Related papers: Temporal Stability and Few-Shot Prompting in Math …
Meta-learning for few-shot learning entails acquiring a prior over previous tasks and experiences, such that new tasks be learned from small amounts of data. However, a critical challenge in few-shot learning is task ambiguity: even when a…
Early identification of at-risk students is critical for effective intervention in online learning environments. This study extends temporal prediction analysis to Week 20 (50% of course duration), comparing Decision Tree and Long Short-…
While text-to-image (T2I) generative models have become ubiquitous, they do not necessarily generate images that align with a given prompt. While previous work has evaluated T2I alignment by proposing metrics, benchmarks, and templates for…
The rise of generative AI tools like ChatGPT has significantly reshaped education, sparking debates about their impact on learning outcomes and academic integrity. While prior research highlights opportunities and risks, there remains a…
Generative Artificial Intelligence (AI) tools such as ChatGPT, Copilot, or Gemini have a crucial impact on academic research and teaching. Empirical data on how students perceive the increasing influence of AI, which different types of…
Large language models that are capable of zero or few-shot prompting approaches have given rise to the new research area of prompt engineering. Recent advances showed that for example Chain-of-Thought (CoT) prompts can improve arithmetic or…
Generative AI compresses within-task skill differences while shifting economic value toward concentrated complementary assets, creating an apparent paradox: the technology that equalizes individual performance may widen aggregate…
AI-powered answer engines are inherently non-deterministic: identical queries submitted at different times can produce different responses and cite different sources. Despite this stochastic behavior, current approaches to measuring domain…
The effectiveness of Multimodal Chain-of-Thought (MCoT) prompting is often limited by the use of randomly or manually selected examples. These examples fail to account for both model-specific knowledge distributions and the intrinsic…
Effective and timely feedback in educational assessments is essential but labor-intensive, especially for complex tasks. Recent developments in automated feedback systems, ranging from deterministic response grading to the evaluation of…
Research suggests that providing specific and timely feedback to human tutors enhances their performance. However, it presents challenges due to the time-consuming nature of assessing tutor performance by human evaluators. Large language…
Recent prompt-based approaches allow pretrained language models to achieve strong performances on few-shot finetuning by reformulating downstream tasks as a language modeling problem. In this work, we demonstrate that, despite its…
Intelligent tutoring systems increasingly provide automated feedback on student work, but robust feedback requires assessing reasoning, not only final answers. We study a failure mode we call the correct answer trap (CAT): models…
We provide a new multi-task benchmark for evaluating text-to-image models. We perform a human evaluation comparing the most common open-source (Stable Diffusion) and commercial (DALL-E 2) models. Twenty computer science AI graduate students…
As generative AI (GenAI) tools are increasingly used as informal tutors for mathematics learning, future systems may become more proactive and process-aware in deciding when and how to offer support. Yet such support raises an important…
This paper presents a theoretical framework for addressing the challenges posed by generative artificial intelligence (AI) in higher education assessment through a machine-versus-machine approach. Large language models like GPT-4, Claude,…
This paper presents our system for Track 1: Mistake Identification in the BEA 2025 Shared Task on Pedagogical Ability Assessment of AI-powered Tutors. The task involves evaluating whether a tutor's response correctly identifies a mistake in…
Modern large language models (LLMs) increasingly rely on inference-time planning and external tools to improve reasoning. We benchmark this behavior on two real-world settings: event-centric question answering over graph-structured…
Incremental learning aims to overcome catastrophic forgetting when learning deep networks from sequential tasks. With impressive learning efficiency and performance, prompt-based methods adopt a fixed backbone to sequential tasks by…
Pre-trained language models have shown excellent results in few-shot learning scenarios using in-context learning. Although it is impressive, the size of language models can be prohibitive to make them usable in on-device applications, such…