paper-with-me

홈 › Papers

LLM-Rubric: A Multidimensional, Calibrated Approach to Automated Evaluation of Natural Language Texts

2024-12-31 · Helia Hashemi, Jason Eisner, Corby Rosset, Benjamin Van Durme, Chris Kedzie

This paper introduces a framework for the automated evaluation of natural language texts. A manually constructed rubric describes how to assess multiple dimensions of interest. To evaluate a text, a large language model (LLM) is prompted with each rubric question and produces a distribution over potential responses. The LLM predictions often fail to agree well with human judges -- indeed, the humans do not fully agree with one another. However, the multiple LLM distributions can be $\textit{combined}$ to $\textit{predict}$ each human judge's annotations on all questions, including a summary question that assesses overall quality or relevance. LLM-Rubric accomplishes this by training a small feed-forward neural network that includes both judge-specific and judge-independent parameters. When evaluating dialogue systems in a human-AI information-seeking task, we find that LLM-Rubric with 9 questions (assessing dimensions such as naturalness, conciseness, and citation quality) predicts human judges' assessment of overall user satisfaction, on a scale of 1--4, with RMS error $< 0.5$, a $2\times$ improvement over the uncalibrated baseline.

📄 PDF Abstract BibTeX arXiv:2501.00274

Code (1)

microsoft/llm-rubric 공식 구현 pytorch

Tasks

Language ModelingLanguage ModellingLarge Language Model

Similar Papers 제목 키워드 기반

Rubric-Guided Fine-tuning of SpeechLLMs for Multi-Aspect, Multi-Rater L2 Reading-Speech Assessment

2026-02-28 · Aditya Kamlesh Parikh, Cristian Tejedor-Garcia, Catia Cucchiarini, Helmer Strik arxiv

Reliable and interpretable automated assessment of second-language (L2) speech remains a central challenge, as large speech-language models (SpeechLLMs) often struggle to align with the nuanced variability of human rater…

ExecRubrics: Executable Tool-Augmented Rubrics for Verifiable and Efficient Long-Form Evaluation

2026-08-23 · Kaustubh D. Dhole, Charles L. A. Clarke, Eugene Y. Agichtein arxiv

Rubrics aim to make language-model evaluation transparent by decomposing response quality into interpretable criteria. However, natural-language rubrics are often ambiguous, require LLM judges, and typically assume crite…

An Instrument to Evaluate Governance Proposals: AI Policy Analysis at Scale

2026-07-30 · Paulo Carvao, Claudio Mayrink Verdun, Isabel Adler, Jeffrey Zhou arxiv

This paper introduces a policy analysis framework for systematic, transparent assessment of AI governance proposals in an evolving and contested regulatory landscape. AI policy debates often collapse into binary position…

VERDI: Single-Call Confidence Estimation for Verification-Based LLM Judges via Decomposed Inference

2026-05-11 · Jasmine Qi, Danylo Dantsev, Muyang Sun arxiv

LLM-as-Judge systems are widely deployed for automated evaluation, yet practitioners lack reliable methods to know when a judge's verdict should be trusted. Token log-probabilities, the standard post-hoc confidence signa…

Natural Language Inference

RULER: Instance-aware Rubric Rewards for SVG Generation

2026-09-21 · Hangyu Ran, Yuhao Zheng, Yingying Zhang, Kevin Qinghong Lin 외 hf

Generating Scalable Vector Graphics (SVG) code from natural-language instructions is an open-ended task without absolute visual ground truth, leaving both evaluation and policy optimization without a faithful signal. Sca…

Reinforcement Learning