# On Learning to Summarize with Large Language Models as References

arXiv: https://arxiv.org/abs/2305.14239 · HTML: https://mlsanity.com/paper/2305.14239/

## Key facts

- Cited by 80 papers in the map (data through 14 Oct 2026).
- Builds on 59 of its 86 references that are in the map.
- First posted on arXiv 23 May 2023.

## Builds on (most cited first, 30 of 59)

- [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)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization](https://mlsanity.com/paper/1808.08745/) (2018)
- [On Faithfulness and Factuality in Abstractive Summarization](https://mlsanity.com/paper/2005.00661/) (2020)
- [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)
- [Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks](https://mlsanity.com/paper/1506.03099/) (2015)
- [Sequence-Level Knowledge Distillation](https://mlsanity.com/paper/1606.07947/) (2016)
- [AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback](https://mlsanity.com/paper/2305.14387/) (2023)
- [Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes](https://mlsanity.com/paper/2305.02301/) (2023)
- [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)
- [Sequence Level Training with Recurrent Neural Networks](https://mlsanity.com/paper/1511.06732/) (2015)
- [RRHF: Rank Responses to Align Language Models with Human Feedback without tears](https://mlsanity.com/paper/2304.05302/) (2023)
- [Benchmarking Large Language Models for News Summarization](https://mlsanity.com/paper/2301.13848/) (2023)
- [Is ChatGPT a Good NLG Evaluator? A Preliminary Study](https://mlsanity.com/paper/2303.04048/) (2023)
- [SLiC-HF: Sequence Likelihood Calibration with Human Feedback](https://mlsanity.com/paper/2305.10425/) (2023)
- [A Deep Reinforced Model for Abstractive Summarization](https://mlsanity.com/paper/1705.04304/) (2017)
- [GPTScore: Evaluate as You Desire](https://mlsanity.com/paper/2302.04166/) (2023)
- [News Summarization and Evaluation in the Era of GPT-3](https://mlsanity.com/paper/2209.12356/) (2022)
- [Deep Reinforcement Learning for Dialogue Generation](https://mlsanity.com/paper/1606.01541/) (2016)
- [Reward Design with Language Models](https://mlsanity.com/paper/2303.00001/) (2023)
- [The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics](https://mlsanity.com/paper/2102.01672/) (2021)

## Built on by (most cited first, 30 of 80)

- [Learn-by-interact: A Data-Centric Framework for Self-Adaptive Agents in Realistic Environments](https://mlsanity.com/paper/2501.10893/) (2025)
- [User-LLM: Efficient LLM Contextualization with User Embeddings](https://mlsanity.com/paper/2402.13598/) (2024)
- [Open-LLM-Leaderboard: From Multi-choice to Open-style Questions for LLMs Evaluation, Benchmark, and Arena](https://mlsanity.com/paper/2406.07545/) (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)
- [A Systematic Survey of Text Summarization: From Statistical Methods to Large Language Models](https://mlsanity.com/paper/2406.11289/) (2024)
- [Beyond Factuality: A Comprehensive Evaluation of Large Language Models as Knowledge Generators](https://mlsanity.com/paper/2310.07289/) (2023)
- [MathVC: An LLM-Simulated Multi-Character Virtual Classroom for Mathematics Education](https://mlsanity.com/paper/2404.06711/) (2024)
- [Beyond Imitation: Leveraging Fine-grained Quality Signals for Alignment](https://mlsanity.com/paper/2311.04072/) (2023)
- [On Context Utilization in Summarization with Large Language Models](https://mlsanity.com/paper/2310.10570/) (2023)
- [Data Augmentation using Large Language Models: Data Perspectives, Learning Paradigms and Challenges](https://mlsanity.com/paper/2403.02990/) (2024)
- [Multi-Agent-as-Judge: Aligning LLM-Agent-Based Automated Evaluation with Multi-Dimensional Human Evaluation](https://mlsanity.com/paper/2507.21028/) (2025)
- [Multi-Layer Transformers Gradient Can be Approximated in Almost Linear Time](https://mlsanity.com/paper/2408.13233/) (2024)
- [Themis: A Reference-free NLG Evaluation Language Model with Flexibility and Interpretability](https://mlsanity.com/paper/2406.18365/) (2024)
- [RAPID: Efficient Retrieval-Augmented Long Text Generation with Writing Planning and Information Discovery](https://mlsanity.com/paper/2503.00751/) (2025)
- [A Survey of Sustainability in Large Language Models: Applications, Economics, and Challenges](https://mlsanity.com/paper/2412.04782/) (2024)
- [DecipherPref: Analyzing Influential Factors in Human Preference Judgments via GPT-4](https://mlsanity.com/paper/2305.14702/) (2023)
- [ALLURE: Auditing and Improving LLM-based Evaluation of Text using Iterative In-Context-Learning](https://mlsanity.com/paper/2309.13701/) (2023)
- [HalluVerse25: Fine-grained Multilingual Benchmark Dataset for LLM Hallucinations](https://mlsanity.com/paper/2503.07833/) (2025)
- [CycleAlign: Iterative Distillation from Black-box LLM to White-box Models for Better Human Alignment](https://mlsanity.com/paper/2310.16271/) (2023)
- [Adapting Large Language Models for Education: Foundational Capabilities, Potentials, and Challenges](https://mlsanity.com/paper/2401.08664/) (2023)
- [TriSum: Learning Summarization Ability from Large Language Models with Structured Rationale](https://mlsanity.com/paper/2403.10351/) (2024)
- [Learning to Substitute Words with Model-based Score Ranking](https://mlsanity.com/paper/2502.05933/) (2025)
- [The Blessing and Curse of Dimensionality in Safety Alignment](https://mlsanity.com/paper/2507.20333/) (2025)
- [Affordable Generative Agents](https://mlsanity.com/paper/2402.02053/) (2024)
- [Focusing by Contrastive Attention: Enhancing VLMs' Visual Reasoning](https://mlsanity.com/paper/2509.06461/) (2025)
- [A Guide To Effectively Leveraging LLMs for Low-Resource Text Summarization: Data Augmentation and Semi-supervised Approaches](https://mlsanity.com/paper/2407.07341/) (2024)
- [Text Generation Models for Luxembourgish with Limited Data: A Balanced Multilingual Strategy](https://mlsanity.com/paper/2412.09415/) (2024)
- [Multi-Dimensional Optimization for Text Summarization via Reinforcement Learning](https://mlsanity.com/paper/2406.00303/) (2024)
- [Factual Dialogue Summarization via Learning from Large Language Models](https://mlsanity.com/paper/2406.14709/) (2024)

## Abstract (arXiv)

Recent studies have found that summaries generated by large language models (LLMs) are favored by human annotators over the original reference summaries in commonly used summarization datasets. Therefore, we study an LLM-as-reference learning setting for smaller text summarization models to investigate whether their performance can be substantially improved. To this end, we use LLMs as both oracle summary generators for standard supervised fine-tuning and oracle summary evaluators for efficient contrastive learning that leverages the LLMs' supervision signals. We conduct comprehensive experiments with source news articles and find that (1) summarization models trained under the LLM-as-reference setting achieve significant performance improvement in both LLM and human evaluations; (2) contrastive learning outperforms standard supervised fine-tuning under both low and high resource settings. Our experimental results also enable a meta-analysis of LLMs' summary evaluation capacities under a challenging setting, showing that LLMs are not well-aligned with human evaluators. Particularly, our expert human evaluation reveals remaining nuanced performance gaps between LLMs and our fine-tuned models, which LLMs fail to capture. Thus, we call for further studies into both the potential and challenges of using LLMs in summarization model development.