AI

My Teacher Thinks the World Is Flat! Can AI Essay Graders Be Fooled?

Kari Jaaskelainen

12 Nov 2025 — 1 min read

Can AI essay graders be fooled?

New research shows many automatic essay scoring (AES) systems reward “word soups” over real writing. Using interpretability tools, the authors found that a few keywords drive most of the score, while flow, grammar, and coherence matter far less.

The wild part: because these models aren’t grounded in world knowledge, adding confident but false lines—like “the world is flat”—can even boost a grade.

Scores barely drop when context around “important” words is removed.
Coherence, content relevance, and common sense are underweighted.
Simple adversarial edits can game the system.

Bottom line: Before using AES for high‑stakes tests, we need models that understand meaning—not just keywords—and rigorous validation across multiple writing skills.

Paper: http://arxiv.org/abs/2012.13872

Paper: http://arxiv.org/abs/2012.13872v1

Register: https://www.AiFeta.com

AI NLP EdTech Assessment MachineLearning ExplainableAI Ethics

Read more

Automating GDPR Compliance: A Roadmap for Companies and Law Firms

Automating GDPR Compliance: A Roadmap for Companies and Law Firms

GDPR compliance is more than checkboxes. A new roadmap from the Privatech project shows how automation and machine learning can help companies and law firms assess—and even generate—privacy compliance. * Shift the focus to data processors’ real workflows: drafting policies, mapping data uses, documenting decisions. * Break compliance into machine-ready

FPGAs for Faster, Leaner Deep Learning: A Review of CNN Accelerators

FPGAs for Faster, Leaner Deep Learning: A Review of CNN Accelerators

Deep learning drives image search, robots, and medical scans. Most systems lean on CPUs and GPUs. This review asks: what if we run convolutional neural networks (CNNs) on FPGAs—reconfigurable chips you can tailor to the model? * Why FPGAs: custom dataflows, low latency, and strong energy efficiency—great for cameras,

Dynamic-K: Recommendations That Know When to Stop

Dynamic-K: Recommendations That Know When to Stop

Most apps show a fixed number of “top” items—say 10 movies or 20 products—assuming there are always enough good options. But that’s not always true: sometimes there are few relevant items, or some users are extra picky. The result? Filler recommendations. Dynamic-K flips the script. Instead of

Teaching chatbots to stop contradicting themselves (DECODE)

Teaching chatbots to stop contradicting themselves (DECODE)

Teaching chatbots to stop contradicting themselves Ever had a bot say one thing, then the opposite a few turns later? This study introduces DECODE—a new task and dataset for spotting contradictions in everyday conversations, drawn from both human-human and human-bot chats. * New data beats existing natural language inference (NLI)