In London last night, the 20th Bafta games awards celebrated a year that was stacked with critically acclaimed games. Taking place against the backdrop of an unprecedented year of layoffs and studio closures in the gaming industry, acknowledged by Bafta chair Sara Putt in her speech at the beginning of the evening, it was a much-needed night of recognition of the creative efforts of the video game development community. The sprawling Dungeons & Dragons-inspired role-playing game Baldur's Gate 3 won five awards, including the public voted EE players' choice award and best game, alongside music, narrative and best performer in a supporting role (won by Andrew Wincott for his role at the devilish Raphael). Nintendo picked up the family and multiplayer awards for the exuberant Super Mario Bros Wonder, and technical achievement for The Legend of Zelda: Tears of the Kingdom. Alan Wake 2, the arresting, idiosyncratic horror game from Finnish studio Remedy, won artistic achievement and audio achievement.

The Knowledge Graph Entity Typing (KGET) task aims to predict missing type annotations for entities in knowledge graphs. Recent works only utilize the \textit{\textbf{structural knowledge}} in the local neighborhood of entities, disregarding \textit{\textbf{semantic knowledge}} in the textual representations of entities, relations, and types that are also crucial for type inference. Additionally, we observe that the interaction between semantic and structural knowledge can be utilized to address the false-negative problem. In this paper, we propose a novel \textbf{\underline{S}}emantic and \textbf{\underline{S}}tructure-aware KG \textbf{\underline{E}}ntity \textbf{\underline{T}}yping~{(SSET)} framework, which is composed of three modules. First, the \textit{Semantic Knowledge Encoding} module encodes factual knowledge in the KG with a Masked Entity Typing task. Then, the \textit{Structural Knowledge Aggregation} module aggregates knowledge from the multi-hop neighborhood of entities to infer missing types. Finally, the \textit{Unsupervised Type Re-ranking} module utilizes the inference results from the two models above to generate type predictions that are robust to false-negative samples. Extensive experiments show that SSET significantly outperforms existing state-of-the-art methods.

This paper proposes a test to perform Thematic Analysis (TA) with Large Language Model (LLM) on data which is in a different language than English. While there has been initial promising work on using pre-trained LLMs for TA on data in English, we lack any tests on whether these models can reasonably perform the same analysis with good quality in other language. In this paper a test will be proposed using an open access dataset of semi-structured interviews in Italian. The test shows that a pre-trained model can perform such a TA on the data, also using prompts in Italian. A comparative test shows the model capacity to produce themes which have a good resemblance with those produced independently by human researchers. The main implication of this study is that pre-trained LLMs may thus be suitable to support analysis in multilingual situations, so long as the language is supported by the model used.

This paper presents a new approach to evaluating the quality of answers in political question-and-answer sessions. We propose to measure an answer's quality based on the degree to which it allows us to infer the initial question accurately. This conception of answer quality inherently reflects their relevance to initial questions. Drawing parallels with semantic search, we argue that this measurement approach can be operationalized by fine-tuning a large language model on the observed corpus of questions and answers without additional labeled data. We showcase our measurement approach within the context of the Question Period in the Canadian House of Commons. Our approach yields valuable insights into the correlates of the quality of answers in the Question Period. We find that answer quality varies significantly based on the party affiliation of the members of Parliament asking the questions and uncover a meaningful correlation between answer quality and the topics of the questions.

The proliferation of large language models (LLMs) has underscored concerns regarding their security vulnerabilities, notably against jailbreak attacks, where adversaries design jailbreak prompts to circumvent safety mechanisms for potential misuse. Addressing these concerns necessitates a comprehensive analysis of jailbreak prompts to evaluate LLMs' defensive capabilities and identify potential weaknesses. However, the complexity of evaluating jailbreak performance and understanding prompt characteristics makes this analysis laborious. We collaborate with domain experts to characterize problems and propose an LLM-assisted framework to streamline the analysis process. It provides automatic jailbreak assessment to facilitate performance evaluation and support analysis of components and keywords in prompts. Based on the framework, we design JailbreakLens, a visual analysis system that enables users to explore the jailbreak performance against the target model, conduct multi-level analysis of prompt characteristics, and refine prompt instances to verify findings. Through a case study, technical evaluations, and expert interviews, we demonstrate our system's effectiveness in helping users evaluate model security and identify model weaknesses.

While past work has started to tease out different actions that users and agents The conversational search task aims to enable a user to resolve perform and respond to during the conversational search process, information needs via natural language dialogue with there has been little work on formalizing these actions an agent. In this paper, we aim to develop a conceptual and decisions. Thus the goal of this paper is to develop a framework of the actions and intents of users and agents conceptual framework of different actions and intents, along explaining how these actions enable the user to explore the with the key decision points within the conversation. Our search space and resolve their information need. We outline aim is to make these tasks explicit in order to formalize the different actions and intents, before discussing key decision the research, development and evaluation of conversational points in the conversation where the agent needs to search agents. To this end, we first examine the key actions decide how to steer the conversational search process to a successful and intents identified in past work, and enumerate these and/or satisfactory conclusion. Essentially, this paper along with others that can be naturally inferred from a simulated provides a conceptualization of the conversational search process conversational context, before discussing the key decisions between an agent and user, which provides a framework that the agent needs to make in order to advance the and a starting point for research, development and evaluation conversation to a satisfactory or successful end. of conversational search agents.

Election deniers are mobilizing their supporters and rolling out new tech to disrupt the November election. These groups are already organizing on hyperlocal levels, and learning to monitor polling places, target election officials, and challenge voter rolls. And though their work was once fringe, its become mainstreamed in the Republican Party. Today on WIRED Politics Lab, we focus on what these groups are doing, and what this means for voters and the election workers already facing threats and harassment. Write to us at politicslab@wired.com. Our show is produced by produced by Jake Harper. Jake Lummus is our studio engineer and Amar Lal mixed this episode. Jordan Bell is the Executive Producer of Audio Development and Chris Bannon is Global Head of Audio at Conde Nast. Also be sure to subscribe to the WIRED Politics Lab newsletter here. You can always listen to this week's podcast through the audio player on this page, but if you want to subscribe for free to get every episode, here's how: If you're on an iPhone or iPad, open the app called Podcasts, or just tap this link. Leah Feiger: Welcome to WIRED Politics Lab, a show about how tech is changing politics. Today, we're going to talk about how election deniers are mobilizing their supporters and rolling out new tech to disrupt November.

Proving geometric theorems constitutes a hallmark of visual reasoning combining both intuitive and logical skills. Therefore, automated theorem proving of Olympiad-level geometry problems is considered a notable milestone in human-level automated reasoning. The introduction of AlphaGeometry, a neuro-symbolic model trained with 100 million synthetic samples, marked a major breakthrough. It solved 25 of 30 International Mathematical Olympiad (IMO) problems whereas the reported baseline based on Wu's method solved only ten. In this note, we revisit the IMO-AG-30 Challenge introduced with AlphaGeometry, and find that Wu's method is surprisingly strong. Wu's method alone can solve 15 problems, and some of them are not solved by any of the other methods. This leads to two key findings: (i) Combining Wu's method with the classic synthetic methods of deductive databases and angle, ratio, and distance chasing solves 21 out of 30 methods by just using a CPU-only laptop with a time limit of 5 minutes per problem. Essentially, this classic method solves just 4 problems less than AlphaGeometry and establishes the first fully symbolic baseline strong enough to rival the performance of an IMO silver medalist. (ii) Wu's method even solves 2 of the 5 problems that AlphaGeometry failed to solve. Thus, by combining AlphaGeometry with Wu's method we set a new state-of-the-art for automated theorem proving on IMO-AG-30, solving 27 out of 30 problems, the first AI method which outperforms an IMO gold medalist.

The mathematician Avi Wigderson has won the 2023 Turing award, often referred to as the Nobel prize for computing, for his work on understanding how randomness can shape and improve computer algorithms. Wigderson, who also won the prestigious Abel prize in 2021 for his mathematical contributions to computer science, was taken aback by the award. "The [Turing] committee fooled me into believing that we were going to have some conversation about collaborating," he says. "When I zoomed in, the whole committee was there and they told me. I was excited, surprised and happy."

Best practices for high conflict conversations like counseling or customer support almost always include recommendations to paraphrase the previous speaker. Although paraphrase classification has received widespread attention in NLP, paraphrases are usually considered independent from context, and common models and datasets are not applicable to dialog settings. In this work, we investigate paraphrases in dialog (e.g., Speaker 1: "That book is mine." becomes Speaker 2: "That book is yours."). We provide an operationalization of context-dependent paraphrases, and develop a training for crowd-workers to classify paraphrases in dialog. We introduce a dataset with utterance pairs from NPR and CNN news interviews annotated for context-dependent paraphrases. To enable analyses on label variation, the dataset contains 5,581 annotations on 600 utterance pairs. We present promising results with in-context learning and with token classification models for automatic paraphrase detection in dialog.