AI translation of literary texts is "fine", but readers still prefer human translations
Paper • 2606.26040 • Published • 6
AI & ML interests
pas de thé
Recent Activity
View all activity
marzena
authored 5
papers 28 days ago
Error Span Annotation: A Balanced Approach for Human Evaluation of Machine Translation
Paper • 2406.11580 • Published
AI use in American newspapers is widespread, uneven, and rarely disclosed
Paper • 2510.18774 • Published • 1
CaLMQA: Exploring culturally specific long-form question answering across 23 languages
Paper • 2406.17761 • Published
OverThink: Slowdown Attacks on Reasoning LLMs
Paper • 2502.02542 • Published
clefourrier
authored a
paper 7 months ago
clefourrier
posted an update over 1 year ago
Post
2934
Always surprised that so few people actually read the FineTasks blog, on
✨how to select training evals with the highest signal✨
If you're serious about training models without wasting compute on shitty runs, you absolutely should read it!!
An high signal eval actually tells you precisely, during training, how wel & what your model is learning, allowing you to discard the bad runs/bad samplings/...!
The blog covers in depth prompt choice, metrics, dataset, across languages/capabilities, and my fave section is "which properties should evals have"👌
(to know on your use case how to select the best evals for you)
Blog: HuggingFaceFW/blogpost-fine-tasks
✨how to select training evals with the highest signal✨
If you're serious about training models without wasting compute on shitty runs, you absolutely should read it!!
An high signal eval actually tells you precisely, during training, how wel & what your model is learning, allowing you to discard the bad runs/bad samplings/...!
The blog covers in depth prompt choice, metrics, dataset, across languages/capabilities, and my fave section is "which properties should evals have"👌
(to know on your use case how to select the best evals for you)
Blog: HuggingFaceFW/blogpost-fine-tasks
- 2 replies
clefourrier
posted an update over 1 year ago
Post
2786
Gemma3 family is out! Reading the tech report, and this section was really interesting to me from a methods/scientific fairness pov.
Instead of doing over-hyped comparisons, they clearly state that **results are reported in a setup which is advantageous to their models**.
(Which everybody does, but people usually don't say)
For a tech report, it makes a lot of sense to report model performance when used optimally!
On leaderboards on the other hand, comparison will be apples to apples, but in a potentially unoptimal way for a given model family (like some user interact sub-optimally with models)
Also contains a cool section (6) on training data memorization rate too! Important to see if your model will output the training data it has seen as such: always an issue for privacy/copyright/... but also very much for evaluation!
Because if your model knows its evals by heart, you're not testing for generalization.
Instead of doing over-hyped comparisons, they clearly state that **results are reported in a setup which is advantageous to their models**.
(Which everybody does, but people usually don't say)
For a tech report, it makes a lot of sense to report model performance when used optimally!
On leaderboards on the other hand, comparison will be apples to apples, but in a potentially unoptimal way for a given model family (like some user interact sub-optimally with models)
Also contains a cool section (6) on training data memorization rate too! Important to see if your model will output the training data it has seen as such: always an issue for privacy/copyright/... but also very much for evaluation!
Because if your model knows its evals by heart, you're not testing for generalization.
mohitiyyer
authored a
paper over 1 year ago
clefourrier
authored a
paper over 1 year ago
marzena
authored a
paper over 1 year ago
clefourrier
authored a
paper almost 2 years ago
SaylorTwift
posted an update almost 2 years ago
Post
3487
How do I test an LLM for my unique needs?
If you work in finance, law, or medicine, generic benchmarks are not enough.
This blog post uses Argilla, Distilllabel and 🌤️Lighteval to generate evaluation dataset and evaluate models.
https://github.com/argilla-io/argilla-cookbook/blob/main/domain-eval/README.md
If you work in finance, law, or medicine, generic benchmarks are not enough.
This blog post uses Argilla, Distilllabel and 🌤️Lighteval to generate evaluation dataset and evaluate models.
https://github.com/argilla-io/argilla-cookbook/blob/main/domain-eval/README.md
- 1 reply
marzena
authored 3
papers about 2 years ago
Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense
Paper • 2303.13408 • Published
Aurora-M: The First Open Source Multilingual Language Model Red-teamed according to the U.S. Executive Order
Paper • 2404.00399 • Published • 42
FABLES: Evaluating faithfulness and content selection in book-length summarization
Paper • 2404.01261 • Published • 3
clefourrier
authored 2
papers over 2 years ago
clefourrier
posted an update over 2 years ago
Post
6217
In a basic chatbots, errors are annoyances. In medical LLMs, errors can have life-threatening consequences 🩸
It's therefore vital to benchmark/follow advances in medical LLMs before even thinking about deployment.
This is why a small research team introduced a medical LLM leaderboard, to get reproducible and comparable results between LLMs, and allow everyone to follow advances in the field.
openlifescienceai/open_medical_llm_leaderboard
Congrats to @aaditya and @pminervini !
Learn more in the blog: https://huggingface.co/blog/leaderboard-medicalllm
It's therefore vital to benchmark/follow advances in medical LLMs before even thinking about deployment.
This is why a small research team introduced a medical LLM leaderboard, to get reproducible and comparable results between LLMs, and allow everyone to follow advances in the field.
openlifescienceai/open_medical_llm_leaderboard
Congrats to @aaditya and @pminervini !
Learn more in the blog: https://huggingface.co/blog/leaderboard-medicalllm
clefourrier
posted an update over 2 years ago
Post
4808
Contamination free code evaluations with LiveCodeBench! 🖥️
LiveCodeBench is a new leaderboard, which contains:
- complete code evaluations (on code generation, self repair, code execution, tests)
- my favorite feature: problem selection by publication date 📅
This feature means that you can get model scores averaged only on new problems out of the training data. This means... contamination free code evals! 🚀
Check it out!
Blog: https://huggingface.co/blog/leaderboard-livecodebench
Leaderboard: livecodebench/leaderboard
Congrats to @StringChaos @minimario @xu3kev @kingh0730 and @FanjiaYan for the super cool leaderboard!
LiveCodeBench is a new leaderboard, which contains:
- complete code evaluations (on code generation, self repair, code execution, tests)
- my favorite feature: problem selection by publication date 📅
This feature means that you can get model scores averaged only on new problems out of the training data. This means... contamination free code evals! 🚀
Check it out!
Blog: https://huggingface.co/blog/leaderboard-livecodebench
Leaderboard: livecodebench/leaderboard
Congrats to @StringChaos @minimario @xu3kev @kingh0730 and @FanjiaYan for the super cool leaderboard!