# SurveyEval: Towards Comprehensive Evaluation of LLM-Generated Academic Surveys

arXiv: https://arxiv.org/abs/2512.02763 · HTML: https://mlsanity.com/paper/2512.02763/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 1 of its 9 references that are in the map.
- First posted on arXiv 2 Dec 2025.

## Builds on (most cited first, 1 of 1)

- [SurveyForge: On the Outline Heuristics, Memory-Driven Generation, and Multi-dimensional Evaluation for Automated Survey Writing](https://mlsanity.com/paper/2503.04629/) (2025)

## Built on by (most cited first, 1 of 1)

- [SurveyLens: A Discipline-Aware Benchmark for Automatic Survey Generation](https://mlsanity.com/paper/2602.11238/) (2026)

## Abstract (arXiv)

LLM-based automatic survey systems are transforming how users acquire information from the web by integrating retrieval, organization, and content synthesis into end-to-end generation pipelines. While recent works focus on developing new generation pipelines, how to evaluate such complex systems remains a significant challenge. To this end, we introduce SurveyEval, a comprehensive benchmark that evaluates automatically generated surveys across three dimensions: overall quality, outline coherence, and reference accuracy. We extend the evaluation across 7 subjects and augment the LLM-as-a-Judge framework with human references to strengthen evaluation-human alignment. Evaluation results show that while general long-text or paper-writing systems tend to produce lower-quality surveys, specialized survey-generation systems are able to deliver substantially higher-quality results. We envision SurveyEval as a scalable testbed to understand and improve automatic survey systems across diverse subjects and evaluation criteria.