Related papers: Spectrum Tuning: Post-Training for Distributional …

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…

Instruction-tuning can be substantially optimized through enhanced diversity, resulting in models capable of handling a broader spectrum of tasks. However, existing data employed for such tuning often exhibit an inadequate coverage of…

As the widespread adoption of Large Language Models (LLMs) accelerates, token consumption from intermediate reasoning traces increasingly contributes to inference latency and operational cost. Recent studies suggest that many real-world…

Training robots in simulation requires diverse 3D scenes that reflect the specific challenges of downstream tasks. However, scenes that satisfy strict task requirements, such as high-clutter environments with plausible spatial arrangement,…

In-context learning (ICL) enables large language models (LLMs) to perform new tasks by prompting them with a sequence of training examples. However, it is known that ICL is very sensitive to the choice of training examples: randomly…

In a multi-task learning (MTL) setting, a single model is trained to tackle a diverse set of tasks jointly. Despite rapid progress in the field, MTL remains challenging due to optimization issues such as conflicting and dominating…

Language models achieve impressive performance on a variety of knowledge, language, and reasoning tasks due to the scale and diversity of pretraining data available. The standard training recipe is a two-stage paradigm: pretraining first on…

Model pruning is an effective approach for compressing large language models (LLMs). However, this process often leads to significant degradation of model capabilities. While post-training techniques such as instruction tuning are commonly…

Prompting Large Language Models (LLMs), or providing context on the expected model of operation, is an effective way to steer the outputs of such models to satisfy human desiderata after they have been trained. But in rapidly evolving…

Despite the success of Instruction Tuning (IT) in training large language models (LLMs), such models often leverage spurious or biased features learnt from their training data and can become misaligned, leading to undesired behaviours.…

Pre-trained language models (PLMs) have become a prevalent technique in deep learning for code, utilizing a two-stage pre-training and fine-tuning procedure to acquire general knowledge about code and specialize in a variety of downstream…

The rise of large language models (LLMs) has created a significant disparity: industrial research labs with their computational resources, expert teams, and advanced infrastructures, can effectively fine-tune LLMs, while individual…

Instruction tuning plays a crucial role in shaping the outputs of language models (LMs) to desired styles. In this work, we propose a simple yet effective method, Instruction Modelling (IM), which trains LMs by applying a loss function to…

Instruction tuning is a widely used approach to improve the instruction-following ability of large language models (LLMs). Instruction-tuning datasets typically include a mixture of context-augmented and context-free examples, yet prior…

Accurate uncertainty quantification is crucial for the safe deployment of machine learning models, and prior research has demonstrated improvements in the calibration of modern language models (LMs). We study in-context learning (ICL), a…

Numerous recent techniques for text style transfer characterize their approaches as variants of reinforcement learning and preference optimization. In this work, we consider the relationship between these approaches and a class of…

Instruction Tuning involves finetuning a language model on a collection of instruction-formatted datasets in order to enhance the generalizability of the model to unseen tasks. Studies have shown the importance of balancing different task…

Instruction tuning for large language models (LLMs) has gained attention from researchers due to its ability to unlock the potential of LLMs in following instructions. While instruction tuning offers advantages for facilitating the…

Parameter-Efficient Tuning (PETuning) methods have been deemed by many as the new paradigm for using pretrained language models (PLMs). By tuning just a fraction amount of parameters comparing to full model finetuning, PETuning methods…

Instruction tuning a large language model with multiple languages can prepare it for multilingual downstream tasks. Nonetheless, it is yet to be determined whether having a handful of languages is sufficient, or whether the benefits…