Named after the hundred-eyed watchman of Greek myth, Argus watches the education landscape: spotting new opportunities, pressure-testing the ventures we're building, and tracing every read back to the real-world signals behind it.
Signal [49] shows cost-efficient generative AI summarization now handles transformer input-length limits for long essays; signal [8] demonstrates that LLMs' internal representations can be probed to identify Bloom's taxonomy cognitive levels; signal [42] shows LLM self-explanations are maturing as a trust mechanism; signal [9] highlights the remaining gap between LLM-as-judge reliability and ground truth, motivating a hybrid human-in-the-loop design.
Automated essay scoring tools provide scores but not transparent, actionable feedback that students can trust and learn from — the black-box nature erodes student buy-in and limits formative value.
K-12 and higher-ed writing instructors, large-enrollment courses (MOOCs, community colleges, state universities) where human feedback at scale is impossible
A writing feedback platform that uses LLM-based scoring augmented with self-explanation and mechanistic interpretability techniques to surface exactly which essay passages drove the score — mapping feedback to cognitive complexity levels (e.g., Bloom's taxonomy) so students understand not just what to fix but why. Instructors get calibration dashboards showing where the model's scoring diverges from human judgment, flagging essays that need human review.
The real-world evidence the pipeline drew on to generate this idea.
arXiv:2607.15829v1 Announce Type: new Abstract: Automated essay scoring (AES) enables scalable assessment and timely feedback but remains challenged by transformer input-length limitations, which can cause information loss when processing long essays. This study proposes a generative AI-assisted summarization framework to improve long-form essay representation while maintaining scoring reliability. Using the ASAP 2.0 dataset, we generate controlled-length summaries with three GPT-5 variants (GPT-5, GPT-5 mini, and GPT-5 nano) and use them as inputs for downstream AES models. To preserve original writing signals, handcrafted linguistic features extracted from full essays are integrated with summary representations to form a hybrid framework. The approach is evaluated in terms of scoring performance, summarization quality, and computational cost. Scoring reliability is measured using quadratic weighted kappa (QWK), while summary quality is assessed through lexical overlap, semantic simil
arXiv:2602.17229v2 Announce Type: replace-cross Abstract: The black-box nature of Large Language Models necessitates novel evaluation frameworks that transcend surface-level performance metrics. This study investigates the internal neural representations of cognitive complexity using Bloom's Taxonomy as a hierarchical lens. By analyzing high-dimensional activation vectors from different LLMs, we probe whether different cognitive levels, ranging from basic recall (Remember) to abstract synthesis (Create), are linearly separable within the model's residual streams. Our results demonstrate that linear classifiers achieve approximately 95% mean accuracy across all Bloom levels, providing strong evidence that cognitive level is encoded in a linearly accessible subspace of the model's representations. These findings provide evidence that the model resolves the cognitive difficulty of a prompt early in the forward pass, with representations becoming increasingly separable across layers.
arXiv:2607.15957v1 Announce Type: new Abstract: Large Language Models (LLMs) can generate natural language explanations that rationalize their own decisions, a phenomenon commonly referred to as self-explanations.Such explanations have emerged as a promising direction for explainable artificial intelligence (XAI), particularly for interpreting LLM behavior.However, while self-explanations often appear plausible, whether they faithfully reflect a model's underlying reasoning process remains an open question. In this opinion paper, we argue that self-explanations can be highly plausible, questionably faithful, and yet highly actionable. From a traditional XAI perspective, we identify the limitations of standard evaluation protocols for LLM-generated self-explanations and propose practical guidelines for assessing their plausibility and faithfulness. Moreover, we argue that evaluation should extend beyond these criteria to actionability, highlighting applications of LLM rationalization ca
arXiv:2607.13347v2 Announce Type: replace Abstract: LLM-as-a-judge is widely used to provide feedback and selection signals in closedloop regeneration, but this use remains insufficiently validated. We study it in table recognition, where deterministic TEDS evaluation provides a controlled testbed, using FinTabNet and OmniDocBench. Three findings emerge. First, judge signals were weak on both datasets: scores frequently tied, rankings were not reproducible, and no tested judge score policy, whether selecting among candidates or accepting revisions under a conservative score margin, improved on the first output on both datasets. Iteration produced better candidates, but the judge recovered them at most partially on one dataset and not at all on the other. Second, severe losses occurred even without specific judge feedback, supporting target-preservation failure under unconstrained regeneration as a proximate mechanism. Third, a structure-preserving instruction reduced the severe-loss ra
arXiv:2607.16085v1 Announce Type: new Abstract: Increasingly, speech and language processing tasks take either audio or text directly rather than extracting features from these as the input to the classifier or regressor. Often these systems make use of complex, for example transformer-based, processes that have the ability to derive highly non-linear mappings between the input and the output. Unfortunately these systems can also learn ''shortcuts'' where the classifier is overly reliant on particular aspects of the input to yield the output. For the task of language proficiency assessment, this over-reliance can enable learners to increase their score by exploiting the shortcut rather than improving their ability. This paper introduces a novel training criterion that is able to reduce the classifier's reliance on shortcuts, thus for example limiting this option for malpractice in language assessment. This process is illustrated on two forms of assessment system, one based on the audio