There is a wide variety of methods, tools and resources for processing text in the English language. However this is not the case for the Greek language even though it has a long documented history spanning at least 3,400 years of written records (including texts in syllabic script), and 28 centuries (Archaic period - new) of written text with alphabet [1, 2]. The over 2500 years literary tradition of Greek is also notable. To aid those that are interested in using, developing or advancing the techniques for Greek processing, in this paper we survey related works and resources organized in categories. We hope this collection and categorization of works to be useful for students and researchers interested in NLP tasks, Information Retrieval and Knowledge Management for the Greek language.

A "match cut" is a common video editing technique where a pair of shots that have a similar composition transition fluidly from one to another. Although match cuts are often visual, certain match cuts involve the fluid transition of audio, where sounds from different sources merge into one indistinguishable transition between two shots. In this paper, we explore the ability to automatically find and create "audio match cuts" within videos and movies. We create a self-supervised audio representation for audio match cutting and develop a coarse-to-fine audio match pipeline that recommends matching shots and creates the blended audio. We further annotate a dataset for the proposed audio match cut task and compare the ability of multiple audio representations to find audio match cut candidates. Finally, we evaluate multiple methods to blend two matching audio candidates with the goal of creating a smooth transition. Project page and examples are available at: https://denfed.github.io/audiomatchcut/

While previous chapters focused on recommendation systems (RSs) based on standardized, non-verbal user feedback such as purchases, views, and clicks -- the advent of LLMs has unlocked the use of natural language (NL) interactions for recommendation. This chapter discusses how LLMs' abilities for general NL reasoning present novel opportunities to build highly personalized RSs -- which can effectively connect nuanced and diverse user preferences to items, potentially via interactive dialogues. To begin this discussion, we first present a taxonomy of the key data sources for language-driven recommendation, covering item descriptions, user-system interactions, and user profiles. We then proceed to fundamental techniques for LLM recommendation, reviewing the use of encoder-only and autoregressive LLM recommendation in both tuned and untuned settings. Afterwards, we move to multi-module recommendation architectures in which LLMs interact with components such as retrievers and RSs in multi-stage pipelines. This brings us to architectures for conversational recommender systems (CRSs), in which LLMs facilitate multi-turn dialogues where each turn presents an opportunity not only to make recommendations, but also to engage with the user in interactive preference elicitation, critiquing, and question-answering.

Existing work on pitch and timbre disentanglement has been mostly focused on single-instrument music audio, excluding the cases where multiple instruments are presented. To fill the gap, we propose DisMix, a generative framework in which the pitch and timbre representations act as modular building blocks for constructing the melody and instrument of a source, and the collection of which forms a set of per-instrument latent representations underlying the observed mixture. By manipulating the representations, our model samples mixtures with novel combinations of pitch and timbre of the constituent instruments. We can jointly learn the disentangled pitch-timbre representations and a latent diffusion transformer that reconstructs the mixture conditioned on the set of source-level representations. We evaluate the model using both a simple dataset of isolated chords and a realistic four-part chorales in the style of J.S. Bach, identify the key components for the success of disentanglement, and demonstrate the application of mixture transformation based on source-level attribute manipulation.

In-context learning (ICL) has proven to be a significant capability with the advancement of Large Language models (LLMs). By instructing LLMs using few-shot demonstrative examples, ICL enables them to perform a wide range of tasks without needing to update millions of parameters. This paper presents a unified framework for LLMs that allows them to self-select influential in-context examples to compose their contexts; self-rank candidates with different demonstration compositions; self-optimize the demonstration selection and ordering through reinforcement learning. Specifically, our method designs a parameter-efficient retrieval head that generates the optimized demonstration after training with rewards from LLM's own preference. Experimental results validate the proposed method's effectiveness in enhancing ICL performance. Additionally, our approach effectively identifies and selects the most representative examples for the current task, and includes more diversity in retrieval.

In current web environment, fake news spreads rapidly across online social networks, posing serious threats to society. Existing multimodal fake news detection (MFND) methods can be classified into knowledge-based and semantic-based approaches. However, these methods are overly dependent on human expertise and feedback, lacking flexibility. To address this challenge, we propose a Dynamic Analysis and Adaptive Discriminator (DAAD) approach for fake news detection. For knowledge-based methods, we introduce the Monte Carlo Tree Search (MCTS) algorithm to leverage the self-reflective capabilities of large language models (LLMs) for prompt optimization, providing richer, domain-specific details and guidance to the LLMs, while enabling more flexible integration of LLM comment on news content. For semantic-based methods, we define four typical deceit patterns: emotional exaggeration, logical inconsistency, image manipulation, and semantic inconsistency, to reveal the mechanisms behind fake news creation. To detect these patterns, we carefully design four discriminators and expand them in depth and breadth, using the soft-routing mechanism to explore optimal detection models. Experimental results on three real-world datasets demonstrate the superiority of our approach. The code will be available at: https://github.com/SuXinqi/DAAD.

Knowledge graph completion (KGC) aims to identify missing triples in a knowledge graph (KG). This is typically achieved through tasks such as link prediction and instance completion. However, these methods often focus on either static knowledge graphs (SKGs) or temporal knowledge graphs (TKGs), addressing only within-scope triples. This paper introduces a new generative completion framework called Generative Subgraph-based KGC (GS-KGC). GS-KGC employs a question-answering format to directly generate target entities, addressing the challenge of questions having multiple possible answers. We propose a strategy that extracts subgraphs centered on entities and relationships within the KG, from which negative samples and neighborhood information are separately obtained to address the one-to-many problem. Our method generates negative samples using known facts to facilitate the discovery of new information. Furthermore, we collect and refine neighborhood path data of known entities, providing contextual information to enhance reasoning in large language models (LLMs). Our experiments evaluated the proposed method on four SKGs and two TKGs, achieving state-of-the-art Hits@1 metrics on five datasets. Analysis of the results shows that GS-KGC can discover new triples within existing KGs and generate new facts beyond the closed KG, effectively bridging the gap between closed-world and open-world KGC.

To assist human fact-checkers, researchers have developed automated approaches for visual misinformation detection. These methods assign veracity scores by identifying inconsistencies between the image and its caption, or by detecting forgeries in the image. However, they neglect a crucial point of the human fact-checking process: identifying the original meta-context of the image. By explaining what is actually true about the image, fact-checkers can better detect misinformation, focus their efforts on check-worthy visual content, engage in counter-messaging before misinformation spreads widely, and make their explanation more convincing. Here, we fill this gap by introducing the task of automated image contextualization. We create 5Pils, a dataset of 1,676 fact-checked images with question-answer pairs about their original meta-context. Annotations are based on the 5 Pillars fact-checking framework. We implement a first baseline that grounds the image in its original meta-context using the content of the image and textual evidence retrieved from the open web. Our experiments show promising results while highlighting several open challenges in retrieval and reasoning. We make our code and data publicly available.

Former FBI Special Agent Nicole Parker joins'Cavuto Live' to weigh in on the cancellation of the Taylor Swift concerts in Vienna due to a terror plot. Former President Trump promoted images on Sunday, including some generated through artificial intelligence, showing apparent support from singer Taylor Swift and her fans, triggering a widespread media outcry. Trump posted a collage of Swift-related images to his Truth Social account showing apparent support from the pop star and her diehard fans known as "Swifties." One doctored image played off the classic Uncle Sam recruiting posters, showing Swift in red, white and blue with the caption, "Taylor Swift Wants You To Vote For Donald Trump." Over the images, he wrote, "I accept!"

Former president Donald Trump has shared AI-generated images that falsely claim Taylor Swift fans are supporting his campaign. In a post on Truth Social, Trump shared screenshots of four posts on X that purport to show a number of young women all wearing "Swifties for Trump" T-shirts in a variety of styles. One of the screenshots claimed that Swifties are supporting Trump now after Taylor Swift canceled her concert in Vienna due to security concerns. Another image included the phrase "Taylor wants you to vote for Donald Trump." "I accept!" Trump captioned his post. However, Trump's post appears to contain a mixture of real and AI-generated images that falsely suggest a widespread and coordinated movement of Swifties for Trump.