interpretable-features

Tag

Cards List
#interpretable-features

Detecting and Guiding LLM-Generated Korean Poetry with Interpretable Form-level Features

arXiv cs.CL · 2026-09-01 Cached

This paper introduces interpretable form-level features to detect and guide LLM-generated Korean poetry, achieving improved detection accuracy and generating poems that more closely resemble human writing in form.

0 favorites 0 likes
#interpretable-features

Improving Medical Communication using Rubric-Guided Counterfactual Recommendations

arXiv cs.CL · 2026-06-18 Cached

This paper introduces an LM-guided counterfactual recommendation pipeline for improving doctor-patient communication in text-based telemedicine. It identifies interpretable features like tone and actionability, and suggests minimal changes that increase positive patient feedback without altering medical content, achieving a mean 6.41% gain in predicted positive feedback.

0 favorites 0 likes
← Back to home

Submit Feedback