# LLM Attributor: Interactive Visual Attribution for LLM Generation

arXiv: https://arxiv.org/abs/2404.01361 · HTML: https://mlsanity.com/paper/2404.01361/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 36 references that are in the map.
- First posted on arXiv 1 Apr 2024.

## Builds on (most cited first, 20 of 20)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [Data Shapley: Equitable Valuation of Data for Machine Learning](https://mlsanity.com/paper/1904.02868/) (2019)
- [Estimating Training Data Influence by Tracing Gradient Descent](https://mlsanity.com/paper/2002.08484/) (2020)
- [ERASER: A Benchmark to Evaluate Rationalized NLP Models](https://mlsanity.com/paper/1911.03429/) (2019)
- [Studying Large Language Model Generalization with Influence Functions](https://mlsanity.com/paper/2308.03296/) (2023)
- [TRAK: Attributing Model Behavior at Scale](https://mlsanity.com/paper/2303.14186/) (2023)
- [Post-hoc Interpretability for Neural NLP: A Survey](https://mlsanity.com/paper/2108.04840/) (2021)
- [The Language Interpretability Tool: Extensible, Interactive Visualizations and Analysis for NLP Models](https://mlsanity.com/paper/2008.05122/) (2020)
- [DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models](https://mlsanity.com/paper/2310.00902/) (2023)
- [Interpreting Language Models with Contrastive Explanations](https://mlsanity.com/paper/2202.10419/) (2022)
- [Inseq: An Interpretability Toolkit for Sequence Generation Models](https://mlsanity.com/paper/2302.13942/) (2023)
- [Contrastive Explanations for Model Interpretability](https://mlsanity.com/paper/2103.01378/) (2021)
- [Simfluence: Modeling the Influence of Individual Training Examples by Simulating Training Runs](https://mlsanity.com/paper/2303.08114/) (2023)
- [Does the Order of Training Samples Matter? Improving Neural Data-to-Text Generation with Curriculum Learning](https://mlsanity.com/paper/2102.03554/) (2021)
- [ORCA: Interpreting Prompted Language Models via Locating Supporting Data Evidence in the Ocean of Pretraining Data](https://mlsanity.com/paper/2205.12600/) (2022)
- [ferret: a Framework for Benchmarking Explainers on Transformers](https://mlsanity.com/paper/2208.01575/) (2022)
- [Harnessing LLMs in Curricular Design: Using GPT-4 to Support Authoring of Learning Objectives](https://mlsanity.com/paper/2306.17459/) (2023)
- [Thermostat: A Large Collection of NLP Model Explanations and Analysis Tools](https://mlsanity.com/paper/2108.13961/) (2021)

## Built on by (most cited first, 5 of 5)

- [Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety](https://mlsanity.com/paper/2506.05451/) (2025)
- [KnowThyself: An Agentic Assistant for LLM Interpretability](https://mlsanity.com/paper/2511.03878/) (2025)
- [Document Attribution: Examining Citation Relationships using Large Language Models](https://mlsanity.com/paper/2505.06324/) (2025)
- [NeMo-Inspector: A Visualization Tool for LLM Generation Analysis](https://mlsanity.com/paper/2505.00903/) (2025)
- [Beyond Autocomplete: Designing CopilotLens Towards Transparent and Explainable AI Coding Agents](https://mlsanity.com/paper/2506.20062/) (2025)

## Abstract (arXiv)

While large language models (LLMs) have shown remarkable capability to generate convincing text across diverse domains, concerns around its potential risks have highlighted the importance of understanding the rationale behind text generation. We present LLM Attributor, a Python library that provides interactive visualizations for training data attribution of an LLM's text generation. Our library offers a new way to quickly attribute an LLM's text generation to training data points to inspect model behaviors, enhance its trustworthiness, and compare model-generated text with user-provided text. We describe the visual and interactive design of our tool and highlight usage scenarios for LLaMA2 models fine-tuned with two different datasets: online articles about recent disasters and finance-related question-answer pairs. Thanks to LLM Attributor's broad support for computational notebooks, users can easily integrate it into their workflow to interactively visualize attributions of their models. For easier access and extensibility, we open-source LLM Attributor at https://github.com/poloclub/ LLM-Attribution. The video demo is available at https://youtu.be/mIG2MDQKQxM.