LLM developers have imposed technical interventions to prevent fine-tuning misuse attacks, attacks where adversaries evade safeguards by fine-tuning the model using a public API. Previous work has established several successful attacks against specific fine-tuning API defences. In this work, we show that defences of fine-tuning APIs that seek to detect individual harmful training or inference samples ('pointwise' detection) are fundamentally limited in their ability to prevent fine-tuning attacks. We construct 'pointwise-undetectable' attacks that repurpose entropy in benign model outputs (e.g. semantic or syntactic variations) to covertly transmit dangerous knowledge. Our attacks are composed solely of unsuspicious benign samples that can be collected from the model before fine-tuning, meaning training and inference samples are all individually benign and low-perplexity. We test our attacks against the OpenAI fine-tuning API, finding they succeed in eliciting answers to harmful multiple-choice questions, and that they evade an enhanced monitoring system we design that successfully detects other fine-tuning attacks. We encourage the community to develop defences that tackle the fundamental limitations we uncover in pointwise fine-tuning API defences.

NASA's Cooperative Autonomous Distributed Robotic Exploration (CADRE) mission, slated for flight to the Moon's Reiner Gamma region in 2025/2026, is designed to demonstrate multi-agent autonomous exploration of the Lunar surface and sub-surface. A team of three robots and a base station will autonomously explore a region near the lander, collecting the data required for 3D reconstruction of the surface with no human input; and then autonomously perform distributed sensing with multi-static ground penetrating radars (GPR), driving in formation while performing coordinated radar soundings to create a map of the subsurface. At the core of CADRE's software architecture is a novel autonomous, distributed planning, scheduling, and execution (PS&E) system. The system coordinates the robots' activities, planning and executing tasks that require multiple robots' participation while ensuring that each individual robot's thermal and power resources stay within prescribed bounds, and respecting ground-prescribed sleep-wake cycles. The system uses a centralized-planning, distributed-execution paradigm, and a leader election mechanism ensures robustness to failures of individual agents. In this paper, we describe the architecture of CADRE's PS&E system; discuss its design rationale; and report on verification and validation (V&V) testing of the system on CADRE's hardware in preparation for deployment on the Moon.

Coastal regions are particularly vulnerable to the impacts of rising sea levels and extreme weather events. Accurate real-time forecasting of hydrodynamic processes in these areas is essential for infrastructure planning and climate adaptation. In this study, we present the Multiple-Input Temporal Operator Network (MITONet), a novel autoregressive neural emulator that employs dimensionality reduction to efficiently approximate high-dimensional numerical solvers for complex, nonlinear problems that are governed by time-dependent, parameterized partial differential equations. Although MITONet is applicable to a wide range of problems, we showcase its capabilities by forecasting regional tide-driven dynamics described by the two-dimensional shallow-water equations, while incorporating initial conditions, boundary conditions, and a varying domain parameter. We demonstrate MITONet's performance in a real-world application, highlighting its ability to make accurate predictions by extrapolating both in time and parametric space.

We introduce a novel multilingual hierarchical corpus annotated for entity framing and role portrayal in news articles. The dataset uses a unique taxonomy inspired by storytelling elements, comprising 22 fine-grained roles, or archetypes, nested within three main categories: protagonist, antagonist, and innocent. Each archetype is carefully defined, capturing nuanced portrayals of entities such as guardian, martyr, and underdog for protagonists; tyrant, deceiver, and bigot for antagonists; and victim, scapegoat, and exploited for innocents. The dataset includes 1,378 recent news articles in five languages (Bulgarian, English, Hindi, European Portuguese, and Russian) focusing on two critical domains of global significance: the Ukraine-Russia War and Climate Change. Over 5,800 entity mentions have been annotated with role labels. This dataset serves as a valuable resource for research into role portrayal and has broader implications for news analysis. We describe the characteristics of the dataset and the annotation process, and we report evaluation results on fine-tuned state-of-the-art multilingual transformers and hierarchical zero-shot learning using LLMs at the level of a document, a paragraph, and a sentence.

The pace of evolution of Large Language Models (LLMs) necessitates new approaches for rigorous and comprehensive evaluation. Traditional human annotation is increasingly impracticable due to the complexities and costs involved in generating high-quality, challenging problems. In this work, we introduce CHASE, a unified framework to synthetically generate challenging problems using LLMs without human involvement. For a given task, our approach builds a hard problem in a bottom-up manner from simpler components. Moreover, our framework decomposes the generation process into independently verifiable sub-tasks, thereby ensuring a high level of quality and correctness. We implement CHASE to create evaluation benchmarks across three diverse domains: (1) document-based question answering, (2) repository-level code completion, and (3) math reasoning. The performance of state-of-the-art LLMs on these synthetic benchmarks lies in the range of 40-60% accuracy, thereby demonstrating the effectiveness of our framework at generating challenging problems. We publicly release our benchmarks and code.

News recommendation systems personalize homepage content to boost engagement, but factors like content type, editorial stance, and geographic focus impact recommendations. Local newspapers balance coverage across regions, yet identifying local articles is challenging due to implicit location cues like slang or landmarks. Traditional methods, such as Named Entity Recognition (NER) and Knowledge Graphs, infer locations, but Large Language Models (LLMs) offer new possibilities while raising concerns about accuracy and explainability. This paper explores LLMs for local article classification in Taboola's "Homepage For You" system, comparing them to traditional techniques. Key findings: (1) Knowledge Graphs enhance NER models' ability to detect implicit locations, (2) LLMs outperform traditional methods, and (3) LLMs can effectively identify local content without requiring Knowledge Graph integration. Offline evaluations showed LLMs excel at implicit location classification, while online A/B tests showed a significant increased in local views. A scalable pipeline integrating LLM-based location classification boosted local article distribution by 27%, preserving newspapers' brand identity and enhancing homepage personalization.

The assessment of argument quality depends on well-established logical, rhetorical, and dialectical properties that are unavoidably subjective: multiple valid assessments may exist, there is no unequivocal ground truth. This aligns with recent paths in machine learning, which embrace the co-existence of different perspectives. However, this potential remains largely unexplored in NLP research on argument quality. One crucial reason seems to be the yet unexplored availability of suitable datasets. We fill this gap by conducting a systematic review of argument quality datasets. We assign them to a multi-layered categorization targeting two aspects: (a) What has been annotated: we collect the quality dimensions covered in datasets and consolidate them in an overarching taxonomy, increasing dataset comparability and interoperability. (b) Who annotated: we survey what information is given about annotators, enabling perspectivist research and grounding our recommendations for future actions. To this end, we discuss datasets suitable for developing perspectivist models (i.e., those containing individual, non-aggregated annotations), and we showcase the importance of a controlled selection of annotators in a pilot study.

Recent advances in natural language processing have raised expectations for generative models to produce coherent text across diverse language varieties. In the particular case of the Portuguese language, the predominance of Brazilian Portuguese corpora online introduces linguistic biases in these models, limiting their applicability outside of Brazil. To address this gap and promote the creation of European Portuguese resources, we developed a cross-domain language variety identifier (LVI) to discriminate between European and Brazilian Portuguese. Motivated by the findings of our literature review, we compiled the PtBrVarId corpus, a cross-domain LVI dataset, and study the effectiveness of transformer-based LVI classifiers for cross-domain scenarios. Although this research focuses on two Portuguese varieties, our contribution can be extended to other varieties and languages. We open source the code, corpus, and models to foster further research in this task.

In the spring of 2014, a trans-anarchist Google engineer petitioned the White House to arrest our national decline. The plan was snappy: "1. Schmidt, then the chairman of Google, was an avatar of technocratic liberalism. Two decades earlier, as the largely unknown C.T.O. of Sun Microsystems, he helped Bill Clinton set up the first White House Web site, and, by the time of the Obama Administration, he served as Silicon Valley's unofficial consul to the Democratic Party. Schmidt was not himself a company "founder," a technologist's most regal credential, but he had performed as an able steward: when Larry Page and Sergey Brin struggled to reconcile their competing visions for Google's first corporate jet--Brin wanted a California king bed, Page did not--Schmidt negotiated a compromise. He was sensible and civic-minded. He was the adult in the room.

In the future, Microsoft suggests, you may be playing AI. No, not on the battlefield, but on games that actually use AI to simulate the entire game itself. As a first step, Microsoft has developed an AI model, called WHAM, that "beta tests" games early in the development cycle using AI instead of human players. Gamers know that realistic AI can turn a good game into something great, like how the older F.E.A.R. games would realistically model how soldiers might react to a hostile, armed player. Microsoft's World and Human Action Model (WHAM) takes the opposite approach -- it tries to figure out how human players will react in a given situation, right down to a specific frame or setup within the existing game world.