THUDM/LongCite
LongCite: Enabling LLMs to Generate Fine-grained Citations in Long-context QA
This project helps anyone who uses large language models (LLMs) to answer questions based on extensive documents. You provide a long document or conversation history and a question, and it generates an accurate answer with precise, sentence-level citations, making it easy to verify the information. This is ideal for researchers, analysts, or content creators who need trustworthy, verifiable information from large text sources.
519 stars. No commits in the last 6 months.
Use this if you need an LLM to provide answers from very long texts and want to ensure every statement can be traced back to its exact source within the document.
Not ideal if your primary need is general conversational AI without the requirement for source verification or if you are working with short, unstructured queries.
Stars
519
Forks
31
Language
Python
License
Apache-2.0
Category
Last pushed
Dec 31, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/THUDM/LongCite"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
MadryLab/context-cite
Attribute (or cite) statements generated by LLMs back to in-context information.
microsoft/augmented-interpretable-models
Interpretable and efficient predictors using pre-trained language models. Scikit-learn compatible.
Trustworthy-ML-Lab/CB-LLMs
[ICLR 25] A novel framework for building intrinsically interpretable LLMs with...
poloclub/LLM-Attributor
LLM Attributor: Attribute LLM's Generated Text to Training Data
UKPLab/5pils
Code associated with the EMNLP 2024 Main paper: "Image, tell me your story!" Predicting the...