Related papers: DynaMiCS: Fine-tuning LLMs with Performance Constr…
Data mixing -- determining the ratios of data from different domains -- is a first-order concern for training language models (LMs). While existing mixing methods show promise, they fall short when applied during real-world LM development.…
Domain reweighting can improve sample efficiency and downstream generalization, but data-mixture optimization for multimodal midtraining remains largely unexplored. Current multimodal training recipes tune mixtures along a single dimension,…
The efficacy of large language models (LLMs) is heavily dependent on the quality of the underlying data, particularly within specialized domains. A common challenge when fine-tuning LLMs for domain-specific applications is the potential…
Large Language Models (LLMs), being generic task solvers, are versatile. However, despite the vast amount of data they are trained on, there are speculations about their adaptation capabilities to a new domain. Additionally, the simple…
Recent research has shown that large language models pretrained using unsupervised approaches can achieve significant performance improvement on many downstream tasks. Typically when adapting these language models to downstream tasks, like…
The data mixture used in the pre-training of a language model is a cornerstone of its final performance. However, a static mixing strategy is suboptimal, as the model's learning preferences for various data domains shift dynamically…
Adapting large language models (LLMs) to low-resource languages (LRLs) is constrained by the scarcity of task data and computational resources. Although Proxy Tuning offers a logit-level strategy for introducing scaling effects, it often…
Optimizing data mixtures is essential for unlocking the full potential of large language models (LLMs), yet identifying the optimal composition remains computationally prohibitive due to reliance on heuristic trials or expensive proxy…
Language models (LMs) excel at tasks across diverse domains, yet require substantial computational resources during inference. Compression techniques such as pruning and quantization offer a practical path towards efficient LM deployment,…
Large language models (LLMs) are at the forefront of transforming numerous domains globally. However, their inclusivity and effectiveness remain limited for non-Latin scripts and low-resource languages. This paper tackles the imperative…
Modern machine learning pipelines are increasingly combining and mixing data from diverse and disparate sources, e.g., pre-training large language models. Yet, finding the optimal data mixture is a challenging and open problem. We formalize…
Augmenting large language models (LLMs) with external tools is a promising approach to enhance their capabilities, especially for complex tasks. Synthesizing tool-use data through real-world simulations is an effective way to achieve this.…
The vast number of parameters in large language models (LLMs) endows them with remarkable capabilities, allowing them to excel in a variety of natural language processing tasks. However, this complexity also presents challenges, making LLMs…
Large language models (LLMs) have shown great potential in domain-specific machine translation (MT). However, one major issue is that LLMs pre-trained on general domain corpus might not generalize well to specific domains due to the lack of…
For most languages of the world, language model pre-training operates in a data-constrained regime where models must repeat their training data many times, degrading generalization. Two remedies exist: aggressive hyperparameter tuning such…
Fine-tuning large language models (LLMs) has become essential for adapting pretrained models to specific downstream tasks. In this paper, we propose Linear Chain Transformation (LinChain), a novel approach that introduces a sequence of…
Large language models (LLMs) deliver impressive results but face challenges from increasing model sizes and computational costs. Structured pruning reduces model size and speeds up inference but often causes uneven degradation across…
This research explores a hybrid approach to fine-tuning large language models (LLMs) by integrating real-world and synthetic data to boost model performance, particularly in generating accurate and contextually relevant responses. By…
We propose a refined approach to efficiently fine-tune large language models (LLMs) on specific domains like the mathematical domain by employing a budgeted subset selection method. Our approach combines utility and diversity metrics to…
Continual pre-training on small-scale task-specific data is an effective method for improving large language models in new target fields, yet it risks catastrophic forgetting of their original capabilities. A common solution is to re-weight…