Challenge: Existing approaches to Continual Multilingual Learning (CML) are based on updating models using new data in stages.
Approach: They propose a parameter-efficient finetuning strategy to increase the number of languages on which the model improves after an update while reducing the magnitude of loss for the remaining languages.
Outcome: The proposed model improves on the languages included in the latest update while reducing the loss of performance on the remaining languages.

Similar Papers

Fine-tuned Language Models are Continual Learners (2022.emnlp-main)

Copied to clipboard

Challenge: Recent work on large language models relies on intuition that most tasks can be described via natural language instructions.
Approach: They propose that a model should be able to keep extending its knowledge without forgetting previous skills.
Outcome: The proposed model can learn 8 new diverse language generation tasks while maintaining good performance on previous tasks, spanning in total of 70 datasets.
TL-CL: Task And Language Incremental Continual Learning (2024.emnlp-main)

Copied to clipboard

Challenge: a multilingual model is periodically updated to accommodate new tasks in previously learned languages or new languages for established tasks.
Approach: They propose an adapter-based parameter-efficient fine-tuning strategy for continual learning in multilingual models.
Outcome: The proposed approach outperforms other parameter-efficient approaches without access to historical data for replay.
HFT: Half Fine-Tuning for Large Language Models (2025.acl-long)

Copied to clipboard

Challenge: Large language models (LLMs) with one or more fine-tuning phases can unlock various capabilities, but can be catastrophic forgetting during sequential training.
Approach: They propose a method to regularly reset partial parameters to mitigate forgetting issues by using half fine-tuning instead of full fine-uning.
Outcome: The proposed approach reduces the risk of catastrophic forgetting during training and the parametric knowledge lost during training may be overwhelmed by incoming training data.
Exploring Two-Phase Continual Instruction Fine-tuning for Multilingual Adaptation in Large Language Models (2026.findings-acl)

Copied to clipboard

Challenge: A key challenge for Large Language Models (LLMs) is improving their Multilingual instruction-following ability over time without deteriorating their ability in languages they already excel at, typically English.
Approach: They propose a two-phase Continual Fine-tuning setup to improve a model's Multilingual adaptability by comparing an English-only LLM with a multilingual instruction dataset.
Outcome: The proposed model improves on two-phase Continual Fine-tuning (CFT) setups on a multilingual instruction dataset.
Unlocking Continual Learning Abilities in Language Models (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing approaches to learning models (LMs) incorporate old task data or task-wise inductive bias into LMs, but old data and accurate task information are often unavailable or costly to collect.
Approach: They propose a rehearsal-free method that updates model parameters with large magnitudes . they found that the L1-normalized magnitude distribution is different when different task data is used .
Outcome: The proposed method improves accuracy and performance on four CL benchmarks.
MAPLE: Multilingual Evaluation of Parameter Efficient Finetuning of Large Language Models (2024.findings-acl)

Copied to clipboard

Challenge: Prior work on multilingual evaluation has shown that there is a large gap between the performance of Large Language Models on English and other languages.
Approach: They propose to finetune Llama-2 and Mistral models on two datasets to determine their effect on model performance on six downstream tasks covering forty one languages.
Outcome: The proposed model can improve on six multilingual tasks while degrading on high-resource languages.
Bridging the Language Gap: Dynamic Learning Strategies for Improving Multilingual Performance in LLMs (2025.coling-main)

Copied to clipboard

Challenge: Large language models (LLMs) excel in diverse applications but still struggle with non-Latin scripts and low-resource languages.
Approach: They propose a dynamic learning approach that optimizes prompt strategy, embedding model, and LLM per query at runtime.
Outcome: The proposed approach achieves 10-15% improvements in multilingual performance over pre-trained models and 4x gains compared to fine-tuned, language-specific models.
Learning to Route for Dynamic Adapter Composition in Continual Learning with Language Models (2024.findings-emnlp)

Copied to clipboard

Challenge: Recent work shows that PEFT methods can be competitive with, or even superior to, full fine-tuning of PLMs.
Approach: They propose a method that isolates the training of new PEFT modules to ensure their task specialization and learns to compose them by training a network of routers that leverages a small memory containing examples of previously seen tasks.
Outcome: The proposed method improves generalization and performance in two CL setups.
Cross-lingual Continual Learning (2023.acl-long)

Copied to clipboard

Challenge: Existing multi-lingual representations such as the one-hop transfer learning pipeline are difficult to adapt to new languages.
Approach: They propose a cross-lingual continuum learning paradigm that evaluates continuous learning approaches that adapt to emerging data from different languages.
Outcome: The proposed model can be used to adapt to new languages in a sequential manner.
A Semantic-Aware Layer-Freezing Approach to Computation-Efficient Fine-Tuning of Language Models (2025.findings-acl)

Copied to clipboard

Challenge: Existing work on how to finetune but neglects the issue of where to fine-tune language models is expensive.
Approach: They propose to use transition traces of latent representation to compute deviations (or loss) and then estimate the gain of each layer in reducing deviation (or gain).
Outcome: The proposed approach outperforms baseline methods and is cost-benefit balanced.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations