Challenge: Existing studies have demonstrated that pre-trained LLMs are limited in certain domains, such as programming, mathematics, biomedical, or finance.
Approach: They propose a new post-pretraining method with an expansion of Transformer blocks to tune the expanded blocks using only new corpus, efficiently and effectively improving the model’s knowledge while mitigating forgetting.
Outcome: The proposed model outperforms existing models in programming and math and its instruction-following counterpart LLaMA Pro-8.3B in general tasks, programming, and mathematics.

Similar Papers

LLaMAX: Scaling Linguistic Horizons of LLM by Enhancing Translation Capabilities Beyond 100 Languages (2024.findings-emnlp)

Copied to clipboard

Challenge: Large Language Models (LLMs) exhibit exceptional translation capabilities in high-resource language tasks, yet their effectiveness in low-resourced languages is suboptimal.
Approach: They conduct extensive multilingual continual pre-training on the LLaMA series models and develop LLiMAX for translation support across more than 100 languages.
Outcome: The proposed model achieves higher translation performance than existing open-source models and performs on-par with specialized translation model on the Flores-101 benchmark.
Effective Long-Context Scaling of Foundation Models (2024.naacl-long)

Copied to clipboard

Challenge: Large language models (LLMs) are rapidly deployed and continue to evolve through scaling.
Approach: They propose a method to train strong long-context LLMs that are capable of utilizing massive context windows of up to 32,000 tokens.
Outcome: The proposed model can surpass gpt-3.5-turbo-16k's overall performance on long-context benchmarks with a cost-effective instruction tuning procedure that is free of expensive annotations.
Language Adaptation of Large Language Models: An Empirical Study on LLaMA2 (2025.coling-main)

Copied to clipboard

Challenge: Popularity of Large Language Models (LLMs) has seen a skyrocketing increase in recent years.
Approach: They present a systematic review of the language adaptation process for Large Language Models including vocabulary expansion, continued pre-training, and instruction fine-tuning.
Outcome: The proposed model is based on empirical studies conducted on LLaMA2 and discussions on various settings affecting the model's capabilities.
CodeT5+: Open Code Large Language Models for Code Understanding and Generation (2023.emnlp-main)

Copied to clipboard

Challenge: Existing code LLMs adopt a specific architecture or rely on a unified encoder-decoder network for downstream tasks, lacking flexibility to operate in the optimal architecture for a particular task.
Approach: They propose to initialize code LLMs with frozen off-the-shelf LLM and explore instruction-tuning to align with natural language instructions.
Outcome: The proposed model outperforms open-source LLMs on 20 code-related benchmarks.
LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models (2024.acl-demos)

Copied to clipboard

Challenge: Efficient fine-tuning of large language models requires non-trivial efforts to implement these methods on different models.
Approach: They propose a framework that democratizes the fine-tuning of large language models by integrating a suite of efficient training methods into one framework.
Outcome: The proposed framework is able to scale to 100+ LLMs without coding and receives over 25,000 stars and 3,000 forks.
Enhancing LLM Capabilities Beyond Scaling Up (2024.emnlp-tutorials)

Copied to clipboard

Challenge: general-purpose large language models (LLMs) are expanding in scale and access to unpublic training data.
Approach: This tutorial aims to examine the capabilities of general-purpose large language models . authors discuss adaptation of LLMs to address conflicts, defense against attacks .
Outcome: This tutorial aims to examine the evolution of general-purpose large language models (LLMs) the authors argue that the evolution is dependent on the availability of training data and the scale of the models.
Walia-LLM: Enhancing Amharic-LLaMA by Integrating Task-Specific and Generative Datasets (2024.findings-emnlp)

Copied to clipboard

Challenge: Low-resource languages are left behind due to the unavailability of resources.
Approach: They propose to integrate task-specific and generative datasets to improve language model performance for Amharic by fine-tuning an Amharican instruction fine-to-tuned model.
Outcome: The proposed model shows promising results in different NLP tasks and compares translated instruction datasets with the original model.
LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-Training (2024.emnlp-main)

Copied to clipboard

Challenge: Mixture-of-Experts (MoE) has gained increasing popularity as a framework for scaling up large language models.
Approach: They investigate how to build Mixture-of-Experts (MoE) models from existing large language models . they use expert construction, Continual pre-training and data sampling strategies .
Outcome: The proposed model outperforms existing models with similar parameters on a wide range of tasks.
Second Language (Arabic) Acquisition of LLMs via Progressive Vocabulary Expansion (2025.acl-long)

Copied to clipboard

Challenge: In the evolving landscape of large language models, the predominant focus has been on English and Chinese.
Approach: They propose to utilize Arabic-specific vocabulary in the tokenizer to accelerate decoding.
Outcome: The proposed model achieves decent performance comparable to the best Arabic LLMs across various Arabic benchmarks.
A Data-Efficient Path to Multilingual LLMs: Language Expansion via Post-training PARAM𝛥 Integration into Upcycled MoE (2026.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) are expensive and require extensive Continued Pre-Training and data-intensive alignment to expand.
Approach: They propose a method which upcycles a dense model into a Mixture-of-Experts architecture, allocating different experts to different languages.
Outcome: Experiments show that the proposed model upcycles a dense model into a Mixture-of-Experts(MoE) architecture, allocating different experts to different languages.

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