Seungyoon Lee, Minhyuk Kim, Seongtae Hong, Youngjoon Jang, Dongsuk Oh, Heuiseok Lim. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Adapting large language models to other languages typically employs supervised finetuning (SFT) as a standard approach.However, it often suffers from an overemphasis on English performance, a phenomenon that is especially pronounced in data-constrained environments.To overcome these challenges, we propose Cross-Lingual Optimization (CLO) that efficiently transfers an English-centric LLM to a target language while preserving its English capabilities.CLO utilizes publicly available English SFT data and a translation model to enable cross-lingual transfer.We conduct experiments using five models on six languages, each possessing varying levels of resource.Our results show that CLO consistently outperforms SFT in both acquiring target language proficiency and maintaining English performance.Remarkably, in low-resource languages, CLO with only 3,200 samples surpasses SFT with 6,400 samples, demonstrating that CLO can achieve better performance with less data.Furthermore, we find that SFT is particularly sensitive to data quantity in medium and lowresource languages, whereas CLO remains robust.Our comprehensive analysis emphasizes the limitations of SFT and incorporates additional training strategies in CLO to enhance efficiency.

Large Language Models (LLMs) have rapidly advanced, with domain-specific expert models emerging to handle specialized tasks across various fields. However, the predominant focus on English-centric models demands extensive data, making it challenging to develop comparable models for middle and low-resource languages. To address this limitation, we introduce Migrate, a novel method that leverages open-source static embedding models and up to 3 million tokens of code-switching data to facilitate the seamless transfer of embeddings to target languages. Migrate enables effective cross-lingual adaptation without requiring large-scale domain-specific corpora in the target language, promoting the accessibility of expert LLMs to a diverse range of linguistic communities. Our experimental results demonstrate that Migrate significantly enhances model performance in target languages, outperforming baseline and existing cross-lingual transfer methods. This approach provides a practical and efficient solution for extending the capabilities of domain-specific expert models.

Recent frontier-level LLMs have saturated many previously difficult benchmarks, leaving little room for further differentiation.This progress highlights the need for challenging benchmarks that provide objective verification.In this paper, we introduce MCBench, a benchmark designed to evaluate whether LLMs can execute string-matching NLP metrics by strictly following step-by-step instructions.Unlike prior benchmarks that depend on subjective judgments or general reasoning, MCBench offers an objective, deterministic and codeverifiable evaluation.This setup allows us to systematically test whether LLMs can maintain accurate step-by-step execution, including instruction adherence, numerical computation, and long-range consistency in handling intermediate results.To ensure objective evaluation of these abilities, we provide a parallel reference code that can evaluate the accuracy of LLM output.We provide three evaluative metrics and three benchmark variants designed to measure the detailed instruction understanding capability of LLMs.Our analyses show that MCBench serves as an effective and objective tool for evaluating the capabilities of cuttingedge LLMs.

In order to compare a research model accurately across different conditions, the model's measures must be invariant across them. In this study, the invariance of the UTAUT model's measures was tested along three dimensions: country, technology, and gender. Data were collected from two countries (Korea and the U.S.) for two technologies (Internet banking and MP3 players). The results show that although the UTAUT model is robust overall across different conditions, possible differences due to measurement non-invariance should be taken into account. The paper discusses implications of the study results and makes recommendations for future research.