# Exposing the Unsaid: Visualizing Hidden LLM Bias through Stochastic Path Aggregation

arXiv: https://arxiv.org/abs/2606.19344 · HTML: https://mlsanity.com/paper/2606.19344/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 41 references that are in the map.
- First posted on arXiv 24 Apr 2026.

## Builds on (most cited first, 28 of 28)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Red Teaming Language Models with Language Models](https://mlsanity.com/paper/2202.03286/) (2022)
- [Beyond Accuracy: Behavioral Testing of NLP models with CheckList](https://mlsanity.com/paper/2005.04118/) (2020)
- [StereoSet: Measuring stereotypical bias in pretrained language models](https://mlsanity.com/paper/2004.09456/) (2020)
- [CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models](https://mlsanity.com/paper/2010.00133/) (2020)
- [Bias and Fairness in Large Language Models: A Survey](https://mlsanity.com/paper/2309.00770/) (2023)
- [The Woman Worked as a Babysitter: On Biases in Language Generation](https://mlsanity.com/paper/1909.01326/) (2019)
- [Towards Understanding and Mitigating Social Biases in Language Models](https://mlsanity.com/paper/2106.13219/) (2021)
- [A Multiscale Visualization of Attention in the Transformer Model](https://mlsanity.com/paper/1906.05714/) (2019)
- [Surface Form Competition: Why the Highest Probability Answer Isn't Always Right](https://mlsanity.com/paper/2104.08315/) (2021)
- [PromptRobust: Towards Evaluating the Robustness of Large Language Models on Adversarial Prompts](https://mlsanity.com/paper/2306.04528/) (2023)
- [Societal Biases in Language Generation: Progress and Challenges](https://mlsanity.com/paper/2105.04054/) (2021)
- [Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyond](https://mlsanity.com/paper/2109.00725/) (2021)
- ["I'm sorry to hear that": Finding New Biases in Language Models with a Holistic Descriptor Dataset](https://mlsanity.com/paper/2205.09209/) (2022)
- [The Language Interpretability Tool: Extensible, Interactive Visualizations and Analysis for NLP Models](https://mlsanity.com/paper/2008.05122/) (2020)
- [Attention Flows: Analyzing and Comparing Attention Mechanisms in Language Models](https://mlsanity.com/paper/2009.07053/) (2020)
- [Embedding Comparator: Visualizing Differences in Global Structure and Local Neighborhoods via Small Multiples](https://mlsanity.com/paper/1912.04853/) (2019)
- [LLM Comparator: Visual Analytics for Side-by-Side Evaluation of Large Language Models](https://mlsanity.com/paper/2402.10524/) (2024)
- [Benchmarking Adversarial Robustness to Bias Elicitation in Large Language Models: Scalable Automated Assessment with LLM-as-a-Judge](https://mlsanity.com/paper/2504.07887/) (2025)
- [Informativeness and Invariance: Two Perspectives on Spurious Correlations in Natural Language](https://mlsanity.com/paper/2204.04487/) (2022)
- [Using Natural Sentences for Understanding Biases in Language Models](https://mlsanity.com/paper/2205.06303/) (2022)
- [LMdiff: A Visual Diff Tool to Compare Language Models](https://mlsanity.com/paper/2111.01582/) (2021)
- [Visual Comparison of Language Model Adaptation](https://mlsanity.com/paper/2208.08176/) (2022)
- [Understanding Large Language Model Behaviors through Interactive Counterfactual Generation and Analysis](https://mlsanity.com/paper/2405.00708/) (2024)
- [Mind Your Bias: A Critical Review of Bias Detection Methods for Contextual Language Models](https://mlsanity.com/paper/2211.08461/) (2022)
- [Revealing the Unwritten: Visual Investigation of Beam Search Trees to Address Language Model Prompting Challenges](https://mlsanity.com/paper/2310.11252/) (2023)
- [Learning the Wrong Lessons: Syntactic-Domain Spurious Correlations in Language Models](https://mlsanity.com/paper/2509.21155/) (2025)
- [generAItor: Tree-in-the-Loop Text Generation for Language Model Explainability and Adaptation](https://mlsanity.com/paper/2403.07627/) (2024)

## Abstract (arXiv)

Large Language Models (LLMs) exhibit representational and syntactic biases that are difficult to evaluate due to the stochastic nature of text generation. Standard auditing methods rely on a single output inspection or static automated metrics. These approaches obscure the underlying probability distributions and fail to capture biases hidden in lower-probability generation branches. This paper introduces TreeTracer, a visual analytics tool designed to evaluate LLM bias through aggregated comparison. Using a systematic perturbation analysis pipeline, the tool replaces ontology-defined terms in each input prompt, aggregates hundreds of stochastic generations into a syntax-aligned hierarchical structure, and then performs classification-aware node merging with an auxiliary language model. The resulting structure is visualized through a custom Sankey diagram. By juxtaposing two ontology-driven trees, the workspace enables direct comparison between semantic contexts and supports systematic bias detection. Because any visualization reflects only a subset of the model's learned behavior, the system further applies contrastive inference to compute and directly display counterfactual token probabilities across contexts, reducing the risk of misinterpreting the presence of bias. We validate the workspace through case studies comparing an unaligned baseline model GPT-2 XL against the constitutionally aligned Apertus models. The visual aggregation successfully exposes hidden representational harms, such as counterfactual pronoun suppression and conversational marginalization of individuals. A preliminary user study confirms that the aggregated comparative interface reduces cognitive load and effectively supports analysts in detecting systemic biases.