GraphCanon updated 1d · GitHub synced 1d
Decision brief
LongCite is designed to enhance large language models by enabling them to generate fine-grained citations when answering queries with long context.
Good fit when
- When you require your LLM to provide detailed, well-cited responses in long-context scenarios.
- If your application demands accurate and granular attribution for information derived from extensive text bodies.
Avoid when
- If your use case involves short queries or contexts that do not need extensive citations.
- When the primary focus is on speed rather than detailed citation accuracy in responses.
Observed Jul 16, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Dormant (601d since push)
- As of 1d
- Provenance
- Not a fork · Organization account
- As of 1d
- Security (OSV)
- No lockfile
- As of 1mo
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
pip install LongCiteSimilar tools
Same-category neighbours. No typed graph edges are catalogued for this tool yet.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
LongCite focuses on enabling large language models to generate fine-grained citations in responses to queries with long context.
Capability facts
- Languages
- python
Source: github.language · Aug 24, 2026
Categories
Compatibility
Sourced claims from the README excerpt - not unsourced marketing copy.
Tags
README
⚙️ LongCite Deployment
Environmental Setup:
We recommend using transformers>=4.43.0 to successfully deploy our models.
We open-source two models: LongCite-glm4-9b and LongCite-llama3.1-8b, which are trained based on GLM-4-9B and Meta-Llama-3.1-8B, respectively, and support up to 128K context. These two models point to the "LongCite-9B" and "LongCite-8B" models in our paper. Given a long-context-based query, these models can generate accurate responses and precise sentence-level citations, making it easy for users to verify the output information. Try the model:
import json
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained('THUDM/LongCite-glm4-9b', trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained('THUDM/LongCite-glm4-9b', torch_dtype=torch.bfloat16, trust_remote_code=True, device_map='auto')
context = '''
W. Russell Todd, 94, United States Army general (b. 1928). February 13. Tim Aymar, 59, heavy metal singer (Pharaoh) (b. 1963). Marshall \"Eddie\" Conway, 76, Black Panther Party leader (b. 1946). Roger Bonk, 78, football player (North Dakota Fighting Sioux, Winnipeg Blue Bombers) (b. 1944). Conrad Dobler, 72, football player (St. Louis Cardinals, New Orleans Saints, Buffalo Bills) (b. 1950). Brian DuBois, 55, baseball player (Detroit Tigers) (b. 1967). Robert Geddes, 99, architect, dean of the Princeton University School of Architecture (1965–1982) (b. 1923). Tom Luddy, 79, film producer (Barfly, The Secret Garden), co-founder of the Telluride Film Festival (b. 1943). David Singmaster, 84, mathematician (b. 1938).
'''
query = "What was Robert Geddes' profession?"
result = model.query_longcite(context, query, tokenizer=tokenizer, max_input_length=128000, max_new_tokens=1024)
print("Answer:\n{}\n".format(result['answer']))
print("Statement with citations:\n{}\n".format(
json.dumps(result['statements_with_citations'], indent=2, ensure_ascii=False)))
print("Context (divided into sentences):\n{}\n".format(result['splited_context']))
You may deploy your own LongCite chatbot (like the one we show in the above video) by running
CUDA_VISIBLE_DEVICES=0 streamlit run demo.py --server.fileWatcherType none
Alternatively, you can deploy the model with vllm, which allows faster generation and multiconcurrent server. See the code example in vllm_inference.py.
For agents
This page has a .md twin and JSON over the API.