Exact unlearning was first introduced as a privacy mechanism that allowed a user to retract their data from machine learning models on request. Shortly after, inexact schemes were proposed to mitigate the impractical costs associated with exact unlearning. More recently unlearning is often discussed as an approach for removal of impermissible knowledge i.e. knowledge that the model should not possess such as unlicensed copyrighted, inaccurate, or malicious information. The promise is that if the model does not have a certain malicious capability, then it cannot be used for the associated malicious purpose. In this paper we revisit the paradigm in which unlearning is used for in Large Language Models (LLMs) and highlight an underlying inconsistency arising from in-context learning. Unlearning can be an effective control mechanism for the training phase, yet it does not prevent the model from performing an impermissible act during inference. We introduce a concept of ununlearning, where unlearned knowledge gets reintroduced in-context, effectively rendering the model capable of behaving as if it knows the forgotten knowledge. As a result, we argue that content filtering for impermissible knowledge will be required and even exact unlearning schemes are not enough for effective content regulation. We discuss feasibility of ununlearning for modern LLMs and examine broader implications.

This paper presents a generative artificial intelligence approach to probabilistic forecasting of electricity market signals, such as real-time locational marginal prices and area control error signals. Inspired by the Wiener-Kallianpur innovation representation of nonparametric time series, we propose a weak innovation autoencoder architecture and a novel deep learning algorithm that extracts the canonical independent and identically distributed innovation sequence of the time series, from which samples of future time series are generated. The validity of the proposed approach is established by proving that, under ideal training conditions, the generated samples have the same conditional probability distribution as that of the ground truth. Three applications involving highly dynamic and volatile time series in real-time market operations are considered: (i) locational marginal price forecasting for self-scheduled resources such as battery storage participants, (ii) interregional price spread forecasting for virtual bidders in interchange markets, and (iii) area control error forecasting for frequency regulations. Numerical studies based on market data from multiple independent system operators demonstrate the superior performance of the proposed generative forecaster over leading classical and modern machine learning techniques under both probabilistic and point forecasting metrics.

The recent proliferation of generative artificial intelligence (AI) technologies such as pre-trained large language models (LLMs) has opened up new frontiers in computational law. An exciting area of development is the use of AI to automate the deductive rule-based reasoning inherent in statutory and contract law. This paper argues that such automated deductive legal reasoning can now be viewed from the lens of software engineering, treating LLMs as interpreters of natural-language programs with natural-language inputs. We show how it is possible to apply principled software engineering techniques to enhance AI-driven legal reasoning of complex statutes and to unlock new applications in automated meta-reasoning such as mutation-guided example generation and metamorphic property-based testing.

Silicon Valley appears, once again, to be getting the better of America's newspapers and magazines. Tech companies are injecting every corner of the web with AI language models, which may pose an existential threat to journalism as we currently know it. After all, why go to a media outlet if ChatGPT can deliver the information you think you need? A growing number of media companies--the publishers of The Wall Street Journal, Business Insider, New York, Politico, The Atlantic, and many others--have signed licensing deals with OpenAI that will formally allow the start-up's AI models to incorporate recent partner articles into their responses. OpenAI is just the beginning, and such deals may soon be standard for major media companies: Perplexity, which runs a popular AI-powered search engine, has had conversations with various publishers (including The Atlantic's business division) about a potential ad-revenue-sharing arrangement, the start-up's chief business officer, Dmitry Shevelenko, told me yesterday.

OpenAI's abrupt move to ban access to its services in China is setting the scene for an industry shakeup, as local AI leaders from Baidu Inc. to Alibaba Group Holding Ltd. move to grab more of the field. The ChatGPT creator this week sent memos to Chinese users warning it will cut off access to its widely used AI development software and tools from July, triggering a scramble to fill the void. Since Tuesday, at least a half-dozen companies and startups including Tencent Holdings Ltd. and Zhipu AI began offering incentives to developers making the switch. OpenAI's shift will accentuate the divide between China and the U.S., which is trying to curb Beijing's AI and chip efforts. While the startup's exit offers an opportunity for sector leaders to grow their user base, it also deprives entrepreneurs and cash-strapped startups of some of the best tools available to fine-tune or get their AI applications off the ground.

OpenAI first added the ability for ChatGPT to speak in a one of several synthetic voices, or "personas," late last year. The demo in May used one of those voices to show off a newer, more capable AI system called GPT-4o that saw the chatbot speak in expressive tones, respond to a person's tone of voice and facial expressions, and have more complex conversations. One of the voices, which OpenAI called Sky, resembles the voice of an AI bot played by Johansson in the 2013 movie "Her," about a lonely man who falls in love with his AI assistant.

As generative Artificial Intelligence (genAI) technologies proliferate across sectors, they offer significant benefits but also risk exacerbating discrimination. This chapter explores how genAI intersects with non-discrimination laws, identifying shortcomings and suggesting improvements. It highlights two main types of discriminatory outputs: (i) demeaning and abusive content and (ii) subtler biases due to inadequate representation of protected groups, which may not be overtly discriminatory in individual cases but have cumulative discriminatory effects. For example, genAI systems may predominantly depict white men when asked for images of people in important jobs. This chapter examines these issues, categorizing problematic outputs into three legal categories: discriminatory content; harassment; and legally hard cases like unbalanced content, harmful stereotypes or misclassification. It argues for holding genAI providers and deployers liable for discriminatory outputs and highlights the inadequacy of traditional legal frameworks to address genAI-specific issues. The chapter suggests updating EU laws, including the AI Act, to mitigate biases in training and input data, mandating testing and auditing, and evolving legislation to enforce standards for bias mitigation and inclusivity as technology advances.

This research introduces an innovative mathematical learning approach that integrates generative AI to cultivate a structured learning rather than quick solution. Our method combines chatbot capabilities and generative AI to offer interactive problem-solving exercises, enhancing learning through a stepby-step approach for varied problems, advocating for the responsible use of AI in education. Our approach emphasizes that immediate answers from ChatGPT can impede real learning. We introduce a reward-based system that requires students to solve mathematical problems effectively to receive the final answer. This encourages a progressive learning path from basic to complex problems, rewarding mastery with final solutions. The goal is to transition students from seeking quick fixes to engaging actively in a comprehensive learning experience.

Since the release of ChatGPT in November 2022 [61], GenAI has become increasingly popular in assisting people with written, auditory, and visual tasks [45, 58, 78]. In research, GenAI offers a new approach to manuscript writing, as it can handle tasks ranging from text improvement suggestions to speech-to-text translation and even crafting initial drafts [45, 52]. Its ability to understand context and generate human-like and grammatically accurate responses fosters innovative brainstorming and enhances the quality and readability of research publications [5]. However, along with GenAI's potential to augment research activities, concerns about transparency, academic integrity, and the urgency of maintaining the credibility of research work have emerged [21, 54, 73, 78]. Despite the growing interest in using GenAI for manuscript writing and research activities [45, 64], many researchers hesitate to acknowledge its use in their papers. This is illustrated by several instances where research publications with undisclosed GenAI use were identified by readers (e.g., [53, 71, 72, 79]). Studies have identified the phenomenon of AI aversion, where AI-generated content, even if factual, is often perceived as inaccurate and misleading [12, 56] and disclosing its use can negatively impact readers' satisfaction and perception of the authors' qualifications and effort [69]. Therefore, researchers' hesitancy is partly due to their fear that acknowledging GenAI use might damage

We present ConvoCache, a conversational caching system that solves the problem of slow and expensive generative AI models in spoken chatbots. ConvoCache finds a semantically similar prompt in the past and reuses the response. In this paper we evaluate ConvoCache on the DailyDialog dataset. We find that ConvoCache can apply a UniEval coherence threshold of 90% and respond to 89% of prompts using the cache with an average latency of 214ms, replacing LLM and voice synthesis that can take over 1s. To further reduce latency we test prefetching and find limited usefulness. Prefetching with 80% of a request leads to a 63% hit rate, and a drop in overall coherence. ConvoCache can be used with any chatbot to reduce costs by reducing usage of generative AI by up to 89%.