The increasing use of Retrieval-Augmented Generation (RAG) systems in various applications necessitates stringent protocols to ensure RAG systems accuracy, safety, and alignment with user intentions. In this paper, we introduce VERA (Validation and Evaluation of Retrieval-Augmented Systems), a framework designed to enhance the transparency and reliability of outputs from large language models (LLMs) that utilize retrieved information. VERA improves the way we evaluate RAG systems in two important ways: (1) it introduces a cross-encoder based mechanism that encompasses a set of multidimensional metrics into a single comprehensive ranking score, addressing the challenge of prioritizing individual metrics, and (2) it employs Bootstrap statistics on LLM-based metrics across the document repository to establish confidence bounds, ensuring the repositorys topical coverage and improving the overall reliability of retrieval systems. Through several use cases, we demonstrate how VERA can strengthen decision-making processes and trust in AI applications. Our findings not only contribute to the theoretical understanding of LLM-based RAG evaluation metric but also promote the practical implementation of responsible AI systems, marking a significant advancement in the development of reliable and transparent generative AI technologies.

Large language models (LLMs) have generated significant attention since their inception, finding applications across various academic and industrial domains. However, these models often suffer from the "hallucination problem", where outputs, though grammatically and logically coherent, lack factual accuracy or are entirely fabricated. A particularly troubling issue discovered and widely discussed recently is the numerical comparison error where multiple LLMs incorrectly infer that "9.11$>$9.9". We discovered that the order in which LLMs generate answers and reasoning impacts their consistency. Specifically, results vary significantly when an LLM generates an answer first and then provides the reasoning versus generating the reasoning process first and then the conclusion. Inspired by this, we propose a new benchmark method for assessing LLM consistency: comparing responses generated through these two different approaches. This benchmark effectively identifies instances where LLMs fabricate answers and subsequently generate justifications. Furthermore, we introduce a novel and straightforward prompt strategy designed to mitigate this issue. Experimental results demonstrate that this strategy improves performance across various LLMs compared to direct questioning. This work not only sheds light on a critical flaw in LLMs but also offers a practical solution to enhance their reliability.

ChatGPT has already been used to write essays, tell jokes and even write best man speeches. But it seems the helpful AI bot can even make sure people on dating apps aren't lying to you about their height. Women are screenshotting photos from dating app profiles, inserting them into ChatGPT and asking it to provide an estimate of how tall they are. Justine Moore, a venture capitalist in San Francisco, said the AI's estimates are accurate to within an inch – not just for men but for women too. So it may be a good tool to size up your romantic interest before you arrange to meet.

Florian Tramer, Gautam Kamath and Nicholas Carlini won an International Conference on Machine Learning (ICML2024) best paper award for their work Position: Considerations for Differentially Private Learning with Large-Scale Public Pretraining. Differential privacy is a rigorous and provable notion of data privacy. Among other things, training a machine learning model with differential privacy can prevent it from spitting out its training data. The issue is that training a model with differential privacy generally comes at a significant hit to a model's utility. By incorporating "public data" (i.e., data that is not subject to privacy constraints) into the training procedure, it can help alleviate this concern and increase the resulting model's utility.

Graph neural networks (GNNs) are frequently used to predict missing facts in knowledge graphs (KGs). Motivated by the lack of explainability for the outputs of these models, recent work has aimed to explain their predictions using Datalog, a widely used logic-based formalism. However, such work has been restricted to certain subclasses of GNNs. In this paper, we consider one of the most popular GNN architectures for KGs, R-GCN, and we provide two methods to extract rules that explain its predictions and are sound, in the sense that each fact derived by the rules is also predicted by the GNN, for any input dataset. Furthermore, we provide a method that can verify that certain classes of Datalog rules are not sound for the R-GCN. In our experiments, we train R-GCNs on KG completion benchmarks, and we are able to verify that no Datalog rule is sound for these models, even though the models often obtain high to near-perfect accuracy. This raises some concerns about the ability of R-GCN models to generalise and about the explainability of their predictions. We further provide two variations to the training paradigm of R-GCN that encourage it to learn sound rules and find a trade-off between model accuracy and the number of learned sound rules.

Despite remarkable performance in legal consultation exhibited by legal Large Language Models(LLMs) combined with legal article retrieval components, there are still cases when the advice given is incorrect or baseless. To alleviate these problems, we propose {\bf ELLA}, a tool for {\bf E}mpowering {\bf L}LMs for interpretable, accurate, and informative {\bf L}egal {\bf A}dvice. ELLA visually presents the correlation between legal articles and LLM's response by calculating their similarities, providing users with an intuitive legal basis for the responses. Besides, based on the users' queries, ELLA retrieves relevant legal articles and displays them to users. Users can interactively select legal articles for LLM to generate more accurate responses. ELLA also retrieves relevant legal cases for user reference. Our user study shows that presenting the legal basis for the response helps users understand better. The accuracy of LLM's responses also improves when users intervene in selecting legal articles for LLM. Providing relevant legal cases also aids individuals in obtaining comprehensive information.

Conceptual Engineers want to make words better. However, they often underestimate how varied our usage of words is. In this paper, we take the first steps in exploring the contextual nuances of words by creating conceptual landscapes -- 2D surfaces representing the pragmatic usage of words -- that conceptual engineers can use to inform their projects. We use the spoken component of the British National Corpus and BERT to create contextualised word embeddings, and use Gaussian Mixture Models, a selection of metrics, and qualitative analysis to visualise and numerically represent lexical landscapes. Such an approach has not yet been used in the conceptual engineering literature and provides a detailed examination of how different words manifest in various contexts that is potentially useful to conceptual engineering projects. Our findings highlight the inherent complexity of conceptual engineering, revealing that each word exhibits a unique and intricate landscape. Conceptual Engineers cannot, therefore, use a one-size-fits-all approach when improving words -- a task that may be practically intractable at scale.

The International Joint Conference on Artificial Intelligence (IJCAI) distinguished paper awards recognise some of the best papers presented at the conference each year. This year, during the conference opening ceremony, three articles were named as distinguished papers. Abstract: As digital marketplaces and services continue to expand, it is crucial to maintain a safe and fair environment for all users. This requires implementing fairness constraints into the sequential decision-making processes of these platforms to ensure equal treatment. However, this can be challenging as these processes often need to solve NP-complete problems with exponentially large decision spaces at each time step.

The utilization of automated depression detection significantly enhances early intervention for individuals experiencing depression. Despite numerous proposals on automated depression detection using recorded clinical interview videos, limited attention has been paid to considering the hierarchical structure of the interview questions. In clinical interviews for diagnosing depression, clinicians use a structured questionnaire that includes routine baseline questions and follow-up questions to assess the interviewee's condition. This paper introduces HiQuE (Hierarchical Question Embedding network), a novel depression detection framework that leverages the hierarchical relationship between primary and follow-up questions in clinical interviews. HiQuE can effectively capture the importance of each question in diagnosing depression by learning mutual information across multiple modalities. We conduct extensive experiments on the widely-used clinical interview data, DAIC-WOZ, where our model outperforms other state-of-the-art multimodal depression detection models and emotion recognition models, showcasing its clinical utility in depression detection.

Object recognition technologies hold the potential to support blind and low-vision people in navigating the world around them. However, the gap between benchmark performances and practical usability remains a significant challenge. This paper presents a study aimed at understanding blind users' interaction with object recognition systems for identifying and avoiding errors. Leveraging a pre-existing object recognition system, URCam, fine-tuned for our experiment, we conducted a user study involving 12 blind and low-vision participants. Through in-depth interviews and hands-on error identification tasks, we gained insights into users' experiences, challenges, and strategies for identifying errors in camera-based assistive technologies and object recognition systems. During interviews, many participants preferred independent error review, while expressing apprehension toward misrecognitions. In the error identification task, participants varied viewpoints, backgrounds, and object sizes in their images to avoid and overcome errors. Even after repeating the task, participants identified only half of the errors, and the proportion of errors identified did not significantly differ from their first attempts. Based on these insights, we offer implications for designing accessible interfaces tailored to the needs of blind and low-vision users in identifying object recognition errors.