Expert Curated Dataset 2026
Collection
The dataset is used for fine-tuning and aligning LLMs with Kazakh culture. • 13 items • Updated
🇰🇿 Kazakh Argument Schema Mapping and Tool Error Recovery Dataset
Dataset Summary
Kazakh Argument Schema Mapping and Tool Error Recovery Dataset is a Kazakh-language dataset designed for training and evaluating Large Language Models (LLMs) in agentic AI workflows that require accurate argument mapping, schema-following, tool-call correction, and recovery from invalid tool calls.
The dataset contains user requests, tool schemas, expected tool calls, mock tool responses, error messages, retry behavior, and complete multi-turn interaction traces. It focuses on scenarios where an assistant must understand a user’s intent in Kazakh, map the request into valid function-call arguments, detect or respond to tool errors, revise invalid arguments, and complete the task through one or more tools.
📊 Dataset Statistics
General Metrics
| Metric | Count |
|---|---|
| Total Samples | 4,028 |
| Total Words (approx.) | 1,561,416 |
| Avg. Words per Sample | 387 |
Word Count Distribution Per Field
The following table shows the distribution of word counts across the main dataset fields.
| Field | Mean | Median | Min | Max | Total Words |
|---|---|---|---|---|---|
| answers | 47.3 | 41.0 | 6 | 305 | 190,620 |
| category | 1.0 | 1.0 | 1 | 1 | 4,028 |
| difficulty | 1.0 | 1.0 | 1 | 1 | 4,028 |
| id | 1.0 | 1.0 | 1 | 1 | 4,028 |
| query | 15.6 | 15.0 | 3 | 43 | 62,873 |
| tools | 85.7 | 82.0 | 24 | 159 | 345,317 |
| turns | 236.0 | 232.0 | 63 | 630 | 950,522 |
Dataset Structure
Each dataset instance represents a complete tool-augmented interaction. A sample usually includes a Kazakh user request, available tools, expected function calls, simulated tool responses, possible error messages, retry attempts, and a final assistant answer.
Data Fields
id: A unique identifier for the sample.query: The original user request in Kazakh. The query may require searching, booking, reservation, calculation, filtering, or other structured actions.category: The task category. For example,05_argument_schema_mappingindicates that the sample focuses on mapping user intent into correct tool arguments according to a given schema.tools: A list of tools available to the assistant. Each tool contains:name: the tool name;description: the tool’s purpose;parameters: the expected argument schema;mock_response: the expected response format.
difficulty: The difficulty label of the sample.answers: The target tool calls expected from the assistant. This may include initial invalid calls, corrected calls, retries, or multiple sequential calls.turns: The full conversation trajectory, including:- user request;
- assistant planning;
- tool calls;
- tool errors;
- retry attempts;
- successful tool responses;
- final answer.
Data Instance
Below is one representative example from the dataset. The sample demonstrates tool-call argument mapping, invalid argument handling, retry behavior, and final task completion. :contentReference[oaicite:0]{index=0}
{
"id": "aliya_id_1",
"query": "Ертең кешкі сағат 19:00-де Алматыда жақсы итальяндық мейрамхана тауып, 4 адамға орын броньда.",
"category": "05_argument_schema_mapping",
"tools": [
{
"name": "web.search",
"description": "Search the web for information",
"parameters": {
"query": {
"type": "string",
"description": "Search query",
"required": true
},
"limit": {
"type": "int",
"description": "Number of results",
"required": false
}
},
"mock_response": {
"results": [
{
"title": "",
"snippet": "",
"url": ""
}
]
}
},
{
"name": "restaurant.reserve",
"description": "Make restaurant reservation",
"parameters": {
"restaurantId": {
"type": "string",
"description": "Restaurant ID",
"required": true
},
"date": {
"type": "string",
"description": "Reservation date YYYY-MM-DD",
"required": true
},
"time": {
"type": "string",
"description": "Time HH:MM",
"required": true
},
"guests": {
"type": "int",
"description": "Number of guests",
"required": true
}
},
"mock_response": {
"reservation_id": "",
"status": "",
"restaurant": "",
"time": ""
}
}
],
"difficulty": "easy",
"answers": [
{
"name": "web.search",
"arguments": "{\"query\": \"Алматыдағы үздік итальян мейрамханалары\", \"limit\": -5}"
},
{
"name": "web.search",
"arguments": "{\"query\": \"Алматыдағы үздік итальян мейрамханалары\", \"limit\": 1}"
},
{
"name": "restaurant.reserve",
"arguments": "{\"restaurantId\": \"ladolcevita_kz\", \"date\": \"2024-06-15\", \"time\": \"19:00\", \"guests\": 4}"
},
{
"name": "restaurant.reserve",
"arguments": "{\"restaurantId\": \"ladolcevita_kz\", \"date\": \"2024-06-15\", \"time\": \"19:00\", \"guests\": 4}"
}
],
"turns": [
{
"role": "user",
"content": "Ертең кешкі сағат 19:00-де Алматыда жақсы итальяндық мейрамхана тауып, 4 адамға орын броньда."
},
{
"role": "assistant",
"content": "Алдымен Алматыдағы итальян мейрамханаларын іздеп, кейін бронь жасаймын.",
"meta": {
"plan": "web.search + restaurant.reserve fetching data",
"tags": [],
"difficulty": "hard"
}
},
{
"role": "assistant",
"content": "",
"tool_call": {
"name": "web.search",
"arguments": "{\"query\": \"Алматыдағы үздік итальян мейрамханалары\", \"limit\": -5}"
}
},
{
"role": "tool",
"content": "{\"error\": true, \"type\": \"Invalid arguments\", \"message\": \"Error of limits\", \"code\": 500}"
},
{
"role": "assistant",
"content": "Деректерді алуды қайталаймын",
"meta": {
"plan": "Fix arguments ..",
"tags": [
"invalid_args",
"retry"
],
"difficulty": "hard"
}
},
{
"role": "assistant",
"content": "",
"tool_call": {
"name": "web.search",
"arguments": "{\"query\": \"Алматыдағы үздік итальян мейрамханалары\", \"limit\": 1}"
}
},
{
"role": "tool",
"content": "{\"results\": [{\"title\": \"La Dolce Vita итальян мейрамханасы\", \"snippet\": \"La Dolce Vita — Алматыдағы ең танымал итальян мейрамханаларының бірі.\", \"url\": \"https://ladolcevita.kz\"}]}"
},
{
"role": "assistant",
"content": "",
"tool_call": {
"name": "restaurant.reserve",
"arguments": "{\"restaurantId\": \"ladolcevita_kz\", \"date\": \"2024-06-15\", \"time\": \"19:00\", \"guests\": 4}"
}
},
{
"role": "tool",
"content": "{\"error\": true, \"type\": \"Invalid arguments\", \"message\": \"Error..\", \"code\": 500}"
},
{
"role": "assistant",
"content": "Деректерді алуды қайталаймын",
"meta": {
"plan": "Fix arguments ..",
"tags": [
"invalid_args",
"retry"
],
"difficulty": "hard"
}
},
{
"role": "assistant",
"content": "",
"tool_call": {
"name": "restaurant.reserve",
"arguments": "{\"restaurantId\": \"ladolcevita_kz\", \"date\": \"2024-06-15\", \"time\": \"19:00\", \"guests\": 4}"
}
},
{
"role": "tool",
"content": "{\"reservation_id\": \"ABC12345\", \"status\": \"confirmed\", \"restaurant\": \"La Dolce Vita\", \"time\": \"2024-06-15 19:00\"}"
},
{
"role": "assistant",
"content": "Алматыдағы La Dolce Vita итальян мейрамханасынан 4 адамға 2024-06-15 күні 19:00-ге орын сәтті брондалды. (Дерек көзі: web.search + restaurant.reserve)"
}
]
},
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