# Show, Don't Tell: Uncovering Implicit Character Portrayal using LLMs

arXiv: https://arxiv.org/abs/2412.04576 · HTML: https://mlsanity.com/paper/2412.04576/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 31 references that are in the map.
- First posted on arXiv 5 Dec 2024.

## Builds on (most cited first, 22 of 22)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [Least-to-Most Prompting Enables Complex Reasoning in Large Language Models](https://mlsanity.com/paper/2205.10625/) (2022)
- [Hierarchical Neural Story Generation](https://mlsanity.com/paper/1805.04833/) (2018)
- [Discovering Language Model Behaviors with Model-Written Evaluations](https://mlsanity.com/paper/2212.09251/) (2022)
- [LLM Evaluators Recognize and Favor Their Own Generations](https://mlsanity.com/paper/2404.13076/) (2024)
- [COMET: Commonsense Transformers for Automatic Knowledge Graph Construction](https://mlsanity.com/paper/1906.05317/) (2019)
- [TinyStories: How Small Can Language Models Be and Still Speak Coherent English?](https://mlsanity.com/paper/2305.07759/) (2023)
- [A Corpus and Evaluation Framework for Deeper Understanding of Commonsense Stories](https://mlsanity.com/paper/1604.01696/) (2016)
- [Large Language Model as Attributed Training Data Generator: A Tale of Diversity and Bias](https://mlsanity.com/paper/2306.15895/) (2023)
- [Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMs](https://mlsanity.com/paper/2311.04892/) (2023)
- [Large Legal Fictions: Profiling Legal Hallucinations in Large Language Models](https://mlsanity.com/paper/2401.01301/) (2024)
- [Evaluating and Mitigating Discrimination in Language Model Decisions](https://mlsanity.com/paper/2312.03689/) (2023)
- [Modeling Protagonist Emotions for Emotion-Aware Storytelling](https://mlsanity.com/paper/2010.06822/) (2020)
- [Uncovering Implicit Gender Bias in Narratives through Commonsense Inference](https://mlsanity.com/paper/2109.06437/) (2021)
- [Heroes, Villains, and Victims, and GPT-3: Automated Extraction of Character Roles Without Training Data](https://mlsanity.com/paper/2205.07557/) (2022)
- ["They are uncultured": Unveiling Covert Harms and Social Threats in LLM Generated Conversations](https://mlsanity.com/paper/2405.05378/) (2024)
- [Shirtless and Dangerous: Quantifying Linguistic Signals of Gender Bias in an Online Fiction Writing Community](https://mlsanity.com/paper/1603.08832/) (2016)
- [The GPT-WritingPrompts Dataset: A Comparative Analysis of Character Portrayal in Short Stories](https://mlsanity.com/paper/2406.16767/) (2024)
- [Portrayal: Leveraging NLP and Visualization for Analyzing Fictional Characters](https://mlsanity.com/paper/2308.04056/) (2023)
- [DramatVis Personae: Visual Text Analytics for Identifying Social Biases in Creative Writing](https://mlsanity.com/paper/2209.00320/) (2022)

## Built on by (most cited first, 3 of 3)

- [Are You There God? Lightweight Narrative Annotation of Christian Fiction with LMs](https://mlsanity.com/paper/2507.19756/) (2025)
- [Story Ribbons: Reimagining Storyline Visualizations with Large Language Models](https://mlsanity.com/paper/2508.06772/) (2025)
- [CASPER in the Machine: Insights into Character Variety in LLM-Generated Stories](https://mlsanity.com/paper/2606.22454/) (2026)

## Abstract (arXiv)

Tools for analyzing character portrayal in fiction are valuable for writers and literary scholars in developing and interpreting compelling stories. Existing tools, such as visualization tools for analyzing fictional characters, primarily rely on explicit textual indicators of character attributes. However, portrayal is often implicit, revealed through actions and behaviors rather than explicit statements. We address this gap by leveraging large language models (LLMs) to uncover implicit character portrayals. We start by generating a dataset for this task with greater cross-topic similarity, lexical diversity, and narrative lengths than existing narrative text corpora such as TinyStories and WritingPrompts. We then introduce LIIPA (LLMs for Inferring Implicit Portrayal for Character Analysis), a framework for prompting LLMs to uncover character portrayals. LIIPA can be configured to use various types of intermediate computation (character attribute word lists, chain-of-thought) to infer how fictional characters are portrayed in the source text. We find that LIIPA outperforms existing approaches, and is more robust to increasing character counts (number of unique persons depicted) due to its ability to utilize full narrative context. Lastly, we investigate the sensitivity of portrayal estimates to character demographics, identifying a fairness-accuracy tradeoff among methods in our LIIPA framework -- a phenomenon familiar within the algorithmic fairness literature. Despite this tradeoff, all LIIPA variants consistently outperform non-LLM baselines in both fairness and accuracy. Our work demonstrates the potential benefits of using LLMs to analyze complex characters and to better understand how implicit portrayal biases may manifest in narrative texts.