The most common method to auto-grade a student's submission in a CS1 or a CS2 course is to run it against a pre-defined test suite and compare the results against reference results. However, this technique cannot be used if the correctness of the solution goes beyond simple output, such as the algorithm used to obtain the result. There is no convenient method for the graders to identify the kind of algorithm used in solving a problem. They must read the source code and understand the algorithm implemented and its features, which makes the process tedious. We propose CASET(Complexity Analysis using Simple Execution Traces), a novel tool to analyze the time complexity of algorithms using dynamic traces and unsupervised machine learning. CASET makes it convenient for tutors to classify the submissions for a program into time complexity baskets. Thus, tutors can identify the algorithms used by the submissions without necessarily going through the code written by the students. CASET's analysis can be used to improve grading and provide detailed feedback for submissions that try to match the results without a proper algorithm, for example, hard-coding a binary result, pattern-matching the visible or common inputs. We show the effectiveness of CASET by computing the time complexity of many classes of algorithms like sorting, searching and those using dynamic programming paradigm.

The widespread adoption of large language models (LLMs) and generative AI (GenAI) tools across diverse applications has amplified the importance of addressing societal biases inherent within these technologies. While the NLP community has extensively studied LLM bias, research investigating how non-expert users perceive and interact with biases from these systems remains limited. As these technologies become increasingly prevalent, understanding this question is crucial to inform model developers in their efforts to mitigate bias. To address this gap, this work presents the findings from a university-level competition, which challenged participants to design prompts for eliciting biased outputs from GenAI tools. We quantitatively and qualitatively analyze the competition submissions and identify a diverse set of biases in GenAI and strategies employed by participants to induce bias in GenAI. Our finding provides unique insights into how non-expert users perceive and interact with biases from GenAI tools.

Language model pre-training benefits from diverse data to enhance performance across domains and languages. However, training on such heterogeneous corpora requires extensive and costly efforts. Since these data sources vary lexically, syntactically, and semantically, they cause negative interference or the ``curse of multilinguality''. We propose a novel pre-training framework to alleviate this curse. Our method, DEPT, decouples embeddings from the transformer body while simultaneously training the latter in multiple contexts. DEPT enables training without a shared global vocabulary and: (1) can train robustly and effectively under significant data heterogeneity, (2) reduces token embedding parameters by up to 80% and the communication costs by 675x for billion-scale models, (3) enhances model generalization and plasticity in adapting to new languages and domains, and (4) permits training with custom optimized vocabularies per data source. We demonstrate DEPT's potential via the first vocabulary-agnostic federated multilingual pre-training of a 1.3 billion-parameter model, limiting its embedding size to 102.4 million instead of 512 million.

Grammatical error correction (GEC) is important for improving written materials for low-resource languages like Zarma -- spoken by over 5 million people in West Africa. Yet it remains a challenging problem. This study compares rule-based methods, machine translation (MT) models, and large language models (LLMs) for GEC in Zarma. We evaluate each approach's effectiveness on our manually-built dataset of over 250,000 examples using synthetic and human-annotated data. Our experiments show that the MT-based approach using the M2M100 model outperforms others, achieving a detection rate of 95.82% and a suggestion accuracy of 78.90% in automatic evaluations, and scoring 3.0 out of 5.0 in logical/grammar error correction during MEs by native speakers. The rule-based method achieved perfect detection (100%) and high suggestion accuracy (96.27%) for spelling corrections but struggled with context-level errors. LLMs like MT5-small showed moderate performance with a detection rate of 90.62% and a suggestion accuracy of 57.15%. Our work highlights the potential of MT models to enhance GEC in low-resource languages, paving the way for more inclusive NLP tools.

Question answering (QA)-producing correct answers for input questions-is popular, but we test a reverse question answering (RQA) task: given an input answer, generate a question with that answer. Past work tests QA and RQA separately, but we test them jointly, comparing their difficulty, aiding benchmark design, and assessing reasoning consistency. 16 LLMs run QA and RQA with trivia questions/answers, showing: 1) Versus QA, LLMs are much less accurate in RQA for numerical answers, but slightly more accurate in RQA for textual answers; 2) LLMs often answer their own invalid questions from RQA accurately in QA, so RQA errors are not from knowledge gaps alone; 3) RQA errors correlate with question difficulty and inversely correlate with answer frequencies in the Dolma corpus; and 4) LLMs struggle to give valid multi-hop questions. By finding question and answer types yielding RQA errors, we suggest improvements for LLM RQA reasoning.

We present a large-scale evaluation of 30 cognitive biases in 20 state-of-the-art large language models (LLMs) under various decision-making scenarios. Our contributions include a novel general-purpose test framework for reliable and large-scale generation of tests for LLMs, a benchmark dataset with 30,000 tests for detecting cognitive biases in LLMs, and a comprehensive assessment of the biases found in the 20 evaluated LLMs. Our work confirms and broadens previous findings suggesting the presence of cognitive Figure 1: An LLM changes its answer as the framing of biases in LLMs by reporting evidence of all the decision changes, indicating the susceptibility of the 30 tested biases in at least some of the 20 LLM to the Framing Effect.

In an era where cultural preservation is increasingly intertwined with technological innovation, this study introduces a groundbreaking approach to promoting and safeguarding the rich heritage of Taiwanese Hakka culture through the development of a Retrieval-Augmented Generation (RAG)-enhanced chatbot. Traditional large language models (LLMs), while powerful, often fall short in delivering accurate and contextually rich responses, particularly in culturally specific domains. By integrating external databases with generative AI models, RAG technology bridges this gap, empowering chatbots to not only provide precise answers but also resonate deeply with the cultural nuances that are crucial for authentic interactions. This study delves into the intricate process of augmenting the chatbot's knowledge base with targeted cultural data, specifically curated to reflect the unique aspects of Hakka traditions, language, and practices. Through dynamic information retrieval, the RAG-enhanced chatbot becomes a versatile tool capable of handling complex inquiries that demand an in-depth understanding of Hakka cultural context. This is particularly significant in an age where digital platforms often dilute cultural identities, making the role of culturally aware AI systems more critical than ever. System usability studies conducted as part of our research reveal a marked improvement in both user satisfaction and engagement, highlighting the chatbot's effectiveness in fostering a deeper connection with Hakka culture. The feedback underscores the potential of RAG technology to not only enhance user experience but also to serve as a vital instrument in the broader mission of ethnic mainstreaming and cultural celebration.

Symbolic neural networks, such as Kolmogorov-Arnold Networks (KAN), offer a promising approach for integrating prior knowledge with data-driven methods, making them valuable for addressing inverse problems in scientific and engineering domains. This study explores the application of KAN in building physics, focusing on predictive modeling, knowledge discovery, and continuous learning. Through four case studies, we demonstrate KAN's ability to rediscover fundamental equations, approximate complex formulas, and capture time-dependent dynamics in heat transfer. While there are challenges in extrapolation and interpretability, we highlight KAN's potential to combine advanced modeling methods for knowledge augmentation, which benefits energy efficiency, system optimization, and sustainability assessments beyond the personal knowledge constraints of the modelers. Additionally, we propose a model selection decision tree to guide practitioners in appropriate applications for building physics.

Most telemanipulation systems for aerial robots provide the operator with only 2D screen visual information. The lack of richer information about the robot's status and environment can limit human awareness and, in turn, task performance. While the pilot's experience can often compensate for this reduced flow of information, providing richer feedback is expected to reduce the cognitive workload and offer a more intuitive experience overall. This work aims to understand the significance of providing additional pieces of information during aerial telemanipulation, namely (i) 3D immersive visual feedback about the robot's surroundings through mixed reality (MR) and (ii) 3D haptic feedback about the robot interaction with the environment. To do so, we developed a human-robot interface able to provide this information. First, we demonstrate its potential in a real-world manipulation task requiring sub-centimeter-level accuracy. Then, we evaluate the individual effect of MR vision and haptic feedback on both dexterity and workload through a human subjects study involving a virtual block transportation task. Results show that both 3D MR vision and haptic feedback improve the operator's dexterity in the considered teleoperated aerial interaction tasks. Nevertheless, pilot experience remains the most significant factor.

UPenn Wharton School Associate Professor Ethan Mollick weighs in on the Biden White House's new guidelines for artificial intelligence in the workplace on'Fox News Live.' The parents of a Massachusetts high school senior who used artificial intelligence (AI) for a social studies project have filed a lawsuit against his teachers and the school after their son received detention and a "D" grade. "He's been accused of cheating, and it wasn't cheating, there was no rule in the handbook against AI," Jennifer Harris, who along with her husband, Dale, are named as plaintiffs in the lawsuit filed in Massachusetts' Plymouth County District Court last month against the Hingham High School administration and the school district, told Boston 25 News. The lawsuit alleges that their son will "suffer irreparable harm that is imminent" over the grade that his parents say kept him out of the National Honor Society, which they claim is threatening his standing with top tier colleges. "So, our argument to the school was could you fail him with a 59 instead of a 53 so he can have a B minus? He's applying to top tier schools," Harris told the news station.