Researchers have investigated how large language models (LLMs) represent essay quality internally, finding that this information is encoded in a linearly accessible form within the models' representations. This information emerges progressively across layers and remains robust across different prompting strategies and even partially transfers across different essay prompts and scoring rubrics. The study also identified specific neurons that correlate strongly with essay scores and whose behavior is sensitive to intervention, offering new insights into the interpretability of LLM-based automated essay scoring systems. AI
IMPACT Provides insights into the interpretability of LLMs for automated essay scoring, potentially improving fairness and transparency in educational assessments.
RANK_REASON The cluster contains an academic paper detailing research findings on LLM representations.
- ASAP++
- Automated essay scoring
- Center for Spiritual and Ethical Education
- cross-prompt generalization
- dimensionality reduction
- Enem
- Hugging Face
- large-language models
- linear probing
- neuron-level analyses
- arXiv
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →
