mlsanityData to 14 Oct 2026

Teaching a Language Model to Speak the Language of Tools

arXiv 2506.23394 ↗First posted 29 Jun 2025cs.IR cs.AI cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

External tool integration through function-calling is essential for practical language model applications, yet most multilingual models lack reliable tool-use capabilities in non-English languages. Even state-of-the-art multilingual models struggle with determining when to use tools and generating the structured outputs required for function calls, often exhibiting language confusion when prompted in lower-resource languages. This work presents a methodology for adapting existing language models to enable robust tool use in any target language, using Bulgarian as a case study. The approach involves continued training of the BgGPT model series (2.6B, 9B, 27B parameters) on a novel bilingual dataset of 10,035 function-calling examples designed to support standardized protocols like MCP (Model Context Protocol). The research introduces TUCAN (Tool-Using Capable Assistant Navigator), which achieves up to 28.75% improvement in function-calling accuracy over base models while preserving core language understanding, as verified on established Bulgarian benchmarks. Beyond accuracy gains, TUCAN models demonstrate production-ready response formatting with clean, parsable function calls, contrasting with the verbose and inconsistent outputs of base models. The models, evaluation framework, and dataset are released to enable replication for other languages. This work demonstrates a practical approach for extending tool-augmented capabilities beyond English-centric systems.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 21 of its 29 references that are in the map. First posted on arXiv 29 Jun 2025.

Builds on

21 of 29 references.

References · 21

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  3. 2025Qwen3 Technical Reportcited by 8,820
  4. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  5. 2018Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challengecited by 4,886
  6. 2019HellaSwag: Can a Machine Really Finish Your Sentence?cited by 4,100
  7. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,935
  8. 2024Gemma 2: Improving Open Language Models at a Practical Sizecited by 1,998
  9. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,947
  10. 2023ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Casescited by 393
  11. 2024ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilitiescited by 295
  12. 2023MetaTool Benchmark for Large Language Models: Deciding Whether to Use Tools and Which to Usecited by 217
9 more
  1. 2022Fine-tuned Language Models are Continual Learnerscited by 156
  2. 2024LLaMA Beyond English: An Empirical Study on Language Capability Transfercited by 95
  3. 2023T-Eval: Evaluating the Tool Utilization Capability of Large Language Models Step by Stepcited by 93
  4. 2024Planning, Creation, Usage: Benchmarking LLMs for Comprehensive Tool Utilization in Real-World Complex Scenarioscited by 86
  5. 2025JSONSchemaBench: A Rigorous Benchmark of Structured Outputs for Language Modelscited by 71
  6. 2024Adapting Multilingual LLMs to Low-Resource Languages using Continued Pre-training and Synthetic Corpuscited by 24
  7. 2024Closing the gap between open-source and commercial large language models for medical evidence summarizationcited by 21
  8. 2024Targeted Multilingual Adaptation for Low-resource Language Familiescited by 9
  9. 2024BgGPT 1.0: Extending English-centric LLMs to other languagescited by 8

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Lost in Execution: On the Multilingual Robustness of Tool Calling in Large Language Models
  2. 2023Toolformer: Language Models Can Teach Themselves to Use Tools
  3. 2025Tool Calling for Arabic LLMs: Data Strategies and Instruction Tuning
  4. 2026PRISM: Transfer and Limits of Activation Interventions in Tool-Calling Language Models
  5. 2024ToolEyes: Fine-Grained Evaluation for Tool Learning Capabilities of Large Language Models in Real-world Scenarios
  6. 2025ToolHop: A Query-Driven Benchmark for Evaluating Large Language Models in Multi-Hop Tool Use
  7. 2025TUMS: Enhancing Tool-use Abilities of LLMs with Multi-structure Handlers
  8. 2026Enhancing Tool Calling in LLMs with the International Tool Calling Dataset