CC-Tuning: A Cross-Lingual Connection Mechanism for Improving Joint Multilingual Supervised Fine-Tuning

• URL: http://arxiv.org/abs/2506.00875v1
• Date: Sun, 01 Jun 2025 07:20:55 GMT
• Title: CC-Tuning: A Cross-Lingual Connection Mechanism for Improving Joint Multilingual Supervised Fine-Tuning
• Authors: Yangfan Ye, Xiaocheng Feng, Zekun Yuan, Xiachong Feng, Libo Qin, Lei Huang, Weitao Ma, Yichong Huang, Zhirui Zhang, Yunfei Lu, Xiaohui Yan, Duyu Tang, Dandan Tu, Bing Qin,
• Abstract summary: CC-Tuning is a novel multilingual fine-tuning paradigm that explicitly establishes a cross-lingual connection mechanism at the latent level.<n>During training, CC-Tuning fuses the feed forward activations from both English and non-English inputs, enabling the model to benefit from both linguistic resources.<n>Experiments on six benchmarks covering 22 languages show that CC-Tuning outperforms vanilla SFT and offers a strong latent-level alternative to data-level augmentation methods.
• Score: 48.69343479132896
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Current large language models (LLMs) often exhibit imbalanced multilingual capabilities due to their English-centric training corpora. To address this, existing fine-tuning approaches operating at the data-level (e.g., through data augmentation or distillation) typically introduce implicit cross-lingual alignment, overlooking the potential for more profound, latent-level cross-lingual interactions. In this work, we propose CC-Tuning, a novel multilingual fine-tuning paradigm that explicitly establishes a cross-lingual connection mechanism at the latent level. During training, CC-Tuning fuses the feed forward activations from both English and non-English inputs, enabling the model to benefit from both linguistic resources. This process is facilitated with a trainable Decision Maker that identifies beneficial activations. Furthermore, during inference, a Transform Matrix is utilized to simulate the cross-lingual connection under monolingual setting through representation transformation. Our experiments on six benchmarks covering 22 languages show that CC-Tuning outperforms vanilla SFT and offers a strong latent-level alternative to data-level augmentation methods. Further analysis also highlights the practicality of CC-Tuning and the potential of latent-level cross-lingual interactions in advancing the multilingual performance of LLMs.

Related papers

• Exploring Cross-lingual Latent Transplantation: Mutual Opportunities and Open Challenges [48.96952594416528]
  Current large language models (LLMs) often exhibit imbalances in multilingual capabilities and cultural adaptability.<n>XTransplant framework enables models to harness the complementary strengths of both English and non-English resources by transplanting latent activations across languages.
  arXiv  Detail & Related papers  (2024-12-17T09:05:30Z)
• Code-Switching Curriculum Learning for Multilingual Transfer in LLMs [43.85646680303273]
  Large language models (LLMs) exhibit near human-level performance in various tasks, but their performance drops drastically after a handful of high-resource languages. Inspired by the human process of second language acquisition, we propose code-switching curriculum learning (CSCL) to enhance cross-lingual transfer for LLMs. CSCL mimics the stages of human language learning by progressively training models with a curriculum consisting of 1) token-level code-switching, 2) sentence-level code-switching, and 3) monolingual corpora.
  arXiv  Detail & Related papers  (2024-11-04T06:31:26Z)
• ShifCon: Enhancing Non-Dominant Language Capabilities with a Shift-based Multilingual Contrastive Framework [78.07201802874529]
  ShifCon is a Shift-based multilingual Contrastive framework that aligns the internal forward process of other languages toward that of the dominant one.<n>Experiments demonstrate that our ShifCon framework significantly enhances the performance of non-dominant languages.
  arXiv  Detail & Related papers  (2024-10-25T10:28:59Z)
• Extracting and Transferring Abilities For Building Multi-lingual Ability-enhanced Large Language Models [104.96990850774566]
  We propose a Multi-lingual Ability Extraction and Transfer approach, named as MAET.<n>Our key idea is to decompose and extract language-agnostic ability-related weights from large language models.<n>Experiment results have shown that MAET can effectively and efficiently extract and transfer the advanced abilities.
  arXiv  Detail & Related papers  (2024-10-10T11:23:18Z)
• Probing the Emergence of Cross-lingual Alignment during LLM Training [10.053333786023089]
  Multilingual Large Language Models (LLMs) achieve remarkable levels of zero-shot cross-lingual transfer performance. We study how such cross-lingual alignment emerges during pre-training of LLMs. We observe a high correlation between neuron overlap and downstream performance.
  arXiv  Detail & Related papers  (2024-06-19T05:31:59Z)
• Cross-lingual QA: A Key to Unlocking In-context Cross-lingual Performance [2.371686365695081]
  Cross-lingual QA is a cross-lingual prompting method that translates only the question and answer parts, thus reducing translation costs. Experiments on four typologically diverse multilingual benchmarks show that Cross-lingual QA effectively stimulates models to elicit their cross-lingual knowledge. We show that prompting open-source MLLMs with cross-lingual in-context examples enhances performance as the model scale increases.
  arXiv  Detail & Related papers  (2023-05-24T15:14:49Z)
• VECO 2.0: Cross-lingual Language Model Pre-training with Multi-granularity Contrastive Learning [56.47303426167584]
  We propose a cross-lingual pre-trained model VECO2.0 based on contrastive learning with multi-granularity alignments. Specifically, the sequence-to-sequence alignment is induced to maximize the similarity of the parallel pairs and minimize the non-parallel pairs. token-to-token alignment is integrated to bridge the gap between synonymous tokens excavated via the thesaurus dictionary from the other unpaired tokens in a bilingual instance.
  arXiv  Detail & Related papers  (2023-04-17T12:23:41Z)
• Building High-accuracy Multilingual ASR with Gated Language Experts and Curriculum Training [45.48362355283723]
  We propose gated language experts and curriculum training to enhance multilingual transformer transducer models. Our method incorporates a gating mechanism and LID loss, enabling transformer experts to learn language-specific information.
  arXiv  Detail & Related papers  (2023-03-01T19:20:01Z)
• Learning Multilingual Representation for Natural Language Understanding with Enhanced Cross-Lingual Supervision [42.724921817550516]
  We propose a network named decomposed attention (DA) as a replacement of MA. The DA consists of an intra-lingual attention (IA) and a cross-lingual attention (CA), which model intralingual and cross-lingual supervisions respectively. Experiments on various cross-lingual natural language understanding tasks show that the proposed architecture and learning strategy significantly improve the model's cross-lingual transferability.
  arXiv  Detail & Related papers  (2021-06-09T16:12:13Z)
• VECO: Variable and Flexible Cross-lingual Pre-training for Language Understanding and Generation [77.82373082024934]
  We plug a cross-attention module into the Transformer encoder to explicitly build the interdependence between languages. It can effectively avoid the degeneration of predicting masked words only conditioned on the context in its own language. The proposed cross-lingual model delivers new state-of-the-art results on various cross-lingual understanding tasks of the XTREME benchmark.
  arXiv  Detail & Related papers  (2020-10-30T03:41:38Z)

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.