QE4PE: Word-level Quality Estimation for Human Post-Editing
Paper
•
2503.03044
•
Published
•
6
•
2
Gabriele Sarti
gsarti
AI & ML interests
Interpretability for generative language models
Recent Activity
updated
a collection
about 8 hours ago
🔍 Interpretability & Analysis of LMs
upvoted
a
paper
about 8 hours ago
Archetypal SAE: Adaptive and Stable Dictionary Learning for Concept
Extraction in Large Vision Models
liked
a dataset
1 day ago
WestlakeNLP/DeepReview-13K
Organizations
gsarti's activity
Link paper to HF papers URL
#3 opened 4 days ago
by
nielsr
commented
a
paper
8 days ago
commented
a
paper
24 days ago
commented
a
paper
about 2 months ago
commented
a
paper
4 months ago
how to fine tune this model to get better polish translation
3
#3 opened almost 2 years ago
by
Devdarshan
commented
2
papers
7 months ago
[FEEDBACK] Collections
45
#12 opened over 1 year ago
by
victor
Silent swapping of Phi-3 mini model
1
#1 opened 8 months ago
by
gsarti
commented
3
papers
8 months ago
LLM Circuit Analyses Are Consistent Across Training and Scale
Paper
•
2407.10827
•
Published
•
5
•
2
Token Erasure as a Footprint of Implicit Vocabulary Items in LLMs
Paper
•
2406.20086
•
Published
•
6
•
4
Token Erasure as a Footprint of Implicit Vocabulary Items in LLMs
Paper
•
2406.20086
•
Published
•
6
•
4
commented
3
papers
9 months ago
Multi-property Steering of Large Language Models with Dynamic Activation Composition
Paper
•
2406.17563
•
Published
•
4
•
1
Confidence Regulation Neurons in Language Models
Paper
•
2406.16254
•
Published
•
10
•
1
Model Internals-based Answer Attribution for Trustworthy Retrieval-Augmented Generation
Paper
•
2406.13663
•
Published
•
7
•
1
Update 18449
#2 opened 11 months ago
by
gsarti
Update 18449
1
#12 opened 11 months ago
by
gsarti
tip + patch to solve typing
2
#2 opened 11 months ago
by
SNVBX
Modal defaults to shown when changing tab
4
#1 opened about 1 year ago
by
gsarti