Related papers: Reinforcement Learning Finetunes Small Subnetworks…

Fine-tuning large language models (LLMs) with limited data poses a practical challenge in low-resource languages, specialized domains, and constrained deployment settings. While pre-trained LLMs provide strong foundations, effective…

Fine-tuning Large Language Models (LLMs) on specific datasets is a common practice to improve performance on target tasks. However, this performance gain often leads to overfitting, where the model becomes too specialized in either the task…

Parameter-Efficient Fine-Tuning (PEFT) is a popular class of techniques that strive to adapt large models in a scalable and resource-efficient manner. Yet, the mechanisms underlying their training performance and generalization remain…

Pre-trained Large Language Model (LLM) exhibits broad capabilities, yet, for specific tasks or domains their attainment of higher accuracy and more reliable reasoning generally depends on post-training through Supervised Fine-Tuning (SFT)…

The Lottery Ticket Hypothesis (LTH) suggests that over-parameterized neural networks contain sparse subnetworks ("winning tickets") capable of matching full model performance when trained from scratch. With the growing reliance on…

Recent reinforcement learning (RL) techniques have yielded impressive reasoning improvements in language models, yet it remains unclear whether post-training truly extends a model's reasoning ability beyond what it acquires during…

Large Language Models (LLMs) are difficult to fully fine-tune (e.g., with instructions or human feedback) due to their sheer number of parameters. A family of parameter-efficient sparse fine-tuning methods have proven promising in terms of…

Large pretrained language models (PLMs) are often domain- or task-adapted via fine-tuning or prompting. Finetuning requires modifying all of the parameters and having enough data to avoid overfitting while prompting requires no training and…

Reinforcement learning (RL) has emerged as a key paradigm for aligning and optimizing large language models (LLMs). Standard approaches treat the LLM as the policy and apply RL directly over the full vocabulary space. However, this…

Large Language Models trained on web-scale text acquire language generation abilities that can solve a wide range of tasks, particularly when task knowledge is refined into the generative prior using in-context examples. However, spurious…

Deep Reinforcement Learning (RL) is a powerful framework for solving complex real-world problems. Large neural networks employed in the framework are traditionally associated with better generalization capabilities, but their increased size…

Full fine-tuning of large language models for alignment and task adaptation has become prohibitively expensive as models have grown in size. Parameter-Efficient Fine-Tuning (PEFT) methods aim at significantly reducing the computational and…

Most of the recent few-shot learning (FSL) algorithms are based on transfer learning, where a model is pre-trained using a large amount of source data, and the pre-trained model is fine-tuned using a small amount of target data. In transfer…

In order to improve reproducibility, deep reinforcement learning (RL) has been adopting better scientific practices such as standardized evaluation metrics and reporting. However, the process of hyperparameter optimization still varies…

Fine-tuning Large Language Models (LLMs) typically relies on large quantities of high-quality annotated data, or questions with well-defined ground truth answers in the case of Reinforcement Learning with Verifiable Rewards (RLVR). While…

Reinforcement learning (RL) applications, where an agent can simply learn optimal behaviors by interacting with the environment, are quickly gaining tremendous success in a wide variety of applications from controlling simple pendulums to…

Large language models are increasingly used for complex reasoning tasks where high-quality offline data such as expert-annotated solutions and distilled reasoning traces are often available. However, in environments with sparse rewards,…

Recent advances in fine-tuning large language models (LLMs) with reinforcement learning (RL) have shown promising improvements in complex reasoning tasks, particularly when paired with chain-of-thought (CoT) prompting. However, these…

Reinforcement Learning (RL) algorithms often require long training to become useful, especially in complex environments with sparse rewards. While techniques like reward shaping and curriculum learning exist to accelerate training, these…

Pre-trained large-scale language models (LLMs) excel at producing coherent articles, yet their outputs may be untruthful, toxic, or fail to align with user expectations. Current approaches focus on using reinforcement learning with human…