The surge in applications of large language models (LLMs) has prompted concerns about the generation of misleading or fabricated information, known as hallucinations. Therefore, detecting hallucinations has become critical to maintaining trust in LLM-generated content. A primary challenge in learning a truthfulness classifier is the lack of a large amount of labeled truthful and hallucinated data. To address the challenge, we introduce HaloScope, a novel learning framework that leverages the unlabeled LLM generations in the wild for hallucination detection. Such unlabeled data arises freely upon deploying LLMs in the open world, and consists of both truthful and hallucinated information. To harness the unlabeled data, we present an automated membership estimation score for distinguishing between truthful and untruthful generations within unlabeled mixture data, thereby enabling the training of a binary truthfulness classifier on top. Importantly, our framework does not require extra data collection and human annotations, offering strong flexibility and practicality for real-world applications. Extensive experiments show that HaloScope can achieve superior hallucination detection performance, outperforming the competitive rivals by a significant margin.

Understanding human mobility patterns has traditionally been a complex challenge in transportation modeling. Due to the difficulties in obtaining high-quality training datasets across diverse locations, conventional activity-based models and learning-based human mobility modeling algorithms are particularly limited by the availability and quality of datasets. Furthermore, current research mainly focuses on the spatial-temporal travel pattern but lacks an understanding of the semantic information between activities, which is crucial for modeling the interdependence between activities. In this paper, we propose an innovative Large Language Model (LLM) empowered human mobility modeling framework. Our proposed approach significantly reduces the reliance on detailed human mobility statistical data, utilizing basic socio-demographic information of individuals to generate their daily mobility patterns. We have validated our results using the NHTS and SCAG-ABM datasets, demonstrating the effective modeling of mobility patterns and the strong adaptability of our framework across various geographic locations.

While NLP research into hate speech detection has grown exponentially in the last three decades, there has been minimal uptake or engagement from policy makers and non-profit organisations. We argue the absence of ethical frameworks have contributed to this rift between current practice and best practice. By adopting appropriate ethical frameworks, NLP researchers may enable the social impact potential of hate speech research. This position paper is informed by reviewing forty-eight hate speech detection systems associated with thirty-seven publications from different venues.

The rapid progress of Large Language Models (LLMs) has opened up new opportunities across various domains and applications; yet it also presents challenges related to potential misuse. To mitigate such risks, red teaming has been employed as a proactive security measure to probe language models for harmful outputs via jailbreak attacks. However, current jailbreak attack approaches are single-turn with explicit malicious queries that do not fully capture the complexity of real-world interactions. In reality, users can engage in multi-turn interactions with LLM-based chat assistants, allowing them to conceal their true intentions in a more covert manner. To bridge this gap, we, first, propose a new jailbreak approach, RED QUEEN ATTACK. This method constructs a multi-turn scenario, concealing the malicious intent under the guise of preventing harm. We craft 40 scenarios that vary in turns and select 14 harmful categories to generate 56k multi-turn attack data points. We conduct comprehensive experiments on the RED QUEEN ATTACK with four representative LLM families of different sizes. Our experiments reveal that all LLMs are vulnerable to RED QUEEN ATTACK, reaching 87.62% attack success rate on GPT-4o and 75.4% on Llama3-70B. Further analysis reveals that larger models are more susceptible to the RED QUEEN ATTACK, with multi-turn structures and concealment strategies contributing to its success. To prioritize safety, we introduce a straightforward mitigation strategy called RED QUEEN GUARD, which aligns LLMs to effectively counter adversarial attacks. This approach reduces the attack success rate to below 1% while maintaining the model's performance across standard benchmarks. Full implementation and dataset are publicly accessible at https://github.com/kriti-hippo/red_queen.

We developed Long Short-Term Memory (LSTM) models to predict the formation of active regions (ARs) on the solar surface. Using the Doppler shift velocity, the continuum intensity, and the magnetic field observations from the Solar Dynamics Observatory (SDO) Helioseismic and Magnetic Imager (HMI), we have created time-series datasets of acoustic power and magnetic flux, which are used to train LSTM models on predicting continuum intensity, 12 hours in advance. These novel machine learning (ML) models are able to capture variations of the acoustic power density associated with upcoming magnetic flux emergence and continuum intensity decrease. Testing of the models' performance was done on data for 5 ARs, unseen from the models during training. Model 8, the best performing model trained, was able to make a successful prediction of emergence for all testing active regions in an experimental setting and three of them in an operational. The model predicted the emergence of AR11726, AR13165, and AR13179 respectively 10, 29, and 5 hours in advance, and variations of this model achieved average RMSE values of 0.11 for both active and quiet areas on the solar disc. This work sets the foundations for ML-aided prediction of solar ARs.

This case study delves into the ethical ramifications of an incident involving Tesla's Autopilot, emphasizing Tesla Motors' moral responsibility. Using a seven-step ethical decision-making process, it examines user behavior, system constraints, and regulatory implications. This incident prompts a broader evaluation of ethical challenges in the automotive industry's adoption of autonomous technologies, urging a reconsideration of industry norms and legal frameworks. The analysis offers a succinct exploration of ethical considerations in evolving technological landscapes.

Predicting flight trajectories is a research area that holds significant merit. In this paper, we propose a data-driven learning framework, that leverages the predictive and feature extraction capabilities of the mixture models and seq2seq-based neural networks while addressing prevalent challenges caused by error propagation and dimensionality reduction. After training with this framework, the learned model can improve long-step prediction accuracy significantly given the past trajectories and the context information. The accuracy and effectiveness of the approach are evaluated by comparing the predicted trajectories with the ground truth. The results indicate that the proposed method has outperformed the state-of-the-art predicting methods on a terminal airspace flight trajectory dataset. The trajectories generated by the proposed method have a higher temporal resolution(1 timestep per second vs 0.1 timestep per second) and are closer to the ground truth.

Influence functions are a popular tool for attributing a model's output to training data. The traditional approach relies on the calculation of inverse Hessian-vector products (iHVP), but the classical solver "Linear time Stochastic Second-order Algorithm" (LiSSA, Agarwal et al. (2017)) is often deemed impractical for large models due to expensive computation and hyperparameter tuning. We show that the three hyperparameters -- the scaling factor, the batch size, and the number of steps -- can be chosen depending on the spectral properties of the Hessian, particularly its trace and largest eigenvalue. By evaluating with random sketching (Swartworth and Woodruff, 2023), we find that the batch size has to be sufficiently large for LiSSA to converge; however, for all of the models we consider, the requirement is mild. We confirm our findings empirically by comparing to Proximal Bregman Retraining Functions (PBRF, Bae et al. (2022)). Finally, we discuss what role the inverse Hessian plays in calculating the influence.

The integration of privacy measures, including differential privacy techniques, ensures a provable privacy guarantee for the synthetic data. However, challenges arise for Generative Deep Learning models when tasked with generating realistic data, especially in critical domains such as Cybersecurity and Healthcare. Generative Models optimized for continuous data struggle to model discrete and non-Gaussian features that have domain constraints. Challenges increase when the training datasets are limited and not diverse. In such cases, generative models create synthetic data that repeats sensitive features, which is a privacy risk. Moreover, generative models face difficulties comprehending attribute constraints in specialized domains. This leads to the generation of unrealistic data that impacts downstream accuracy. To address these issues, this paper proposes a novel model, KIPPS, that infuses Domain and Regulatory Knowledge from Knowledge Graphs into Generative Deep Learning models for enhanced Privacy Preserving Synthetic data generation. The novel framework augments the training of generative models with supplementary context about attribute values and enforces domain constraints during training. This added guidance enhances the model's capacity to generate realistic and domain-compliant synthetic data. The proposed model is evaluated on real-world datasets, specifically in the domains of Cybersecurity and Healthcare, where domain constraints and rules add to the complexity of the data. Our experiments evaluate the privacy resilience and downstream accuracy of the model against benchmark methods, demonstrating its effectiveness in addressing the balance between privacy preservation and data accuracy in complex domains.

Current regulations on powerful AI capabilities are narrowly focused on "foundation" or "frontier" models. However, these terms are vague and inconsistently defined, leading to an unstable foundation for governance efforts. Critically, policy debates often fail to consider the data used with these models, despite the clear link between data and model performance. Even (relatively) "small" models that fall outside the typical definitions of foundation and frontier models can achieve equivalent outcomes when exposed to sufficiently specific datasets. In this work, we illustrate the importance of considering dataset size and content as essential factors in assessing the risks posed by models both today and in the future. More broadly, we emphasize the risk posed by over-regulating reactively and provide a path towards careful, quantitative evaluation of capabilities that can lead to a simplified regulatory environment.