Quantile tokens inserted into LLM inputs combined with neighbor retrieval enable direct prediction of full distributions, yielding lower MAPE and narrower intervals than baselines on Airbnb and StackSample tasks.
Enhancing Automated Essay Scoring Performance via Fine-tuning Pre-trained Language Models with Combination of Regression and Ranking
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
LLM representations encode essay quality in a linearly decodable form that emerges across layers and includes identifiable scoring neurons whose distribution shifts with essay length.
citing papers explorer
-
Text-to-Distribution Prediction with Quantile Tokens and Neighbor Context
Quantile tokens inserted into LLM inputs combined with neighbor retrieval enable direct prediction of full distributions, yielding lower MAPE and narrower intervals than baselines on Airbnb and StackSample tasks.
-
From Texts to Scores: Tracing the Emergence of Essay Quality Representations in Large Language Models
LLM representations encode essay quality in a linearly decodable form that emerges across layers and includes identifiable scoring neurons whose distribution shifts with essay length.