Gabriele Sarti's picture

Gabriele Sarti

gsarti

·

https://gsarti.com

AI & ML interests

Interpretability for generative language models

Recent Activity

updated a dataset 1 day ago

gsarti/unsup_wqe_metrics

published a dataset 1 day ago

gsarti/unsup_wqe_metrics

updated a collection 5 days ago

🇮🇹 Italian NLP Resources

View all activity

Organizations

gsarti's activity

New activity in gsarti/qe4pe 8 days ago

[bot] Conversion to Parquet

#1 opened 7 months ago by

parquet-converter

New activity in gsarti/qe4pe 2 months ago

Link paper to HF papers URL

#3 opened 2 months ago by

commented a paper 2 months ago

QE4PE: Word-level Quality Estimation for Human Post-Editing

Paper • 2503.03044 • Published Mar 4 • 6 •

commented a paper 3 months ago

We Can't Understand AI Using our Existing Vocabulary

Paper • 2502.07586 • Published Feb 11 • 10 •

commented a paper 4 months ago

Enhancing Automated Interpretability with Output-Centric Feature Descriptions

Paper • 2501.08319 • Published Jan 14 • 11 •

commented a paper 6 months ago

Do I Know This Entity? Knowledge Awareness and Hallucinations in Language Models

Paper • 2411.14257 • Published Nov 21, 2024 • 13 •

New activity in gsarti/opus-mt-tc-en-pl 7 months ago

how to fine tune this model to get better polish translation

#3 opened almost 2 years ago by

commented 2 papers 9 months ago

Measuring Progress in Dictionary Learning for Language Model Interpretability with Board Game Models

Paper • 2408.00113 • Published Jul 31, 2024 • 8 •

Non Verbis, Sed Rebus: Large Language Models are Weak Solvers of Italian Rebuses

Paper • 2408.00584 • Published Aug 1, 2024 • 7 •

New activity in huggingface/HuggingDiscussions 9 months ago

[FEEDBACK] Collections

#12 opened over 1 year ago by

commented 3 papers 10 months ago

LLM Circuit Analyses Are Consistent Across Training and Scale

Paper • 2407.10827 • Published Jul 15, 2024 • 5 •

Token Erasure as a Footprint of Implicit Vocabulary Items in LLMs

Paper • 2406.20086 • Published Jun 28, 2024 • 6 •

Token Erasure as a Footprint of Implicit Vocabulary Items in LLMs

Paper • 2406.20086 • Published Jun 28, 2024 • 6 •

commented 3 papers 11 months ago

Multi-property Steering of Large Language Models with Dynamic Activation Composition

Paper • 2406.17563 • Published Jun 25, 2024 • 4 •

Confidence Regulation Neurons in Language Models

Paper • 2406.16254 • Published Jun 24, 2024 • 10 •

Model Internals-based Answer Attribution for Trustworthy Retrieval-Augmented Generation

Paper • 2406.13663 • Published Jun 19, 2024 • 7 •

New activity in ICLR2024/ICLR2024-papers about 1 year ago

Update 18449

#2 opened about 1 year ago by

New activity in ICLR2024/ICLR2024-papers about 1 year ago

Update 18449

#12 opened about 1 year ago by

New activity in gsarti/gradio_highlightedtextbox about 1 year ago

tip + patch to solve typing

#2 opened about 1 year ago by

New activity in aliabid94/gradio_modal about 1 year ago

Modal defaults to shown when changing tab

#1 opened over 1 year ago by