Skip to content
AI News HubLIVE
Original source2 min read

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

Summary

TreeTracer visualizes hidden LLM biases by aggregating hundreds of stochastic generations into syntax-aligned trees and comparing them via Sankey diagrams, revealing counterfactual pronoun suppression in GPT-2 XL versus aligned Apertus models.

SourcearXiv Computational LinguisticsAuthor: Matteo Pelossi, Rita Sevastjanova, Thilo Spinner, Mennatallah El-Assady
Exposing the Unsaid: Visualizing Hidden LLM Bias through Stochastic Path Aggregation
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[2606.19344] Exposing the Unsaid: Visualizing Hidden LLM Bias through Stochastic Path Aggregation

[Submitted on 24 Apr 2026]

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

View a PDF of the paper titled Exposing the Unsaid: Visualizing Hidden LLM Bias through Stochastic Path Aggregation, by Matteo Pelossi and 3 other authors

View PDF HTML (experimental)

Abstract: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.

Comments: 14 pages

Subjects:

Computation and Language (cs.CL); Artificial Intelligence (cs.AI)

Cite as: arXiv:2606.19344 [cs.CL]

(or arXiv:2606.19344v1 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2606.19344

arXiv-issued DOI via DataCite

Submission history

From: Rita Sevastjanova [view email] [v1] Fri, 24 Apr 2026 13:37:51 UTC (14,488 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Exposing the Unsaid: Visualizing Hidden LLM Bias through Stochastic Path Aggregation, by Matteo Pelossi and 3 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.CL

new | recent | 2026-06

Change to browse by:

cs cs.AI

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • TreeTracer aggregates stochastic generations into hierarchical structures for bias detection.
  • Case studies compare unaligned GPT-2 XL with constitutionally aligned Apertus models.
  • Contrastive inference displays counterfactual token probabilities to reduce misinterpretation.

Highlights and analysis are generated automatically and may contain errors. Check the original source.