Despite advances in AI alignment, language models (LM) remain vulnerable to adversarial attacks or jailbreaking, in which adversaries modify input prompts to induce harmful behavior. While some defenses have been proposed, they focus on narrow threat models and fall short of a strong defense, which we posit should be effective, universal, and practical. To achieve this, we propose the first adversarial objective for defending LMs against jailbreaking attacks and an algorithm, robust prompt optimization (RPO), that uses gradient-based token optimization to enforce harmless outputs. This results in an easily accessible suffix that significantly improves robustness to both jailbreaks seen during optimization and unknown, held-out jailbreaks, reducing the attack success rate on Starling-7B from 84% to 8.66% across 20 jailbreaks. In addition, we find that RPO has a minor effect on benign use, is successful under adaptive attacks, and can transfer to black-box models, reducing the success rate of the strongest attack on GPT-4, GUARD, from 92% to 6%.

This study explores linguistic differences between human and LLM-generated dialogues, using 19.5K dialogues generated by ChatGPT-3.5 as a companion to the EmpathicDialogues dataset. The research employs Linguistic Inquiry and Word Count (LIWC) analysis, comparing ChatGPT-generated conversations with human conversations across 118 linguistic categories. Results show greater variability and authenticity in human dialogues, but ChatGPT excels in categories such as social processes, analytical style, cognition, attentional focus, and positive emotional tone, reinforcing recent findings of LLMs being "more human than human." However, no significant difference was found in positive or negative affect between ChatGPT and human dialogues. Classifier analysis of dialogue embeddings indicates implicit coding of the valence of affect despite no explicit mention of affect in the conversations. The research also contributes a novel, companion ChatGPT-generated dataset of conversations between two independent chatbots, which were designed to replicate a corpus of human conversations available for open access and used widely in AI research on language modeling. Our findings increase understanding of ChatGPT's linguistic capabilities and inform ongoing efforts to distinguish between human and LLM-generated text, which is critical in detecting AI-generated fakes, misinformation, and disinformation.

Most NLP tasks are modeled as supervised learning and thus require labeled training data to train effective models. However, manually producing such data at sufficient quality and quantity is known to be costly and time-intensive. Current research addresses this bottleneck by exploring a novel paradigm called zero-shot learning via dataset generation. Here, a powerful LLM is prompted with a task description to generate labeled data that can be used to train a downstream NLP model. For instance, an LLM might be prompted to "generate 500 movie reviews with positive overall sentiment, and another 500 with negative sentiment." The generated data could then be used to train a binary sentiment classifier, effectively leveraging an LLM as a teacher to a smaller student model. With this demo, we introduce Fabricator, an open-source Python toolkit for dataset generation. Fabricator implements common dataset generation workflows, supports a wide range of downstream NLP tasks (such as text classification, question answering, and entity recognition), and is integrated with well-known libraries to facilitate quick experimentation. With Fabricator, we aim to support researchers in conducting reproducible dataset generation experiments using LLMs and help practitioners apply this approach to train models for downstream tasks.

Misinformation, propaganda, and outright lies proliferate on the web, with some narratives having dangerous real-world consequences on public health, elections, and individual safety. However, despite the impact of misinformation, the research community largely lacks automated and programmatic approaches for tracking news narratives across online platforms. In this work, utilizing daily scrapes of 1,334 unreliable news websites, the large-language model MPNet, and DP-Means clustering, we introduce a system to automatically identify and track the narratives spread within online ecosystems. Identifying 52,036 narratives on these 1,334 websites, we describe the most prevalent narratives spread in 2022 and identify the most influential websites that originate and amplify narratives. Finally, we show how our system can be utilized to detect new narratives originating from unreliable news websites and to aid fact-checkers in more quickly addressing misinformation. We release code and data at https://github.com/hanshanley/specious-sites.

Ricardo Santiago, director at Diamond Behavioral Health, tells Fox News Digital about the'One Week No Booze' trend and how it could impact relationship with alcohol. In a significant blow to TikTok, Universal Music Group (UMG) has initiated the removal of its extensive music catalog from the platform, impacting global superstars such as Taylor Swift, Drake and Olivia Rodrigo. This drastic action comes as a result of failed negotiations to renew the licensing agreement that allowed TikTok to feature music from some of the biggest names in the industry. TAYLOR SWIFT IS THE LATEST HIGH-PROFILE DEEPFAKE VICTIM. HERE'S WHAT LAWMAKERS ARE DOING TO PROTECT THEM The discord between the two giants centers on several critical issues, including financial compensation for artists and songwriters, the handling of AI-generated music, and measures to ensure online safety, safeguarding against hate speech, bigotry, bullying, and harassment.

Heritage Foundation tech policy director Kara Frederick joins'America's Newsroom' to discuss pornographic AI photos of Taylor Swift sparking conversations about deepfake regulation. Even before pornographic and violent deepfake images of Taylor Swift began widely circulating in the past few days, state lawmakers across the U.S. had been searching for ways to quash such nonconsensual images of both adults and children. But in this Taylor-centric era, the problem has been getting a lot more attention since she was targeted through deepfakes, the computer-generated images using artificial intelligence to seem real. Here are things to know about what states have done and what they are considering. HOUSE LAWMAKERS TO SHINE LIGHT ON HOW AI CAN MAKE CONGRESS'MORE EFFICIENT' Artificial intelligence hit the mainstream last year like never before, enabling people to create ever-more realistic deepfakes.

Artificial Intelligence (AI) is proliferating throughout society, but so too are calls for practicing Responsible AI.4 The ACM Code of Ethics and Professional Conduct states computing professionals should contribute to society and human well-being (General Ethical Principle 1.1), but it can be difficult for a computer scientist to judge the impacts of a particular application in all fields. AI is influencing a range of social domains from law and medicine to journalism, government, and education. Technologists do not just need to make the technology work and scale it up, they must make it work while also being responsible for a host of societal, ethical, legal, and other human-centered concerns in these domains.11 There is no shortcut to becoming an expert social scientist, ethicist, or legal scholar.

Yet an AI investment tool may simply reflect all of the thinking errors and poor judgements of its developers. More than that, it may lose the benefit of intuitive experience and rapid reaction when unprecedented events strike in the future, such as the financial crash, and the Covid pandemic. Very few humans could create AI algorithms to cope with those massive events.

Due to strong capabilities in conducting fluent, multi-turn conversations with users, Large Language Models (LLMs) have the potential to further improve the performance of Conversational Recommender System (CRS). Unlike the aimless chit-chat that LLM excels at, CRS has a clear target. So it is imperative to control the dialogue flow in the LLM to successfully recommend appropriate items to the users. Furthermore, user feedback in CRS can assist the system in better modeling user preferences, which has been ignored by existing studies. However, simply prompting LLM to conduct conversational recommendation cannot address the above two key challenges. In this paper, we propose Multi-Agent Conversational Recommender System (MACRS) which contains two essential modules. First, we design a multi-agent act planning framework, which can control the dialogue flow based on four LLM-based agents. This cooperative multi-agent framework will generate various candidate responses based on different dialogue acts and then choose the most appropriate response as the system response, which can help MACRS plan suitable dialogue acts. Second, we propose a user feedback-aware reflection mechanism which leverages user feedback to reason errors made in previous turns to adjust the dialogue act planning, and higher-level user information from implicit semantics. We conduct extensive experiments based on user simulator to demonstrate the effectiveness of MACRS in recommendation and user preferences collection. Experimental results illustrate that MACRS demonstrates an improvement in user interaction experience compared to directly using LLMs.

The outfit generation problem involves recommending a complete outfit to a user based on their interests. Existing approaches focus on recommending items based on anchor items or specific query styles but do not consider customer interests in famous characters from movie, social media, etc. In this paper, we define a new Character-based Outfit Generation (COG) problem, designed to accurately interpret character information and generate complete outfit sets according to customer specifications such as age and gender. To tackle this problem, we propose a novel framework LVA-COG that leverages Large Language Models (LLMs) to extract insights from customer interests (e.g., character information) and employ prompt engineering techniques for accurate understanding of customer preferences. Additionally, we incorporate text-to-image models to enhance the visual understanding and generation (factual or counterfactual) of cohesive outfits. Our framework integrates LLMs with text-to-image models and improves the customer's approach to fashion by generating personalized recommendations. With experiments and case studies, we demonstrate the effectiveness of our solution from multiple dimensions.