Saved in:
Bibliographic Details
Main Authors: Kalra, Nimit, Tang, Leonard
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2502.18018
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911248804741120
author Kalra, Nimit
Tang, Leonard
author_facet Kalra, Nimit
Tang, Leonard
contents The use of LLMs as automated judges ("LLM-as-a-judge") is now widespread, yet standard judges suffer from a multitude of reliability issues. To address these challenges, we introduce Verdict, an open-source library for scaling judge-time compute to enhance the accuracy, reliability, and interpretability of automated evaluators. Verdict leverages the composition of modular reasoning units (such as verification, debate, and aggregation) and increased inference-time compute to improve LLM judge quality. Across a variety of challenging tasks such as content moderation, fact-checking, and hallucination detection, Verdict judges achieves performance competitive with orders-of-magnitude larger fine-tuned judges, prompted judges, and reasoning models. Our framework establishes a foundation for scalable, interpretable, and reliable LLM-based evaluation systems for both researchers and practitioners.
format Preprint
id arxiv_https___arxiv_org_abs_2502_18018
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Verdict: A Library for Scaling Judge-Time Compute
Kalra, Nimit
Tang, Leonard
Computation and Language
The use of LLMs as automated judges ("LLM-as-a-judge") is now widespread, yet standard judges suffer from a multitude of reliability issues. To address these challenges, we introduce Verdict, an open-source library for scaling judge-time compute to enhance the accuracy, reliability, and interpretability of automated evaluators. Verdict leverages the composition of modular reasoning units (such as verification, debate, and aggregation) and increased inference-time compute to improve LLM judge quality. Across a variety of challenging tasks such as content moderation, fact-checking, and hallucination detection, Verdict judges achieves performance competitive with orders-of-magnitude larger fine-tuned judges, prompted judges, and reasoning models. Our framework establishes a foundation for scalable, interpretable, and reliable LLM-based evaluation systems for both researchers and practitioners.
title Verdict: A Library for Scaling Judge-Time Compute
topic Computation and Language
url https://arxiv.org/abs/2502.18018