# Large Language Models are Not Yet Human-Level Evaluators for Abstractive Summarization

arXiv: https://arxiv.org/abs/2305.13091 · HTML: https://mlsanity.com/paper/2305.13091/

## Key facts

- Cited by 70 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 37 of its 53 references that are in the map.
- First posted on arXiv 22 May 2023.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 30 of 37)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [Hierarchical Neural Story Generation](https://mlsanity.com/paper/1805.04833/) (2018)
- [PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization](https://mlsanity.com/paper/1912.08777/) (2019)
- [Teaching Machines to Read and Comprehend](https://mlsanity.com/paper/1506.03340/) (2015)
- [Can Large Language Models Be an Alternative to Human Evaluations?](https://mlsanity.com/paper/2305.01937/) (2023)
- [BARTScore: Evaluating Generated Text as Text Generation](https://mlsanity.com/paper/2106.11520/) (2021)
- [SummEval: Re-evaluating Summarization Evaluation](https://mlsanity.com/paper/2007.12626/) (2020)
- [Multi-News: a Large-Scale Multi-Document Summarization Dataset and Abstractive Hierarchical Model](https://mlsanity.com/paper/1906.01749/) (2019)
- [Is ChatGPT a Good NLG Evaluator? A Preliminary Study](https://mlsanity.com/paper/2303.04048/) (2023)
- [Generating Wikipedia by Summarizing Long Sequences](https://mlsanity.com/paper/1801.10198/) (2018)
- [Faithful Chain-of-Thought Reasoning](https://mlsanity.com/paper/2301.13379/) (2023)
- [Understanding Factuality in Abstractive Summarization with FRANK: A Benchmark for Factuality Metrics](https://mlsanity.com/paper/2104.13346/) (2021)
- [Challenges in Detoxifying Language Models](https://mlsanity.com/paper/2109.07445/) (2021)
- [Human-like Summarization Evaluation with ChatGPT](https://mlsanity.com/paper/2304.02554/) (2023)
- [Large Language Model Is Not a Good Few-shot Information Extractor, but a Good Reranker for Hard Samples!](https://mlsanity.com/paper/2303.08559/) (2023)
- [Zero-Shot Listwise Document Reranking with a Large Language Model](https://mlsanity.com/paper/2305.02156/) (2023)
- [Of Human Criteria and Automatic Metrics: A Benchmark of the Evaluation of Story Generation](https://mlsanity.com/paper/2208.11646/) (2022)
- [Leveraging Graph to Improve Abstractive Multi-Document Summarization](https://mlsanity.com/paper/2005.10043/) (2020)
- [Large Language Models are Diverse Role-Players for Summarization Evaluation](https://mlsanity.com/paper/2303.15078/) (2023)
- [UNION: An Unreferenced Metric for Evaluating Open-ended Story Generation](https://mlsanity.com/paper/2009.07602/) (2020)
- [Neural Document Summarization by Jointly Learning to Score and Select Sentences](https://mlsanity.com/paper/1807.02305/) (2018)
- [BanditSum: Extractive Summarization as a Contextual Bandit](https://mlsanity.com/paper/1809.09672/) (2018)
- [MReD: A Meta-Review Dataset for Structure-Controllable Text Generation](https://mlsanity.com/paper/2110.07474/) (2021)
- [Improving Abstraction in Text Summarization](https://mlsanity.com/paper/1808.07913/) (2018)

## Built on by (most cited first, 30 of 70)

- [Instruction-Following Evaluation for Large Language Models](https://mlsanity.com/paper/2311.07911/) (2023)
- [Lessons from the Trenches on Reproducible Evaluation of Language Models](https://mlsanity.com/paper/2405.14782/) (2024)
- [Aligning with Human Judgement: The Role of Pairwise Preference in Large Language Model Evaluators](https://mlsanity.com/paper/2403.16950/) (2024)
- [A Systematic Survey and Critical Review on Evaluating Large Language Models: Challenges, Limitations, and Recommendations](https://mlsanity.com/paper/2407.04069/) (2024)
- [FineSurE: Fine-grained Summarization Evaluation using LLMs](https://mlsanity.com/paper/2407.00908/) (2024)
- [LLM-based NLG Evaluation: Current Status and Challenges](https://mlsanity.com/paper/2402.01383/) (2024)
- [Benchmarking Generation and Evaluation Capabilities of Large Language Models for Instruction Controllable Summarization](https://mlsanity.com/paper/2311.09184/) (2023)
- [Wisdom of the Silicon Crowd: LLM Ensemble Prediction Capabilities Rival Human Crowd Accuracy](https://mlsanity.com/paper/2402.19379/) (2024)
- [A Systematic Survey of Text Summarization: From Statistical Methods to Large Language Models](https://mlsanity.com/paper/2406.11289/) (2024)
- [LongGenBench: Benchmarking Long-Form Generation in Long Context LLMs](https://mlsanity.com/paper/2409.02076/) (2024)
- [Large Language Models have Intrinsic Self-Correction Ability](https://mlsanity.com/paper/2406.15673/) (2024)
- [Exploring the Potential of Large Language Models in Computational Argumentation](https://mlsanity.com/paper/2311.09022/) (2023)
- [Auto-Arena: Automating LLM Evaluations with Agent Peer Battles and Committee Discussions](https://mlsanity.com/paper/2405.20267/) (2024)
- [FENICE: Factuality Evaluation of summarization based on Natural language Inference and Claim Extraction](https://mlsanity.com/paper/2403.02270/) (2024)
- [PROXYQA: An Alternative Framework for Evaluating Long-Form Text Generation with Large Language Models](https://mlsanity.com/paper/2401.15042/) (2024)
- [CLAVE: An Adaptive Framework for Evaluating Values of LLM Generated Responses](https://mlsanity.com/paper/2407.10725/) (2024)
- [ExpertAF: Expert Actionable Feedback from Video](https://mlsanity.com/paper/2408.00672/) (2024)
- [DEBATE: Devil's Advocate-Based Assessment and Text Evaluation](https://mlsanity.com/paper/2405.09935/) (2024)
- [METAL: Towards Multilingual Meta-Evaluation](https://mlsanity.com/paper/2404.01667/) (2024)
- [Adapting Large Language Models for Education: Foundational Capabilities, Potentials, and Challenges](https://mlsanity.com/paper/2401.08664/) (2023)
- [CARE: Confounder-Aware Aggregation for Reliable LLM Evaluation](https://mlsanity.com/paper/2603.00039/) (2026)
- [Contextualized Evaluations: Judging Language Model Responses to Underspecified Queries](https://mlsanity.com/paper/2411.07237/) (2024)
- [A Better LLM Evaluator for Text Generation: The Impact of Prompt Output Sequencing and Optimization](https://mlsanity.com/paper/2406.09972/) (2024)
- [A Survey on Transformer Context Extension: Approaches and Evaluation](https://mlsanity.com/paper/2503.13299/) (2025)
- [Detectors for Safe and Reliable LLMs: Implementations, Uses, and Limitations](https://mlsanity.com/paper/2403.06009/) (2024)
- [Do LLMs Understand Your Translations? Evaluating Paragraph-level MT with Question Answering](https://mlsanity.com/paper/2504.07583/) (2025)
- [Cross-lingual Cross-temporal Summarization: Dataset, Models, Evaluation](https://mlsanity.com/paper/2306.12916/) (2023)
- [DOLOMITES: Domain-Specific Long-Form Methodical Tasks](https://mlsanity.com/paper/2405.05938/) (2024)
- [SC4ANM: Identifying Optimal Section Combinations for Automated Novelty Prediction in Academic Papers](https://mlsanity.com/paper/2505.16330/) (2025)
- [Estimating LLM Consistency: A User Baseline vs Surrogate Metrics](https://mlsanity.com/paper/2505.23799/) (2025)

## Abstract (arXiv)

With the recent undeniable advancement in reasoning abilities in large language models (LLMs) like ChatGPT and GPT-4, there is a growing trend for using LLMs on various tasks. One area where LLMs can be employed is as an alternative evaluation metric for complex generative tasks, which generally demands expensive human judges to complement the traditional automatic metrics for various evaluation dimensions such as fluency and consistency. In this work, we conduct extensive analysis to investigate the stability and reliability of LLMs as automatic evaluators for abstractive summarization. We found that while ChatGPT and GPT-4 outperform the commonly used automatic metrics, they are not ready as human replacements due to significant limitations. That is, LLM evaluators rate each candidate system inconsistently and are dimension-dependent. They also struggle to compare candidates with close performance and become more unreliable with higher-quality summaries by obtaining a lower correlation with humans. In other words, with better abstractive summarization systems being introduced at a fast pace, LLMs may result in misleading and unreliable evaluations.