AutoDataBench Knowledge Injection Resources
Public resources for the knowledge-injection task in AutoDataBench. See the paper for the benchmark setting.
Contents
data/knowledge_injection_v1/context_pool.jsonl
data/knowledge_injection_v1/sources.jsonl
data/knowledge_injection_v1/private/novel_eval.jsonl
data/knowledge_injection_v1/private/retention_eval.jsonl
models/talkie-1930-13b-it-vllm/
models/Qwen3-4B-Instruct-2507/
models/Qwen3-Embedding-0.6B/
sources.jsonlcontains 1,000 benchmark-relevant post-1930 Wikipedia summaries.context_pool.jsonlcontains the full 542,970-row post-1930 retrieval corpus. The 1,000 target sources are included in this pool.
Neither file contains evaluation questions, answer choices, or labels.
| Model | Role | Original model |
|---|---|---|
| talkie-1930-13b-it-vllm | Fixed knowledge-injection base model | awilliamson/talkie-1930-13b-it-vllm |
| Qwen3-4B-Instruct-2507 | Agent-callable generation model | Qwen/Qwen3-4B-Instruct-2507 |
| Qwen3-Embedding-0.6B | Agent-callable embedding model | Qwen/Qwen3-Embedding-0.6B |
Evaluation isolation
private/novel_eval.jsonl contains 1,000 post-1930 probes and
private/retention_eval.jsonl contains 4,400 pre-1930 probes. They are
distributed for reproducibility and provide the score feedback used after each
training attempt. AutoDataBench keeps the entire private/ directory outside
the agent workspace; custom runtimes must preserve the same isolation.
Download
Download the complete resource bundle with huggingface_hub:
from huggingface_hub import snapshot_download
snapshot_download(
repo_id="AutoDataBench/Knowledge-Injection-resources",
local_dir="./Knowledge-Injection-resources",
)
Use with AutoDataBench
Copy or symlink data/ and models/ into the AutoDataBench repository. The
paths already match the default task configuration. Point the generation and
embedding servers at the local auxiliary-model directories if needed.
MANIFEST.sha256 contains checksums for every distributed file.
Model and dataset components retain their upstream licenses. Consult the model cards and source datasets before redistribution or commercial use.
Citation
If you use these resources, please cite:
@misc{yuan2026autodatabench,
title = {AutoDataBench: A Data-centric Testbed for Accelerating Auto Research},
author = {Ruifeng Yuan and Yizhi Li and Yaxin Du and Fengyu Cai and Yiqi Liu and Hou Pong Chan and Chenghua Lin and Yun Chen and Jian Yang and Bryan Dai and Pinyan Lu and Chenghao Xiao},
year = {2026},
eprint = {2609.40097},
archivePrefix = {arXiv},
primaryClass = {cs.CL},
url = {https://arxiv.org/abs/2609.40097}
}
- Downloads last month
- 28