Related papers: AD-DROP: Attribution-Driven Dropout for Robust Lan…

Post-training large language models (LLMs) often suffers from catastrophic forgetting, where improvements on a target objective degrade previously acquired capabilities. Recent evidence suggests that this phenomenon is primarily driven by…

Federated learning can be used to train machine learning models on the edge on local data that never leave devices, providing privacy by default. This presents a challenge pertaining to the communication and computation costs associated…

Adapter-based tuning has recently arisen as an alternative to fine-tuning. It works by adding light-weight adapter modules to a pretrained language model (PrLM) and only updating the parameters of adapter modules when learning on a…

Among the various pre-trained neural language models that are popular today, dropout is already an indispensable regularization technique. To solve the inconsistency between training and inference caused by the randomness of dropout, some…

Supervised fine-tuning (SFT) of large language models can be viewed as an off-policy learning problem, where expert demonstrations come from a fixed behavior policy while training aims to optimize a target policy. Importance sampling is the…

Multiple Additive Regression Trees (MART), an ensemble model of boosted regression trees, is known to deliver high prediction accuracy for diverse tasks, and it is widely used in practice. However, it suffers an issue which we call…

Large language models (LLMs), owing to their extensive open-domain knowledge and semantic reasoning capabilities, have been increasingly integrated into recommender systems (RS). However, a substantial gap remains between the pre-training…

Many tasks in natural language understanding require learning relationships between two sequences for various tasks such as natural language inference, paraphrasing and entailment. These aforementioned tasks are similar in nature, yet they…

Defending pre-trained vision-language models (VLMs), such as CLIP, against adversarial attacks is crucial, as these models are widely used in diverse zero-shot tasks, including image classification. However, existing adversarial training…

The computational burden and inherent redundancy of large-scale datasets challenge the training of contemporary machine learning models. Data pruning offers a solution by selecting smaller, informative subsets, yet existing methods…

Early stopping based on the validation set performance is a popular approach to find the right balance between under- and overfitting in the context of supervised learning. However, in reinforcement learning, even for supervised…

Autoregressive (AR) models are highly effective for image generation, yet their standard maximum-likelihood estimation training lacks direct optimization for sample quality and diversity. While reinforcement learning (RL) has been used to…

Training large-scale recommendation models under a single global objective implicitly assumes homogeneity across user populations. However, real-world data are composites of heterogeneous cohorts with distinct conditional distributions. As…

Out-of-distribution (OOD) detection is a critical task for reliable predictions over text. Fine-tuning with pre-trained language models has been a de facto procedure to derive OOD detectors with respect to in-distribution (ID) data. Despite…

Model-based reinforcement learning is a widely accepted solution for solving excessive sample demands. However, the predictions of the dynamics models are often not accurate enough, and the resulting bias may incur catastrophic decisions…

Data attribution seeks to trace model outputs back to training data. With the recent development of diffusion models, data attribution has become a desired module to properly assign valuations for high-quality or copyrighted training…

Parameter-efficient fine-tuning methods, represented by LoRA, play an essential role in adapting large-scale pre-trained models to downstream tasks. However, fine-tuning LoRA-series models also faces the risk of overfitting on the training…

In this work, we introduce Y-Drop, a regularization method that biases the dropout algorithm towards dropping more important neurons with higher probability. The backbone of our approach is neuron conductance, an interpretable measure of…

Pronouns are frequently omitted in pro-drop languages, such as Chinese, generally leading to significant challenges with respect to the production of complete translations. To date, very little attention has been paid to the dropped pronoun…

Data attribution methods trace model behavior back to its training dataset, offering an effective approach to better understand ''black-box'' neural networks. While prior research has established quantifiable links between model output and…