Recent weeks have not been kind to OpenAI. The release of the company's latest model, GPT-4o, has been somewhat overshadowed by a series of accusations leveled at both the company and its CEO, Sam Altman. This comes at the same time that several high-profile employees, including co-founder and chief scientist Ilya Sutskever, have chosen to leave the company. This is not the first time the Silicon Valley startup has been embroiled in scandal. In November, Altman was briefly ousted from the company after the board found he had not been "consistently candid" with them.

Tech evangelists like to say that AI will eat the world--a reference to a famous line about software from the venture capitalist Marc Andreessen. In the past few weeks, we've finally gotten a sense of what they mean. This spring, tech companies have made clear that AI will be a defining feature of online life, whether people want it to be or not. First, Meta surprised users with an AI chatbot that lives in the search bar on Instagram and Facebook. It has since informed European users that their data are being used to train its AI--presumably sent only to comply with the continent's privacy laws. OpenAI released GPT-4o, billed as a new, more powerful and conversational version of its large language model.

An ex-employee has accused Amazon of breaching UK sanctions by selling facial recognition technology to Moscow following its invasion of Ukraine, The Financial Times reported. Charles Forrest alleged that he was unfairly dismissed in 2023 after accusing Amazon of wrongdoing on a number of issues between November 2022 and May 2023, according to the article. The allegations were presented to a London employment tribunal as part of a hearing this week. Forrest said that Amazon closed a deal with Russian firm VisionLabs to provide access to its Rekognition facial recognition technology. It did that "through what appears to be a shell company based in the Netherlands," according to the tribunal filings.

Should artificial intelligence be used in the justice system, and if so should it apply the letter or the spirit of the law? While there are no plans for AI judges yet, this is a question that the UK government is already wrestling with as it considers the potential uses of AI in the English court system. Despite this, lawyers and computer scientists are warning that current systems can't handle the ambiguity and nuance often required in legal situations.…

As large language models (LLMs) become increasingly integrated into real-world applications such as code generation and chatbot assistance, extensive efforts have been made to align LLM behavior with human values, including safety. Jailbreak attacks, aiming to provoke unintended and unsafe behaviors from LLMs, remain a significant/leading LLM safety threat. In this paper, we aim to defend LLMs against jailbreak attacks by introducing SafeDecoding, a safety-aware decoding strategy for LLMs to generate helpful and harmless responses to user queries. Our insight in developing SafeDecoding is based on the observation that, even though probabilities of tokens representing harmful contents outweigh those representing harmless responses, safety disclaimers still appear among the top tokens after sorting tokens by probability in descending order. This allows us to mitigate jailbreak attacks by identifying safety disclaimers and amplifying their token probabilities, while simultaneously attenuating the probabilities of token sequences that are aligned with the objectives of jailbreak attacks. We perform extensive experiments on five LLMs using six state-of-the-art jailbreak attacks and four benchmark datasets. Our results show that SafeDecoding significantly reduces the attack success rate and harmfulness of jailbreak attacks without compromising the helpfulness of responses to benign user queries. SafeDecoding outperforms six defense methods.

We introduce LlavaGuard, a family of VLM-based safeguard models, offering a versatile framework for evaluating the safety compliance of visual content. Specifically, we designed LlavaGuard for dataset annotation and generative model safeguarding. To this end, we collected and annotated a high-quality visual dataset incorporating a broad safety taxonomy, which we use to tune VLMs on context-aware safety risks. As a key innovation, LlavaGuard's new responses contain comprehensive information, including a safety rating, the violated safety categories, and an in-depth rationale. Further, our introduced customizable taxonomy categories enable the context-specific alignment of LlavaGuard to various scenarios. Our experiments highlight the capabilities of LlavaGuard in complex and real-world applications. We provide checkpoints ranging from 7B to 34B parameters demonstrating state-of-the-art performance, with even the smallest models outperforming baselines like GPT-4. We make our dataset and model weights publicly available and invite further research to address the diverse needs of communities and contexts.

A comprehensive and up-to-date collection of Russian legislation considered a'gold standard' does not exist. From a legal perspective, the collapse of the Soviet Union in the 1990s and the new Russian statehood became a starting point for collecting legal documents. While not every Soviet-era legal act was repealed, most had been completely abolished. We collect all federal regulations covering 1991 to 2023 and prepared these texts for linguistic analysis. We discuss the place of the present corpus among the related corpora (Section 2). We also provide a brief institutional context of the Russian promulgation routine (Section 3) and descriptive statistics (Section 4) and describe our processing pipeline (Sections 5, 6, 7).

Although safely enhanced Large Language Models (LLMs) have achieved remarkable success in tackling various complex tasks in a zero-shot manner, they remain susceptible to jailbreak attacks, particularly the unknown jailbreak attack. To enhance LLMs' generalized defense capabilities, we propose a two-stage adversarial tuning framework, which generates adversarial prompts to explore worst-case scenarios by optimizing datasets containing pairs of adversarial prompts and their safe responses. In the first stage, we introduce the hierarchical meta-universal adversarial prompt learning to efficiently and effectively generate token-level adversarial prompts. In the second stage, we propose the automatic adversarial prompt learning to iteratively refine semantic-level adversarial prompts, further enhancing LLM's defense capabilities. We conducted comprehensive experiments on three widely used jailbreak datasets, comparing our framework with six defense baselines under five representative attack scenarios. The results underscore the superiority of our proposed methods. Furthermore, our adversarial tuning framework exhibits empirical generalizability across various attack strategies and target LLMs, highlighting its potential as a transferable defense mechanism.

The emerging field of \emph{value awareness engineering} claims that software agents and systems should be value-aware, i.e. they must make decisions in accordance with human values. In this context, such agents must be capable of explicitly reasoning as to how far different courses of action are aligned with these values. For this purpose, values are often modelled as preferences over states or actions, which are then aggregated to determine the sequences of actions that are maximally aligned with a certain value. Recently, additional value admissibility constraints at this level have been considered as well. However, often relaxed versions of these constraints are needed, and this increases considerably the complexity of computing value-aligned policies. To obtain efficient algorithms that make value-aligned decisions considering admissibility relaxation, we propose the use of learning techniques, in particular, we have used constrained reinforcement learning algorithms. In this paper, we present two algorithms, $\epsilon\text{-}ADQL$ for strategies based on local alignment and its extension $\epsilon\text{-}CADQL$ for a sequence of decisions. We have validated their efficiency in a water distribution problem in a drought scenario.

Large language models (LLMs) have demonstrated impressive performance on reasoning tasks, which can be further improved through few-shot prompting techniques. However, the current evaluation primarily focuses on carefully constructed benchmarks and neglects the consideration of real-world reasoning problems that present missing and contradictory conditions, known as ill-defined problems. Our observations suggest that existing few-shot prompting techniques are ineffective in such scenarios, often providing overconfident answers or hallucination. To further study this problem, we develop a benchmark called Problems with Missing and Contradictory conditions (PMC) and introduce two novel metrics to evaluate the performance of few-shot prompting methods in these scenarios. Our analysis using the PMC benchmark reveals a trade-off dilemma between the performance of mathematical reasoning for well-defined problems and the ability to recognize ill-defined problems. To address the challenges posed by PMC, we propose a novel few-shot prompting method called SMT-LIB Prompting (SLP), which utilizes the SMT-LIB language to model the problems instead of solving them directly. Subsequently, a double-check solving strategy checks the satisfiability and uniqueness of the solution and provides final feedback. Extensive experiments demonstrate the superiority of our SLP approach compared to existing few-shot prompting methods when dealing with problems with missing and contradictory conditions. We will open-source our benchmark and code to facilitate future research.