相关论文: Exploiting Instruction-Following Retrievers for Ma…

Recent advances in instruction-following large language models (LLMs) have led to dramatic improvements in a range of NLP tasks. Unfortunately, we find that the same improved capabilities amplify the dual-use risks for malicious purposes of…

Exploratory searches are characterized by under-specified goals and evolving query intents. In such scenarios, retrieval models that can capture user-specified nuances in query intent and adapt results accordingly are desirable --…

Presently, with the assistance of advanced LLM application development frameworks, more and more LLM-powered applications can effortlessly augment the LLMs' knowledge with external content using the retrieval augmented generation (RAG)…

Recent advancements in Reinforcement Learning with Verifiable Rewards (RLVR) have gained significant attention due to their objective and verifiable reward signals, demonstrating strong performance in reasoning and code generation tasks.…

Long-context LLMs can infer objectives that are not stated explicitly. This capability is useful for reasoning over documents, code, retrieved evidence, and tool traces, but it also creates a safety risk: harmful intent can be distributed…

Large language models (LLMs) have shown great potential as general-purpose AI assistants in various domains. To meet the requirements of different applications, LLMs are often customized by further fine-tuning. However, the powerful…

Retrieval-Augmented Generation (RAG) improves pre-trained models by incorporating external knowledge at test time to enable customized adaptation. We study the risk of datastore leakage in Retrieval-In-Context RAG Language Models (LMs). We…

Agentic reinforcement learning (RL) trains large language models to autonomously call tools during reasoning, with search as the most common application. These models excel at multi-step reasoning tasks, but their safety properties are not…

Instruction-tuned language models (LM) are able to respond to imperative commands, providing a more natural user interface compared to their base counterparts. In this work, we present Promptriever, the first retrieval model able to be…

Large Language Models (LLMs) can comply with harmful instructions, raising serious safety concerns despite their impressive capabilities. Recent work has leveraged probing-based approaches to study the separability of malicious and benign…

As large language models (LLMs) have been deployed in various real-world settings, concerns about the harm they may propagate have grown. Various jailbreaking techniques have been developed to expose the vulnerabilities of these models and…

While large language models (LLMs) exhibit remarkable capabilities across a wide range of tasks, they pose potential safety concerns, such as the ``jailbreak'' problem, wherein malicious instructions can manipulate LLMs to exhibit…

Training large language models to follow instructions makes them perform better on a wide range of tasks and generally become more helpful. However, a perfectly helpful model will follow even the most malicious instructions and readily…

Large Language Models (LLMs) are constrained by outdated information and a tendency to generate incorrect data, commonly referred to as "hallucinations." Retrieval-Augmented Generation (RAG) addresses these limitations by combining the…

Vision-and-Language Navigation (VLN) requires an agent to follow natural-language instructions and navigate through previously unseen environments. Recent approaches increasingly employ large language models (LLMs) as high-level navigators…

Retrieval augmented generation (RAG) is frequently used to mitigate hallucinations and provide up-to-date knowledge for large language models (LLMs). However, given that document retrieval is an imprecise task and sometimes results in…

Retrieval-Augmented Generative (RAG) models enhance Large Language Models (LLMs) by integrating external knowledge bases, improving their performance in applications like fact-checking and information searching. In this paper, we…

Dense retrievers have achieved state-of-the-art performance in various information retrieval tasks, but to what extent can they be safely deployed in real-world applications? In this work, we propose a novel attack for dense retrieval…

While there has been progress towards aligning Large Language Models (LLMs) with human values and ensuring safe behaviour at inference time, safety guards can easily be removed when fine tuned on unsafe and harmful datasets. While this…

AI agents augment large language models with external tools such as web retrieval, enabling grounded and up-to-date responses. However, incorporating external content into the generation pipeline can weaken the safety alignment mechanisms…