FBI Agent's Sworn Testimony Contradicts Claims ICE's Jonathan Ross Made Under Oath The testimony also calls into question whether Ross failed to follow his training during the incident in which he reportedly shot and killed Minnesota citizen Renee Good. In testimony last month in federal court in Minnesota, FBI special agent Bernardo Medellin appeared to directly contradict a claim that ICE agent Jonathan Ross made under oath about whether a man they were trying to detain had asked to speak to his attorney. Medellin's testimony, which details federal training for interactions with drivers, also calls into question whether Ross followed his training during the interaction that led to the shooting and killing of Renee Nicole Good, a 37-year-old mother, last week. Ross has been identified by multiple media outlets as the shooter; while the Trump administration has declined to confirm those reports, details about the shooter shared by Vice President JD Vance match details of Ross' biography. As WIRED previously reported, in December Ross testified that last June he led a team seeking to apprehend a man named Roberto Carlos Muñoz-Guatemala, who had an administrative warrant out for being in the US without authorization.

This paper introduces TurnaboutLLM, a novel framework and dataset for evaluating the deductive reasoning abilities of Large Language Models (LLMs) by leveraging the interactive gameplay of detective games Ace Attorney and Danganronpa. The framework tasks LLMs with identifying contradictions between testimonies and evidences within long narrative contexts, a challenging task due to the large answer space and diverse reasoning types presented by its questions. We evaluate twelve state-of-the-art LLMs on the dataset, hinting at limitations of popular strategies for enhancing deductive reasoning such as extensive thinking and Chain-of-Thought prompting. The results also suggest varying effects of context size, the number of reasoning step and answer space size on model performance. Overall, TurnaboutLLM presents a substantial challenge for LLMs' deductive reasoning abilities in complex, narrative-rich environments.

Breakthroughs, discoveries, and DIY tips sent every weekday. We like to think our brains are reliable recorders--but reality says otherwise. From misremembered childhood moments to mistakenly "recalling" that you took your pills when you didn't, false memories are surprisingly common. And in high-stakes situations like courtroom testimony, these errors can have devastating consequences. Wouldn't it be amazing if there were an objective way to measure just how accurate someone's memory really is? New research suggests we might be able to do just that--by watching the eyes.

Generative large language models as tools in the legal domain have the potential to improve the justice system. However, the reasoning behavior of current generative models is brittle and poorly understood, hence cannot be responsibly applied in the domains of law and evidence. In this paper, we introduce an approach for creating benchmarks that can be used to evaluate the reasoning capabilities of generative language models. These benchmarks are dynamically varied, scalable in their complexity, and have formally unambiguous interpretations. In this study, we illustrate the approach on the basis of witness testimony, focusing on the underlying argument attack structure. We dynamically generate both linear and non-linear argument attack graphs of varying complexity and translate these into reasoning puzzles about witness testimony expressed in natural language. We show that state-of-the-art large language models often fail in these reasoning puzzles, already at low complexity. Obvious mistakes are made by the models, and their inconsistent performance indicates that their reasoning capabilities are brittle. Furthermore, at higher complexity, even state-of-the-art models specifically presented for reasoning capabilities make mistakes. We show the viability of using a parametrized benchmark with varying complexity to evaluate the reasoning capabilities of generative language models. As such, the findings contribute to a better understanding of the limitations of the reasoning capabilities of generative models, which is essential when designing responsible AI systems in the legal domain.

Google has been paying Samsung tons of cash every month to pre-install the AI app Gemini on its smartphones, according to a report by Bloomberg . This information comes to us as part of a pre-existing antitrust case against Google. Peter Fitzgerald, Google's VP of platforms and device partnerships, testified in federal court that it began paying Samsung for this service back in January. The pair of companies have a contract that's set to run at least two years. Fitzgerald told Judge Amit Metha, who is overseeing the case, that Google provides Samsung with both fixed monthly payments and a percentage of revenue earned from advertisers within the Gemini app.

It has been 113 years since the Titanic sank beneath the waves, claiming the lives of more than 1,500 passengers and crew. But new evidence has finally cleared the tragedy's Scottish scapegoat: First Officer William Murdoch. For years, Officer Murdoch has been accused of taking bribes, abandoning his post, and was even depicted shooting a passenger in the James Cameron movie. Now, more than a century later, 3D scans show that Officer Murdoch did not flee his position, but died while helping passengers escape until the very end. Deep sea scanning company Magellan has snapped 715,000 photos of the Titanic wreck 12,500 feet beneath the Atlantic.

This work presents the task of unsupervised location mapping, which seeks to map the trajectory of an individual narrative on a spatial map of locations in which a large set of narratives take place. Despite the fundamentality and generality of the task, very little work addressed the spatial mapping of narrative texts. The task consists of two parts: (1) inducing a ``map'' with the locations mentioned in a set of texts, and (2) extracting a trajectory from a single narrative and positioning it on the map. Following recent advances in increasing the context length of large language models, we propose a pipeline for this task in a completely unsupervised manner without predefining the set of labels. We test our method on two different domains: (1) Holocaust testimonies and (2) Lake District writing, namely multi-century literature on travels in the English Lake District. We perform both intrinsic and extrinsic evaluations for the task, with encouraging results, thereby setting a benchmark and evaluation practices for the task, as well as highlighting challenges.

This essay explores the possibility of making use of Evidenc e Theory (ET) [51] in order to represent communication between and within living organisms ranging from humans to bacteria. ET, also known as "Dempster-Shafer Theo ry" or "Belief Functions Theory," is a mathematical theory of uncertain reasoning th at takes as prototypical situation a judge evaluating testimonies, or a detective ex amining cues, rather than a gambler playing dice [48] [52]. This marks a sharp differenc e with Probability Theory (PT) because, albeit fundamental constructs such as Bayes' Theorem can be obtained from the corresponding expressions of ET as special cases, g amblers know the faces of a die or the numbers on a roulette -- they assume to live in a clos ed world -- whereas judges and detectives are aware that unexpected clues and te stimonies may open up novel possibilities -- they are aware of living in an open worl d [23]. I submit that ET is more appropriate than PT to represent info rmation transmission through arbitrary codes that multiply the generation o f novelties. Furthermore, its paradigmatic situation of judges listening to testimonies is structurally similar to information communication, whereas the paradigmatic situation of gamblers playing games of chance is not [52].

Incongruence detection in eyewitness narratives is critical for understanding the reliability of testimonies, yet traditional approaches often fail to address the nuanced inconsistencies inherent in such accounts. In this paper, we introduce a novel task of incongruence detection in eyewitness testimonies. Given a pair of testimonies containing of multiple pairs of question and answer by two subjects, we identify contextually related incongruence between the two subjects. We also mark the span of incongruences in the utterances. To achieve this, we developed MIND(MultI-EyewitNess Deception) - a comprehensive dataset consisting of 2927 pairs of contextually related answers designed to capture both explicit and implicit contradictions. INstruction - TunEd iNcongruity Detection framework based on 6W and multi-hop reasoning approach, aka. INTEND. Drawing from investigative techniques, INTEND address the task as a close-style problem, contradicting on the who, what, when, where and why aspect of the content. Our findings shows that prompt tuning, especially when utilizing our framework, enhances the detection of incongruences by a margin of +5.63 percent. We compare our approach with multiple fine-tuning and prompt tuning techniques on MLMs and LLMs. Emperical results demonstrate convincing performance improvement in F1-score over fine-tuned and regular prompt-tuning techniques, highlighting the effectiveness of our approach.

This work presents a computational approach to analyze character development along the narrative timeline. The analysis characterizes the inner and outer changes the protagonist undergoes within a narrative, and the interplay between them. We consider transcripts of Holocaust survivor testimonies as a test case, each telling the story of an individual in first-person terms. We focus on the survivor's religious trajectory, examining the evolution of their disposition toward religious belief and practice along the testimony. Clustering the resulting trajectories in the dataset, we identify common sequences in the data. Our findings highlight multiple common structures of religiosity across the narratives: in terms of belief, most present a constant disposition, while for practice, most present an oscillating structure, serving as valuable material for historical and sociological research. This work demonstrates the potential of natural language processing techniques for analyzing character evolution through thematic trajectories in narratives.