The emergence of Retrieval-augmented generation (RAG) has alleviated the issues of outdated and hallucinatory content in the generation of large language models (LLMs), yet it still reveals numerous limitations. When a general-purpose LLM serves as the RAG generator, it often suffers from inadequate response informativeness, response robustness, and citation quality. Past approaches to tackle these limitations, either by incorporating additional steps beyond generating responses or optimizing the generator through supervised fine-tuning (SFT), still failed to align with the RAG requirement thoroughly. Consequently, optimizing the RAG generator from multiple preference perspectives while maintaining its end-to-end LLM form remains a challenge. To bridge this gap, we propose Multiple Perspective Preference Alignment for Retrieval-Augmented Generation (PA-RAG), a method for optimizing the generator of RAG systems to align with RAG requirements comprehensively. Specifically, we construct high-quality instruction fine-tuning data and multi-perspective preference data by sampling varied quality responses from the generator across different prompt documents quality scenarios. Subsequently, we optimize the generator using SFT and Direct Preference Optimization (DPO). Extensive experiments conducted on four question-answer datasets across three LLMs demonstrate that PA-RAG can significantly enhance the performance of RAG generators. Our code and datasets are available at https://github.com/wujwyi/PA-RAG.

This paper introduces a novel approach to enhancing closed-domain Question Answering (QA) systems, focusing on the specific needs of the Lawrence Berkeley National Laboratory (LBL) Science Information Technology (ScienceIT) domain. Utilizing a rich dataset derived from the ScienceIT documentation, our study embarks on a detailed comparison of two fine-tuned large language models and five retrieval-augmented generation (RAG) models. Through data processing techniques, we transform the documentation into structured context-question-answer triples, leveraging the latest Large Language Models (AWS Bedrock, GCP PaLM2, Meta LLaMA2, OpenAI GPT-4, Google Gemini-Pro) for data-driven insights. Additionally, we introduce the Aggregated Knowledge Model (AKM), which synthesizes responses from the seven models mentioned above using K-means clustering to select the most representative answers. The evaluation of these models across multiple metrics offers a comprehensive look into their effectiveness and suitability for the LBL ScienceIT environment. The results demonstrate the potential benefits of integrating fine-tuning and retrieval-augmented strategies, highlighting significant performance improvements achieved with the AKM. The insights gained from this study can be applied to develop specialized QA systems tailored to specific domains.

Artificial Intelligence (AI) for health has the potential to significantly change and improve healthcare. However in most African countries, identifying culturally and contextually attuned approaches for deploying these solutions is not well understood. To bridge this gap, we conduct a qualitative study to investigate the best practices, fairness indicators, and potential biases to mitigate when deploying AI for health in African countries, as well as explore opportunities where artificial intelligence could make a positive impact in health. We used a mixed methods approach combining in-depth interviews (IDIs) and surveys. We conduct 1.5-2 hour long IDIs with 50 experts in health, policy, and AI across 17 countries, and through an inductive approach we conduct a qualitative thematic analysis on expert IDI responses. We administer a blinded 30-minute survey with case studies to 672 general population participants across 5 countries in Africa and analyze responses on quantitative scales, statistically comparing responses by country, age, gender, and level of familiarity with AI. We thematically summarize open-ended responses from surveys. Our results find generally positive attitudes, high levels of trust, accompanied by moderate levels of concern among general population participants for AI usage for health in Africa. This contrasts with expert responses, where major themes revolved around trust/mistrust, ethical concerns, and systemic barriers to integration, among others. This work presents the first-of-its-kind qualitative research study of the potential of AI for health in Africa from an algorithmic fairness angle, with perspectives from both experts and the general population. We hope that this work guides policymakers and drives home the need for further research and the inclusion of general population perspectives in decision-making around AI usage.

This paper presents a set of intersectional feminist principles for conducting equitable, ethical, and sustainable AI research. In Data Feminism (2020), we offered seven principles for examining and challenging unequal power in data science. Here, we present a rationale for why feminism remains deeply relevant for AI research, rearticulate the original principles of data feminism with respect to AI, and introduce two potential new principles related to environmental impact and consent. Together, these principles help to 1) account for the unequal, undemocratic, extractive, and exclusionary forces at work in AI research, development, and deployment; 2) identify and mitigate predictable harms in advance of unsafe, discriminatory, or otherwise oppressive systems being released into the world; and 3) inspire creative, joyful, and collective ways to work towards a more equitable, sustainable world in which all of us can thrive.

The sun had yet to rise in Delray Beach, Fla., when Jeremy Banner flicked on Autopilot. His red Tesla Model 3 sped down the highway at nearly 70 mph, his hands no longer detected on the wheel. Seconds later, the Tesla plowed into a semi-truck, shearing off its roof as it slid under the truck's trailer. Banner was killed on impact. Banner's family sued after the gruesome 2019 collision, one of at least 10 active lawsuits involving Tesla's Autopilot, several of which are expected to go to court over the next year. Together, the cases could determine whether the driver is solely responsible when things go wrong in a vehicle guided by Autopilot -- or whether the software should also bear some of the blame.

Pre-trained large language models (LLMs) have recently achieved better generalization and sample efficiency in autonomous web automation. However, the performance on real-world websites has still suffered from (1) open domainness, (2) limited context length, and (3) lack of inductive bias on HTML. We introduce WebAgent, an LLM-driven agent that learns from self-experience to complete tasks on real websites following natural language instructions. WebAgent plans ahead by decomposing instructions into canonical sub-instructions, summarizes long HTML documents into task-relevant snippets, and acts on websites via Python programs generated from those. We design WebAgent with Flan-U-PaLM, for grounded code generation, and HTML-T5, new pre-trained LLMs for long HTML documents using local and global attention mechanisms and a mixture of long-span denoising objectives, for planning and summarization. We empirically demonstrate that our modular recipe improves the success on real websites by over 50%, and that HTML-T5 is the best model to solve various HTML understanding tasks; achieving 18.7% higher success rate than the prior method on MiniWoB web automation benchmark, and SoTA performance on Mind2Web, an offline task planning evaluation.

We present a forest fire firefighting simulation tool named FORFIS that is implemented in Python. Unlike other existing software, we focus on a user-friendly software interface with an easy-to-modify software engine. Our tool is published under GNU GPLv3 license and comes with a GUI as well as additional output functionality. The used wildfire model is based on the well-established approach by cellular automata in two variants - a rectangular and a hexagonal cell decomposition of the wildfire area. The model takes wind into account. In addition, our tool allows the user to easily include a customized firefighting strategy for the firefighting agents.

We are looking for a Senior NLP/ML Engineer to join our team. As a member of the Engineering team, you will work closely with other data scientists and software engineers as a key player in designing and building state-of-the-art ML decision systems for insurance claim processing. Work at Exadel - Who We Are: Since 1998, Exadel has been engineering its own software products and custom software for clients of all sizes. Headquartered in Walnut Creek, California, Exadel currently has 2700 employees in development centers across the Americas, Europe, and Asia. Our people drive Exadel's success, and they are at the core of our values.

Craniofacial Superimposition involves the superimposition of an image of a skull with a number of ante-mortem face images of an individual and the analysis of their morphological correspondence. Despite being used for one century, it is not yet a mature and fully accepted technique due to the absence of solid scientific approaches, significant reliability studies, and international standards. In this paper we present a comprehensive experimentation on the limitations of Craniofacial Superimposition as a forensic identification technique. The study involves different experiments over more than 1 Million comparisons performed by a landmark-based automatic 3D/2D superimposition method. The total sample analyzed consists of 320 subjects and 29 craniofacial landmarks.

An education in data science can help you land a job as a data analyst, data engineer, data architect, or data scientist. The data science path you ultimately choose will depend on your skillset and interests, but each career path will require some level of programming, data visualization, statistics, and machine learning knowledge and skills. Data engineers and data architects spend more time dealing with code, databases, and complex queries, whereas data analysts and data scientists typically focus on analyzing, collecting, and interpreting large datasets to help guide business decisions. Here are the top 15 data science boot camps to help you launch a career in data science, according to reviews and data collected from Switchup. WeCloudData is a data science and AI academy that offers a number of bootcamps as well as a diploma program and learning paths composed of sequential courses.