Related papers: Detecting Instruction Fine-tuning Attacks using In…

Fine-tuning large language models (LLMs) on chain-of-thought (CoT) data shows that a small amount of high-quality data can outperform massive datasets. Yet, what constitutes "quality" remains ill-defined. Existing reasoning methods rely on…

From the perspective of content safety issues, alignment has shown to limit large language models' (LLMs) harmful content generation. This intentional method of reinforcing models to not respond to certain user inputs seem to be present in…

Large language models (LLMs) have demonstrated great performance across various benchmarks, showing potential as general-purpose task solvers. However, as LLMs are typically trained on vast amounts of data, a significant concern in their…

We consider the task of few-shot intent detection, which involves training a deep learning model to classify utterances based on their underlying intents using only a small amount of labeled data. The current approach to address this…

Recently, there has been growing interest in collecting reasoning-intensive pretraining data to improve LLMs' complex reasoning ability. Prior approaches typically rely on supervised classifiers to identify such data, which requires…

Small Language Models (SLMs) are increasingly being deployed in resource-constrained environments, yet their behavioral robustness to data contamination during instruction tuning remains poorly understood. We systematically investigate the…

Large language models (LLMs) are initially pretrained for broad capabilities and then finetuned with instruction-following datasets to improve their performance in interacting with humans. Despite advances in finetuning, a standardized…

Reasoning-enhanced large language models (LLMs) explicitly generate intermediate reasoning steps prior to generating final answers, helping the model excel in complex problem-solving. In this paper, we demonstrate that this emerging…

Data contamination poses a significant threat to the reliable evaluation of Large Language Models (LLMs). This issue arises when benchmark samples may inadvertently appear in training sets, compromising the validity of reported performance.…

Semi-supervised machine learning models learn from a (small) set of labeled training examples, and a (large) set of unlabeled training examples. State-of-the-art models can reach within a few percentage points of fully-supervised training,…

Data contamination, i.e., the presence of test data from downstream tasks in the training data of large language models (LLMs), is a potential major issue in measuring LLMs' real effectiveness on other tasks. We propose a straightforward…

Influence functions provide crucial insights into model training, but existing methods suffer from large computational costs and limited generalization. Particularly, recent works have proposed various metrics and algorithms to calculate…

Instruction Fine-tuning~(IFT) is a critical phase in building large language models~(LLMs). Previous works mainly focus on the IFT's role in the transfer of behavioral norms and the learning of additional world knowledge. However, the…

Instruction-tuning plays a vital role in enhancing the task-solving abilities of large language models (LLMs), improving their usability in generating helpful responses on various tasks. However, previous work has demonstrated that they are…

Data poisoning attacks compromise the integrity of machine-learning models by introducing malicious training samples to influence the results during test time. In this work, we investigate backdoor data poisoning attack on deep neural…

The spread of fake news, polarizing, politically biased, and harmful content on online platforms has been a serious concern. With large language models becoming a promising approach, however, no study has properly benchmarked their…

The opacity in developing large language models (LLMs) is raising growing concerns about the potential contamination of public benchmarks in the pre-training data. Existing contamination detection methods are typically based on the text…

Recent studies have uncovered a troubling vulnerability in the fine-tuning stage of large language models (LLMs): even fine-tuning on entirely benign datasets can lead to a significant increase in the harmfulness of LLM outputs. Building on…

Large language models (LLMs) have gained widespread adoption across diverse applications due to their impressive generative capabilities. Their plug-and-play nature enables both developers and end users to interact with these models through…

Quantifying the impact of training data points is crucial for understanding the outputs of machine learning models and for improving the transparency of the AI pipeline. The influence function is a principled and popular data attribution…