",
"description": "Transfer money between accounts",
"parameters": {
"from_account": {
"type": "string",
"description": "Source account",
"required": true
},
"to_account": {
"type": "string",
"description": "Destination account",
"required": true
},
"amount": {
"type": "float",
"description": "Amount to transfer",
"required": true
},
"api_key": {
"type": "string",
"description": "Auth key",
"required": true
}
},
"mock_response": {
"transaction_id": "",
"status": "",
"amount": null,
"currency": "",
"remaining_balance": null
}
}
],
"difficulty": "easy",
"answers": [
{
"name": "bank.balance",
"arguments": "{\"account\": \"123456789\", \"api_key\": \"example-key\"}"
},
{
"name": "bank.transfer",
"arguments": "{\"from_account\": \"123456789\", \"to_account\": \"987654321\", \"amount\": 10000.0, \"api_key\": \"example-key\"}"
}
],
"turns": [
{
"role": "user",
"content": "Менің 123456789 шотымдағы ақшаны 987654321 шотына 10000 теңге аударшы."
},
{
"role": "assistant",
"content": "Алдымен балансты тексеріп, сосын аударым жасаймын.",
"meta": {
"plan": "Extract and normalize bank.balance + bank.transfer data",
"tags": [],
"difficulty": "hard"
}
},
{
"role": "assistant",
"content": "",
"tool_call": {
"name": "bank.balance",
"arguments": "{\"account\": \"123456789\", \"api_key\": \"example-key\"}"
}
},
{
"role": "tool",
"content": "{\"account\": \"123456789\", \"balance\": 25000.0, \"currency\": \"KZT\"}"
},
{
"role": "assistant",
"content": "",
"tool_call": {
"name": "bank.transfer",
"arguments": "{\"from_account\": \"123456789\", \"to_account\": \"987654321\", \"amount\": 10000.0, \"api_key\": \"example-key\"}"
}
},
{
"role": "tool",
"content": "{\"transaction_id\": \"tr12345\", \"status\": \"success\", \"amount\": 10000.0, \"currency\": \"KZT\", \"remaining_balance\": 15000.0}"
},
{
"role": "assistant",
"content": "123456789 шотынан 987654321 шотына 10000 теңге сәтті аударылды. Қалған баланс: 15000 теңге. (Дерек көзі: bank.balance + bank.transfer)"
}
]
},
Funding
This dataset was developed as part of the project funded by the Ministry of Science and Higher Education of the Republic of Kazakhstan under Grant No. BR24993001, “Creation of a Large Language Model (LLM) to Support the Kazakh Language and Advance Technological Development.”
Citation
If you use this dataset in your research, please cite the following article:
APA
Kadyrbek, N., Tuimebayev, Z., Mansurova, M., & Viegas, V. (2025). The development of small-scale language models for low-resource languages, with a focus on Kazakh and direct preference optimization. Big Data and Cognitive Computing, 9(5), 137. https://doi.org/10.3390/bdcc9050137
BibTeX
@article{kadyrbek2025development,
title = {The Development of Small-Scale Language Models for Low-Resource Languages, with a Focus on Kazakh and Direct Preference Optimization},
author = {Kadyrbek, Nurgali and Tuimebayev, Zhanseit and Mansurova, Madina and Viegas, Vitor},
journal = {Big Data and Cognitive Computing},
volume = {9},
number = {5},
pages = {137},
year = {2025},
publisher = {MDPI},
doi = {10.3390/bdcc9050137},
url = {https://www.mdpi.com/2504-2289/9/5/137}
}
- Downloads last month
- 13