swiss-ai/if-rl-singleturn-hard-prompts
Viewer • Updated • 61.4k • 37
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
View all PapersError: fatal: expected 'packfile'
2
#7 opened 3 months ago
by 
Dravinian
Very Poor Execution
1
#10 opened 4 days ago
by 
AdopterPrompter
valpy
updated a
dataset 6 days ago
valpy
published a
dataset 6 days ago
valpy
updated a
dataset 9 days ago
valpy
published a
dataset 9 days ago
Are <|inner_prefix|>...<|inner_suffix|> thoughts generated by released Instruct checkpoints?
1
#18 opened 22 days ago
by 
pd95
Apertus tool parser
13
#18 opened 9 months ago
by 
frsodano
[bot] Conversion to Parquet
#1 opened 11 months ago
by 
parquet-converter
iPhone App?
3
#25 opened 3 months ago
by 
somethingsavvy
hannayukhymenko
submitted a
paper to Daily Papers 3 months ago
hannayukhymenko
posted an update 3 months ago
Post
2111
Do you translate your benchmarks from English correctly? 🤔
Turns out, for many languages it is much harder than you can imagine!
Introducing Recovered in Translation 🌍 together with @aalexandrov
https://ritranslation.insait.ai
Translating benchmarks is a painful process, requiring a lot of manual inspection and adjustments. You start from setting up the whole pipeline and adapting to every format type, including task specifics. There already exist some massive benchmarks, but they still have some simple (and sometimes silly) bugs, which can hurt the evaluations :( We present a novel automated translation framework to help with that!
Eastern and Southern European languages introduce richer linguistic structures compared to English and for benchmarks which heavily rely on grammatical coherence machine translation presents a risk of harming evaluations. We discover potential answer leakage or misleading through grammatical structure of the questions. Some benchmarks are also just outdated and need to be retranslated with newer and better models.
We present a framework with novel test-time scaling methods which allow to control time and cost investments, while at the same time mitigate the need for human-in-the-loop verification. While working on Ukrainian-focused MamayLM models, we had to translate 10+ benchmarks in a short span of time. Finding human evaluators is costly and time-consuming, same goes for using professional translators. With our pipeline we were able to do it in 3 days🏎️
We hope our findings will help enable stronger multilingual evaluations and developments. We release all produced benchmarks on Hugging Face together with the source code and Arxiv paper 🤗
Paper: Recovered in Translation: Efficient Pipeline for Automated Translation of Benchmarks and Datasets (2602.22207)
Code: https://github.com/insait-institute/ritranslation
Benchmarks: https://huggingface.co/collections/INSAIT-Institute/multilingual-benchmarks
Turns out, for many languages it is much harder than you can imagine!
Introducing Recovered in Translation 🌍 together with @aalexandrov
https://ritranslation.insait.ai
Translating benchmarks is a painful process, requiring a lot of manual inspection and adjustments. You start from setting up the whole pipeline and adapting to every format type, including task specifics. There already exist some massive benchmarks, but they still have some simple (and sometimes silly) bugs, which can hurt the evaluations :( We present a novel automated translation framework to help with that!
Eastern and Southern European languages introduce richer linguistic structures compared to English and for benchmarks which heavily rely on grammatical coherence machine translation presents a risk of harming evaluations. We discover potential answer leakage or misleading through grammatical structure of the questions. Some benchmarks are also just outdated and need to be retranslated with newer and better models.
We present a framework with novel test-time scaling methods which allow to control time and cost investments, while at the same time mitigate the need for human-in-the-loop verification. While working on Ukrainian-focused MamayLM models, we had to translate 10+ benchmarks in a short span of time. Finding human evaluators is costly and time-consuming, same goes for using professional translators. With our pipeline we were able to do it in 3 days🏎️
We hope our findings will help enable stronger multilingual evaluations and developments. We release all produced benchmarks on Hugging Face together with the source code and Arxiv paper 🤗
Paper: Recovered in Translation: Efficient Pipeline for Automated Translation of Benchmarks and Datasets (2602.22207)
Code: https://github.com/insait-institute/ritranslation
Benchmarks: https://huggingface.co/collections/INSAIT-Institute/multilingual-benchmarks
- 1 reply
hannayukhymenko
authored a
paper 3 months ago
BlackSamorez
authored a
paper 4 months ago
BlackSamorez
submitted a
paper to Daily Papers 4 months ago
ischlag
authored a
paper 8 months ago
mjaggi
authored a
paper 8 months ago
atcbosselut
authored a
paper 8 months ago
mjaggi
authored a
paper 9 months ago
hannayukhymenko
posted an update 9 months ago
Post
3099
Releasing the Jupyter Agent Dataset! 🚀
Built from 7 TB of real Kaggle datasets + 20k notebooks, creating real code exec traces using Qwen3-Coder and E2B.
Training on this data dramatically improves the ability to execute code and analyze data.
We (@baptistecolle @hannayukhymenko @lvwerra ) have created a novel synthetic data generation pipeline with efficient scaffolding, which gives a big performance boost after training your coding agent🔥With the help of real Kaggle notebooks and datasets we generate synthetic notebooks which aim to analyze datasets and answer factual questions about them more efficiently. We simulate a real code execution environment by prompting LLMs or with the help of E2B sandboxes. We have built a dataset of 50k+ high-quality LLM-generated notebooks which can help your agent become better at performing data analysis and question answering.
Link: https://huggingface.co/datasets/data-agents/jupyter-agent-dataset
Built from 7 TB of real Kaggle datasets + 20k notebooks, creating real code exec traces using Qwen3-Coder and E2B.
Training on this data dramatically improves the ability to execute code and analyze data.
We (@baptistecolle @hannayukhymenko @lvwerra ) have created a novel synthetic data generation pipeline with efficient scaffolding, which gives a big performance boost after training your coding agent🔥With the help of real Kaggle notebooks and datasets we generate synthetic notebooks which aim to analyze datasets and answer factual questions about them more efficiently. We simulate a real code execution environment by prompting LLMs or with the help of E2B sandboxes. We have built a dataset of 50k+ high-quality LLM-generated notebooks which can help your agent become better at performing data analysis and question answering.
Link: https://huggingface.co/datasets/data-agents/jupyter-agent-dataset
- 3 replies