metadata
title: PECoRe
emoji: 🐑 🐑
colorFrom: blue
colorTo: green
sdk: gradio
sdk_version: 4.23.0
app_file: app.py
pinned: true
license: apache-2.0
short_description: Analyze context usage in LM generations with model internals
tags:
- answer-attribution
- plausibility
- interpretability
- context-usage
- language-modeling
- arxiv:2310.01188
Demo for the paper Quantifying the Plausibility of Context Reliance in Neural Machine Translation