Our study presents a multifaceted approach to enhancing user interaction and content relevance in social media platforms through a federated learning framework. We introduce personalized GPT and Context-based Social Media LLM models, utilizing federated learning for privacy and security. Four client entities receive a base GPT-2 model and locally collected social media data, with federated aggregation ensuring up-to-date model maintenance. Subsequent modules focus on categorizing user posts, computing user persona scores, and identifying relevant posts from friends' lists. A quantifying social engagement approach, coupled with matrix factorization techniques, facilitates personalized content suggestions in real-time. An adaptive feedback loop and readability score algorithm also enhance the quality and relevance of content presented to users. Our system offers a comprehensive solution to content filtering and recommendation, fostering a tailored and engaging social media experience while safeguarding user privacy.

End-to-end robot learning, particularly for long-horizon tasks, often results in unpredictable outcomes and poor generalization. To address these challenges, we propose a novel Therblig-based Backbone Framework (TBBF) to enhance robot task understanding and transferability. This framework uses therbligs (basic action elements) as the backbone to decompose high-level robot tasks into elemental robot configurations, which are then integrated with current foundation models to improve task understanding. The approach consists of two stages: offline training and online testing. During the offline training stage, we developed the Meta-RGate SynerFusion (MGSF) network for accurate therblig segmentation across various tasks. In the online testing stage, after a one-shot demonstration of a new task is collected, our MGSF network extracts high-level knowledge, which is then encoded into the image using Action Registration (ActionREG). Additionally, the Large Language Model (LLM)-Alignment Policy for Visual Correction (LAP-VC) is employed to ensure precise action execution, facilitating trajectory transfer in novel robot scenarios. Experimental results validate these methods, achieving 94.37% recall in therblig segmentation and success rates of 94.4% and 80% in real-world online robot testing for simple and complex scenarios, respectively. Supplementary material is available at: https://sites.google.com/view/therbligsbasedbackbone/home

Traditional base station siting (BSS) methods rely heavily on drive testing and user feedback, which are laborious and require extensive expertise in communication, networking, and optimization. As large language models (LLMs) and their associated technologies advance, particularly in the realms of prompt engineering and agent engineering, network optimization will witness a revolutionary approach. This approach entails the strategic use of well-crafted prompts to infuse human experience and knowledge into these sophisticated LLMs, and the deployment of autonomous agents as a communication bridge to seamlessly connect the machine language based LLMs with human users using natural language. This integration represents the future paradigm of artificial intelligence (AI) as a service and AI for more ease. As a preliminary exploration, this research first develops a novel LLM-empowered BSS optimization framework, and heuristically proposes four different potential implementations: the strategies based on Prompt-optimized LLM (PoL), human-in-the-Loop LLM (HiLL), LLM-empowered autonomous BSS agent (LaBa), and Cooperative multiple LLM-based autonomous BSS agents (CLaBa). Through evaluation on real-world data, the experiments demonstrate that prompt-assisted LLMs and LLM-based agents can generate more efficient, cost-effective, and reliable network deployments, noticeably enhancing the efficiency of BSS optimization and reducing trivial manual participation.

The ability of Large Language Models (LLMs) to generate structured outputs, such as JSON, is crucial for their use in Compound AI Systems. However, evaluating and improving this capability remains challenging. In this work, we introduce StructuredRAG, a benchmark of six tasks designed to assess LLMs' proficiency in following response format instructions. We evaluate two state-of-the-art LLMs, Gemini 1.5 Pro and Llama 3 8B-instruct with 4-bit quantization using two distinct prompting strategies. We introduce these prompting strategies as f-String and Follow the Format (FF) prompting. Across 24 experiments, we find an average success rate of 82.55%. We further find a high variance in performance across tasks, models, and prompting strategies with success rates ranging from 0 to 100%. We find that Llama 3 8B-instruct often performs competitively with Gemini 1.5 Pro. We observe that task complexity significantly influences performance, with tasks involving lists or composite object outputs proving more challenging. Our findings highlight the need for further research into improving the reliability and consistency of structured output generation in LLMs. We have open-sourced our experimental code and results at github.com/weaviate/structured-rag.

Computer programming initially required humans to directly translate their goals into machine code. These goals could have easily been expressed as a written (or human) language directive. Computers, however, had no capacity to satisfactorily interpret written language. Large language model's provide exactly this capability; automatic generation of computer programs or even assembly code from written language directives. This research examines dynamic code execution of written language directives within the context of a running application. It implements a text editor whose business logic is purely backed by large language model prompts. That is, the program's execution uses prompts and written language directives to dynamically generate application logic at the point in time it is needed. The research clearly shows how written language directives, backed by a large language model, offer radically new programming and operating system paradigms. For example, empowerment of users to directly implement requirements via written language directives, thus supplanting the need for a team ofprogrammers, a release schedule and the like. Or, new security mechanisms where static executables, always a target for reverse engineering or fuzzing, no longer exist. They are replaced by ephemeral executables that may continually change, be completely removed, and are easily updated.

Generating fair and accurate predictions plays a pivotal role in deploying large language models (LLMs) in the real world. However, existing debiasing methods inevitably generate unfair or incorrect predictions as they are designed and evaluated to achieve parity across different social groups but leave aside individual commonsense facts, resulting in modified knowledge that elicits unreasonable or undesired predictions. In this paper, we first establish a new bias mitigation benchmark, BiaScope, which systematically assesses performance by leveraging newly constructed datasets and metrics on knowledge retention and generalization. Then, we propose a novel debiasing approach, Fairness Stamp (FAST), which enables fine-grained calibration of individual social biases. FAST identifies the decisive layer responsible for storing social biases and then calibrates its outputs by integrating a small modular network, considering both bias mitigation and knowledge-preserving demands. Comprehensive experiments demonstrate that FAST surpasses state-of-the-art baselines with superior debiasing performance while not compromising the overall model capability for knowledge retention and downstream predictions. This highlights the potential of fine-grained debiasing strategies to achieve fairness in LLMs. Code will be publicly available. Warning: this paper contains content that may be offensive or upsetting.

This paper presents a study on the growing threat of "sleeper social bots," AI-driven social bots in the political landscape, created to spread disinformation and manipulate public opinion. We based the name sleeper social bots on their ability to pass as humans on social platforms, where they're embedded like political "sleeper" agents, making them harder to detect and more disruptive. To illustrate the threat these bots pose, our research team at the University of Southern California constructed a demonstration using a private Mastodon server, where ChatGPT-driven bots, programmed with distinct personalities and political viewpoints, engaged in discussions with human participants about a fictional electoral proposition. Our preliminary findings suggest these bots can convincingly pass as human users, actively participate in conversations, and effectively disseminate disinformation. Moreover, they can adapt their arguments based on the responses of human interlocutors, showcasing their dynamic and persuasive capabilities. College students participating in initial experiments failed to identify our bots, underscoring the urgent need for increased awareness and education about the dangers of AI-driven disinformation, and in particular, disinformation spread by bots. The implications of our research point to the significant challenges posed by social bots in the upcoming 2024 U.S. presidential election and beyond.

AI assistants are being increasingly used by students enrolled in higher education institutions. While these tools provide opportunities for improved teaching and education, they also pose significant challenges for assessment and learning outcomes. We conceptualize these challenges through the lens of vulnerability, the potential for university assessments and learning outcomes to be impacted by student use of generative AI. We investigate the potential scale of this vulnerability by measuring the degree to which AI assistants can complete assessment questions in standard university-level STEM courses. Specifically, we compile a novel dataset of textual assessment questions from 50 courses at EPFL and evaluate whether two AI assistants, GPT-3.5 and GPT-4 can adequately answer these questions. We use eight prompting strategies to produce responses and find that GPT-4 answers an average of 65.8% of questions correctly, and can even produce the correct answer across at least one prompting strategy for 85.1% of questions. When grouping courses in our dataset by degree program, these systems already pass non-project assessments of large numbers of core courses in various degree programs, posing risks to higher education accreditation that will be amplified as these models improve. Our results call for revising program-level assessment design in higher education in light of advances in generative AI.

Large Language Models (LLMs) have excelled at language understanding and generating human-level text. However, even with supervised training and human alignment, these LLMs are susceptible to adversarial attacks where malicious users can prompt the model to generate undesirable text. LLMs also inherently encode potential biases that can cause various harmful effects during interactions. Bias evaluation metrics lack standards as well as consensus and existing methods often rely on human-generated templates and annotations which are expensive and labor intensive. In this work, we train models to automatically create adversarial prompts to elicit biased responses from target LLMs. We present LLM- based bias evaluation metrics and also analyze several existing automatic evaluation methods and metrics. We analyze the various nuances of model responses, identify the strengths and weaknesses of model families, and assess where evaluation methods fall short. We compare these metrics to human evaluation and validate that the LLM-as-a-Judge metric aligns with human judgement on bias in response generation.

We explore visual prompt injection (VPI) that maliciously exploits the ability of large vision-language models (LVLMs) to follow instructions drawn onto the input image. We propose a new VPI method, "goal hijacking via visual prompt injection" (GHVPI), that swaps the execution task of LVLMs from an original task to an alternative task designated by an attacker. The quantitative analysis indicates that GPT-4V is vulnerable to the GHVPI and demonstrates a notable attack success rate of 15.8%, which is an unignorable security risk. Our analysis also shows that successful GHVPI requires high character recognition capability and instruction-following ability in LVLMs.