Related papers: Prefix Probing: Lightweight Harmful Content Detect…

Current AI regulations require discarding sensitive features (e.g., gender, race, religion) in the algorithm's decision-making process to prevent unfair outcomes. However, even without sensitive features in the training set, algorithms can…

Recent research shows that pre-trained language models (PLMs) suffer from "prompt bias" in factual knowledge extraction, i.e., prompts tend to introduce biases toward specific labels. Prompt bias presents a significant challenge in…

Instruction fine-tuning attacks pose a serious threat to large language models (LLMs) by subtly embedding poisoned examples in fine-tuning datasets, leading to harmful or unintended behaviors in downstream applications. Detecting such…

The cost and scarcity of fully supervised labels in statistical machine learning encourage using partially labeled data for model validation as a cheaper and more accessible alternative. Effectively collecting and leveraging weakly…

Modern language modeling tasks are often underspecified: for a given token prediction, many words may satisfy the user's intent of producing natural language at inference time, however only one word will minimize the task's loss function at…

In this paper, we present a novel algorithm, FastWordBug, to efficiently generate small text perturbations in a black-box setting that forces a sentiment analysis or text classification mode to make an incorrect prediction. By combining the…

Large Language Model (LLM) jailbreak refers to a type of attack aimed to bypass the safeguard of an LLM to generate contents that are inconsistent with the safe usage guidelines. Based on the insights from the self-attention computation…

Given an input sequence (or prefix), modern language models often assign high probabilities to output sequences that are repetitive, incoherent, or irrelevant to the prefix; as such, model-generated text also contains such artifacts. To…

With the rapid advancement of large language models (LLMs), ensuring their safe use becomes increasingly critical. Fine-tuning is a widely used method for adapting models to downstream tasks, yet it is vulnerable to jailbreak attacks.…

This work investigates the potential of undermining both fairness and detection performance in abusive language detection. In a dynamic and complex digital world, it is crucial to investigate the vulnerabilities of these detection models to…

Detecting whether a given text is a member of the pre-training data of Large Language Models (LLMs) is crucial for ensuring data privacy and copyright protection. Most existing methods rely on the LLM's hidden information (e.g., model…

The success of Large Language Models (LLMs) relies heavily on the huge amount of pre-training data learned in the pre-training phase. The opacity of the pre-training process and the training data causes the results of many benchmark tests…

Language learning refers to the problem of inferring a mathematical model which accurately represents a formal language. Many language learning algorithms learn by asking certain types of queries about the language being modeled. Language…

Recent advances on instruction fine-tuning have led to the development of various prompting techniques for large language models, such as explicit reasoning steps. However, the success of techniques depends on various parameters, such as…

We show that remotely hosted applications employing in-context learning when augmented with a retrieval function to select in-context examples can be vulnerable to membership-inference attacks even when the service provider and users are…

We present a novel, language-agnostic approach to "priming" language models for the task of event extraction, providing particularly effective performance in low-resource and zero-shot cross-lingual settings. With priming, we augment the…

Efficiently fine-tuning Large Language Models (LLMs) for specific tasks presents a considerable challenge in natural language processing. Traditional methods, like prompt or prefix tuning, typically rely on arbitrary tokens for training,…

Improving the reasoning capabilities of large language models (LLMs) typically requires supervised fine-tuning with labeled data or computationally expensive sampling. We introduce Unsupervised Prefix Fine-Tuning (UPFT), which leverages the…

Recent work has shown how to prompt large language models with explanations to obtain strong performance on textual reasoning tasks, i.e., the chain-of-thought paradigm. However, subtly different explanations can yield widely varying…

In this paper, we tackle the emerging challenge of unintended harmful content generation in Large Language Models (LLMs) with a novel dual-stage optimisation technique using adversarial fine-tuning. Our two-pronged approach employs an…