# Can Large Language Model Summarizers Adapt to Diverse Scientific Communication Goals?

arXiv: https://arxiv.org/abs/2401.10415 · HTML: https://mlsanity.com/paper/2401.10415/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 44 references that are in the map.
- First posted on arXiv 18 Jan 2024.

## Builds on (most cited first, 26 of 26)

- [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)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [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)
- [SummEval: Re-evaluating Summarization Evaluation](https://mlsanity.com/paper/2007.12626/) (2020)
- [A Discourse-Aware Attention Model for Abstractive Summarization of Long Documents](https://mlsanity.com/paper/1804.05685/) (2018)
- [Benchmarking Large Language Models for News Summarization](https://mlsanity.com/paper/2301.13848/) (2023)
- [News Summarization and Evaluation in the Era of GPT-3](https://mlsanity.com/paper/2209.12356/) (2022)
- [All That's 'Human' Is Not Gold: Evaluating Human Evaluation of Generated Text](https://mlsanity.com/paper/2107.00061/) (2021)
- [LongT5: Efficient Text-To-Text Transformer for Long Sequences](https://mlsanity.com/paper/2112.07916/) (2021)
- [Sources of Hallucination by Large Language Models on Inference Tasks](https://mlsanity.com/paper/2305.14552/) (2023)
- [Controllable Abstractive Summarization](https://mlsanity.com/paper/1711.05217/) (2017)
- [Stay on topic with Classifier-Free Guidance](https://mlsanity.com/paper/2306.17806/) (2023)
- [Element-aware Summarization with Large Language Models: Expert-aligned Evaluation and Chain-of-Thought Method](https://mlsanity.com/paper/2305.13412/) (2023)
- [Gradient-Based Constrained Sampling from Language Models](https://mlsanity.com/paper/2205.12558/) (2022)
- [Making Science Simple: Corpora for the Lay Summarisation of Scientific Literature](https://mlsanity.com/paper/2210.09932/) (2022)
- [What Comes Next? Evaluating Uncertainty in Neural Text Generators Against Human Production Variability](https://mlsanity.com/paper/2305.11707/) (2023)
- [Investigating Efficiently Extending Transformers for Long Input Summarization](https://mlsanity.com/paper/2208.04347/) (2022)
- [Long Document Summarization with Top-down and Bottom-up Inference](https://mlsanity.com/paper/2203.07586/) (2022)
- [Large Language Models and the Reverse Turing Test](https://mlsanity.com/paper/2207.14382/) (2022)
- [ASPECTNEWS: Aspect-Oriented Summarization of News Documents](https://mlsanity.com/paper/2110.08296/) (2021)
- [EntSUM: A Data Set for Entity-Centric Summarization](https://mlsanity.com/paper/2204.02213/) (2022)
- [Adapting Pretrained Text-to-Text Models for Long Text Sequences](https://mlsanity.com/paper/2209.10052/) (2022)
- [Factorizing Content and Budget Decisions in Abstractive Summarization of Long Documents](https://mlsanity.com/paper/2205.12486/) (2022)

## Built on by (most cited first, 6 of 6)

- [Koel-TTS: Enhancing LLM based Speech Generation with Preference Alignment and Classifier Free Guidance](https://mlsanity.com/paper/2502.05236/) (2025)
- [Zero-Shot Strategies for Length-Controllable Summarization](https://mlsanity.com/paper/2501.00233/) (2024)
- [Rethinking Scientific Summarization Evaluation: Grounding Explainable Metrics on Facet-aware Benchmark](https://mlsanity.com/paper/2402.14359/) (2024)
- [A Critical Look at Meta-evaluating Summarisation Evaluation Metrics](https://mlsanity.com/paper/2409.19507/) (2024)
- [Beyond In-Context Learning: Aligning Long-form Generation of Large Language Models via Task-Inherent Attribute Guidelines](https://mlsanity.com/paper/2506.01265/) (2025)
- [Summarization is Not Dead Yet](https://mlsanity.com/paper/2606.08000/) (2026)

## Abstract (arXiv)

In this work, we investigate the controllability of large language models (LLMs) on scientific summarization tasks. We identify key stylistic and content coverage factors that characterize different types of summaries such as paper reviews, abstracts, and lay summaries. By controlling stylistic features, we find that non-fine-tuned LLMs outperform humans in the MuP review generation task, both in terms of similarity to reference summaries and human preferences. Also, we show that we can improve the controllability of LLMs with keyword-based classifier-free guidance (CFG) while achieving lexical overlap comparable to strong fine-tuned baselines on arXiv and PubMed. However, our results also indicate that LLMs cannot consistently generate long summaries with more than 8 sentences. Furthermore, these models exhibit limited capacity to produce highly abstractive lay summaries. Although LLMs demonstrate strong generic summarization competency, sophisticated content control without costly fine-tuning remains an open problem for domain-specific applications.