Related papers: SafeTune: Search-based Harmfulness Minimisation fo…
Large Language Models (LLMs) presents significant priority in text understanding and generation. However, LLMs suffer from the risk of generating harmful contents especially while being employed to applications. There are several black-box…
As Large Language Models (LLMs) are increasingly integrated into academic peer review, their vulnerability to adversarial hidden prompts, i.e., adversarial instructions embedded in submissions to manipulate outcomes, poses a critical threat…
As the popularity of Large Language Models (LLMs) grow, combining model safety with utility becomes increasingly important. The challenge is making sure that LLMs can recognize and decline dangerous prompts without sacrificing their ability…
Large language models (LLMs) have gained human trust due to their capabilities and helpfulness. However, this in turn may allow LLMs to affect users' mindsets by manipulating language. It is termed as gaslighting, a psychological effect. In…
Existing large language models (LLMs) driven search agents typically rely on prompt engineering to decouple the user queries into search plans, limiting their effectiveness in complex scenarios requiring reasoning. Furthermore, they suffer…
In education, the capability of generating human-like text of Large Language Models (LLMs) inspired work on how they can increase the efficiency of learning and teaching. We study the affordability of these models for educators and students…
Instruction fine-tuning of large language models (LLMs) is a powerful method for improving task-specific performance, but it can inadvertently lead to a phenomenon where models generate harmful responses when faced with malicious prompts.…
Large Language Models (LLMs) have the potential to significantly enhance threat intelligence by automating the collection, preprocessing, and analysis of threat data. However, the usability of these tools is critical to ensure their…
Several recent works have argued that Large Language Models (LLMs) can be used to tame the data deluge in the cybersecurity field, by improving the automation of Cyber Threat Intelligence (CTI) tasks. This work presents an evaluation…
This paper explores the pressing issue of risk assessment in Large Language Models (LLMs) as they become increasingly prevalent in various applications. Focusing on how reward models, which are designed to fine-tune pretrained LLMs to align…
Large Language Models (LLMs) such as GPT-4o can handle a wide range of complex tasks with the right prompt. As per token costs are reduced, the advantages of fine-tuning Small Language Models (SLMs) for real-world applications -- faster…
The proliferation of Large Language Models (LLMs) has intensified concerns about manipulative or deceptive behaviors that can undermine user autonomy, trust, and well-being. Existing safety benchmarks predominantly rely on coarse binary…
Alignment tuning has enabled large language models to excel in reasoning, instruction-following, and minimizing harmful generations. However, despite their widespread deployment, these models exhibit a monolingual bias, raising concerns…
Large Language Models (LLMs) are acquiring a wider range of capabilities, including understanding and responding in multiple languages. While they undergo safety training to prevent them from answering illegal questions, imbalances in…
Vision Large Language Models (VLLMs) represent a significant advancement in artificial intelligence by integrating image-processing capabilities with textual understanding, thereby enhancing user interactions and expanding application…
Large Language Models (LLMs) pose a significant risk of safety misalignment after finetuning, as models can be compromised by both explicitly and implicitly harmful data. Even some seemingly benign data can inadvertently steer a model…
Robotics researchers increasingly leverage large language models (LLM) in robotics systems, using them as interfaces to receive task commands, generate task plans, form team coalitions, and allocate tasks among multi-robot and human agents.…
Open-source Large Language Models (LLMs) often employ safety alignment methods to resist harmful instructions. However, recent research shows that maliciously fine-tuning these LLMs on harmful data can easily bypass these safeguards. To…
Harmful fine-tuning can invalidate safety alignment of large language models, exposing significant safety risks. In this paper, we utilize the attention sink mechanism to mitigate harmful fine-tuning. Specifically, we first measure a…
Safety alignment approaches in large language models (LLMs) often lead to the over-refusal of benign queries, significantly diminishing their utility in sensitive scenarios. To address this challenge, we introduce FalseReject, a…