Full Text Available

Note: Clicking the button above will open the full text document at the original institutional repository in a new window.

Predicting Disagreement with Human Raters in LLM-as-a-Judge Difficulty Assessment without Using Generation-Time Probability Signals

Saved in:
Bibliographic Details
Published in:ArXiv cs.CL Recent Papers
Format: Online Article RSS Article
Published: 2026
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1865127356581019650
collection WordPress RSS
FRELIP Feed Integration
container_title ArXiv cs.CL Recent Papers
description
discipline_display Engineering & Technology
discipline_facet Engineering & Technology
format Online Article
RSS Article
genre Journal Article
id rss_article:51501
institution FRELIP
journal_source_facet ArXiv cs.CL Recent Papers
publishDate 2026
publishDateSort 2026
record_format rss_article
spellingShingle Predicting Disagreement with Human Raters in LLM-as-a-Judge Difficulty Assessment without Using Generation-Time Probability Signals
ArXiv cs.CL Recent Papers
Civil & Construction
Engineering & Technology
sub_discipline_display Civil & Construction
sub_discipline_facet Civil & Construction
subject_display ArXiv cs.CL Recent Papers
Civil & Construction
Engineering & Technology
ArXiv cs.CL Recent Papers
Civil & Construction
Engineering & Technology
subject_facet ArXiv cs.CL Recent Papers
Civil & Construction
Engineering & Technology
title Predicting Disagreement with Human Raters in LLM-as-a-Judge Difficulty Assessment without Using Generation-Time Probability Signals
title_auth Predicting Disagreement with Human Raters in LLM-as-a-Judge Difficulty Assessment without Using Generation-Time Probability Signals
title_full Predicting Disagreement with Human Raters in LLM-as-a-Judge Difficulty Assessment without Using Generation-Time Probability Signals
title_fullStr Predicting Disagreement with Human Raters in LLM-as-a-Judge Difficulty Assessment without Using Generation-Time Probability Signals
title_full_unstemmed Predicting Disagreement with Human Raters in LLM-as-a-Judge Difficulty Assessment without Using Generation-Time Probability Signals
title_short Predicting Disagreement with Human Raters in LLM-as-a-Judge Difficulty Assessment without Using Generation-Time Probability Signals
title_sort predicting disagreement with human raters in llm-as-a-judge difficulty assessment without using generation-time probability signals
topic ArXiv cs.CL Recent Papers
Civil & Construction
Engineering & Technology
url https://arxiv.org/abs/2605.12422v1