Many measures of human-robot trust have proliferated across the HRI research literature because each attempts to capture the factors that impact trust despite its many dimensions. None of the previous trust measures, however, address the systems of inequity and structures of power present in HRI research or attempt to counteract the systematic biases and potential harms caused by HRI systems. This position paper proposes a participatory and social justice-oriented approach for the design and evaluation of a trust measure. This proposed process would iteratively co-design the trust measure with the community for whom the HRI system is being created. The process would prioritize that community's needs and unique circumstances to produce a trust measure that accurately reflects the factors that impact their trust in a robot.

While ethical challenges are widely discussed in HCI, far less is reported about the ethical processes that researchers routinely navigate. We reflect on a multispecies project that negotiated an especially complex ethical approval process. Cat Royale was an artist-led exploration of creating an artwork to engage audiences in exploring trust in autonomous systems. The artwork took the form of a robot that played with three cats. Gaining ethical approval required an extensive dialogue with three Institutional Review Boards (IRBs) covering computer science, veterinary science and animal welfare, raising tensions around the welfare of the cats, perceived benefits and appropriate methods, and reputational risk to the University. To reveal these tensions we introduce beneficiary-epistemology space, that makes explicit who benefits from research (humans or animals) and underlying epistemologies. Positioning projects and IRBs in this space can help clarify tensions and highlight opportunities to recruit additional expertise.

Rule-based reasoning, a fundamental type of legal reasoning, enables us to draw conclusions by accurately applying a rule to a set of facts. We explore causal language models as rule-based reasoners, specifically with respect to compositional rules - rules consisting of multiple elements which form a complex logical expression. Reasoning about compositional rules is challenging because it requires multiple reasoning steps, and attending to the logical relationships between elements. We introduce a new prompting method, Chain of Logic, which elicits rule-based reasoning through decomposition (solving elements as independent threads of logic), and recomposition (recombining these sub-answers to resolve the underlying logical expression). This method was inspired by the IRAC (Issue, Rule, Application, Conclusion) framework, a sequential reasoning approach used by lawyers. We evaluate chain of logic across eight rule-based reasoning tasks involving three distinct compositional rules from the LegalBench benchmark and demonstrate it consistently outperforms other prompting methods, including chain of thought and self-ask, using open-source and commercial language models.

This study explores the realm of knowledge-base question answering (KBQA). KBQA is considered a challenging task, particularly in parsing intricate questions into executable logical forms. Traditional semantic parsing (SP)-based methods require extensive data annotations, which result in significant costs. Recently, the advent of few-shot in-context learning, powered by large language models (LLMs), has showcased promising capabilities. Yet, fully leveraging LLMs to parse questions into logical forms in low-resource scenarios poses a substantial challenge. To tackle these hurdles, we introduce Interactive-KBQA, a framework designed to generate logical forms through direct interaction with knowledge bases (KBs). Within this framework, we have developed three generic APIs for KB interaction. For each category of complex question, we devised exemplars to guide LLMs through the reasoning processes. Our method achieves competitive results on the WebQuestionsSP, ComplexWebQuestions, KQA Pro, and MetaQA datasets with a minimal number of examples (shots). Importantly, our approach supports manual intervention, allowing for the iterative refinement of LLM outputs. By annotating a dataset with step-wise reasoning processes, we showcase our model's adaptability and highlight its potential for contributing significant enhancements to the field.

Drawing causal inferences from observational studies (OS) requires unverifiable validity assumptions; however, one can falsify those assumptions by benchmarking the OS with experimental data from a randomized controlled trial (RCT). A major limitation of existing procedures is not accounting for censoring, despite the abundance of RCTs and OSes that report right-censored time-to-event outcomes. We consider two cases where censoring time (1) is independent of time-to-event and (2) depends on time-to-event the same way in OS and RCT. For the former, we adopt a censoring-doubly-robust signal for the conditional average treatment effect (CATE) to facilitate an equivalence test of CATEs in OS and RCT, which serves as a proxy for testing if the validity assumptions hold. For the latter, we show that the same test can still be used even though unbiased CATE estimation may not be possible. We verify the effectiveness of our censoring-aware tests via semi-synthetic experiments and analyze RCT and OS data from the Women's Health Initiative study.

Google is pausing its new Gemini AI tool after users blasted the image generator for being'too woke' by replacing white historical figures with people of color. Artificial intelligence programs learn from the information available to them, and researchers have warned that AI is prone to recreate the racism, sexism, and other biases of its creators and of society at large. In this case, Google may have overcorrected in its efforts to address discrimination, as some users fed it prompt after prompt in failed attempts to get the AI to make a picture of a white person. X user Frank J. Fleming posted multiple images of people of color that he said Gemini generated. Each time, he said he was attempting to get the AI to give him a picture of a white man, and each time.

The Justice Department named its first-ever official focused on artificial intelligence (AI) on Thursday in anticipation of the rapidly evolving technology's impact on the criminal justice system. Jonathan Mayer, a professor at Princeton University who focuses on the "intersection of technology and law, with emphasis on national security, criminal procedure, consumer privacy, network management, and online speech," according to his online biography, was selected to serve as the DOJ's chief science and technology adviser and chief AI officer, Reuters reported. "The Justice Department must keep pace with rapidly evolving scientific and technological developments in order to fulfill our mission to uphold the rule of law, keep our country safe and protect civil rights," U.S. Attorney General Merrick Garland said in a statement. Mayer previously served as the technology adviser to Vice President Kamala Harris during her time as a U.S. senator, and as the Chief Technologist of the Federal Communications Commission Enforcement Bureau. In his new role, he is expected to advise Garland and DOJ leadership on matters related to emerging technologies, including how to responsibly integrate AI into the department's investigations and criminal prosecutions, according to Reuters.

Some of the major limitations identified in the areas of argument mining, argument generation, and natural language argument analysis are related to the complexity of annotating argumentatively rich data, the limited size of these corpora, and the constraints that represent the different languages and domains in which these data is annotated. To address these limitations, in this paper we present the following contributions: (i) an effective methodology for the automatic generation of natural language arguments in different topics and languages, (ii) the largest publicly available corpus of natural language argumentation schemes, and (iii) a set of solid baselines and fine-tuned models for the automatic identification of argumentation schemes.

Modern generative search engines enhance the reliability of large language model (LLM) responses by providing cited evidence. However, evaluating the answer's attribution, i.e., whether every claim within the generated responses is fully supported by its cited evidence, remains an open problem. This verification, traditionally dependent on costly human evaluation, underscores the urgent need for automatic attribution evaluation methods. To bridge the gap in the absence of standardized benchmarks for these methods, we present AttributionBench, a comprehensive benchmark compiled from various existing attribution datasets. Our extensive experiments on AttributionBench reveal the challenges of automatic attribution evaluation, even for state-of-the-art LLMs. Specifically, our findings show that even a fine-tuned GPT-3.5 only achieves around 80% macro-F1 under a binary classification formulation. A detailed analysis of more than 300 error cases indicates that a majority of failures stem from the model's inability to process nuanced information, and the discrepancy between the information the model has access to and that human annotators do.

Large language models (LLMs) have become the secret ingredient driving numerous industrial applications, showcasing their remarkable versatility across a diverse spectrum of tasks. From natural language processing and sentiment analysis to content generation and personalized recommendations, their unparalleled adaptability has facilitated widespread adoption across industries. This transformative shift driven by LLMs underscores the need to explore the underlying associated challenges and avenues for enhancement in their utilization. In this paper, our objective is to unravel and evaluate the obstacles and opportunities inherent in leveraging LLMs within an industrial context. To this end, we conduct a survey involving a group of industry practitioners, develop four research questions derived from the insights gathered, and examine 68 industry papers to address these questions and derive meaningful conclusions.