Related papers: Probe-based Fine-tuning for Reducing Toxicity
Linear probes are a promising approach for monitoring AI systems for deceptive behaviour. Previous work has shown that a linear classifier trained on a contrastive instruction pair and a simple dataset can achieve good performance. However,…
Large NLP models have recently shown impressive performance in language understanding tasks, typically evaluated by their fine-tuned performance. Alternatively, probing has received increasing attention as being a lightweight method for…
Instruction data selection aims to identify a high-quality subset from the training set that matches or exceeds the performance of the full dataset on target tasks. Existing methods focus on the instruction-to-response mapping, but neglect…
Foundation models have recently gained attention within the field of machine learning thanks to its efficiency in broad data processing. While researchers had attempted to extend this success to time series models, the main challenge is…
In inductive transfer learning, fine-tuning pre-trained convolutional networks substantially outperforms training from scratch. When using fine-tuning, the underlying assumption is that the pre-trained model extracts generic features, which…
Test-time prompt tuning for vision-language models has demonstrated impressive generalization capabilities under zero-shot settings. However, tuning the learnable prompts solely based on unlabeled test data may induce prompt optimization…
Instruction-following language models are trained to be helpful and safe, yet their safety behavior can deteriorate under benign fine-tuning and worsen under adversarial updates. Existing defenses often offer limited protection or force a…
As a dominant paradigm, fine-tuning a pre-trained model on the target data is widely used in many deep learning applications, especially for small data sets. However, recent studies have empirically shown that training from scratch has the…
While alignment algorithms are now commonly used to tune pre-trained language models towards a user's preferences, we lack explanations for the underlying mechanisms in which models become ``aligned'', thus making it difficult to explain…
Trustworthy machine learning is of primary importance to the practical deployment of deep learning models. While state-of-the-art models achieve astonishingly good performance in terms of accuracy, recent literature reveals that their…
Fine-tuning is arguably the most straightforward way to tailor a pre-trained model (e.g., a foundation model) to downstream applications, but it also comes with the risk of losing valuable knowledge the model had learned in pre-training.…
Software, while beneficial, poses potential cybersecurity risks due to inherent vulnerabilities. Detecting these vulnerabilities is crucial, and deep learning has shown promise as an effective tool for this task due to its ability to…
He et al. (2018) have called into question the utility of pre-training by showing that training from scratch can often yield similar performance to pre-training. We show that although pre-training may not improve performance on traditional…
In software engineering, deep learning models are increasingly deployed for critical tasks such as bug detection and code review. However, overfitting remains a challenge that affects the quality, reliability, and trustworthiness of…
Alignment, endowing a pre-trained Large language model (LLM) with the ability to follow instructions, is crucial for its real-world applications. Conventional supervised fine-tuning (SFT) methods formalize it as causal language modeling…
Learning from preference labels plays a crucial role in fine-tuning large language models. There are several distinct approaches for preference fine-tuning, including supervised learning, on-policy reinforcement learning (RL), and…
Current approaches to novelty or anomaly detection are based on deep neural networks. Despite their effectiveness, neural networks are also vulnerable to imperceptible deformations of the input data. This is a serious issue in critical…
Reinforcement learning is used to align language models with human preference signals after first pre-training the model to predict the next token of text within a large corpus using likelihood maximization. Before being deployed in a…
In computer vision, fine-tuning is the de-facto approach to leverage pre-trained vision models to perform downstream tasks. However, deploying it in practice is quite challenging, due to adopting parameter inefficient global update and…
Contrastive learning models have demonstrated impressive abilities to capture semantic similarities by aligning representations in the embedding space. However, their performance can be limited by the quality of the training data and its…