Research map / Large language models / Language, safety and interpretability
Activations as Features: Probing LLMs for Generalizable Essay Scoring Representations
Jinwei Chi, Ke Wang, Yu Chen, Xuanye Lin, Qiang Xu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use nonlinear MLP probe instead of linear ridge probe (ablation) | Qwen3-8B activations · cross-prompt traits avg | QWK: 0.653 -> 0.512 | Hurt |
| use nonlinear MLP probe instead of linear ridge probe (ablation) | Llama-2-7b-chat-hf activations · cross-prompt prompts avg | QWK: 0.652 -> 0.587 | Hurt |
| remove instruction from LLM input (ablation) | Llama-2-7b-chat-hf probe · cross-prompt prompts avg | QWK: 0.652 -> 0.541 | Hurt |
| remove essay prompt from LLM input (ablation) | Llama-2-7b-chat-hf probe · cross-prompt prompts avg | QWK: 0.652 -> 0.576 | Hurt |
| remove both prompt and instruction (ablation) | Llama-2-7b-chat-hf probe · cross-prompt traits avg | QWK: 0.651 -> 0.527 | Hurt |
| increase model size within Qwen3 (0.6B to 8B) | linear probe · cross-prompt prompts avg | QWK: 0.622 -> 0.654 | Improved |
| use DeepSeek-R1-Distill-Llama-8B instead of Qwen3-8B | linear probe · cross-prompt prompts avg | QWK: 0.654 -> 0.631 | Hurt |
| drop prompt 7 data from training (ablation) | Llama-2-7b-chat-hf probe · other prompts, Conventions trait on prompt 8 | QWK relative change: +23.46% (P8 Conventions); -2.81% (P3 Content) | Mixed |
| use best-head linear probe on Qwen3-8B instead of KAES | cross-prompt scoring · ASAP/ASAP++ prompts avg | QWK: 0.597 -> 0.654 | Improved |
Closest papers by meaning
- Unveiling the Tapestry of Automated Essay Scoring: A Comprehensive Investigation of Accuracy, Fairness, and Generalizability (AAAI 2024 · similarity 0.91)
- KAES: Multi-aspect Shared Knowledge Finding and Aligning for Cross-prompt Automated Scoring of Essay Traits (AAAI 2025 · similarity 0.90)
- Evaluating Large Language Models at Evaluating Instruction Following (ICLR 2024 · similarity 0.85)
- IDGen: Item Discrimination Induced Prompt Generation for LLM Evaluation (NeurIPS 2024 · similarity 0.84)
- Towards Automatic Boundary Detection for Human-AI Collaborative Hybrid Essay in Education (AAAI 2024 · similarity 0.84)
- From Jack of All Trades to Master of One: Specializing LLM-based Autoraters to a Test Set (ICML 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
