Opinionated users often seek information that aligns with their preexisting beliefs while dismissing contradictory evidence due to confirmation bias. This conduct hinders their ability to consider alternative stances when searching the web. Despite this, few studies have analyzed how the diversification of search results on disputed topics influences the search behavior of highly opinionated users. To this end, we present a preregistered user study (n = 257) investigating whether different levels (low and high) of bias metrics and search results presentation (with or without AI-predicted stances labels) can affect the stance diversity consumption and search behavior of opinionated users on three debated topics (i.e., atheism, intellectual property rights, and school uniforms). Our results show that exposing participants to (counter-attitudinally) biased search results increases their consumption of attitude-opposing content, but we also found that bias was associated with a trend toward overall fewer interactions within the search page. We also found that 19% of users interacted with queries and search pages but did not select any search results. When we removed these participants in a post-hoc analysis, we found that stance labels increased the diversity of stances consumed by users, particularly when the search results were biased. Our findings highlight the need for future research to explore distinct search scenario settings to gain insight into opinionated users' behavior.

Dynamic adversarial question generation, where humans write examples to stump a model, aims to create examples that are realistic and informative. However, the advent of large language models (LLMs) has been a double-edged sword for human authors: more people are interested in seeing and pushing the limits of these models, but because the models are so much stronger an opponent, they are harder to defeat. To understand how these models impact adversarial question writing process, we enrich the writing guidance with LLMs and retrieval models for the authors to reason why their questions are not adversarial. While authors could create interesting, challenging adversarial questions, they sometimes resort to tricks that result in poor questions that are ambiguous, subjective, or confusing not just to a computer but also to humans. To address these issues, we propose new metrics and incentives for eliciting good, challenging questions and present a new dataset of adversarially authored questions.

There has been considerable recent interest in estimating heterogeneous causal effects. In this paper, we introduce conditional average partial causal effects (CAPCE) to reveal the heterogeneity of causal effects with continuous treatment. We provide conditions for identifying CAPCE in an instrumental variable setting. We develop three families of CAPCE estimators: sieve, parametric, and reproducing kernel Hilbert space (RKHS)-based, and analyze their statistical properties. We illustrate the proposed CAPCE estimators on synthetic and real-world data.

ChatGPT explores a strategic blueprint of question answering (QA) in delivering medical diagnosis, treatment recommendations, and other healthcare support. This is achieved through the increasing incorporation of medical domain data via natural language processing (NLP) and multimodal paradigms. By transitioning the distribution of text, images, videos, and other modalities from the general domain to the medical domain, these techniques have expedited the progress of medical domain question answering (MDQA). They bridge the gap between human natural language and sophisticated medical domain knowledge or expert manual annotations, handling large-scale, diverse, unbalanced, or even unlabeled data analysis scenarios in medical contexts. Central to our focus is the utilizing of language models and multimodal paradigms for medical question answering, aiming to guide the research community in selecting appropriate mechanisms for their specific medical research requirements. Specialized tasks such as unimodal-related question answering, reading comprehension, reasoning, diagnosis, relation extraction, probability modeling, and others, as well as multimodal-related tasks like vision question answering, image caption, cross-modal retrieval, report summarization, and generation, are discussed in detail. Each section delves into the intricate specifics of the respective method under consideration. This paper highlights the structures and advancements of medical domain explorations against general domain methods, emphasizing their applications across different tasks and datasets. It also outlines current challenges and opportunities for future medical domain research, paving the way for continued innovation and application in this rapidly evolving field.

Agents based on Large Language Models (LLMs) are increasingly permeating various domains of human production and life, highlighting the importance of aligning them with human values. The current alignment of AI systems primarily focuses on passively aligning LLMs through human intervention. However, agents possess characteristics like receiving environmental feedback and self-evolution, rendering the LLM alignment methods inadequate. In response, we propose an evolutionary framework for agent evolution and alignment, named EvolutionaryAgent, which transforms agent alignment into a process of evolution and selection under the principle of survival of the fittest. In an environment where social norms continuously evolve, agents better adapted to the current social norms will have a higher probability of survival and proliferation, while those inadequately aligned dwindle over time. Experimental results assessing the agents from multiple perspectives in aligning with social norms demonstrate that EvolutionaryAgent can align progressively better with the evolving social norms while maintaining its proficiency in general tasks. Effectiveness tests conducted on various open and closed-source LLMs as the foundation for agents also prove the applicability of our approach.

Human educators possess an intrinsic ability to anticipate and seek educational explanations from students, which drives them to pose thought-provoking questions when students cannot articulate these explanations independently. We aim to imbue Intelligent Tutoring Systems with this ability using few-shot learning capability of Large Language Models. Our work proposes a novel prompting technique, Assertion Enhanced Few-Shot Learning, to facilitate the generation of accurate, detailed oriented educational explanations. Our central hypothesis is that, in educational domain, few-shot demonstrations are necessary but not a sufficient condition for quality explanation generation. We conducted a study involving 12 in-service teachers, comparing our approach to Traditional Few-Shot Learning. The results show that Assertion Enhanced Few-Shot Learning improves explanation accuracy by 15% and yields higher-quality explanations, as evaluated by teachers. We also conduct a qualitative ablation study to factor the impact of assertions to provide educator-friendly prompting guidelines for generating explanations in their domain of interest.

Most current methods for multi-hop question answering (QA) over knowledge graphs (KGs) only provide final conclusive answers without explanations, such as a set of KG entities that is difficult for normal users to review and comprehend. This issue severely limits the application of KG-based QA in real-world scenarios. However, it is non-trivial to solve due to two challenges: First, annotations of reasoning chains of multi-hop questions, which could serve as supervision for explanation generation, are usually lacking. Second, it is difficult to maintain high efficiency when explicit KG triples need to be retrieved to generate explanations. In this paper, we propose a novel Graph Neural Network-based Two-Step Reasoning model (GNN2R) to solve this issue. GNN2R can provide both final answers and reasoning subgraphs as a rationale behind final answers efficiently with only weak supervision that is available through question-final answer pairs. We extensively evaluated GNN2R with detailed analyses in experiments. The results demonstrate that, in terms of effectiveness, efficiency, and quality of generated explanations, GNN2R outperforms existing state-of-the-art methods that are applicable to this task. Our code and pre-trained models are available at https://github.com/ruijie-wang-uzh/GNN2R.

Large Language Models (LLMs) and Large Multimodal Models (LMMs) exhibit impressive problem-solving skills in many tasks and domains, but their ability in mathematical reasoning in visual contexts has not been systematically studied. To bridge this gap, we present MathVista, a benchmark designed to combine challenges from diverse mathematical and visual tasks. It consists of 6,141 examples, derived from 28 existing multimodal datasets involving mathematics and 3 newly created datasets (i.e., IQTest, FunctionQA, and PaperQA). Completing these tasks requires fine-grained, deep visual understanding and compositional reasoning, which all state-of-the-art foundation models find challenging. With MathVista, we have conducted a comprehensive, quantitative evaluation of 12 prominent foundation models. The best-performing GPT-4V model achieves an overall accuracy of 49.9%, substantially outperforming Bard, the second-best performer, by 15.1%. Our in-depth analysis reveals that the superiority of GPT-4V is mainly attributed to its enhanced visual perception and mathematical reasoning. However, GPT-4V still falls short of human performance by 10.4%, as it often struggles to understand complex figures and perform rigorous reasoning. This significant gap underscores the critical role that MathVista will play in the development of general-purpose AI agents capable of tackling mathematically intensive and visually rich real-world tasks. We further explore the new ability of self-verification, the application of self-consistency, and the interactive chatbot capabilities of GPT-4V, highlighting its promising potential for future research. The project is available at https://mathvista.github.io/.

A Baltimore, Maryland school district has launched an investigation after a high school principal was allegedly recorded making racist comments to students and staff. In a Wednesday email to parents, Baltimore County Schools superintendent Myriam Rogers said that while the statements were "deeply disturbing," the district could not "confirm the veracity of this recording at this time." "I understand how upsetting this recording is for many members of the Team BCPS community," Rogers said, according to a report in WMAR2 News. "We will not tolerate disparaging remarks about any member of the Team BCPS community." Things became more perplexing after The Council of Administrative & Supervising Employees (CASE), the union representing Pikesville High School Principal Eric Eiswert, claimed the recording was fraudulent and generated using artificial intelligence (AI).

One of the most prestigious universities in the country is offering a course in playing video games as part of a shocking 40,000-a-year curriculum. The University of California (UC), Berkeley will launch a course in'The Art of Fighting Games' - which aims to make students better at video games for its Spring 2024 curriculum. The class will focus on the Japanese video game, 'Street Fighter III 3rd Strike,' with homework assignments consisting of students actually recording themselves playing the game, according to the class syllabus. University of California Berkeley is offering a course in'The Art of Fighting Games' Prerequisites are not required and students will not be graded based on their performance. UC Berkeley labels the class as an'introduction to fighting games, geared towards people with less than 100 hours in the genre,' but the university does not explain how the class could help students enter and succeed in life after college. Enrollment continues through January 24 and the university has encouraged students to sign up by stating: 'The only thing you do need is a willingness to learn and fail!' The university continues to explain that students will be graded on their'eagerness, commitment to improvement, and effort in the course assignments.'