# Exploring Iterative Controllable Summarization with Large Language Models

arXiv: https://arxiv.org/abs/2411.12460 · HTML: https://mlsanity.com/paper/2411.12460/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 46 references that are in the map.
- First posted on arXiv 19 Nov 2024.

## Builds on (most cited first, 30 of 34)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing](https://mlsanity.com/paper/2305.11738/) (2023)
- [Benchmarking Large Language Models for News Summarization](https://mlsanity.com/paper/2301.13848/) (2023)
- [QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarization](https://mlsanity.com/paper/2104.05938/) (2021)
- [News Summarization and Evaluation in the Era of GPT-3](https://mlsanity.com/paper/2209.12356/) (2022)
- [Large Language Models are Better Reasoners with Self-Verification](https://mlsanity.com/paper/2212.09561/) (2022)
- [Towards a Unified Multi-Dimensional Evaluator for Text Generation](https://mlsanity.com/paper/2210.07197/) (2022)
- [QuestEval: Summarization Asks for Fact-based Evaluation](https://mlsanity.com/paper/2103.12693/) (2021)
- [GSum: A General Framework for Guided Neural Abstractive Summarization](https://mlsanity.com/paper/2010.08014/) (2020)
- [Controllable Abstractive Summarization](https://mlsanity.com/paper/1711.05217/) (2017)
- [Benchmarking Generation and Evaluation Capabilities of Large Language Models for Instruction Controllable Summarization](https://mlsanity.com/paper/2311.09184/) (2023)
- [Summ^N: A Multi-Stage Summarization Framework for Long Input Dialogues and Documents](https://mlsanity.com/paper/2110.10150/) (2021)
- [SummIt: Iterative Text Summarization via ChatGPT](https://mlsanity.com/paper/2305.14835/) (2023)
- [Following Length Constraints in Instructions](https://mlsanity.com/paper/2406.17744/) (2024)
- [Exploring Neural Models for Query-Focused Summarization](https://mlsanity.com/paper/2112.07637/) (2021)
- [ASPECTNEWS: Aspect-Oriented Summarization of News Documents](https://mlsanity.com/paper/2110.08296/) (2021)
- [Controllable Neural Dialogue Summarization with Personal Named Entity Planning](https://mlsanity.com/paper/2109.13070/) (2021)
- [DYLE: Dynamic Latent Extraction for Abstractive Long-Input Summarization](https://mlsanity.com/paper/2110.08168/) (2021)
- [Exploring the Numerical Reasoning Capabilities of Language Models: A Comprehensive Analysis on Tabular Data](https://mlsanity.com/paper/2311.02216/) (2023)
- [NEWTS: A Corpus for News Topic-Focused Summarization](https://mlsanity.com/paper/2205.15661/) (2022)
- [Generating Summaries with Controllable Readability Levels](https://mlsanity.com/paper/2310.10623/) (2023)
- [EntSUM: A Data Set for Entity-Centric Summarization](https://mlsanity.com/paper/2204.02213/) (2022)
- [Controllable Text Summarization: Unraveling Challenges, Approaches, and Prospects -- A Survey](https://mlsanity.com/paper/2311.09212/) (2023)
- [Socratic Pretraining: Question-Driven Pretraining for Controllable Summarization](https://mlsanity.com/paper/2212.10449/) (2022)

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

- [Simulating Students or Sycophantic Problem Solving? On Misconception Faithfulness of LLM Simulators](https://mlsanity.com/paper/2605.12748/) (2026)

## Abstract (arXiv)

Large language models (LLMs) have demonstrated remarkable performance in abstractive summarization tasks. However, their ability to precisely control summary attributes (e.g., length or topic) remains underexplored, limiting their adaptability to specific user preferences. In this paper, we systematically explore the controllability of LLMs. To this end, we revisit summary attribute measurements and introduce iterative evaluation metrics, failure rate and average iteration count to precisely evaluate controllability of LLMs, rather than merely assessing errors. Our findings show that LLMs struggle more with numerical attributes than with linguistic attributes. To address this challenge, we propose a guide-to-explain framework (GTE) for controllable summarization. Our GTE framework enables the model to identify misaligned attributes in the initial draft and guides it in self-explaining errors in the previous output. By allowing the model to reflect on its misalignment, GTE generates well-adjusted summaries that satisfy the desired attributes with robust effectiveness, requiring surprisingly fewer iterations than other iterative approaches.