# Evaluation Metrics in the Era of GPT-4: Reliably Evaluating Large Language Models on Sequence to Sequence Tasks

arXiv: https://arxiv.org/abs/2310.13800 · HTML: https://mlsanity.com/paper/2310.13800/

## Key facts

- Cited by 53 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 44 references that are in the map.
- First posted on arXiv 20 Oct 2023.

## Builds on (most cited first, 20 of 20)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Multitask Prompted Training Enables Zero-Shot Task Generalization](https://mlsanity.com/paper/2110.08207/) (2021)
- [Large Language Models are not Fair Evaluators](https://mlsanity.com/paper/2305.17926/) (2023)
- [Teaching Machines to Read and Comprehend](https://mlsanity.com/paper/1506.03340/) (2015)
- [A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity](https://mlsanity.com/paper/2302.04023/) (2023)
- [ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks](https://mlsanity.com/paper/2303.15056/) (2023)
- [Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond](https://mlsanity.com/paper/1602.06023/) (2016)
- [Can Large Language Models Be an Alternative to Human Evaluations?](https://mlsanity.com/paper/2305.01937/) (2023)
- [SummEval: Re-evaluating Summarization Evaluation](https://mlsanity.com/paper/2007.12626/) (2020)
- [UL2: Unifying Language Learning Paradigms](https://mlsanity.com/paper/2205.05131/) (2022)
- [OPT-IML: Scaling Language Model Instruction Meta Learning through the Lens of Generalization](https://mlsanity.com/paper/2212.12017/) (2022)
- [Neural CRF Model for Sentence Alignment in Text Simplification](https://mlsanity.com/paper/2005.02324/) (2020)
- [Is ChatGPT a Highly Fluent Grammatical Error Correction System? A Comprehensive Evaluation](https://mlsanity.com/paper/2304.01746/) (2023)
- [ChatGPT or Grammarly? Evaluating ChatGPT on Grammatical Error Correction Benchmark](https://mlsanity.com/paper/2303.13648/) (2023)
- [POTATO: The Portable Text Annotation Tool](https://mlsanity.com/paper/2212.08620/) (2022)
- [Investigating Efficiently Extending Transformers for Long Input Summarization](https://mlsanity.com/paper/2208.04347/) (2022)

## Built on by (most cited first, 30 of 53)

- [LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods](https://mlsanity.com/paper/2412.05579/) (2024)
- [Self-Preference Bias in LLM-as-a-Judge](https://mlsanity.com/paper/2410.21819/) (2024)
- [Judging the Judges: Evaluating Alignment and Vulnerabilities in LLMs-as-Judges](https://mlsanity.com/paper/2406.12624/) (2024)
- [Superfiltering: Weak-to-Strong Data Filtering for Fast Instruction-Tuning](https://mlsanity.com/paper/2402.00530/) (2024)
- [Trust or Escalate: LLM Judges with Provable Guarantees for Human Agreement](https://mlsanity.com/paper/2407.18370/) (2024)
- [FinTextQA: A Dataset for Long-form Financial Question Answering](https://mlsanity.com/paper/2405.09980/) (2024)
- [Extending Context Window of Large Language Models via Semantic Compression](https://mlsanity.com/paper/2312.09571/) (2023)
- [Evaluating Scoring Bias in LLM-as-a-Judge](https://mlsanity.com/paper/2506.22316/) (2025)
- [Revisiting Knowledge Distillation for Autoregressive Language Models](https://mlsanity.com/paper/2402.11890/) (2024)
- [Leveraging Large Language Models for NLG Evaluation: Advances and Challenges](https://mlsanity.com/paper/2401.07103/) (2024)
- [Are LLM-based Evaluators Confusing NLG Quality Criteria?](https://mlsanity.com/paper/2402.12055/) (2024)
- [CopyBench: Measuring Literal and Non-Literal Reproduction of Copyright-Protected Text in Language Model Generation](https://mlsanity.com/paper/2407.07087/) (2024)
- [Towards Reasoning Ability of Small Language Models](https://mlsanity.com/paper/2502.11569/) (2025)
- [Towards Completeness-Oriented Tool Retrieval for Large Language Models](https://mlsanity.com/paper/2405.16089/) (2024)
- [Explainable Generative AI (GenXAI): A Survey, Conceptualization, and Research Agenda](https://mlsanity.com/paper/2404.09554/) (2024)
- [ReLearn: Unlearning via Learning for Large Language Models](https://mlsanity.com/paper/2502.11190/) (2025)
- [TrustJudge: Inconsistencies of LLM-as-a-Judge and How to Alleviate Them](https://mlsanity.com/paper/2509.21117/) (2025)
- [Themis: A Reference-free NLG Evaluation Language Model with Flexibility and Interpretability](https://mlsanity.com/paper/2406.18365/) (2024)
- [Healthcare Copilot: Eliciting the Power of General LLMs for Medical Consultation](https://mlsanity.com/paper/2402.13408/) (2024)
- [Beyond Traditional Benchmarks: Analyzing Behaviors of Open LLMs on Data-to-Text Generation](https://mlsanity.com/paper/2401.10186/) (2024)
- [A User-Centric Multi-Intent Benchmark for Evaluating Large Language Models](https://mlsanity.com/paper/2404.13940/) (2024)
- [CRAFT Your Dataset: Task-Specific Synthetic Dataset Generation Through Corpus Retrieval and Augmentation](https://mlsanity.com/paper/2409.02098/) (2024)
- [Bone Soups: A Seek-and-Soup Model Merging Approach for Controllable Multi-Objective Generation](https://mlsanity.com/paper/2502.10762/) (2025)
- [Uncertainty Aware Learning for Language Model Alignment](https://mlsanity.com/paper/2406.04854/) (2024)
- [ARES: Alternating Reinforcement Learning and Supervised Fine-Tuning for Enhanced Multi-Modal Chain-of-Thought Reasoning Through Diverse AI Feedback](https://mlsanity.com/paper/2407.00087/) (2024)
- [RuleR: Improving LLM Controllability by Rule-based Data Recycling](https://mlsanity.com/paper/2406.15938/) (2024)
- [CharacterGPT: A Persona Reconstruction Framework for Role-Playing Agents](https://mlsanity.com/paper/2405.19778/) (2024)
- [mCSQA: Multilingual Commonsense Reasoning Dataset with Unified Creation Strategy by Language Models and Humans](https://mlsanity.com/paper/2406.04215/) (2024)
- [Rethinking the Roles of Large Language Models in Chinese Grammatical Error Correction](https://mlsanity.com/paper/2402.11420/) (2024)
- [Mosaic-IT: Cost-Free Compositional Data Synthesis for Instruction Tuning](https://mlsanity.com/paper/2405.13326/) (2024)

## Abstract (arXiv)

Large Language Models (LLMs) evaluation is a patchy and inconsistent landscape, and it is becoming clear that the quality of automatic evaluation metrics is not keeping up with the pace of development of generative models. We aim to improve the understanding of current models' performance by providing a preliminary and hybrid evaluation on a range of open and closed-source generative LLMs on three NLP benchmarks: text summarisation, text simplification and grammatical error correction (GEC), using both automatic and human evaluation. We also explore the potential of the recently released GPT-4 to act as an evaluator. We find that ChatGPT consistently outperforms many other popular models according to human reviewers on the majority of metrics, while scoring much more poorly when using classic automatic evaluation metrics. We also find that human reviewers rate the gold reference as much worse than the best models' outputs, indicating the poor quality of many popular benchmarks. Finally, we find that GPT-4 is capable of ranking models' outputs in a way which aligns reasonably closely to human judgement despite task-specific variations, with a lower alignment in the GEC task.