Tofillthisgap,thispaper proposes amulti-lingual finetuning method, dubbed Less-forgetting Multi-lingual Fine-tuning (LF-MLF).

Multi-lingual fine-tuning (MLF), which fine-tunes a multi-lingual language model (MLLM) with multiple source languages, aims to gain good zero-shot performance on target languages. In MLF, the fine-tuned model tends to fit the source languages while forgetting its cross-lingual knowledge obtained from the pre-training stage. This forgetting phenomenon degenerates the zero-shot performance of MLF, which remains under-explored. To fill this gap, this paper proposes a multi-lingual fine-tuning method, dubbed Less-forgetting Multi-lingual Fine-tuning (LF-MLF). In LF-MLF, we cast multi-lingual fine-tuning as a constrained optimization problem, where the optimization objective is to minimize forgetting, and constraints are reducing the fine-tuning loss. The proposed method has superior zero-shot performance; furthermore, it can achieve the Pareto stationarity. Extensive experiments on Named Entity Recognition, Question Answering and Natural Language Inference back up our theoretical analysis and validate the superiority of our proposals.

Neural networks are capable of translating between languages--in some cases even between two languages where there is little or no access to parallel translations, in what is known as Unsupervised Machine Translation (UMT).

Cross-lingual Natural Language Processing (NLP) has gained significant traction in recent years, offering practical solutions in low-resource settings by transferring linguistic knowledge from resource-rich to low-resource languages. This field leverages techniques like annotation projection and model transfer for language adaptation, supported by multilingual pre-trained language models. However, linguistic divergences hinder language transfer, especially among typologically distant languages. In this paper, we present an analysis of predicate-argument structures in parallel Chinese and English sentences. We explore the alignment and misalignment of predicate annotations, inspecting similarities and differences and proposing a categorization of structural divergences. The analysis and the categorization are supported by a qualitative and quantitative analysis of the results of an annotation projection experiment, in which, in turn, one of the two languages has been used as source language to project annotations into the corresponding parallel sentences. The results of this analysis show clearly that language transfer is asymmetric. An aspect that requires attention when it comes to selecting the source language in transfer learning applications and that needs to be investigated before any scientific claim about cross-lingual NLP is proposed.

Speech Large Language Models (SpeechLLMs) have achieved breakthroughs in multilingual speech-to-text translation (S2TT). However, existing approaches often overlook semantic commonalities across source languages, leading to biased translation performance. In this work, we propose \textbf{POTSA} (Parallel Optimal Transport for Speech Alignment), a new framework based on cross-lingual parallel speech pairs and Optimal Transport (OT), designed to bridge high- and low-resource translation gaps. First, we introduce a Bias Compensation module to coarsely align initial speech representations across languages. Second, we impose token-level OT constraints on a Q-Former using parallel speech pairs to establish fine-grained consistency of representations. Then, we apply a layer scheduling strategy to focus OT constraints on the most semantically beneficial layers. Experiments on the FLEURS dataset show that our method achieves SOTA performance, with +0.93 BLEU on average over five common languages and +5.05 BLEU on zero-shot languages, using only 10 hours of parallel speech per source language.

Recent advances in large language models have catalyzed the development of multimodal LLMs (MLLMs) that integrate text, speech, and vision within unified frameworks. As MLLMs evolve from narrow, monolingual, task-specific systems to general-purpose instruction-following models, a key frontier lies in evaluating their multilingual and multimodal capabilities over both long and short contexts. However, existing benchmarks fall short in evaluating these dimensions jointly: they are often limited to English, mostly focus on one single modality at a time, rely on short-form contexts, or lack human annotations -- hindering comprehensive assessment of model performance across languages, modalities, and task complexity. To address these gaps, we introduce MCIF (Multimodal Crosslingual Instruction Following), the first multilingual human-annotated benchmark based on scientific talks that is designed to evaluate instruction-following in crosslingual, multimodal settings over both short- and long-form inputs. MCIF spans three core modalities -- speech, vision, and text -- and four diverse languages (English, German, Italian, and Chinese), enabling a comprehensive evaluation of MLLMs' abilities to interpret instructions across languages and combine them with multimodal contextual information. MCIF is released under a CC-BY 4.0 license to encourage open research and progress in MLLMs development.

The political biases of Large Language Models (LLMs) are usually assessed by simulating their answers to English surveys. In this work, we propose an alternative framing of political biases, relying on principles of fairness in multilingual translation. We systematically compare the translation quality of speeches in the European Parliament (EP), observing systematic differences with majority parties from left, center, and right being better translated than outsider parties. This study is made possible by a new, 21-way multiparallel version of EuroParl, the parliamentary proceedings of the EP, which includes the political affiliations of each speaker. The dataset consists of 1.5M sentences for a total of 40M words and 249M characters. It covers three years, 1000+ speakers, 7 countries, 12 EU parties, 25 EU committees, and hundreds of national parties.

Multilingual generation with large language models (LLMs) is often of poor quality for mid- to low-resource languages, but the causes for this are not well-understood. We first demonstrate the existence of an implicit task-solving-->translation pipeline for generation, whereby the model first solves the required task in a largely target-language-agnostic manner, and subsequently translates answer concepts into the intended target language. We hypothesize that the failure of the translation stage, despite task-solving success, is an important culprit for the observed low quality of final outputs, and formalize this as the translation barrier hypothesis. We quantify the extent to which either stage in the pipeline is responsible for final failure for a word translation task across 108 language pairs, and find that the translation barrier explains a dominant portion of error for a majority of language pairs, and is especially severe for low-resource target languages. Our results highlight an important bottleneck for end-to-end multilingual generation, relevant for future work seeking to improve multilinguality in LLMs.

We present NN-Rank, an algorithm for ranking source languages for cross-lingual transfer, which leverages hidden representations from multilingual models and unlabeled target-language data. We experiment with two pretrained multilingual models and two tasks: part-of-speech tagging (POS) and named entity recognition (NER). We consider 51 source languages and evaluate on 56 and 72 target languages for POS and NER, respectively. When using in-domain data, NN-Rank beats state-of-the-art baselines that leverage lexical and linguistic features, with average improvements of up to 35.56 NDCG for POS and 18.14 NDCG for NER. As prior approaches can fall back to language-level features if target language data is not available, we show that NN-Rank remains competitive using only the Bible, an out-of-domain corpus available for a large number of languages. Ablations on the amount of unlabeled target data show that, for subsets consisting of as few as 25 examples, NN-Rank produces high-quality rankings which achieve 92.8% of the NDCG achieved using all available target data for ranking.