LLMs exhibit positional bias and context-dependent scoring patterns when judging document similarity, with each model showing a stable scoring fingerprint but a shared hierarchy of sensitivity to different semantic perturbations.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
roles
method 1polarities
use method 1representative citing papers
Introduces Quicksort and Bradley-Terry based preference aggregation methods for portfolio selection that claim to outperform prior aggregation techniques and support sampling to reduce pairwise comparisons.
A survey that organizes LLMs-as-judges research into functionality, methodology, applications, meta-evaluation, and limitations.
citing papers explorer
-
Semantic Needles in Document Haystacks: Sensitivity Testing of LLM-as-a-Judge Similarity Scoring
LLMs exhibit positional bias and context-dependent scoring patterns when judging document similarity, with each model showing a stable scoring fingerprint but a shared hierarchy of sensitivity to different semantic perturbations.
-
Efficient Portfolio Selection through Preference Aggregation with Quicksort and the Bradley--Terry Model
Introduces Quicksort and Bradley-Terry based preference aggregation methods for portfolio selection that claim to outperform prior aggregation techniques and support sampling to reduce pairwise comparisons.
-
LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods
A survey that organizes LLMs-as-judges research into functionality, methodology, applications, meta-evaluation, and limitations.