In this paper, we introduce the BeaverTails dataset, aimed at fostering research on safety alignment in large language models (LLMs). This dataset uniquely separates annotations of helpfulness and harmlessness for question-answering pairs, thus offering distinct perspectives on these crucial attributes. In total, we have gathered safety meta-labels for 333,963 question-answer (QA) pairs and 361,903 pairs of expert comparison data for both the helpfulness and harmlessness metrics. We further showcase applications of BeaverTails in content moderation and reinforcement learning with human feedback (RLHF), emphasizing its potential for practical safety measures in LLMs. We believe this dataset provides vital resources for the community, contributing towards the safe development and deployment of LLMs. Our project page is available at the following URL: https://sites.google.com/view/pku-beavertails.

Current self-supervised learning (SSL) methods (e.g., SimCLR, DINO, VICReg,MOCOv3) target primarily on representations at instance level and do not generalize well to dense prediction tasks, such as object detection and segmentation.Towards aligning SSL with dense predictions, this paper demonstrates for the first time the underlying mean-shift clustering process of Vision Transformers (ViT), which aligns well with natural image semantics (e.g., a world of objects and stuffs). By employing transformer for joint embedding and clustering, we propose a two-level feature clustering SSL method, coined Feature-Level Self-supervised Learning (FLSL). We present the formal definition of the FLSL problem and construct the objectives from the mean-shift and k-means perspectives. We show that FLSL promotes remarkable semantic cluster representations and learns an embedding scheme amenable to intra-view and inter-view feature clustering. Experiments show that FLSL yields significant improvements in dense prediction tasks, achieving 44.9 (+2.8)% AP and 46.5% AP in object detection, as well as 40.8 (+2.3)% AP and 42.1% AP in instance segmentation on MS-COCO, using Mask R-CNN with ViT-S/16 and ViT-S/8 as backbone, respectively. FLSL consistently outperforms existing SSL methods across additional benchmarks, including UAV17 object detection on UAVDT, and video instance segmentation on DAVIS 2017.We conclude by presenting visualization and various ablation studies to better understand the success of FLSL. The source code is available at https://github.com/ISL-CV/FLSL.

In-context learning (ICL), the ability of large language models to perform novel tasks by conditioning on a prompt with a few task examples, requires these examples to be informative about the test instance. The standard approach of independently ranking and selecting the most similar examples selects redundant examples while omitting important information. In this work, we show that BERTScore-Recall (BSR) selects better examples that demonstrate more of the salient aspects, e.g. reasoning patterns, of the test input. We further extend BSR and many standard metrics to easily optimizable set-level metrics, giving still better coverage of those salient aspects. On 15 datasets spanning 6 tasks and with 7 diverse LLMs, we show that (1) BSR is the superior metric for in-context example selection across the board, and (2) for compositional tasks, set selection using Set-BSR outperforms independent ranking by up to 17 points on average and, despite being training-free, surpasses methods that leverage task or LLM-specific training.

Kernel methods are learning algorithms that enjoy solid theoretical foundations while suffering from important computational limitations. Sketching, which consists in looking for solutions among a subspace of reduced dimension, is a well-studied approach to alleviate these computational burdens. However, statistically-accurate sketches, such as the Gaussian one, usually contain few null entries, such that their application to kernel methods and their non-sparse Gram matrices remains slow in practice. In this paper, we show that sparsified Gaussian (and Rademacher) sketches still produce theoretically-valid approximations while allowing for important time and space savings thanks to an efficient decomposition trick. To support our method, we derive excess risk bounds for both single and multiple output kernel problems, with generic Lipschitz losses, hereby providing new guarantees for a wide range of applications, from robust regression to multiple quantile regression. Our theoretical results are complemented with experiments showing the empirical superiority of our approach over state-of-the-art sketching methods.

JERUSALEM – For Mitchai Sarabon, a Thai fieldhand working on Kibbutz Alumim in southern Israel, Oct. 7 started like any other Saturday. His one day off a week, the 32-year-old said, he woke early and began doing his laundry. His friends – a mix of Thai migrant workers and Nepalese agricultural students – were also milling about the compound where they lived on the edge of the kibbutz, taking care of various personal tasks, when suddenly they heard gunshots. "Suddenly, I saw one of the Nepalese guys being shot, others ran to hide in a bomb shelter and then the terrorists arrived," Sarabon recounted to Fox News Digital in a video interview from his home in Udon Thani, Thailand, on Friday. "They threw a grenade inside, some of the people died instantly and others ran away, they were shot dead too."

About a decade ago, 125 amateur cyclists from all over the UK filed into the laboratories at King's College London. Aged between 55 and 79, they were there to participate in a long-term study examining how regular physical activity affects the ageing process. Janet Lord, professor of immune cell biology at Birmingham University, who conducted the study in collaboration with King's professor Steve Harridge, said the team were surprised by some findings when they examined the cyclists' bodies and took blood samples over several years. Her subjects, described as "very keen cyclists", were fairly fit, riding up to 60 miles a week. "We found things like increased fat in the body, which a lot of people tell you'oh, there's nothing you can do about that, that's part of ageing' – just were not true. They didn't happen in this group. We compared them with healthy older adults who were not regular exercisers. Our group did not lose muscle … and didn't lose much bone mass either," said Lord, who is the director of the university's Institute for Inflammation and Ageing, and a special adviser to the House of Lords inquiry into ageing, which published a report in 2021.

Generative transformer models have become increasingly complex, with large numbers of parameters and the ability to process multiple input modalities. Current methods for explaining their predictions are resource-intensive. Most crucially, they require prohibitively large amounts of extra memory, since they rely on backpropagation which allocates almost twice as much GPU memory as the forward pass. This makes it difficult, if not impossible, to use them in production. We present AtMan that provides explanations of generative transformer models at almost no extra cost. Specifically, AtMan is a modality-agnostic perturbation method that manipulates the attention mechanisms of transformers to produce relevance maps for the input with respect to the output prediction. Instead of using backpropagation, AtMan applies a parallelizable token-based search method based on cosine similarity neighborhood in the embedding space. Our exhaustive experiments on text and image-text benchmarks demonstrate that AtMan outperforms current state-of-the-art gradient-based methods on several metrics while being computationally efficient. As such, AtMan is suitable for use in large model inference deployments.

Protecting the anonymity of authors has become a difficult task given the rise of automated authorship attributors. These attributors are capable of attributing the author of a text amongst a pool of authors with great accuracy. In order to counter the rise of these automated attributors, there has also been a rise of automated obfuscators. These obfuscators are capable of taking some text, perturbing the text in some manner, and, if successful, deceive an automated attributor in misattributing the wrong author. We devised three novel authorship obfuscation methods that utilized a Psycho-linguistic theory known as Uniform Information Density (UID) theory. This theory states that humans evenly distribute information amongst speech or text so as to maximize efficiency. Utilizing this theory in our three obfuscation methods, we attempted to see how successfully we could deceive two separate attributors. Obfuscating 50 human and 50 GPT-3 generated articles from the TuringBench dataset, we observed how well each method did on deceiving the attributors. While the quality of the obfuscation in terms of semantic preservation and sensical changes was high, we were not able to find any evidence to indicate UID was a viable guiding metric for obfuscation. However, due to restrictions in time we were unable to test a large enough sample of article or tune the parameters for our attributors to comment conclusively on UID in obfuscation.

Vicious assaults, malware, and various ransomware pose a cybersecurity threat, causing considerable damage to computer structures, servers, and mobile and web apps across various industries and businesses. These safety concerns are important and must be addressed immediately. Ransomware detection and classification are critical for guaranteeing rapid reaction and prevention. This study uses the XGBoost classifier and Random Forest (RF) algorithms to detect and classify ransomware attacks. This approach involves analyzing the behaviour of ransomware and extracting relevant features that can help distinguish between different ransomware families. The models are evaluated on a dataset of ransomware attacks and demonstrate their effectiveness in accurately detecting and classifying ransomware. The results show that the XGBoost classifier, Random Forest Classifiers, can effectively detect and classify different ransomware attacks with high accuracy, thereby providing a valuable tool for enhancing cybersecurity.

Explainable AI (XAI) aims to bridge the gap between complex algorithmic systems and human stakeholders. Current discourse often examines XAI in isolation as either a technological tool, user interface, or policy mechanism. This paper proposes a unifying ethical framework grounded in moral duties and the concept of reciprocity. We argue that XAI should be appreciated not merely as a right, but as part of our moral duties that helps sustain a reciprocal relationship between humans affected by AI systems. This is because, we argue, explanations help sustain constitutive symmetry and agency in AI-led decision-making processes. We then assess leading XAI communities and reveal gaps between the ideal of reciprocity and practical feasibility. Machine learning offers useful techniques but overlooks evaluation and adoption challenges. Human-computer interaction provides preliminary insights but oversimplifies organizational contexts. Policies espouse accountability but lack technical nuance. Synthesizing these views exposes barriers to implementable, ethical XAI. Still, positioning XAI as a moral duty transcends rights-based discourse to capture a more robust and complete moral picture. This paper provides an accessible, detailed analysis elucidating the moral value of explainability.