This paper investigates using knowledge editing techniques to detoxify Large Language Models (LLMs). We construct a benchmark, SafeEdit, which covers nine unsafe categories with various powerful attack prompts and equips comprehensive metrics for systematic evaluation. We conduct experiments with several knowledge editing approaches, indicating that knowledge editing has the potential to detoxify LLMs with a limited impact on general performance efficiently. Then, we propose a simple yet effective baseline, dubbed Detoxifying with Intraoperative Neural Monitoring (DINM), to diminish the toxicity of LLMs within a few tuning steps via only one instance. We further provide an in-depth analysis of the internal mechanism for various detoxifying approaches, demonstrating that previous methods like SFT and DPO may merely suppress the activations of toxic parameters, while DINM mitigates the toxicity of the toxic parameters to a certain extent, making permanent adjustments. We hope that these insights could shed light on future work of developing detoxifying approaches and the underlying knowledge mechanisms of LLMs. Code and benchmark are available at https://github.com/zjunlp/EasyEdit.

We investigate challenges and possibilities of formal reasoning for encoder-only transformers (EOT), meaning sound and complete methods for verifying or interpreting behaviour. In detail, we condense related formal reasoning tasks in the form of a naturally occurring satisfiability problem (SAT). We find that SAT is undecidable if we consider EOT, commonly considered in the expressiveness community. Furthermore, we identify practical scenarios where SAT is decidable and establish corresponding complexity bounds. Besides trivial cases, we find that quantized EOT, namely those restricted by some fixed-width arithmetic, lead to the decidability of SAT due to their limited attention capabilities. However, the problem remains difficult, as we establish those scenarios where SAT is NEXPTIME-hard and those where we can show that it is solvable in NEXPTIME for quantized EOT. To complement our theoretical results, we put our findings and their implications in the overall perspective of formal reasoning.

Intelligent agents must be generalists, capable of quickly adapting to various tasks. In reinforcement learning (RL), model-based RL learns a dynamics model of the world, in principle enabling transfer to arbitrary reward functions through planning. However, autoregressive model rollouts suffer from compounding error, making model-based RL ineffective for long-horizon problems. Successor features offer an alternative by modeling a policy's long-term state occupancy, reducing policy evaluation under new tasks to linear reward regression. Yet, policy improvement with successor features can be challenging. This work proposes a novel class of models, i.e., generalized occupancy models (GOMs), that learn a distribution of successor features from a stationary dataset, along with a policy that acts to realize different successor features. These models can quickly select the optimal action for arbitrary new tasks. By directly modeling long-term outcomes in the dataset, GOMs avoid compounding error while enabling rapid transfer across reward functions. We present a practical instantiation of GOMs using diffusion models and show their efficacy as a new class of transferable models, both theoretically and empirically across various simulated robotics problems.

Many of the recent remarkable advances in computer vision and language models can be attributed to the success of transfer learning via the pre-training of large foundation models. However, a theoretical framework which explains this empirical success is incomplete and remains an active area of research. Flatness of the loss surface and neural collapse have recently emerged as useful pre-training metrics which shed light on the implicit biases underlying pre-training. In this paper, we explore the geometric complexity of a model's learned representations as a fundamental mechanism that relates these two concepts. We show through experiments and theory that mechanisms which affect the geometric complexity of the pre-trained network also influence the neural collapse. Furthermore, we show how this effect of the geometric complexity generalizes to the neural collapse of new classes as well, thus encouraging better performance on downstream tasks, particularly in the few-shot setting.

Adaptive moment estimation (Adam), as a Stochastic Gradient Descent (SGD) variant, has gained widespread popularity in federated learning (FL) due to its fast convergence. However, federated Adam (FedAdam) algorithms suffer from a threefold increase in uplink communication overhead compared to federated SGD (FedSGD) algorithms, which arises from the necessity to transmit both local model updates and first and second moment estimates from distributed devices to the centralized server for aggregation. Driven by this issue, we propose a novel sparse FedAdam algorithm called FedAdam-SSM, wherein distributed devices sparsify the updates of local model parameters and moment estimates and subsequently upload the sparse representations to the centralized server. To further reduce the communication overhead, the updates of local model parameters and moment estimates incorporate a shared sparse mask (SSM) into the sparsification process, eliminating the need for three separate sparse masks. Theoretically, we develop an upper bound on the divergence between the local model trained by FedAdam-SSM and the desired model trained by centralized Adam, which is related to sparsification error and imbalanced data distribution. By minimizing the divergence bound between the model trained by FedAdam-SSM and centralized Adam, we optimize the SSM to mitigate the learning performance degradation caused by sparsification error. Additionally, we provide convergence bounds for FedAdam-SSM in both convex and non-convex objective function settings, and investigate the impact of local epoch, learning rate and sparsification ratio on the convergence rate of FedAdam-SSM. Experimental results show that FedAdam-SSM outperforms baselines in terms of convergence rate (over 1.1$\times$ faster than the sparse FedAdam baselines) and test accuracy (over 14.5\% ahead of the quantized FedAdam baselines).

Recent work on dialogue-based collaborative plan acquisition (CPA) has suggested that Theory of Mind (ToM) modelling can improve missing knowledge prediction in settings with asymmetric skill-sets and knowledge. Although ToM was claimed to be important for effective collaboration, its real impact on this novel task remains under-explored. By representing plans as graphs and by exploiting task-specific constraints we show that, as performance on CPA nearly doubles when predicting one's own missing knowledge, the improvements due to ToM modelling diminish. This phenomenon persists even when evaluating existing baseline methods. To better understand the relevance of ToM for CPA, we report a principled performance comparison of models with and without ToM features. Results across different models and ablations consistently suggest that learned ToM features are indeed more likely to reflect latent patterns in the data with no perceivable link to ToM. This finding calls for a deeper understanding of the role of ToM in CPA and beyond, as well as new methods for modelling and evaluating mental states in computational collaborative agents.

Machine learning (ML) methods have experienced significant growth in the past decade, yet their practical application in high-impact real-world domains has been hindered by their opacity. When ML methods are responsible for making critical decisions, stakeholders often require insights into how to alter these decisions. Counterfactual explanations (CFEs) have emerged as a solution, offering interpretations of opaque ML models and providing a pathway to transition from one decision to another. However, most existing CFE methods require access to the model's training dataset, few methods can handle multivariate time-series, and none can handle multivariate time-series without training datasets. These limitations can be formidable in many scenarios. In this paper, we present CFWoT, a novel reinforcement-learning-based CFE method that generates CFEs when training datasets are unavailable. CFWoT is model-agnostic and suitable for both static and multivariate time-series datasets with continuous and discrete features. Users have the flexibility to specify non-actionable, immutable, and preferred features, as well as causal constraints which CFWoT guarantees will be respected. We demonstrate the performance of CFWoT against four baselines on several datasets and find that, despite not having access to a training dataset, CFWoT finds CFEs that make significantly fewer and significantly smaller changes to the input time-series. These properties make CFEs more actionable, as the magnitude of change required to alter an outcome is vastly reduced.

GLOCON is a database of contentious events automatically extracted from national news sources from various countries in multiple languages. National news sources are utilized, and complete news archives are processed to create an event list for each source. Automation is achieved using a gold standard corpus sampled randomly from complete news archives (Yörük et al. 2022) and all annotated by at least two domain experts based on the event definition provided in Duruşan et al. (2022). The database consists of the following countries and sources provided in Table 1 as of May 2024.

Protecting Internet of things (IoT) devices against cyber attacks is imperative owing to inherent security vulnerabilities. These vulnerabilities can include a spectrum of sophisticated attacks that pose significant damage to both individuals and organizations. Employing robust security measures like intrusion detection systems (IDSs) is essential to solve these problems and protect IoT systems from such attacks. In this context, our proposed IDS model consists on a combination of convolutional neural network (CNN) and long short-term memory (LSTM) deep learning (DL) models. This fusion facilitates the detection and classification of IoT traffic into binary categories, benign and malicious activities by leveraging the spatial feature extraction capabilities of CNN for pattern recognition and the sequential memory retention of LSTM for discerning complex temporal dependencies in achieving enhanced accuracy and efficiency. In assessing the performance of our proposed model, the authors employed the new CICIoT2023 dataset for both training and final testing, while further validating the model's performance through a conclusive testing phase utilizing the CICIDS2017 dataset. Our proposed model achieves an accuracy rate of 98.42%, accompanied by a minimal loss of 0.0275. False positive rate(FPR) is equally important, reaching 9.17% with an F1-score of 98.57%. These results demonstrate the effectiveness of our proposed CNN-LSTM IDS model in fortifying IoT environments against potential cyber threats.

The 2024 Brain Tumor Segmentation Meningioma Radiotherapy (BraTS-MEN-RT) challenge aims to advance automated segmentation algorithms using the largest known multi-institutional dataset of radiotherapy planning brain MRIs with expert-annotated target labels for patients with intact or post-operative meningioma that underwent either conventional external beam radiotherapy or stereotactic radiosurgery. Each case includes a defaced 3D post-contrast T1-weighted radiotherapy planning MRI in its native acquisition space, accompanied by a single-label "target volume" representing the gross tumor volume (GTV) and any at-risk post-operative site. Target volume annotations adhere to established radiotherapy planning protocols, ensuring consistency across cases and institutions. For pre-operative meningiomas, the target volume encompasses the entire GTV and associated nodular dural tail, while for post-operative cases, it includes at-risk resection cavity margins as determined by the treating institution. Case annotations were reviewed and approved by expert neuroradiologists and radiation oncologists. Participating teams will develop, containerize, and evaluate automated segmentation models using this comprehensive dataset. Model performance will be assessed using the lesion-wise Dice Similarity Coefficient and the 95% Hausdorff distance. The top-performing teams will be recognized at the Medical Image Computing and Computer Assisted Intervention Conference in October 2024. BraTS-MEN-RT is expected to significantly advance automated radiotherapy planning by enabling precise tumor segmentation and facilitating tailored treatment, ultimately improving patient outcomes.