Get Started
Home
Topics
Search
Library
Research questionHow can LLMs give story-specific feedback that helps writers fix the most important problem?Automated feedback often produces generic comments, vague advice, and no clear priority among a story’s weaknesses. Writers may therefore struggle to know what to change first or how to improve it.
AI
Evaluation & Benchmarks
LLM Pretraining & Post-training
Machine Learning
Natural Language Processing
Reinforcement Learning
Latest papersRecent research connected to this question, newest first.Generating Constructive Feedback on Stories via Reinforcement LearningThe work studies LLM-generated feedback for stories using reinforcement learning without ground-truth feedback. It reports automatic and human evaluations across three story corpora, finding that actionable suggestions are the main driver of constructive feedback.research paper · Sep 4, 2026
Related questions
Can user feedback reliably guide LLM revisions if LLM judges overlook the resulting improvements?How can LLMs assess academic proposals and peer feedback with pedagogically grounded scores?How can LLM prompts be automatically refined from recurring reasoning errors without laborious manual engineering?How can LLMs generate diverse stories rather than converge on generic narratives?