# Reading Subtext: Evaluating Large Language Models on Short Story Summarization with Writers

arXiv: https://arxiv.org/abs/2403.01061 · HTML: https://mlsanity.com/paper/2403.01061/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 62 references that are in the map.
- First posted on arXiv 2 Mar 2024.

## Builds on (most cited first, 30 of 37)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation](https://mlsanity.com/paper/2305.14251/) (2023)
- [Teaching Machines to Read and Comprehend](https://mlsanity.com/paper/1506.03340/) (2015)
- [Large Language Models](https://mlsanity.com/paper/2307.05782/) (2023)
- [SummEval: Re-evaluating Summarization Evaluation](https://mlsanity.com/paper/2007.12626/) (2020)
- [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)
- [Newsroom: A Dataset of 1.3 Million Summaries with Diverse Extractive Strategies](https://mlsanity.com/paper/1804.11283/) (2018)
- [Recursively Summarizing Books with Human Feedback](https://mlsanity.com/paper/2109.10862/) (2021)
- [AlignScore: Evaluating Factual Consistency with a Unified Alignment Function](https://mlsanity.com/paper/2305.16739/) (2023)
- [Towards a Unified Multi-Dimensional Evaluator for Text Generation](https://mlsanity.com/paper/2210.07197/) (2022)
- [QAFactEval: Improved QA-Based Factual Consistency Evaluation for Summarization](https://mlsanity.com/paper/2112.08542/) (2021)
- [Does Writing with Language Models Reduce Content Diversity?](https://mlsanity.com/paper/2309.05196/) (2023)
- [BookSum: A Collection of Datasets for Long-form Narrative Summarization](https://mlsanity.com/paper/2105.08209/) (2021)
- [Art or Artifice? Large Language Models and the False Promise of Creativity](https://mlsanity.com/paper/2309.14556/) (2023)
- [BooookScore: A systematic exploration of book-length summarization in the era of LLMs](https://mlsanity.com/paper/2310.00785/) (2023)
- [Understanding Factual Errors in Summarization: Errors, Summarizers, Datasets, Error Detectors](https://mlsanity.com/paper/2205.12854/) (2022)
- [LongEval: Guidelines for Human Evaluation of Faithfulness in Long-form Summarization](https://mlsanity.com/paper/2301.13298/) (2023)
- [Fantastic Questions and Where to Find Them: FairytaleQA -- An Authentic Dataset for Narrative Comprehension](https://mlsanity.com/paper/2203.13947/) (2022)
- [SummScreen: A Dataset for Abstractive Screenplay Summarization](https://mlsanity.com/paper/2104.07091/) (2021)
- [Help me write a poem: Instruction Tuning as a Vehicle for Collaborative Poetry Writing](https://mlsanity.com/paper/2210.13669/) (2022)
- [Creative Writing with an AI-Powered Writing Assistant: Perspectives from Professional Writers](https://mlsanity.com/paper/2211.05030/) (2022)
- [Benchmarking Generation and Evaluation Capabilities of Large Language Models for Instruction Controllable Summarization](https://mlsanity.com/paper/2311.09184/) (2023)
- [TofuEval: Evaluating Hallucinations of LLMs on Topic-Focused Dialogue Summarization](https://mlsanity.com/paper/2402.13249/) (2024)
- [OpenToM: A Comprehensive Benchmark for Evaluating Theory-of-Mind Reasoning Capabilities of Large Language Models](https://mlsanity.com/paper/2402.06044/) (2024)
- [SQuALITY: Building a Long-Document Summarization Dataset the Hard Way](https://mlsanity.com/paper/2205.11465/) (2022)
- [Summarization is (Almost) Dead](https://mlsanity.com/paper/2309.09558/) (2023)
- [Evaluation of African American Language Bias in Natural Language Generation](https://mlsanity.com/paper/2305.14291/) (2023)
- [A Comprehensive Evaluation of Large Language Models on Benchmark Biomedical Text Processing Tasks](https://mlsanity.com/paper/2310.04270/) (2023)

## Built on by (most cited first, 19 of 19)

- [Can AI writing be salvaged? Mitigating Idiosyncrasies and Improving Human-AI Alignment in the Writing Process through Edits](https://mlsanity.com/paper/2409.14509/) (2024)
- [HEART-felt Narratives: Tracing Empathy and Narrative Style in Personal Stories with LLMs](https://mlsanity.com/paper/2405.17633/) (2024)
- [GINGER: Grounded Information Nugget-Based Generation of Responses](https://mlsanity.com/paper/2503.18174/) (2025)
- [STORYSUMM: Evaluating Faithfulness in Story Summarization](https://mlsanity.com/paper/2407.06501/) (2024)
- [Revealing and Mitigating the Challenge of Detecting Character Knowledge Errors in LLM Role-Playing](https://mlsanity.com/paper/2409.11726/) (2024)
- [LLMs as Span Annotators: A Comparative Study of LLMs and Humans](https://mlsanity.com/paper/2504.08697/) (2025)
- [Empowering Meta-Analysis: Leveraging Large Language Models for Scientific Synthesis](https://mlsanity.com/paper/2411.10878/) (2024)
- [Using LLM-as-a-Judge/Jury to Advance Scalable, Clinically-Validated Safety Evaluations of Model Responses to Users Demonstrating Psychosis](https://mlsanity.com/paper/2604.02359/) (2026)
- [Guiding Generative Storytelling with Knowledge Graphs](https://mlsanity.com/paper/2505.24803/) (2025)
- [Literary Evidence Retrieval via Long-Context Language Models](https://mlsanity.com/paper/2506.03090/) (2025)
- [UiS-IAI@LiveRAG: Retrieval-Augmented Information Nugget-Based Generation of Responses](https://mlsanity.com/paper/2506.22210/) (2025)
- [Are You There God? Lightweight Narrative Annotation of Christian Fiction with LMs](https://mlsanity.com/paper/2507.19756/) (2025)
- [NARRA-Gym for Evaluating Interactive Narrative Agents](https://mlsanity.com/paper/2605.08503/) (2026)
- [Is the Top Still Spinning? Evaluating Subjectivity in Narrative Understanding](https://mlsanity.com/paper/2504.01132/) (2025)
- [PEPS: Quantum-Inspired Reinforcement Learning for Coherent Reasoning Traces in LLMs](https://mlsanity.com/paper/2509.20105/) (2025)
- [LitVISTA: A Benchmark for Narrative Orchestration in Literary Text](https://mlsanity.com/paper/2601.06445/) (2026)
- [Beneath the Surface: Investigating LLMs' Capabilities for Communicating with Subtext](https://mlsanity.com/paper/2604.05273/) (2026)
- [FocalLens: Visualizing Narratives through Focalization](https://mlsanity.com/paper/2604.14456/) (2026)
- [Evaluating Epistemic Guardrails in AI Reading Assistants: A Behavioral Audit of a Minimal Prototype](https://mlsanity.com/paper/2604.27275/) (2026)

## Abstract (arXiv)

We evaluate recent Large Language Models (LLMs) on the challenging task of summarizing short stories, which can be lengthy, and include nuanced subtext or scrambled timelines. Importantly, we work directly with authors to ensure that the stories have not been shared online (and therefore are unseen by the models), and to obtain informed evaluations of summary quality using judgments from the authors themselves. Through quantitative and qualitative analysis grounded in narrative theory, we compare GPT-4, Claude-2.1, and LLama-2-70B. We find that all three models make faithfulness mistakes in over 50% of summaries and struggle with specificity and interpretation of difficult subtext. We additionally demonstrate that LLM ratings and other automatic metrics for summary quality do not correlate well with the quality ratings from the writers.