When the API Speaks the Wrong Language: Revisiting Post-Training for Multilingual Tool Use

• URL: http://arxiv.org/abs/2608.11715v1
• Date: Wed, 12 Aug 2026 06:55:04 GMT
• Title: When the API Speaks the Wrong Language: Revisiting Post-Training for Multilingual Tool Use
• Abstract summary: A common failure occurs when a model selects the correct tool but generates argument values in an inconsistent language.<n>We revisit post-training strategies for mitigating Argument Language Mismatch (ALM)<n>We find that supervised fine-tuning improves argument language consistency and end-to-end function call accuracy.
• Score: 2.4319925598898133
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The reliability of Large Language Models (LLMs) for API calling degrades in multilingual settings. A common failure occurs when a model selects the correct tool but generates argument values in an inconsistent language, which we term Argument Language Mismatch (ALM). Although semantically correct, such outputs are operationally invalid and not captured by standard API-calling metrics. We revisit post-training strategies for mitigating ALM and find that, in our benchmark, supervised fine-tuning (SFT) provides a strong baseline, substantially improving argument language consistency and end-to-end function call accuracy. Under consistent model selection, SFT achieves performance comparable to, and sometimes exceeding more complex reinforcement learning (RL) approaches. We further examine whether RL with structured, argument-aware rewards offers additional benefits. While methods such as Group Relative Policy Optimization (GRPO) can improve language consistency and better preserve general reasoning ability, these gains are incremental and most pronounced in generalization and multi-objective trade-offs. Overall, our results suggest that much of the performance in multilingual API grounding can be achieved through careful supervised training, with RL providing targeted rather than fundamental improvements.

Related papers

• AdaMame: A Training Recipe for Adaptive Multilingual Reasoning [32.31269959716733]
  Large Reasoning Models (LRMs) often fail to reason in the language of the query.<n>AdaMame is a two-stage training recipe for multilingual mathematical reasoning.
  arXiv  Detail & Related papers  (2026-06-13T03:22:35Z)
• Learning to Route Languages for Multilingual Policy Optimization [50.044784120224335]
  Large language models are trained on heterogeneous multilingual corpora.<n>We propose language-routed policy optimization (LRPO), an online policy optimization framework that treats language as a selectable variable.
  arXiv  Detail & Related papers  (2026-05-25T02:28:41Z)
• TLPO: Token-Level Policy Optimization for Mitigating Language Confusion in Large Language Models [6.468917070386353]
  Large language models (LLMs) demonstrate strong multilingual capabilities, yet often fail to consistently generate responses in the intended language.<n>We introduce Token-Level Policy Optimization (TLPO), a fine-tuning framework designed to mitigate language confusion through localized, token-level updates.
  arXiv  Detail & Related papers  (2026-04-29T11:39:43Z)
• Can Linguistically Related Languages Guide LLM Translation in Low-Resource Settings? [0.1957338076370071]
  We study a data-efficient setup that combines linguistically related pivot languages with few-shot in-context examples.<n>Our analysis shows that while pivot-based prompting can yield improvements in certain configurations, the gains are often modest and sensitive to few shot example construction.<n>Our findings provide empirical guidance on how and when inference-time prompting and pivot-based examples can be used as a lightweight alternative to fine-tuning in low-resource translation settings.
  arXiv  Detail & Related papers  (2026-03-17T15:28:46Z)
• Optimizing Language Models for Crosslingual Knowledge Consistency [90.86445137816942]
  Large language models are known to often exhibit inconsistent knowledge.<n>This is particularly problematic in multilingual scenarios, where models are likely to be asked similar questions in different languages.<n>In this work, we show that this issue can be mitigated using reinforcement learning with a structured reward function.
  arXiv  Detail & Related papers  (2026-03-04T23:36:55Z)
• Language-Coupled Reinforcement Learning for Multilingual Retrieval-Augmented Generation [73.54930910609328]
  We propose LcRL, a multilingual search-augmented reinforcement learning framework.<n>LcRL integrates a language-coupled Group Relative Policy Optimization into the policy and reward models.<n>We adopt the language-coupled group sampling in the rollout module to reduce knowledge bias, and regularize an auxiliary anti-consistency penalty in the reward models to mitigate the knowledge conflict.
  arXiv  Detail & Related papers  (2026-01-21T11:32:32Z)
• Lost in Execution: On the Multilingual Robustness of Tool Calling in Large Language Models [5.6688028729584055]
  Large Language Models (LLMs) are increasingly deployed as agents that invoke external tools through structured function calls.<n>We introduce MLCL, a diagnostic benchmark, and conduct a systematic evaluation of multilingual tool calling across Chinese, Hindi, and the low-resource language Igbo.
  arXiv  Detail & Related papers  (2026-01-08T20:44:28Z)
• The Unreasonable Effectiveness of Model Merging for Cross-Lingual Transfer in LLMs [45.08958917457921]
  Large language models (LLMs) still struggle across tasks outside of high-resource languages.<n>In this work, we investigate cross-lingual transfer to lower-resource languages where task-specific post-training data is scarce.
  arXiv  Detail & Related papers  (2025-05-23T20:28:31Z)
• SMILE: Speech Meta In-Context Learning for Low-Resource Language Automatic Speech Recognition [55.2480439325792]
  Speech Meta In-Context LEarning (SMILE) is an innovative framework that combines meta-learning with speech in-context learning (SICL)<n>We show that SMILE consistently outperforms baseline methods in training-free few-shot multilingual ASR tasks.
  arXiv  Detail & Related papers  (2024-09-16T16:04:16Z)
• Offline RL for Natural Language Generation with Implicit Language Q Learning [87.76695816348027]
  Large language models can be inconsistent when it comes to completing user specified tasks. We propose a novel RL method, that combines both the flexible utility framework of RL with the ability of supervised learning. In addition to empirically validating ILQL, we present a detailed empirical analysis situations where offline RL can be useful in natural language generation settings.
  arXiv  Detail & Related papers  (2022-06-05T18:38:42Z)
• Distributionally Robust Multilingual Machine Translation [94.51866646879337]
  We propose a new learning objective for Multilingual neural machine translation (MNMT) based on distributionally robust optimization. We show how to practically optimize this objective for large translation corpora using an iterated best response scheme. Our method consistently outperforms strong baseline methods in terms of average and per-language performance under both many-to-one and one-to-many translation settings.
  arXiv  Detail & Related papers  (2021-09-09T03:48:35Z)

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.