Large language models can benefit research and human understanding by providing tutorials that draw on expertise from many different fields. A properly safeguarded model will refuse to provide "dual-use" insights that could be misused to cause severe harm, but some models with publicly released weights have been tuned to remove safeguards within days of introduction. Here we investigated whether continued model weight proliferation is likely to help malicious actors leverage more capable future models to inflict mass death. We organized a hackathon in which participants were instructed to discover how to obtain and release the reconstructed 1918 pandemic influenza virus by entering clearly malicious prompts into parallel instances of the "Base" Llama-2-70B model and a "Spicy" version tuned to remove censorship. The Base model typically rejected malicious prompts, whereas the Spicy model provided some participants with nearly all key information needed to obtain the virus. Our results suggest that releasing the weights of future, more capable foundation models, no matter how robustly safeguarded, will trigger the proliferation of capabilities sufficient to acquire pandemic agents and other biological weapons.
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： ·
估計/估計量
·
SimPLe
·
Networking
·
Processing（編程語言）
·
Fusing measurements from multiple, heterogeneous, partial sources, observing a common object or process, poses challenges due to the increasing availability of numbers and types of sensors. In this work we propose, implement and validate an end-to-end computational pipeline in the form of a multiple-auto-encoder neural network architecture for this task. The inputs to the pipeline are several sets of partial observations, and the result is a globally consistent latent space, harmonizing (rigidifying, fusing) all measurements. The key enabler is the availability of multiple slightly perturbed measurements of each instance:, local measurement, "bursts", that allows us to estimate the local distortion induced by each instrument. We demonstrate the approach in a sequence of examples, starting with simple two-dimensional data sets and proceeding to a Wi-Fi localization problem and to the solution of a "dynamical puzzle" arising in spatio-temporal observations of the solutions of Partial Differential Equations.
At the staggering pace with which the capabilities of large language models (LLMs) are increasing, creating future-proof evaluation sets to assess their understanding becomes more and more challenging. In this paper, we propose a novel paradigm for evaluating LLMs which leverages the idea that correct world understanding should be consistent across different (Fregean) senses of the same meaning. Accordingly, we measure understanding not in terms of correctness but by evaluating consistency across multiple senses that are generated by the model itself. We showcase our approach by instantiating a test where the different senses are different languages, hence using multilingual self-consistency as a litmus test for the model's understanding and simultaneously addressing the important topic of multilinguality. Taking one of the latest versions of ChatGPT as our object of study, we evaluate multilingual consistency for two different tasks across three different languages. We show that its multilingual consistency is still lacking, and that its task and world understanding are thus not language-independent. As our approach does not require any static evaluation corpora in languages other than English, it can easily and cheaply be extended to different languages and tasks and could become an integral part of future benchmarking efforts.
Time efficiency is paramount for the localisation industry, which demands ever-faster turnaround times. However, translation speed is largely underresearched, and there is a lack of clarity about how language service providers (LSPs) can evaluate the performance of their post-editing (PE) and human translation (HT) services. This study constitutes the first large-scale investigation of translation and revision speed in HT and in the PE of neural machine translation, based on real-world data from an LSP. It uses an exploratory data analysis approach to investigate data for 90 million words translated by 879 linguists across 11 language pairs, over 2.5 years. The results of this research indicate that (a) PE is usually but not always faster than HT; (b) average speed values may be misleading; (c) translation speed is highly variable; and (d) edit distance cannot be used as a proxy for post-editing productivity, because it does not correlate strongly with speed.
Compared to large speech foundation models, small distilled models exhibit degraded noise robustness. The student's robustness can be improved by introducing noise at the inputs during pre-training. Despite this, using the standard distillation loss still yields a student with degraded performance. Thus, this paper proposes improving student robustness via distillation with correlation metrics. Teacher behavior is learned by maximizing the teacher and student cross-correlation matrix between their representations towards identity. Noise robustness is encouraged via the student's self-correlation minimization. The proposed method is agnostic of the teacher model and consistently outperforms the previous approach. This work also proposes an heuristic to weigh the importance of the two correlation terms automatically. Experiments show consistently better clean and noise generalization on Intent Classification, Keyword Spotting, and Automatic Speech Recognition tasks on SUPERB Challenge.
Modeling of real-world biological multi-agents is a fundamental problem in various scientific and engineering fields. Reinforcement learning (RL) is a powerful framework to generate flexible and diverse behaviors in cyberspace; however, when modeling real-world biological multi-agents, there is a domain gap between behaviors in the source (i.e., real-world data) and the target (i.e., cyberspace for RL), and the source environment parameters are usually unknown. In this paper, we propose a method for adaptive action supervision in RL from real-world demonstrations in multi-agent scenarios. We adopt an approach that combines RL and supervised learning by selecting actions of demonstrations in RL based on the minimum distance of dynamic time warping for utilizing the information of the unknown source dynamics. This approach can be easily applied to many existing neural network architectures and provide us with an RL model balanced between reproducibility as imitation and generalization ability to obtain rewards in cyberspace. In the experiments, using chase-and-escape and football tasks with the different dynamics between the unknown source and target environments, we show that our approach achieved a balance between the reproducibility and the generalization ability compared with the baselines. In particular, we used the tracking data of professional football players as expert demonstrations in football and show successful performances despite the larger gap between behaviors in the source and target environments than the chase-and-escape task.
Cooperative relationships between humans and agents are becoming more important for the social coexistence of anthropomorphic agents, including virtual agents and robots. One way to improve the relationship between humans and agents is for humans to empathize with the agents. Empathy can help humans become more accepting of agents. In this study, we focus on the IKEA effect in creating agents and investigate human empathy toward agents through relationships with others in the same space. For this reason, this study used a robot assembly task in which two participants cooperatively build the same robot or individually their own robot. We conducted experiments to examine the relationship between participants, the IKEA effect in creating an agent, and the influence of the empathy object on human empathy. The results showed that the IKEA effect promoted empathy toward the agent regardless of the relationship between participants. On the other hand, there was no significant difference in empathy from one participant to another before and after the task. These results indicate that regardless of the relationship between participants in the same space, the creation of an agent can promote empathy toward the agent.
Generative language models, such as ChatGPT, have garnered attention for their ability to generate human-like writing in various fields, including academic research. The rapid proliferation of generated texts has bolstered the need for automatic identification to uphold transparency and trust in the information. However, these generated texts closely resemble human writing and often have subtle differences in the grammatical structure, tones, and patterns, which makes systematic scrutinization challenging. In this work, we attempt to detect the Abstracts generated by ChatGPT, which are much shorter in length and bounded. We extract the texts semantic and lexical properties and observe that traditional machine learning models can confidently detect these Abstracts.
Age-Period-Cohort (APC) models are well used in the context of modelling health and demographic data to produce smooth estimates of each time trend. When smoothing in the context of APC models, there are two main schools, frequentist using penalised smoothing splines, and Bayesian using random processes with little crossover between them. In this article, we clearly lay out the theoretical link between the two schools, provide examples using simulated and real data to highlight similarities and difference, and help a general APC user understand potentially inaccessible theory from functional analysis. As intuition suggests, both approaches lead to comparable and almost identical in-sample predictions, but random processes within a Bayesian approach might be beneficial for out-of-sample prediction as the sources of uncertainty are captured in a more complete way.
Modern machine learning techniques in the natural language processing domain can be used to automatically generate scripts for goal-oriented dialogue systems. The current article presents a general framework for studying the automatic generation of scripts for goal-oriented dialogue systems. A method for preprocessing dialog data sets in JSON format is described. A comparison is made of two methods for extracting user intent based on BERTopic and latent Dirichlet allocation. A comparison has been made of two implemented algorithms for classifying statements of users of a goal-oriented dialogue system based on logistic regression and BERT transformer models. The BERT transformer approach using the bert-base-uncased model showed better results for the three metrics Precision (0.80), F1-score (0.78) and Matthews correlation coefficient (0.74) in comparison with other methods.
Incorporating prior knowledge into pre-trained language models has proven to be effective for knowledge-driven NLP tasks, such as entity typing and relation extraction. Current pre-training procedures usually inject external knowledge into models by using knowledge masking, knowledge fusion and knowledge replacement. However, factual information contained in the input sentences have not been fully mined, and the external knowledge for injecting have not been strictly checked. As a result, the context information cannot be fully exploited and extra noise will be introduced or the amount of knowledge injected is limited. To address these issues, we propose MLRIP, which modifies the knowledge masking strategies proposed by ERNIE-Baidu, and introduce a two-stage entity replacement strategy. Extensive experiments with comprehensive analyses illustrate the superiority of MLRIP over BERT-based models in military knowledge-driven NLP tasks.
小貼士
登錄享
相關主題
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191