Forecasting from atmospheric soundings is a fundamental task in operational meteorology, often requiring structured visual reasoning over Skew-T log-P diagrams by human forecasters. While recent advances in Vision-Language Models (VLMs) have shown promise in other scientific domains, their application to meteorological diagram interpretation remains largely unexplored. In this study, we present a lightweight AI assistant that interprets Skew-T diagrams using a small language model (LM) and a small VLM fine-tuned to emulate human forecasters. Using a curriculum learning framework, we first train the models to identify key atmospheric features from diagrams through visual question answering, followed by chain-of-thought reasoning tasks that estimate precipitation probability based on the derived visual groundings. Model inputs include either textual summaries or generated Skew-T diagrams derived from operational Numerical Weather Prediction (NWP) forecasts, paired with three-hour precipitation observations from South Korea's Auto Weather Stations network. Evaluation results demonstrate that the fine-tuned VLM achieves skill comparable to an operational NWP model, despite relying solely on static atmospheric profiles. Ablation studies reveal that visual grounding and reasoning supervision are critical for performance, while attention map analysis confirms that the model learns to focus on relevant meteorological features. These findings highlight the potential of compact, interpretable multimodal models to support weather forecasting tasks. The approach offers a computationally efficient alternative to large-scale systems, and future work could extend it to more complex applications.

Given news articles about an entity, such as a public figure or organization, timeline summarization (TLS) involves generating a timeline that summarizes the key events about the entity. However, the TLS task is too underspecified, since what is of interest to each reader may vary, and hence there is not a single ideal or optimal timeline. In this paper, we introduce a novel task, called Constrained Timeline Summarization (CTLS), where a timeline is generated in which all events in the timeline meet some constraint. An example of a constrained timeline concerns the legal battles of Tiger Woods, where only events related to his legal problems are selected to appear in the timeline. We collected a new human-verified dataset of constrained timelines involving 47 entities and 5 constraints per entity. We propose an approach that employs a large language model (LLM) to summarize news articles according to a specified constraint and cluster them to identify key events to include in a constrained timeline. In addition, we propose a novel self-reflection method during summary generation, demonstrating that this approach successfully leads to improved performance.

The black box problem in machine learning has led to the introduction of an ever-increasing set of explanation methods for complex models. These explanations have different properties, which in turn has led to the problem of method selection: which explanation method is most suitable for a given use case? In this work, we propose a unifying framework of attribution-based explanation methods, which provides a step towards a rigorous study of the similarities and differences of explanations. We first introduce removal-based attribution methods (RBAMs), and show that an extensively broad selection of existing methods can be viewed as such RBAMs. We then introduce the canonical additive decomposition (CAD). This is a general construction for additively decomposing any function based on the central idea of removing (groups of) features. We proceed to show that indeed every valid additive decomposition is an instance of the CAD, and that any removal-based attribution method is associated with a specific CAD. Next, we show that any removal-based attribution method can be completely defined as a game-theoretic value or interaction index for a specific (possibly constant-shifted) cooperative game, which is defined using the corresponding CAD of the method. We then use this intrinsic connection to define formal descriptions of specific behaviours of explanation methods, which we also call functional axioms, and identify sufficient conditions on the corresponding CAD and game-theoretic value or interaction index of an attribution method under which the attribution method is guaranteed to adhere to these functional axioms. Finally, we show how this unifying framework can be used to develop new, efficient approximations for existing explanation methods.

Accurately attributing answer text to its source document is crucial for developing a reliable question-answering system. However, attribution for long documents remains largely unexplored. Post-hoc attribution systems are designed to map answer text back to the source document, yet the granularity of this mapping has not been addressed. Furthermore, a critical question arises: What exactly should be attributed? This involves identifying the specific information units within an answer that require grounding. In this paper, we propose and investigate a novel approach to the factual decomposition of generated answers for attribution, employing template-based in-context learning. To accomplish this, we utilize the question and integrate negative sampling during few-shot in-context learning for decomposition. This approach enhances the semantic understanding of both abstractive and extractive answers. We examine the impact of answer decomposition by providing a thorough examination of various attribution approaches, ranging from retrieval-based techniques to LLM-based attributors.

US auto-safety regulators said on Friday that their investigation into Tesla's Autopilot had identified at least 13 fatal crashes in which the feature had been involved. The investigation also found the electric carmaker's claims did not match up with reality. The National Highway Traffic Safety Administration (NHTSA) disclosed on Friday that during its three-year Autopilot safety investigation, which it launched in August 2021, it identified at least 13 Tesla crashes involving one or more death, and many more involving serious injuries, in which "foreseeable driver misuse of the system played an apparent role". It also found evidence that "Tesla's weak driver engagement system was not appropriate for Autopilot's permissive operating capabilities", which resulted in a "critical safety gap". The NHTSA also raised concerns that Tesla's Autopilot name "may lead drivers to believe that the automation has greater capabilities than it does and invite drivers to overly trust the automation".

Tesla is recalling just over 2m vehicles in the United States fitted with its Autopilot advanced driver-assistance system to install new safeguards, after a safety regulator said the system was open to "foreseeable misuse". The National Highway Traffic Safety Administration (NHTSA) has been investigating the electric automaker led by the billionaire Elon Musk for more than two years over whether Tesla vehicles adequately ensure that drivers pay attention when using the driver assistance system. Tesla said in the recall filing that Autopilot's software system controls "may not be sufficient to prevent driver misuse" and could increase the risk of a crash. The acting NHTSA administrator, Ann Carlson, told Reuters in August it was "really important that driver monitoring systems take into account that humans over-trust technology". Tesla's Autopilot is intended to enable cars to steer, accelerate and brake automatically within their lane, while enhanced Autopilot can assist in changing lanes on highways but does not make them autonomous.

Publishing a book is a big occasion for any writer, and Rory Cellan-Jones is no exception. "Like any author, I obsessively check Amazon," he said. The former BBC technology correspondent wrote a memoir untangling the truth about his family history. What had popped up on the Amazon website was a biography of Cellan-Jones, with a naively designed cover by someone he had never heard of. "I thought: 'This is strange – who's writing a biography of me?'" Cellan-Jones told the Observer.

While chatbots are extensively being used by companies to engage and interact with their customers, yet another technology, conversational artificial intelligence (AI), is gaining popularity, and promises to take over chatbots soon with its clear advantages over them. Businesses are constantly reinventing the way they interact with their customers to keep them interested in their products. While chatbots served this purpose for a while, businesses are now looking to provide their customers with more engaging and personalized experiences, and conversational AI might just be the solution they are looking for. Conversational AI is an integration of technologies that makes it possible for people and machines to have successful verbal and written exchanges. Conversational AI functions by identifying a user's speech or text communications to understand their intentions and provide automated responses.