This paper investigates Who's Harry Potter (WHP), a pioneering yet insufficiently understood method for LLM unlearning. We explore it in two steps. First, we introduce a new task of LLM targeted unlearning, where given an unlearning target (e.g., a person) and some unlearning documents, we aim to unlearn only the information about the target, rather than everything in the unlearning documents. We further argue that a successful unlearning should satisfy criteria such as not outputting gibberish, not fabricating facts about the unlearning target, and not releasing factual information under jailbreak attacks. Second, we construct a causal intervention framework for targeted unlearning, where the knowledge of the unlearning target is modeled as a confounder between LLM input and output, and the unlearning process as a deconfounding process. This framework justifies and extends WHP, deriving a simple unlearning algorithm that includes WHP as a special case. Experiments on existing and new datasets show that our approach, without explicitly optimizing for the aforementioned criteria, achieves competitive performance in all of them. Our code is available at https://github.com/UCSB-NLP-Chang/causal_unlearn.git.

In this study, we address the growing issue of misleading charts, a prevalent problem that undermines the integrity of information dissemination. Misleading charts can distort the viewer's perception of data, leading to misinterpretations and decisions based on false information. The development of effective automatic detection methods for misleading charts is an urgent field of research. The recent advancement of multimodal Large Language Models (LLMs) has introduced a promising direction for addressing this challenge. We explored the capabilities of these models in analyzing complex charts and assessing the impact of different prompting strategies on the models' analyses. We utilized a dataset of misleading charts collected from the internet by prior research and crafted nine distinct prompts, ranging from simple to complex, to test the ability of four different multimodal LLMs in detecting over 21 different chart issues. Through three experiments--from initial exploration to detailed analysis--we progressively gained insights into how to effectively prompt LLMs to identify misleading charts and developed strategies to address the scalability challenges encountered as we expanded our detection range from the initial five issues to 21 issues in the final experiment. Our findings reveal that multimodal LLMs possess a strong capability for chart comprehension and critical thinking in data interpretation. There is significant potential in employing multimodal LLMs to counter misleading information by supporting critical thinking and enhancing visualization literacy. This study demonstrates the applicability of LLMs in addressing the pressing concern of misleading charts.

One of Amazon's most iconic products has turned out to be a major money drain, newly unearthed documents show. The retail giant invested in Alexa voice technology in its relatively cheap Echo speaker products in the hopes people would use it to order more products online. But this is said to have backfired dramatically - with new market research showing customers see the AI voice assistant as a secretary and mostly use it for free apps like setting their alarms and checking the weather. 'We worried we've hired 10,000 people and we've built a smart timer,' a former senior employee told the Wall Street Journal. Sources shared internal documents with the newspaper showing that between 2017 and 2021, Amazon suffered more than 25 billion in losses from its devices business.

For all its stacked selection of original content, like Fallout, The Boys and Rings of Power, Prime Video has historically pffered a cluttered, confusing and less-than-intuitive layout -- especially compared to rivals like Netflix. That changes today as Amazon begins rolling out a new Prime Video UI that, in the company's words, brings "clarity and simplicity back to streaming." The Prime Video redesign starts with a streamlined navigation bar that should make it easier to find your way around. To the left, the bar includes the general categories Home, Movies, TV Shows, Sports and Live TV. Immediately to the right, the nav bar continues with a dedicated tab for content bundled with your Prime membership, followed by sections for add-on subscriptions like Max, Paramount, Crunchyroll and others. There's a separate section to add new subscriptions -- from Amazon's more than 100 options -- straight from the bar.

Condé Nast, the media giant that owns The New Yorker, Vogue and Wired, has sent a cease-and-desist letter to AI-powered search startup Perplexity, according to The Information. The letter, sent on Monday, demanded Perplexity stop using content from Condé Nast publications in its AI-generated responses and accused the startup of plagiarism. It comes a month after Forbes took similar action. Condé Nast CEO Roger Lynch has warned "many" media companies could face financial ruin in the time it would take for litigation against generative AI companies to conclude. Lynch has called upon Congress to take "immediate action."

We introduce Lifelong ICL, a problem setting that challenges long-context language models (LMs) to learn from a sequence of language tasks through in-context learning (ICL). We further introduce Task Haystack, an evaluation suite dedicated to assessing and diagnosing how long-context LMs utilizes contexts in Lifelong ICL. When given a task instruction and test inputs, long-context LMs are expected to leverage the relevant demonstrations in the Lifelong ICL prompt, avoid distraction and interference from other tasks, and achieve test accuracies that are not significantly worse than the Single-task ICL baseline. Task Haystack draws inspiration from the widely-adopted "needle-in-a-haystack" (NIAH) evaluation, but presents new and unique challenges. It demands that models (1) utilize the contexts with deeper understanding, rather than resorting to simple copying and pasting; (2) navigate through long streams of evolving topics and tasks, which closely approximates the complexities of real-world usage of long-context LMs. Additionally, Task Haystack inherits the controllability aspect of NIAH, providing model developers with tools and visualizations to identify model vulnerabilities effectively. We benchmark 12 long-context LMs using Task Haystack. We find that state-of-the-art closed models such as GPT-4o still struggle in this setting, failing 15% of the cases on average, while all open-weight models we evaluate further lack behind by a large margin, failing up to 61% of the cases. In our controlled analysis, we identify factors such as distraction and recency bias as contributors to these failure cases. Further, we observe declines in performance when task instructions are paraphrased at test time or when ICL demonstrations are repeated excessively, raising concerns about the robustness, instruction understanding, and true context utilization of current long-context LMs.

Open Information Extraction (OIE) is a field of natural language processing that aims to present textual information in a format that allows it to be organized, analyzed and reflected upon. Numerous OIE systems are developed, claiming ever-increasing performance, marking the need for objective benchmarks. BenchIE is the latest reference we know of. Despite being very well thought out, we noticed a number of issues we believe are limiting. Therefore, we propose $\textit{BenchIE}^{FL}$, a new OIE benchmark which fully enforces the principles of BenchIE while containing fewer errors, omissions and shortcomings when candidate facts are matched towards reference ones. $\textit{BenchIE}^{FL}$ allows insightful conclusions to be drawn on the actual performance of OIE extractors.

Systems for synthesizer sound matching, which automatically set the parameters of a synthesizer to emulate an input sound, have the potential to make the process of synthesizer programming faster and easier for novice and experienced musicians alike, whilst also affording new means of interaction with synthesizers. Considering the enormous variety of synthesizers in the marketplace, and the complexity of many of them, general-purpose sound matching systems that function with minimal knowledge or prior assumptions about the underlying synthesis architecture are particularly desirable. With this in mind, we introduce a synthesizer sound matching model based on the Audio Spectrogram Transformer. We demonstrate the viability of this model by training on a large synthetic dataset of randomly generated samples from the popular Massive synthesizer. We show that this model can reconstruct parameters of samples generated from a set of 16 parameters, highlighting its improved fidelity relative to multi-layer perceptron and convolutional neural network baselines. We also provide audio examples demonstrating the out-of-domain model performance in emulating vocal imitations, and sounds from other synthesizers and musical instruments.

The broadcasting industry is increasingly adopting IP techniques, revolutionising both live and pre-recorded content production, from news gathering to live music events. IP broadcasting allows for the transport of audio and video signals in an easily configurable way, aligning with modern networking techniques. This shift towards an IP workflow allows for much greater flexibility, not only in routing signals but with the integration of tools using standard web development techniques. One possible tool could include the use of live audio tagging, which has a number of uses in the production of content. These include from automated closed captioning to identifying unwanted sound events within a scene. In this paper, we describe the process of containerising an audio tagging model into a microservice, a small segregated code module that can be integrated into a multitude of different network setups. The goal is to develop a modular, accessible, and flexible tool capable of seamless deployment into broadcasting workflows of all sizes, from small productions to large corporations. Challenges surrounding latency of the selected audio tagging model and its effect on the usefulness of the end product are discussed.

We propose a novel approach for the automatic equalization of individual musical instrument tracks. Our method begins by identifying the instrument present within a source recording in order to choose its corresponding ideal spectrum as a target. Next, the spectral difference between the recording and the target is calculated, and accordingly, an equalizer matching model is used to predict settings for a parametric equalizer. To this end, we build upon a differentiable parametric equalizer matching neural network, demonstrating improvements relative to previously established state-of-the-art. Unlike past approaches, we show how our system naturally allows real-world audio data to be leveraged during the training of our matching model, effectively generating suitably produced training targets in an automated manner mirroring conditions at inference time. Consequently, we illustrate how fine-tuning our matching model on such examples considerably improves parametric equalizer matching performance in real-world scenarios, decreasing mean absolute error by 24% relative to methods relying solely on random parameter sampling techniques as a self-supervised learning strategy. We perform listening tests, and demonstrate that our proposed automatic equalization solution subjectively enhances the tonal characteristics for recordings of common instrument types.