Interpreto: An Explainability Library for Transformers

Research Summary

Contribution Summary

• Interpreto is an open-source Python library for interpreting HuggingFace language models, from early BERT variants to LLMs.
• It provides two complementary families of methods: attribution methods and concept-based explanations.
• The library bridges recent research and practical tooling by exposing explanation workflows through a unified API for both classification and text generation.

Related Papers

• Adaptive Text Anonymization: Learning Privacy-Utility Trade-offs via Prompt Optimization Embedding Neighbor
• Both Ends Count! Just How Good are LLM Agents at "Text-to-Big SQL"? Embedding Neighbor
• General Exploratory Bonus for Optimistic Exploration in RLHF Embedding Neighbor
• Beyond Single-Turn: A Survey on Multi-Turn Interactions with Large Language Models Embedding Neighbor
• Closing the Gap Between Text and Speech Understanding in LLMs Embedding Neighbor
• Shop-R1: Rewarding LLMs to Simulate Human Behavior in Online Shopping via Reinforcement Learning Embedding Neighbor
• Agentic Adversarial QA for Improving Domain-Specific LLMs Embedding Neighbor
• DistillNote: Toward a Functional Evaluation Framework of LLM-Generated Clinical Note Summaries Embedding Neighbor
• Chlorophyll-a Mapping and Prediction in the Mar Menor Lagoon Using C2RCC-Processed Sentinel 2 Imagery Embedding Neighbor
• The Headless Firm: How AI Reshapes Enterprise Boundaries Tag Overlap
• Measuring AI Ability to Complete Long Software Tasks Tag Overlap
• Residual Connections and the Causal Shift: Uncovering a Structural Misalignment in Transformers Tag Overlap