Although Large Language Models (LLMs) have demonstrated impressive text generation capabilities, they are easily misled by untruthful contexts provided by users or knowledge augmentation tools, leading to hallucinations. To alleviate LLMs from being misled by untruthful context and take advantage of knowledge augmentation, we propose Truth-Aware Context Selection (TACS), a lightweight method to adaptively recognize and mask untruthful context from the inputs. TACS begins by performing truth detection on the input context, leveraging the parameterized knowledge within the LLM. Subsequently, it constructs a corresponding attention mask based on the truthfulness of each position, selecting the truthful context and discarding the untruthful context. Additionally, we introduce a new evaluation metric, Disturbance Adaption Rate, to further study the LLMs' ability to accept truthful information and resist untruthful information. Experimental results indicate that TACS can effectively filter untruthful context and significantly improve the overall quality of LLMs' responses when presented with misleading information.

The success of Large Language Models (LLMs) has led to a parallel rise in the development of Large Multimodal Models (LMMs), which have begun to transform a variety of applications. These sophisticated multimodal models are designed to interpret and analyze complex data by integrating multiple modalities such as text and images, thereby opening new avenues for a range of applications. This paper investigates the applicability and effectiveness of prompt-engineered LMMs that process both images and text, including models such as LLaVA, BakLLaVA, Moondream, Gemini-pro-vision, and GPT-4o, compared to fine-tuned Vision Transformer (ViT) models in addressing critical security challenges. We focus on two distinct security tasks: 1) a visually evident task of detecting simple triggers, such as small pixel variations in images that could be exploited to access potential backdoors in the models, and 2) a visually non-evident task of malware classification through visual representations. In the visually evident task, some LMMs, such as Gemini-pro-vision and GPT-4o, have demonstrated the potential to achieve good performance with careful prompt engineering, with GPT-4o achieving the highest accuracy and F1-score of 91.9\% and 91\%, respectively. However, the fine-tuned ViT models exhibit perfect performance in this task due to its simplicity. For the visually non-evident task, the results highlight a significant divergence in performance, with ViT models achieving F1-scores of 97.11\% in predicting 25 malware classes and 97.61\% in predicting 5 malware families, whereas LMMs showed suboptimal performance despite iterative prompt improvements. This study not only showcases the strengths and limitations of prompt-engineered LMMs in cybersecurity applications but also emphasizes the unmatched efficacy of fine-tuned ViT models for precise and dependable tasks.

In recent years, large language models (LLMs) have demonstrated notable success across various tasks, but the trustworthiness of LLMs is still an open problem. One specific threat is the potential to generate toxic or harmful responses. Attackers can craft adversarial prompts that induce harmful responses from LLMs. In this work, we pioneer a theoretical foundation in LLMs security by identifying bias vulnerabilities within the safety fine-tuning and design a black-box jailbreak method named DRA (Disguise and Reconstruction Attack), which conceals harmful instructions through disguise and prompts the model to reconstruct the original harmful instruction within its completion. We evaluate DRA across various open-source and closed-source models, showcasing state-of-the-art jailbreak success rates and attack efficiency. Notably, DRA boasts a 91.1% attack success rate on OpenAI GPT-4 chatbot.

Woman critically injured in ride'malfunction' 10 hours agoShareBBCOn Sunday tarpaulin was seen around one of the rides, although it is not clear which ride suffered the malfunction A woman in her 40s is in hospital with life-threatening injuries after a funfair ride malfunctioned at a country show in south London, the Met Police has said. The incident happened during Lambeth Country Show in Brockwell Park at about 18:20 BST on Saturday. A man in his 40s is also being treated for "potentially life-threatening injuries", the force said. Lambeth Council said the investigation would "determine the cause of the malfunction". Two other people, a man in his 50s and an 11-year-old girl, were injured in the incident and have since been discharged from hospital, the Met said.

Despite what UFO enthusiasts might claim, virtually every scientist agrees that humanity is yet to receive a message let alone a visitor from beyond our planet. But in the vast scale of the universe – containing an estimated 2 trillion galaxies – scientists say there is a '100 per cent chance' that there is life somewhere apart from Earth. This raises a intriguing question: If alien life truly is common in the Universe, why haven't we heard from them? From the'Dark Forest Hypothesis' to the inevitability of nuclear war, the answer to this question may offer a chilling glimpse into the future of our own civilisation. Professor Frederick Walter, a galactic astronomer from Stony Brook University says: 'Life is a biochemical process, it's going to happen, but as you go further down the chain things become more uncertain.'

This story originally appeared in WIRED Italia and has been translated from Italian. The latest in a series of duels announced by the European Commission is with Bing, Microsoft's search engine. Brussels suspects that the giant based in Redmond, Washington, has failed to properly moderate content produced by the generative AI systems on Bing, Copilot, and Image Creator, and that as a result, it may have violated the Digital Services Act (DSA), one of Europe's latest digital regulations. On May 17, the EU summit requested company documents to understand how Microsoft handled the spread of hallucinations (inaccurate or nonsensical answers produced by AI), deepfakes, and attempts to improperly influence the upcoming European Parliament elections. At the beginning of June, voters in the 27 states of the European Union will choose their representatives to the European Parliament, in a campaign over which looms the ominous shadow of technology with its potential to manipulate the outcome. The commission has given Microsoft until May 27 to respond, only days before voters go to the polls.

Fine-resolution spatial patterns of water table depth (WTD) play a crucial role in shaping ecological resilience, hydrological connectivity, and anthropocentric objectives. Generally, a large-scale (e.g., continental or global) spatial map of static WTD can be simulated using either physically-based (PB) or machine learning-based (ML) models. We construct three fine-resolution (500 m) ML simulations of WTD, using the XGBoost algorithm and more than 20 million real and proxy observations of WTD, across the United States and Canada. The three ML models were constrained using known physical relations between WTD's drivers and WTD and were trained by sequentially adding real and proxy observations of WTD. We interpret the black box of our physically constrained ML models and compare it against available literature in groundwater hydrology. Through an extensive (pixel-by-pixel) evaluation, we demonstrate that our models can more accurately predict unseen real and proxy observations of WTD across most of North America's ecoregions compared to three available PB simulations of WTD. However, we still argue that large-scale WTD estimation is far from being a solved problem. We reason that due to biased observational data mainly collected from low-elevation floodplains, the misspecification of equations within physically-based models, and the over-flexibility of machine learning models, verifiably accurate simulations of WTD do not yet exist. Ultimately, we thoroughly discuss future directions that may help hydrogeologists decide how to proceed with WTD estimations, with a particular focus on the application of machine learning and the use of proxy satellite data.

Automatically generated questions often suffer from problems such as unclear expression or factual inaccuracies, requiring a reliable and comprehensive evaluation of their quality. Human evaluation is frequently used in the field of question generation (QG) and is one of the most accurate evaluation methods. It also serves as the standard for automatic metrics. However, there is a lack of unified evaluation criteria, which hampers the development of both QG technologies and automatic evaluation methods. To address this, we propose QGEval, a multi-dimensional Evaluation benchmark for Question Generation, which evaluates both generated questions and existing automatic metrics across 7 dimensions: fluency, clarity, conciseness, relevance, consistency, answerability, and answer consistency. We demonstrate the appropriateness of these dimensions by examining their correlations and distinctions. Analysis with QGEval reveals that 1) most QG models perform unsatisfactorily in terms of answerability and answer consistency, and 2) existing metrics fail to align well with human assessments when evaluating generated questions across the 7 dimensions. We expect this work to foster the development of both QG technologies and automatic metrics for QG.

When making decisions under uncertainty, individuals often deviate from rational behavior, which can be evaluated across three dimensions: risk preference, probability weighting, and loss aversion. Given the widespread use of large language models (LLMs) in decision-making processes, it is crucial to assess whether their behavior aligns with human norms and ethical expectations or exhibits potential biases. Several empirical studies have investigated the rationality and social behavior performance of LLMs, yet their internal decision-making tendencies and capabilities remain inadequately understood. This paper proposes a framework, grounded in behavioral economics, to evaluate the decision-making behaviors of LLMs. Through a multiple-choice-list experiment, we estimate the degree of risk preference, probability weighting, and loss aversion in a context-free setting for three commercial LLMs: ChatGPT-4.0-Turbo, Claude-3-Opus, and Gemini-1.0-pro. Our results reveal that LLMs generally exhibit patterns similar to humans, such as risk aversion and loss aversion, with a tendency to overweight small probabilities. However, there are significant variations in the degree to which these behaviors are expressed across different LLMs. We also explore their behavior when embedded with socio-demographic features, uncovering significant disparities. For instance, when modeled with attributes of sexual minority groups or physical disabilities, Claude-3-Opus displays increased risk aversion, leading to more conservative choices. These findings underscore the need for careful consideration of the ethical implications and potential biases in deploying LLMs in decision-making scenarios. Therefore, this study advocates for developing standards and guidelines to ensure that LLMs operate within ethical boundaries while enhancing their utility in complex decision-making environments.

We study interactive learning of LLM-based language agents based on user edits made to the agent's output. In a typical setting such as writing assistants, the user interacts with a language agent to generate a response given a context, and may optionally edit the agent response to personalize it based on their latent preference, in addition to improving the correctness. The edit feedback is naturally generated, making it a suitable candidate for improving the agent's alignment with the user's preference, and for reducing the cost of user edits over time. We propose a learning framework, PRELUDE that infers a description of the user's latent preference based on historic edit data. The inferred user preference descriptions are used to define prompts for generating responses in the future. This avoids fine-tuning the agent, which is costly, challenging to scale with the number of users, and may even degrade its performance on other tasks. Furthermore, learning descriptive preference improves interpretability, allowing the user to view and modify the learned preference. However, user preference can be complex, subtle, and vary based on context, making it challenging to learn. To address this, we propose a simple yet effective algorithm named CIPHER that leverages the LLM to infer the user preference for a given context based on user edits. In the future, CIPHER retrieves inferred preferences from the k-closest contexts in the history, and forms an aggregate preference for response generation. We introduce two interactive environments -- summarization and email writing, and use a GPT-4 simulated user for evaluation. On both tasks, CIPHER outperforms several baselines by achieving the lowest edit distance cost while only having a small overhead in LLM query cost. Our analysis reports that user preferences learned by CIPHER show significant similarity to the ground truth latent preferences.