In the rapidly advancing field of artificial intelligence, the concept of Red-Teaming or Jailbreaking large language models (LLMs) has emerged as a crucial area of study. This approach is especially significant in terms of assessing and enhancing the safety and robustness of these models. This paper investigates the intricate consequences of such modifications through model editing, uncovering a complex relationship between enhancing model accuracy and preserving its ethical integrity. Our in-depth analysis reveals a striking paradox: while injecting accurate information is crucial for model reliability, it can paradoxically destabilize the model's foundational framework, resulting in unpredictable and potentially unsafe behaviors. Additionally, we propose a benchmark dataset NicheHazardQA to investigate this unsafe behavior both within the same and cross topical domain. This aspect of our research sheds light on how the edits, impact the model's safety metrics and guardrails. Our findings show that model editing serves as a cost-effective tool for topical red-teaming by methodically applying targeted edits and evaluating the resultant model behavior.
相關內容
ACM/IEEE第23屆模型驅動工程語言和系統國際會議，是模型驅動軟件和系統工程的首要會議系列，由ACM-SIGSOFT和IEEE-TCSE支持組織。自1998年以來，模型涵蓋了建模的各個方面，從語言和方法到工具和應用程序。模特的參加者來自不同的背景，包括研究人員、學者、工程師和工業專業人士。MODELS 2019是一個論壇，參與者可以圍繞建模和模型驅動的軟件和系統交流前沿研究成果和創新實踐經驗。今年的版本將為建模社區提供進一步推進建模基礎的機會，并在網絡物理系統、嵌入式系統、社會技術系統、云計算、大數據、機器學習、安全、開源等新興領域提出建模的創新應用以及可持續性。
官網鏈接： ·
Prompt
·
MoDELS
·
語言模型化
·
Performance
·
The performance of large language models (LLMs) is acutely sensitive to the phrasing of prompts, which raises significant concerns about their reliability in real-world scenarios. Existing studies often divide prompts into task-level instructions and case-level inputs and primarily focus on evaluating and improving robustness against variations in tasks-level instructions. However, this setup fails to fully address the diversity of real-world user queries and assumes the existence of task-specific datasets. To address these limitations, we introduce RobustAlpacaEval, a new benchmark that consists of semantically equivalent case-level queries and emphasizes the importance of using the worst prompt performance to gauge the lower bound of model performance. Extensive experiments on RobustAlpacaEval with ChatGPT and six open-source LLMs from the Llama, Mistral, and Gemma families uncover substantial variability in model performance; for instance, a difference of 45.48% between the worst and best performance for the Llama-2-70B-chat model, with its worst performance dipping as low as 9.38%. We further illustrate the difficulty in identifying the worst prompt from both model-agnostic and model-dependent perspectives, emphasizing the absence of a shortcut to characterize the worst prompt. We also attempt to enhance the worst prompt performance using existing prompt engineering and prompt consistency methods, but find that their impact is limited. These findings underscore the need to create more resilient LLMs that can maintain high performance across diverse prompts. Data and code are available at //github.com/cbwbuaa/On-the-Worst-Prompt- Performance-of-LLMs.
Sixth-generation (6G) networks leverage simultaneously transmitting and reflecting reconfigurable intelligent surfaces (STAR-RISs) to overcome the limitations of traditional RISs. STAR-RISs offer 360-degree full-space coverage and optimized transmission and reflection for enhanced network performance and dynamic control of the indoor propagation environment. However, deploying STAR-RISs indoors presents challenges in interference mitigation, power consumption, and real-time configuration. In this work, a novel network architecture utilizing multiple access points (APs) and STAR-RISs is proposed for indoor communication. An optimization problem encompassing user assignment, access point beamforming, and STAR-RIS phase control for reflection and transmission is formulated. The inherent complexity of the formulated problem necessitates a decomposition approach for an efficient solution. This involves tackling different sub-problems with specialized techniques: a many-to-one matching algorithm is employed to assign users to appropriate access points, optimizing resource allocation. To facilitate efficient resource management, access points are grouped using a correlation-based K-means clustering algorithm. Multi-agent deep reinforcement learning (MADRL) is leveraged to optimize the control of the STAR-RIS. Within the proposed MADRL framework, a novel approach is introduced where each decision variable acts as an independent agent, enabling collaborative learning and decision-making. Additionally, the proposed MADRL approach incorporates convex approximation (CA). This technique utilizes suboptimal solutions from successive convex approximation (SCA) to accelerate policy learning for the agents, thereby leading to faster environment adaptation and convergence. Simulations demonstrate significant network utility improvements compared to baseline approaches.
The recent successes and spread of large neural language models (LMs) call for a thorough understanding of their computational ability. Describing their computational abilities through LMs' \emph{representational capacity} is a lively area of research. However, investigation into the representational capacity of neural LMs has predominantly focused on their ability to \emph{recognize} formal languages. For example, recurrent neural networks (RNNs) with Heaviside activations are tightly linked to regular languages, i.e., languages defined by finite-state automata (FSAs). Such results, however, fall short of describing the capabilities of RNN \emph{language models} (LMs), which are definitionally \emph{distributions} over strings. We take a fresh look at the representational capacity of RNN LMs by connecting them to \emph{probabilistic} FSAs and demonstrate that RNN LMs with linearly bounded precision can express arbitrary regular LMs.
Generative large language models (LLMs) have been shown to exhibit harmful biases and stereotypes. While safety fine-tuning typically takes place in English, if at all, these models are being used by speakers of many different languages. There is existing evidence that the performance of these models is inconsistent across languages and that they discriminate based on demographic factors of the user. Motivated by this, we investigate whether the social stereotypes exhibited by LLMs differ as a function of the language used to prompt them, while controlling for cultural differences and task accuracy. To this end, we present MBBQ (Multilingual Bias Benchmark for Question-answering), a carefully curated version of the English BBQ dataset extended to Dutch, Spanish, and Turkish, which measures stereotypes commonly held across these languages. We further complement MBBQ with a parallel control dataset to measure task performance on the question-answering task independently of bias. Our results based on several open-source and proprietary LLMs confirm that some non-English languages suffer from bias more than English, even when controlling for cultural shifts. Moreover, we observe significant cross-lingual differences in bias behaviour for all except the most accurate models. With the release of MBBQ, we hope to encourage further research on bias in multilingual settings. The dataset and code are available at //github.com/Veranep/MBBQ.
It is imperative for Large language models (LLMs) to follow instructions with elaborate requirements (i.e. Complex Instructions Following). Yet, it remains under-explored how to enhance the ability of LLMs to follow complex instructions with multiple constraints. To bridge the gap, we initially study what training data is effective in enhancing complex constraints following abilities. We found that training LLMs with instructions containing multiple constraints enhances their understanding of complex instructions, especially those with lower complexity levels. The improvement can even generalize to compositions of out-of-domain constraints. Additionally, we further propose methods addressing how to obtain and utilize the effective training data. Finally, we conduct extensive experiments to prove the effectiveness of our methods in terms of overall performance and training efficiency. We also demonstrate that our methods improve models' ability to follow instructions generally and generalize effectively across out-of-domain, in-domain, and adversarial settings, while maintaining general capabilities.
With the rapid development of artificial intelligence, large language models (LLMs) have made remarkable advancements in natural language processing. These models are trained on vast datasets to exhibit powerful language understanding and generation capabilities across various applications, including machine translation, chatbots, and agents. However, LLMs have revealed a variety of privacy and security issues throughout their life cycle, drawing significant academic and industrial attention. Moreover, the risks faced by LLMs differ significantly from those encountered by traditional language models. Given that current surveys lack a clear taxonomy of unique threat models across diverse scenarios, we emphasize the unique privacy and security threats associated with five specific scenarios: pre-training, fine-tuning, retrieval-augmented generation systems, deployment, and LLM-based agents. Addressing the characteristics of each risk, this survey outlines potential threats and countermeasures. Research on attack and defense situations can offer feasible research directions, enabling more areas to benefit from LLMs.
This paper presents an analysis of open-source large language models (LLMs) and their application in Retrieval-Augmented Generation (RAG) tasks, specific for enterprise-specific data sets scraped from their websites. With the increasing reliance on LLMs in natural language processing, it is crucial to evaluate their performance, accessibility, and integration within specific organizational contexts. This study examines various open-source LLMs, explores their integration into RAG frameworks using enterprise-specific data, and assesses the performance of different open-source embeddings in enhancing the retrieval and generation process. Our findings indicate that open-source LLMs, combined with effective embedding techniques, can significantly improve the accuracy and efficiency of RAG systems, offering a viable alternative to proprietary solutions for enterprises.
The advent of large language models marks a revolutionary breakthrough in artificial intelligence. With the unprecedented scale of training and model parameters, the capability of large language models has been dramatically improved, leading to human-like performances in understanding, language synthesizing, and common-sense reasoning, etc. Such a major leap-forward in general AI capacity will change the pattern of how personalization is conducted. For one thing, it will reform the way of interaction between humans and personalization systems. Instead of being a passive medium of information filtering, large language models present the foundation for active user engagement. On top of such a new foundation, user requests can be proactively explored, and user's required information can be delivered in a natural and explainable way. For another thing, it will also considerably expand the scope of personalization, making it grow from the sole function of collecting personalized information to the compound function of providing personalized services. By leveraging large language models as general-purpose interface, the personalization systems may compile user requests into plans, calls the functions of external tools to execute the plans, and integrate the tools' outputs to complete the end-to-end personalization tasks. Today, large language models are still being developed, whereas the application in personalization is largely unexplored. Therefore, we consider it to be the right time to review the challenges in personalization and the opportunities to address them with LLMs. In particular, we dedicate this perspective paper to the discussion of the following aspects: the development and challenges for the existing personalization system, the newly emerged capabilities of large language models, and the potential ways of making use of large language models for personalization.
Knowledge plays a critical role in artificial intelligence. Recently, the extensive success of pre-trained language models (PLMs) has raised significant attention about how knowledge can be acquired, maintained, updated and used by language models. Despite the enormous amount of related studies, there still lacks a unified view of how knowledge circulates within language models throughout the learning, tuning, and application processes, which may prevent us from further understanding the connections between current progress or realizing existing limitations. In this survey, we revisit PLMs as knowledge-based systems by dividing the life circle of knowledge in PLMs into five critical periods, and investigating how knowledge circulates when it is built, maintained and used. To this end, we systematically review existing studies of each period of the knowledge life cycle, summarize the main challenges and current limitations, and discuss future directions.
Temporal sentence grounding in videos (TSGV), a.k.a., natural language video localization (NLVL) or video moment retrieval (VMR), aims to retrieve a temporal moment that semantically corresponds to a language query from an untrimmed video. Connecting computer vision and natural language, TSGV has drawn significant attention from researchers in both communities. This survey attempts to provide a summary of fundamental concepts in TSGV and current research status, as well as future research directions. As the background, we present a common structure of functional components in TSGV, in a tutorial style: from feature extraction from raw video and language query, to answer prediction of the target moment. Then we review the techniques for multimodal understanding and interaction, which is the key focus of TSGV for effective alignment between the two modalities. We construct a taxonomy of TSGV techniques and elaborate methods in different categories with their strengths and weaknesses. Lastly, we discuss issues with the current TSGV research and share our insights about promising research directions.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191