Artificial Intelligence Bias on English Language Learners in Automatic Scoring (2025 · 15 citations)
The paper asks whether automatic scoring of short written science answers treats English Language Learners (ELLs) unfairly, and in particular whether ELLs being underrepresented in training data is the cause.
PanGu-π: Enhancing Language Model Architectures via Nonlinearity Compensation (2023 · 10 citations)
Progress in large language models has mostly come from adding parameters and data. The design of the Transformer block itself gets little attention, even though large models are costly to run. The authors study LLaMA-style decoders and identify feature collapse: a rank metric shows token representations growing more…
BRIDGE the Gap: Mitigating Bias Amplification in Automated Scoring of English Language Learners via Inter-group Data Augmentation (2026)
Automated scorers for student answers, built on deep models and LLMs, can widen score gaps between student groups beyond the gaps in the human labels they learn from.
LLMs for Now, Fine-Tuning for Later: An Ensemble Approach to Data Drift in Domain-Specific Tasks (2026)
Real-world domain-specific deployments, such as clinical or legal work, face two problems. Expert labels are scarce, and the incoming data keeps changing over time (data drift). Active Learning (AL) can steadily improve a small model with expert labels, but each drift returns it to a weak cold-start state. LLMs work…

Co-authors here

12 of 19 co-authors with a page, the most papers together first.

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

Papers of our library cite their works 11 times (of the 149,439 papers whose bibliographies we read); 4 citing papers with a page here →.

Updated 1 November 2026