Related papers: Sparse Tuning Enhances Plasticity in PTM-based Con…
Supervised fine-tuning (SFT) is a pivotal approach to adapting large language models (LLMs) for downstream tasks; however, performance often suffers from the ``seesaw phenomenon'', where indiscriminate parameter updates yield progress on…
We consider the problem of accurate sparse fine-tuning of large language models (LLMs), that is, fine-tuning pretrained LLMs on specialized tasks, while inducing sparsity in their weights. On the accuracy side, we observe that standard…
Large Language Models (LLMs) have become pivotal in advancing the field of artificial intelligence, yet their immense sizes pose significant challenges for both fine-tuning and deployment. Current post-training pruning methods, while…
Motivation and gap: PID-family controllers remain a pragmatic choice for many robotic systems due to their simplicity and interpretability, but tuning stable, high-performing gains is time-consuming and typically non-transferable across…
Prompts for pre-trained language models (PLMs) have shown remarkable performance by bridging the gap between pre-training tasks and various downstream tasks. Among these methods, prompt tuning, which freezes PLMs and only tunes soft…
Works on lottery ticket hypothesis (LTH) and single-shot network pruning (SNIP) have raised a lot of attention currently on post-training pruning (iterative magnitude pruning), and before-training pruning (pruning at initialization). The…
Model merging has emerged as a compelling data-free paradigm for multi-task learning, enabling the fusion of multiple fine-tuned models into a single, powerful entity. A key technique in merging methods is sparsification, which prunes…
Large language models possess strong chemical reasoning capabilities, making them effective molecular editors. However, property-relevant information is implicitly entangled across their dense hidden states, providing no explicit handle for…
During the preference optimization of large language models (LLMs), distribution shifts may arise between newly generated model samples and the data used to train the reward model (RM). This shift reduces the efficacy of the RM, which in…
We investigate parameter-efficient fine-tuning (PEFT) methods that can provide good accuracy under limited computational and memory budgets in the context of large language models (LLMs). We present a new PEFT method called Robust…
While pre-trained language models have achieved great success on various natural language understanding tasks, how to effectively leverage them into non-autoregressive generation tasks remains a challenge. To solve this problem, we present…
Continual learning (CL) refers to the ability of an intelligent system to sequentially acquire and retain knowledge from a stream of data with as little computational overhead as possible. To this end; regularization, replay, architecture,…
Fine-tuning is a promising technique for leveraging Transformer-based language models in downstream tasks. As model sizes continue to grow, updating all model parameters becomes increasingly costly. Parameter-efficient fine-tuning methods…
Fine-tuning pretrained language models (PLMs) on downstream tasks has become common practice in natural language processing. However, most of the PLMs are vulnerable, e.g., they are brittle under adversarial attacks or imbalanced data,…
Recent studies show that prompt tuning can better leverage the power of large language models than fine-tuning on downstream natural language understanding tasks. However, the existing prompt tuning methods have training instability issues,…
Continual learning in natural language processing plays a crucial role in adapting to evolving data and preventing catastrophic forgetting. Despite significant progress, existing methods still face challenges, such as inefficient parameter…
A wide range of NLP tasks benefit from the fine-tuning of pretrained language models (PLMs). However, a number of redundant parameters which contribute less to the downstream task are observed in a directly fine-tuned model. We consider the…
Most approaches to deep neural network compression via pruning either evaluate a filter's importance using its weights or optimize an alternative objective function with sparsity constraints. While these methods offer a useful way to…
Large language models (LLMs) exhibit remarkable capabilities in handling natural language tasks; however, they may struggle to consistently follow complex instructions including those involve multiple constraints. Post-training LLMs using…
Recovering jointly sparse signals in the multiple measurement vectors (MMV) setting is a fundamental problem in machine learning, but traditional methods often require careful parameter tuning or prior knowledge of the sparsity of the…