We introduce Loki, an open-source tool designed to address the growing problem of misinformation. Loki adopts a human-centered approach, striking a balance between the quality of fact-checking and the cost of human involvement. It decomposes the fact-checking task into a five-step pipeline: breaking down long texts into individual claims, assessing their check-worthiness, generating queries, retrieving evidence, and verifying the claims. Instead of fully automating the claim verification process, Loki provides essential information at each step to assist human judgment, especially for general users such as journalists and content moderators. Moreover, it has been optimized for latency, robustness, and cost efficiency at a commercially usable level. Loki is released under an MIT license and is available on GitHub. We also provide a video presenting the system and its capabilities.

Generative Large Language Models have shown impressive in-context learning abilities, performing well across various tasks with just a prompt. Previous melody-to-lyric research has been limited by scarce high-quality aligned data and unclear standard for creativeness. Most efforts focused on general themes or emotions, which are less valuable given current language model capabilities. In tonal contour languages like Mandarin, pitch contours are influenced by both melody and tone, leading to variations in lyric-melody fit. Our study, validated by the Mpop600 dataset, confirms that lyricists and melody writers consider this fit during their composition process. In this research, we developed a multi-agent system that decomposes the melody-to-lyric task into sub-tasks, with each agent controlling rhyme, syllable count, lyric-melody alignment, and consistency. Listening tests were conducted via a diffusion-based singing voice synthesizer to evaluate the quality of lyrics generated by different agent groups.

Byte-Pair Encoding (BPE) is an algorithm commonly used in Natural Language Processing to build a vocabulary of subwords, which has been recently applied to symbolic music. Given that symbolic music can differ significantly from text, particularly with polyphony, we investigate how BPE behaves with different types of musical content. This study provides a qualitative analysis of BPE's behavior across various instrumentations and evaluates its impact on a musical phrase segmentation task for both monophonic and polyphonic music. Our findings show that the BPE training process is highly dependent on the instrumentation and that BPE "supertokens" succeed in capturing abstract musical content. In a musical phrase segmentation task, BPE notably improves performance in a polyphonic setting, but enhances performance in monophonic tunes only within a specific range of BPE merges.

The development and evaluation of Large Language Models (LLMs) have largely focused on individual capabilities. However, this overlooks the intersection of multiple abilities across different types of expertise that are often required for real-world tasks, which we term cross capabilities. To systematically explore this concept, we first define seven core individual capabilities and then pair them to form seven common cross capabilities, each supported by a manually constructed taxonomy. Building on these definitions, we introduce CrossEval, a benchmark comprising 1,400 human-annotated prompts, with 100 prompts for each individual and cross capability. To ensure reliable evaluation, we involve expert annotators to assess 4,200 model responses, gathering 8,400 human ratings with detailed explanations to serve as reference examples. Our findings reveal that, in both static evaluations and attempts to enhance specific abilities, current LLMs consistently exhibit the "Law of the Weakest Link," where cross-capability performance is significantly constrained by the weakest component. Specifically, across 58 cross-capability scores from 17 models, 38 scores are lower than all individual capabilities, while 20 fall between strong and weak, but closer to the weaker ability. These results highlight the under-performance of LLMs in cross-capability tasks, making the identification and improvement of the weakest capabilities a critical priority for future research to optimize performance in complex, multi-dimensional scenarios.

I'm part-way through writing a book about the history of fake news, so I'm well aware that people making stuff up is not new. But what is new is the reach that troublemakers have, whether their actions are deliberate or accidental. Social media and the wider web changed the game for mischief-makers, and made it easier for the rest of us to be inadvertently hoodwinked online (see: the odd "Goodbye Meta AI" trend that I wrote about this week for the Guardian). The rise of generative AI since the release of ChatGPT in 2022 has also supercharged the risks. While early research suggests our biggest fears about the impact of AI-generated deepfakes on elections are unfounded, the overall information environment is a puzzling one.

When faced with a bit of downtime, many of my friends will turn to the same party game. It's based on the surrealist game Exquisite Corpse, and involves translating brief written descriptions into rapidly made drawings and back again. One group calls it Telephone Pictionary; another refers to it as Writey-Drawey. The internet tells me it is also called Eat Poop You Cat, a sequence of words surely inspired by one of the game's results. As recently as three years ago, it was rare to encounter text-to-image or image-to-text mistranslations in daily life, which made the outrageous outcomes of the game feel especially novel. But we have since entered a new era of image-making. With the aid of AI image generators like Dall-E 3, Stable Diffusion and Midjourney, and the generative features integrated into Adobe's Creative Cloud programs, you can now transform a sentence or phrase into a highly detailed image in mere seconds. Images, likewise, can be nearly instantly translated into descriptive text.

This paper presents a machine learning approach to classify countries as peaceful or non-peaceful using linguistic patterns extracted from global media articles. We employ vector embeddings and cosine similarity to develop a supervised classification model that effectively identifies peaceful countries. Additionally, we explore the impact of dataset size on model performance, investigating how shrinking the dataset influences classification accuracy. Our results highlight the challenges and opportunities associated with using large-scale text data for peace studies.

While large language models (LLMs) have seen unprecedented advancements in capabilities and applications across a variety of use-cases, safety alignment of these models is still an area of active research. The fragile nature of LLMs, even models that have undergone extensive alignment and safety training regimes, warrants additional safety steering steps via training-free, inference-time methods. While recent work in the area of mechanistic interpretability has investigated how activations in latent representation spaces may encode concepts, and thereafter performed representation engineering to induce such concepts in LLM outputs, the applicability of such for safety is relatively under-explored. Unlike recent inferencetime safety steering works, in this paper we explore safety steering of LLM outputs using: (i) category-specific steering vectors, thereby enabling fine-grained control over the steering, and (ii) sophisticated methods for extracting informative steering vectors for more effective safety steering while retaining quality of the generated text. We demonstrate our exploration on multiple LLMs and datasets, and showcase the effectiveness of the proposed steering method, along with a discussion on the implications and best practices. Content Warning: This paper contains examples of harmful language.

Comparing bridging annotations across coreference resources is difficult, largely due to a lack of standardization across definitions and annotation schemas and narrow coverage of disparate text domains across resources. To alleviate domain coverage issues and consolidate schemas, we compare guidelines and use interpretable predictive models to examine the bridging instances annotated in the GUM, GENTLE and ARRAU corpora. Examining these cases, we find that there is a large difference in types of phenomena annotated as bridging. Beyond theoretical results, we release a harmonized, subcategorized version of the test sets of GUM, GENTLE and the ARRAU Wall Street Journal data to promote meaningful and reliable evaluation of bridging resolution across domains.

Automatic sound classification has a wide range of applications in machine listening, enabling context-aware sound processing and understanding. This paper explores methodologies for automatically classifying heterogeneous sounds characterized by high intra-class variability. Our study evaluates the classification task using the Broad Sound Taxonomy, a two-level taxonomy comprising 28 classes designed to cover a heterogeneous range of sounds with semantic distinctions tailored for practical user applications. We construct a dataset through manual annotation to ensure accuracy, diverse representation within each class and relevance in real-world scenarios. We compare a variety of both traditional and modern machine learning approaches to establish a baseline for the task of heterogeneous sound classification. We investigate the role of input features, specifically examining how acoustically derived sound representations compare to embeddings extracted with pre-trained deep neural networks that capture both acoustic and semantic information about sounds. Experimental results illustrate that audio embeddings encoding acoustic and semantic information achieve higher accuracy in the classification task. After careful analysis of classification errors, we identify some underlying reasons for failure and propose actions to mitigate them. The paper highlights the need for deeper exploration of all stages of classification, understanding the data and adopting methodologies capable of effectively handling data complexity and generalizing in real-world sound environments.