# Learning to Summarize from LLM-generated Feedback

arXiv: https://arxiv.org/abs/2410.13116 · HTML: https://mlsanity.com/paper/2410.13116/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Placed in Human values and AI feedback alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 45 of its 59 references that are in the map.
- First posted on arXiv 17 Oct 2024.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Human values and AI feedback alignment](https://mlsanity.com/alignment/human-values-and-ai-feedback-alignment/)

## Builds on (most cited first, 30 of 45)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [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)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [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)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization](https://mlsanity.com/paper/1912.08777/) (2019)
- [On Faithfulness and Factuality in Abstractive Summarization](https://mlsanity.com/paper/2005.00661/) (2020)
- [Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond](https://mlsanity.com/paper/1602.06023/) (2016)
- [RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback](https://mlsanity.com/paper/2309.00267/) (2023)
- [Text Summarization with Pretrained Encoders](https://mlsanity.com/paper/1908.08345/) (2019)
- [A Discourse-Aware Attention Model for Abstractive Summarization of Long Documents](https://mlsanity.com/paper/1804.05685/) (2018)
- [Is ChatGPT a Good NLG Evaluator? A Preliminary Study](https://mlsanity.com/paper/2303.04048/) (2023)
- [SummaC: Re-Visiting NLI-based Models for Inconsistency Detection in Summarization](https://mlsanity.com/paper/2111.09525/) (2021)
- [Hallucination of Multimodal Large Language Models: A Survey](https://mlsanity.com/paper/2404.18930/) (2024)
- [Efficient Attentions for Long Document Summarization](https://mlsanity.com/paper/2104.02112/) (2021)
- [Understanding Factuality in Abstractive Summarization with FRANK: A Benchmark for Factuality Metrics](https://mlsanity.com/paper/2104.13346/) (2021)
- [Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging](https://mlsanity.com/paper/2310.11564/) (2023)
- [Towards a Unified Multi-Dimensional Evaluator for Text Generation](https://mlsanity.com/paper/2210.07197/) (2022)
- [MiniCheck: Efficient Fact-Checking of LLMs on Grounding Documents](https://mlsanity.com/paper/2404.10774/) (2024)
- [QAFactEval: Improved QA-Based Factual Consistency Evaluation for Summarization](https://mlsanity.com/paper/2112.08542/) (2021)
- [WikiHow: A Large Scale Text Summarization Dataset](https://mlsanity.com/paper/1810.09305/) (2018)
- [DialogSum: A Real-Life Scenario Dialogue Summarization Dataset](https://mlsanity.com/paper/2105.06762/) (2021)
- [Re-evaluating Evaluation in Text Summarization](https://mlsanity.com/paper/2010.07100/) (2020)
- [Controllable Preference Optimization: Toward Controllable Multi-Objective Alignment](https://mlsanity.com/paper/2402.19085/) (2024)
- [MediaSum: A Large-scale Media Interview Dataset for Dialogue Summarization](https://mlsanity.com/paper/2103.06410/) (2021)

## Built on by (most cited first, 24 of 24)

- [EXIT: Context-Aware Extractive Compression for Enhancing Retrieval-Augmented Generation](https://mlsanity.com/paper/2412.12559/) (2024)
- [PIIvot: A Lightweight NLP Anonymization Framework for Question-Anchored Tutoring Dialogues](https://mlsanity.com/paper/2505.16931/) (2025)
- [Learning to summarize user information for personalized reinforcement learning from human feedback](https://mlsanity.com/paper/2507.13579/) (2025)
- [The Bias is in the Details: An Assessment of Cognitive Bias in LLMs](https://mlsanity.com/paper/2509.22856/) (2025)
- [Hallucinate at the Last in Long Response Generation: A Case Study on Long Document Summarization](https://mlsanity.com/paper/2505.15291/) (2025)
- [Unraveling Misinformation Propagation in LLM Reasoning](https://mlsanity.com/paper/2505.18555/) (2025)
- [Flex-Judge: Text-Only Reasoning Unleashes Zero-Shot Multimodal Evaluators](https://mlsanity.com/paper/2505.18601/) (2025)
- [ReFeed: Multi-dimensional Summarization Refinement with Reflective Reasoning on Feedback](https://mlsanity.com/paper/2503.21332/) (2025)
- [FeedEval: Pedagogically Aligned Evaluation of LLM-Generated Essay Feedback](https://mlsanity.com/paper/2601.04574/) (2026)
- [Learning to Control Summaries with Score Ranking](https://mlsanity.com/paper/2604.17197/) (2026)
- [Calibrating Model-Based Evaluation Metrics for Summarization](https://mlsanity.com/paper/2604.17200/) (2026)
- [Aligning Extraction and Generation for Robust Retrieval-Augmented Generation](https://mlsanity.com/paper/2503.04789/) (2025)
- [Adaptive Planning for Multi-Attribute Controllable Summarization with Monte Carlo Tree Search](https://mlsanity.com/paper/2509.26435/) (2025)
- [What Are They Talking About? A Benchmark of Knowledge-Grounded Discussion Summarization](https://mlsanity.com/paper/2505.12474/) (2025)
- [Alignment Tuning for Large Language Models: A Data-Centric Lens on Alignment Data Pipelines](https://mlsanity.com/paper/2605.26442/) (2026)
- [A Large-Scale Multi-Dimensional Empirical Study of LLMs for Conversation Summarization](https://mlsanity.com/paper/2606.15974/) (2026)
- [References Indeed Matter? Reference-Free Preference Optimization for Conversational Query Reformulation](https://mlsanity.com/paper/2505.06552/) (2025)
- [MARCO: Meta-Reflection with Cross-Referencing for Code Reasoning](https://mlsanity.com/paper/2505.17481/) (2025)
- [Keystep Recognition using Graph Neural Networks](https://mlsanity.com/paper/2506.01102/) (2025)
- [DIAL-SUMMER: A Structured Evaluation Framework of Hierarchical Errors in Dialogue Summaries](https://mlsanity.com/paper/2602.08149/) (2026)
- [Beyond Overlap Metrics: Rewarding Reasoning and Preferences for Faithful Multi-Role Dialogue Summarization](https://mlsanity.com/paper/2604.17188/) (2026)
- [LLM-ReSum: A Framework for LLM Reflective Summarization through Self-Evaluation](https://mlsanity.com/paper/2604.25665/) (2026)
- [Distilling Long-CoT Reasoning through Collaborative Step-wise Multi-Teacher Decoding](https://mlsanity.com/paper/2605.02290/) (2026)
- [Ready2Blend: From Natural-Language Instructions to Composable Alignment Prompts](https://mlsanity.com/paper/2609.39365/) (2026)

## Abstract (arXiv)

Developing effective text summarizers remains a challenge due to issues like hallucinations, key information omissions, and verbosity in LLM-generated summaries. This work explores using LLM-generated feedback to improve summary quality by aligning the summaries with human preferences for faithfulness, completeness, and conciseness. We introduce FeedSum, a large-scale dataset containing multi-dimensional LLM feedback on summaries of varying quality across diverse domains. Our experiments show how feedback quality, dimensionality, and granularity influence preference learning, revealing that high-quality, multi-dimensional, fine-grained feedback significantly improves summary generation. We also compare two methods for using this feedback: supervised fine-tuning and direct preference optimization. Finally, we introduce SummLlama3-8b, a model that outperforms the nearly 10x larger Llama3-70b-instruct in generating human-preferred summaries, demonstrating that smaller models can achieve superior performance with appropriate training. The full dataset and SummLlama3-8B model are available at https://huggingface.co/datasets/DISLab/FeedSum and https://huggingface.co/DISLab/SummLlama3-8B.