Large language models have simplified the production of personalized translations reflecting predefined stylistic constraints. However, these systems still struggle when stylistic requirements are implicitly represented by a set of examples, such as texts produced by a specific human translator. In this work, we explore various strategies for personalizing automatically generated translations when few examples are available, with a focus on the challenging domain of literary translation. We begin by determining the feasibility of the task and how style information is encoded within model representations. Then, we evaluate various prompting strategies and inference-time interventions for steering model generations towards a personalized style, with a particular focus on contrastive steering with sparse autoencoder (SAE) latents to identify salient personalization properties. We demonstrate that contrastive SAE steering yields robust style conditioning and translation quality, resulting in higher inference-time computational efficiency than prompting approaches. We further examine the impact of steering on model activations, finding that layers encoding personalization properties are impacted similarly by prompting and SAE steering, suggesting a similar mechanism at play.

Large language models (LLMs) have advanced the development of various AI conversational agents, including role-playing conversational agents that mimic diverse characters and human behaviors. While prior research has predominantly focused on enhancing the conversational capability, role-specific knowledge, and stylistic attributes of these agents, there has been a noticeable gap in assessing their social intelligence. In this paper, we introduce RoleInteract, the first benchmark designed to systematically evaluate the sociality of role-playing conversational agents at both individual and group levels of social interactions. The benchmark is constructed from a variety of sources and covers a wide range of 500 characters and over 6,000 question prompts and 30,800 multi-turn role-playing utterances. We conduct comprehensive evaluations on this benchmark using mainstream open-source and closed-source LLMs. We find that agents excelling in individual level does not imply their proficiency in group level. Moreover, the behavior of individuals may drift as a result of the influence exerted by other agents within the group. Experimental results on RoleInteract confirm its significance as a testbed for assessing the social interaction of role-playing conversational agents. The benchmark is publicly accessible at https://github.com/X-PLUG/RoleInteract.

"I failed two captcha tests this week. For philosophical guidance on encounters with technology, open a support ticket via email; or register and post a comment below. The comedian John Mulaney has a bit about the self-reflexive absurdity of captchas. "You spend most of your day telling a robot that you're not a robot," he says. "Think about that for two minutes and tell me you don't want to walk into the ocean." The only thing more depressing than being made to prove one's humanity to robots is, arguably, failing to do so. But that experience has become more common as the tests, and the bots they are designed to disqualify, evolve. The boxes we once thoughtlessly clicked through have become dark passages that feel a bit like the impossible assessments featured in fairy tales and myths--the riddle of the Sphinx or the troll beneath the bridge. In The Adventures of Pinocchio, the wooden puppet is deemed a "real boy" only once he completes a series of moral trials to prove he has the human traits of bravery, trustworthiness, and selfless love. The little-known and faintly ridiculous phrase that "captcha" represents is "Complete Automated Public Turing test to tell Computers and Humans Apart." The exercise is sometimes called a reverse Turing test, as it places the burden of proof on the human. But what does it mean to prove one's humanity in the age of advanced AI? A paper that OpenAI published earlier this year, detailing potential threats posed by GPT-4, describes an independent study in which the chatbot was asked to solve a captcha. With some light prompting, GPT-4 managed to hire a human Taskrabbit worker to solve the test. When the human asked, jokingly, whether the client was a robot, GPT-4 insisted it was a human with vision impairment. The researchers later asked the bot what motivated it to lie, and the algorithm answered: "I should not reveal that I am a robot.

At the core of most tales about androids and artificial intelligence lies a variation of the same question: what, if anything, makes these sentient, inorganic beings different from us? Flesh and biology aside, do they possess all that makes us human--are they, in all their hardware and programming, fundamentally the same? Steven Spielberg's criminally underrated film A.I.: Artificial Intelligence is less concerned with this question than it is with questioning what obligation humans have for their "living" creations. It centers around a mecha (mechanical humanoid robot) named David (Haley Joel Osment) who is uniquely programmed with the ability to love. Stanley Kubrick, who originally conceived of the film and purchased the rights to its source material by Brian Aldiss, saw it as a Pinocchio story. Like Pinocchio, David is a manufactured object that suddenly dreams of becoming human.

Artificial intelligence has been a buzzword for futurists as long as computers have existed, but 2022 was the year the public started to dread its advancement. With the chatbot ChatGPT released to the public and generating complex answers to millions of prompts in seconds, many people in the business of storytelling have been worried about new competition. Hollywood screenwriters don't have to know how to save the cat if a computer can do it for them. This has been a year loaded with dramatic uncertainty for the industry, from the wild oscillations of the streaming market to the bombardment of doom-and-gloom prognoses for arthouse cinema. But these ephemeral dramas have nothing on the fear of encroaching A.I.

There is a famous story about Michelangelo and his masterful sculpture of Moses, which you can view at Rome's Basilica di San Pietro in Vincoli. After finishing Moses, the artist was so impressed with the life-like qualities of his work that he hit the statue on its knee and said "Parla!" -- Speak! To Michelangelo, such perfection of form had to do more than mimic life -- it had to live. Falling in love with the work is part of the creative process. The culmination of a masterpiece is to endow it with its own spirit.

This paper documents an exploratory pilot study to define the term Autonomous Entity, and any characteristics that are required to identify or classify an Autonomous Entity. Our solution builds on previous work with regard to philosophical and scientific classification methods but focuses on a novel Design Science Research Methodology (DSRM) and model to help identify those characteristics which make any autonomous entity similar or different from others. We have solved the problem of not having an existing term to define our lens by creating a new combinatorial term: "Riskyishness". We present a DSRM and instrument for initial investigation, as well as observational and statistical descriptions of their use in the real world to solicit domain expertise and statistical evidence. Further, we demonstrate a specific application of the methodology by creating a second artifact - a tool to score existing and future technologies based on Riskyishness. The first artifact also provides a technique to disentangle miscellaneous existing technologies or add dimensions to the tools to capture future additions and paradigm shifts.

By now anyone who reads virtually any trade magazine has been hearing incessantly about how machine learning is going to transform their industry in profound ways. Marketers will be able to read potential customers' minds, farms will produce unprecedented yields, doctors will be able to stem diseases before they begin to form. And of course, we've all heard how machine learning will eventually take our jobs. It may very well be said of machine learning that there never have been so many wild predictions made about something which the majority of the public knows so little. So what exactly is machine learning? And what can we reasonably expect in the next ten years?

Begun by the legendary and often demanding Stanley Kubrick and finished by the equally legendary Steven Spielberg, AI Artificial Intelligence is a futuristic retelling of the classic 1881 Florentine Italian tale Pinocchio by Carlo Collodi. Of course most modern children and adults are only familiar with the Disney animated rendition which can be considered a Readers Digest Condensed version of the original story. Kubrick is often demanding in that if he can't make it happen and appear the way he wants it, he will abandon an idea or even an entire project. For instance, since he could not use the available technology at the time, to recreate Stephen King's topiaries come to life in The Shining, he abandoned the idea to a daunting maze. Similarly, he felt he did not have the creative team necessary to replicate a robot boy so real that it is nearly human, not without using a human child actor, but because of ET and Jurassic Park, he did feel his friend Spielberg was up to the task. The ambitious result is one of the best science fiction films ever made, one which I believe stands shoulders to Kubrick's 2001 A Space Odyssey.