Kentucky mother and daughter turn down $26.5MILLION to sell their farms to secretive tech giant that wants to build data center there Horrifying next twist in the Alexander brothers case: MAUREEN CALLAHAN exposes an unthinkable perversion that's been hiding in plain sight Hollywood icon who starred in Psycho after Hitchcock dubbed her'my new Grace Kelly' looks incredible at 95 Kylie Jenner's total humiliation in Hollywood: Derogatory rumor leaves her boyfriend's peers'laughing at her' behind her back Tucker Carlson erupts at Trump adviser as she hurls'SLANDER' claim linking him to synagogue shooting Ben Affleck'scores $600m deal' with Netflix to sell his AI film start-up Long hair over 45 is ageing and try-hard. I've finally cut mine off. Alexander brothers' alleged HIGH SCHOOL rape video: Classmates speak out on sickening footage... as creepy unseen photos are exposed Heartbreaking video shows very elderly DoorDash driver shuffle down customer's driveway with coffee order because he is too poor to retire Amber Valletta, 52, was a '90s Vogue model who made movies with Sandra Bullock and Kate Hudson, see her now Model Cindy Crawford, 60, mocked for her'out of touch' morning routine: 'Nothing about this is normal' Icebergs, penguins and 23ft waves: Our science editor reviews a'once in a lifetime' trip to Antarctica that involved crossing the world's most terrifying stretch of ocean READ MORE: £30,000 job with all living costs paid...but it's in the Antarctic'If you can explain Antarctica, you've never been there.' That was the quote from our captain, Jorn Bowitz, as we set off on our voyage to the White Continent. But you really can visit the magical place - the coldest, windiest and driest on Earth - for yourself.

This thesis explores advanced approaches to improve explainability in computer vision by analyzing and modeling the features exploited by deep neural networks. Initially, it evaluates attribution methods, notably saliency maps, by introducing a metric based on algorithmic stability and an approach utilizing Sobol indices, which, through quasi-Monte Carlo sequences, allows a significant reduction in computation time. In addition, the EVA method offers a first formulation of attribution with formal guarantees via verified perturbation analysis. Experimental results indicate that in complex scenarios these methods do not provide sufficient understanding, particularly because they identify only "where" the model focuses without clarifying "what" it perceives. Two hypotheses are therefore examined: aligning models with human reasoning -- through the introduction of a training routine that integrates the imitation of human explanations and optimization within the space of 1-Lipschitz functions -- and adopting a conceptual explainability approach. The CRAFT method is proposed to automate the extraction of the concepts used by the model and to assess their importance, complemented by MACO, which enables their visualization. These works converge towards a unified framework, illustrated by an interactive demonstration applied to the 1000 ImageNet classes in a ResNet model.

For large groups, use the name of the group or consortium and include a full list of the authors and affiliations at the end of the main manuscript or in the Supplementary Materials. Abstract: How diverse are the outputs of large language models when diversity is desired? We examine the diversity of responses of various models to questions with multiple possible answers, comparing them with human responses. Our findings suggest that models' outputs are highly concentrated, reflecting a narrow, mainstream'worldview', in comparison to humans, whose responses exhibit a much longer-tail. We examine three ways to increase models' output diversity: 1) increasing generation randomness via temperature sampling; 2) prompting models to answer from diverse perspectives; 3) aggregating outputs from several models. A combination of these measures significantly increases models' output diversity, reaching that of humans. We discuss implications of these findings for AI policy that wishes to preserve cultural diversity, an essential building block of a democratic social fabric. Conversely, a lack of diversity can result in extremism and exclusion (e.g., 1, 2).

Large language models excel at creative generation but continue to struggle with the issues of hallucination and bias. While retrieval-augmented generation (RAG) provides a framework for grounding LLMs' responses in accurate and up-to-date information, it still raises the question of bias: which sources should be selected for inclusion in the context? And how should their importance be weighted? In this paper, we study the challenge of cross-lingual RAG and present a dataset to investigate the robustness of existing systems at answering queries about geopolitical disputes, which exist at the intersection of linguistic, cultural, and political boundaries. Our dataset is sourced from Wikipedia pages containing information relevant to the given queries and we investigate the impact of including additional context, as well as the composition of this context in terms of language and source, on an LLM's response. Our results show that existing RAG systems continue to be challenged by cross-lingual use cases and suffer from a lack of consistency when they are provided with competing information in multiple languages. We present case studies to illustrate these issues and outline steps for future research to address these challenges. We make our dataset and code publicly available at https://github.com/manestay/bordIRlines.

Boulders form from a variety of geological processes, which their size, shape, and orientation may help us better understand. Furthermore, they represent potential hazards to spacecraft landing that need to be characterized. However, mapping individual boulders across vast areas is extremely labor-intensive, often limiting the extent over which they are characterized and the statistical robustness of obtained boulder morphometrics. To automate boulder characterization, we use an instance segmentation neural network, Mask R-CNN, to detect and outline boulders in high-resolution satellite images. Our neural network, BoulderNet, was trained from a dataset of > 33,000 boulders in > 750 image tiles from Earth, the Moon, and Mars. BoulderNet not only correctly detects the majority of boulders in images, but it identifies the outline of boulders with high fidelity, achieving average precision and recall values of 72% and 64% relative to manually digitized boulders from the test dataset, when only detections with intersection-over-union ratios > 50% are considered valid. These values are similar to those obtained by human mappers. On Earth, equivalent boulder diameters, aspect ratios, and orientations extracted from predictions were benchmarked against ground measurements and yield values within 15%, 0.20, and 20 degrees of their ground-truth values, respectively. BoulderNet achieves better boulder detection and characterization performance relative to existing methods, providing a versatile open-source tool to characterize entire boulder fields on planetary surfaces.

Prompting-based large language models (LLMs) are surprisingly powerful at generating natural language reasoning steps or Chains-of-Thoughts (CoT) for multi-step question answering (QA). They struggle, however, when the necessary knowledge is either unavailable to the LLM or not up-to-date within its parameters. While using the question to retrieve relevant text from an external knowledge source helps LLMs, we observe that this one-step retrieve-and-read approach is insufficient for multi-step QA. Here, \textit{what to retrieve} depends on \textit{what has already been derived}, which in turn may depend on \textit{what was previously retrieved}. To address this, we propose IRCoT, a new approach for multi-step QA that interleaves retrieval with steps (sentences) in a CoT, guiding the retrieval with CoT and in turn using retrieved results to improve CoT. Using IRCoT with GPT3 substantially improves retrieval (up to 21 points) as well as downstream QA (up to 15 points) on four datasets: HotpotQA, 2WikiMultihopQA, MuSiQue, and IIRC. We observe similar substantial gains in out-of-distribution (OOD) settings as well as with much smaller models such as Flan-T5-large without additional training. IRCoT reduces model hallucination, resulting in factually more accurate CoT reasoning. Code, data, and prompts are available at \url{https://github.com/stonybrooknlp/ircot}

In this thesis, we investigated the relevance, faithfulness, and succinctness aspects of Long Form Question Answering (LFQA). LFQA aims to generate an in-depth, paragraph-length answer for a given question, to help bridge the gap between real scenarios and the existing open-domain QA models which can only extract short-span answers. LFQA is quite challenging and under-explored. Few works have been done to build an effective LFQA system. It is even more challenging to generate a good-quality long-form answer relevant to the query and faithful to facts, since a considerable amount of redundant, complementary, or contradictory information will be contained in the retrieved documents. Moreover, no prior work has been investigated to generate succinct answers. We are among the first to research the LFQA task. We pioneered the research direction to improve the answer quality in terms of 1) query-relevance, 2) answer faithfulness, and 3) answer succinctness.

Most of the important archaeological sites in Central America were "discovered" by archaeologists who, in fact, didn't discover them at all but were led to the ruins by local people. I've known several Maya archaeologists who routinely started fieldwork in a new area by heading into a dive bar and hoisting beers with the locals while listening to various bullshitters spin tales about ruins they'd seen in the jungle; once in a while, a story would turn out to be true. But, because these sites were long known to local people, they had invariably been disturbed, if not badly looted. The revelation of an ancient city in a valley in the Mosquitia mountains, of Honduras, one of the last scientifically unexplored regions on Earth, was a different story. This was the first time a large archaeological site had been discovered in a purely speculative search using a technology called LIDAR, or "light detection and ranging," which can map terrain through the thickest jungle foliage, an event I chronicled in a story for the magazine in 2013.

Two years ago, a lawyer in Indiana sent me a check for seventy-eight thousand dollars. The money was from my uncle Walt, who had died six months earlier. I hadn't been expecting any money from Walt, still less counting on it. So I thought I should earmark my inheritance for something special, to honor Walt's memory. It happened that my longtime girlfriend, a native Californian, had promised to join me on a big vacation. She'd been feeling grateful to me for understanding why she had to return full time to Santa Cruz and look after her mother, who was ninety-four and losing her short-term memory. She'd said to me, impulsively, "I will take a trip with you anywhere in the world you've always wanted to go." To this I'd replied, for reasons I'm at a loss to reconstruct, "Antarctica?" Her eyes widened in a way that I should have paid closer attention to. But a promise was a promise. Hoping to make Antarctica more palatable to my temperate Californian, I decided to spend Walt's money on the most deluxe of bookings--a three-week Lindblad National Geographic expedition to Antarctica, South Georgia island, and the Falklands. I paid a deposit, and the Californian and I proceeded to joke, uneasily, when the topic arose, about the nasty cold weather and the heaving South Polar seas to which she'd consented to subject herself. I kept reassuring her that as soon as she saw a penguin she'd be happy she'd made the trip. But when it came time to pay the balance, she asked if we might postpone by a year. Her mother's situation was unstable, and she was loath to put herself so irretrievably far from home. By this point, I, too, had developed a vague aversion to the trip, an inability to recall why I'd proposed Antarctica in the first place. The idea of "seeing it before it melts" was dismal and self-cancelling: why not just wait for it to melt and cross itself off the list of travel destinations? I was also put off by the seventh continent's status as a trophy, too remote and expensive for the common tourist to set foot on. It was true that there were extraordinary birds to be seen, not just penguins but oddities like the snowy sheathbill and the world's southernmost-breeding songbird, the South Georgia pipit. But the number of Antarctic species is fairly small, and I'd already reconciled myself to never seeing every bird species in the world. The best reason I could think of for going to Antarctica was that it was absolutely not the kind of thing the Californian and I did; we'd learned that our ideal getaway lasts three days.