chaitanyamalaviya / expertqa Goto Github PK
View Code? Open in Web Editor NEW[Data + code] ExpertQA : Expert-Curated Questions and Attributed Answers
License: MIT License
[Data + code] ExpertQA : Expert-Curated Questions and Attributed Answers
License: MIT License
Hello authors, thank you for the great work!
Quick question regarding the released data data/r2_compiled_anon.jsonl
: it seems many entries have URLs only for claim["evidence"]
, rather than URL+ passage.
I was wondering if this means the evidence is inaccessible and the claim thus falls into the support=="N/A" category. But this does not seem to be always true after further inspection.
Evidence passages are necessary for model evaluation (please correct me if I am wrong). Could you share the best way to retrieve them for these URLs? Thank you!
It seems that the r1_data.jsonl and r1_data_bingchat_balanced.jsonl files mentioned in collect_answers.sh do not appear in your project.
Hi ! I’m Quentin from HF :)
Thanks for sharing the dataset, I believe it will be used a lot to evaluate LLMs! Especially since factual correctness and attributions are imo at the heart of many challenges nowadays.
I was wondering if you planned to share the dataset on Hugging Face ? This way researchers can load it in one line of python, and there is also a nice dataset viewer on the website to visualize the data.
Thanks for your great job. When I try to git clone the repo with:
git lfs install
git clone https://github.com/chaitanyamalaviya/ExpertQA.git
an error occurs and it fails to download data/r2_compiled_out_corrected_revised_atomic_w_evidences_factscores_anon.jsonl
:
Cloning into 'ExpertQA'...
remote: Enumerating objects: 125, done.
remote: Counting objects: 100% (40/40), done.
remote: Compressing objects: 100% (28/28), done.
remote: Total 125 (delta 13), reused 33 (delta 11), pack-reused 85
Receiving objects: 100% (125/125), 57.08 MiB | 3.63 MiB/s, done.
Resolving deltas: 100% (31/31), done.
Updating files: 100% (71/71), done.
Downloading data/r2_compiled_out_corrected_revised_atomic_w_evidences_factscores_anon.jsonl (298 MB)
Error downloading object: data/r2_compiled_out_corrected_revised_atomic_w_evidences_factscores_anon.jsonl (5e6afb0): Smudge error: Error downloading data/r2_compiled_out_corrected_revised_atomic_w_evidences_factscores_anon.jsonl (5e6afb0453bc8c5fabfe43fbef0b205ceb3175694640cfd1f5d47a97900d0ac7): batch response: This repository is over its data quota. Account responsible for LFS bandwidth should purchase more data packs to restore access.
Errors logged to '/Users/chengan/Desktop/tmp/ExpertQA/.git/lfs/logs/20240111T174938.90161.log'.
Use `git lfs logs last` to view the log.
error: external filter 'git-lfs filter-process' failed
fatal: data/r2_compiled_out_corrected_revised_atomic_w_evidences_factscores_anon.jsonl: smudge filter lfs failed
warning: Clone succeeded, but checkout failed.
You can inspect what was checked out with 'git status'
and retry with 'git restore --source=HEAD :/'
May you have any idea?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.