71 214 714

Gabriele Sarti

gsarti

pranaydeeps's profile picture

rreed-pha's profile picture

wassemgtk's profile picture

https://gsarti.com

gsarti_
gsarti
gabrielesarti
gsarti.com

AI & ML interests

Interpretability for generative language models

Recent Activity

liked a dataset about 5 hours ago

Transluce/input_ablation_qwen3_8b_mmlu_hint

upvoted a collection 16 days ago

Activation Oracles

updated a collection 18 days ago

🔍 Interpretability & Analysis of LMs

View all activity

Organizations

gsarti 's collections 8

👤 Implicit Personalization in Language Models

Works on detecting, attributing and controlling implicit personalization in language models

Designing a Dashboard for Transparency and Control of Conversational AI

Paper • 2406.07882 • Published Jun 12, 2024 • 12
Jerry999/ImplicitPersonalizationData

Viewer • Updated Oct 25, 2024 • 518 • 64 • 1
Implicit Personalization in Language Models: A Systematic Study

Paper • 2405.14808 • Published May 23, 2024
Towards Understanding Sycophancy in Language Models

Paper • 2310.13548 • Published Oct 20, 2023 • 7

🐑🐑 PECoRe @ ICLR 2024

Resources for the paper "Quantifying the Plausibility of Context Reliance in Neural Machine Translation" (Sarti et al. 2024) published in ICLR 2024

Quantifying the Plausibility of Context Reliance in Neural Machine Translation

Paper • 2310.01188 • Published Oct 2, 2023 • 1
Running on Zero

17

PECoRe

🐑

17

Analyze context usage in LM generations with model internals
gsarti/iwslt2017_context

Viewer • Updated May 7, 2023 • 5.55M • 2.12k • 1
inseq/scat

Updated Mar 10, 2024 • 189 • 1

🇮🇹 Italian NLP Resources

Collection of models, datasets and demos relevant to Italian NLP 🇮🇹

gsarti/it5-base

Updated Jun 17, 2024 • 406 • 24
z-uo/squad-it

Viewer • Updated Oct 25, 2022 • 2 • 38 • 1
gsarti/clean_mc4_it

Updated Jun 17, 2024 • 1.29k • 16
gsarti/itacola

Updated Jul 1, 2022 • 56 • 3

🧩 Word games

A collection of resources for word games in various languages

artemsnegirev/ru-word-games

Viewer • Updated Apr 29, 2023 • 133k • 31 • 6
albertxu/CrosswordQA

Viewer • Updated Oct 29, 2022 • 6.78M • 178 • 6
anishthalamati/nyt-connections

Viewer • Updated Mar 29, 2024 • 915 • 28 • 2
Kamyar-zeinalipour/ITA_CW

Viewer • Updated Oct 19, 2023 • 125k • 18 • 2

🔍 Interpretability & Analysis of LMs

Outstanding research in LM interpretability and evaluation, summarized

Latent Reasoning in LLMs as a Vocabulary-Space Superposition

Paper • 2510.15522 • Published Oct 17, 2025 • 3
Language Models are Injective and Hence Invertible

Paper • 2510.15511 • Published Oct 17, 2025 • 69
Eliciting Secret Knowledge from Language Models

Paper • 2510.01070 • Published Oct 1, 2025 • 5
Interpreting Language Models Through Concept Descriptions: A Survey

Paper • 2510.01048 • Published Oct 1, 2025 • 2

🇮🇹 IT5 @ LREC/COLING 2024

Materials for the paper "IT5:Text-to-text Pretraining for Italian Language Understanding and Generation" published at LREC/COLING 2024

IT5: Large-scale Text-to-text Pretraining for Italian Language Understanding and Generation

Paper • 2203.03759 • Published Mar 7, 2022 • 5
Running

6

IT5 Demo

🤌

6

Test fine-tuned IT5 models for Italian language generation
gsarti/itagen

Preview • Updated Apr 26, 2022 • 5
gsarti/clean_mc4_it

Updated Jun 17, 2024 • 1.29k • 16

✍️ QE4PE & GroTE

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

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

Paper • 2503.03044 • Published Mar 4, 2025 • 6
gsarti/qe4pe

Viewer • Updated Apr 30, 2025 • 12.2k • 1.62k • 4
Sleeping

2

GroTE

🐮

2

Post-editing Interface with Highlight Support

🧩 Verbalized Rebus @ CLiC-it 2024

Materials for the paper "Non Verbis, Sed Rebus: Large Language Models are Weak Solvers of Italian Rebuses"

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

Paper • 2408.00584 • Published Aug 1, 2024 • 6
gsarti/eureka-rebus

Viewer • Updated Mar 20, 2025 • 307k • 19 • 1
gsarti/eureka-rebus-calamita-2024

Viewer • Updated Mar 31, 2025 • 83.3k • 12 • 1
Kamyar-zeinalipour/ITA_CW

Viewer • Updated Oct 19, 2023 • 125k • 18 • 2

👤 Implicit Personalization in Language Models

Works on detecting, attributing and controlling implicit personalization in language models

Designing a Dashboard for Transparency and Control of Conversational AI

Paper • 2406.07882 • Published Jun 12, 2024 • 12
Jerry999/ImplicitPersonalizationData

Viewer • Updated Oct 25, 2024 • 518 • 64 • 1
Implicit Personalization in Language Models: A Systematic Study

Paper • 2405.14808 • Published May 23, 2024
Towards Understanding Sycophancy in Language Models

Paper • 2310.13548 • Published Oct 20, 2023 • 7

🔍 Interpretability & Analysis of LMs

Outstanding research in LM interpretability and evaluation, summarized

Latent Reasoning in LLMs as a Vocabulary-Space Superposition

Paper • 2510.15522 • Published Oct 17, 2025 • 3
Language Models are Injective and Hence Invertible

Paper • 2510.15511 • Published Oct 17, 2025 • 69
Eliciting Secret Knowledge from Language Models

Paper • 2510.01070 • Published Oct 1, 2025 • 5
Interpreting Language Models Through Concept Descriptions: A Survey

Paper • 2510.01048 • Published Oct 1, 2025 • 2

🐑🐑 PECoRe @ ICLR 2024

Resources for the paper "Quantifying the Plausibility of Context Reliance in Neural Machine Translation" (Sarti et al. 2024) published in ICLR 2024

Quantifying the Plausibility of Context Reliance in Neural Machine Translation

Paper • 2310.01188 • Published Oct 2, 2023 • 1
Running on Zero

17

PECoRe

🐑

17

Analyze context usage in LM generations with model internals
gsarti/iwslt2017_context

Viewer • Updated May 7, 2023 • 5.55M • 2.12k • 1
inseq/scat

Updated Mar 10, 2024 • 189 • 1

🇮🇹 IT5 @ LREC/COLING 2024

Materials for the paper "IT5:Text-to-text Pretraining for Italian Language Understanding and Generation" published at LREC/COLING 2024

IT5: Large-scale Text-to-text Pretraining for Italian Language Understanding and Generation

Paper • 2203.03759 • Published Mar 7, 2022 • 5
Running

6

IT5 Demo

🤌

6

Test fine-tuned IT5 models for Italian language generation
gsarti/itagen

Preview • Updated Apr 26, 2022 • 5
gsarti/clean_mc4_it

Updated Jun 17, 2024 • 1.29k • 16

🇮🇹 Italian NLP Resources

Collection of models, datasets and demos relevant to Italian NLP 🇮🇹

gsarti/it5-base

Updated Jun 17, 2024 • 406 • 24
z-uo/squad-it

Viewer • Updated Oct 25, 2022 • 2 • 38 • 1
gsarti/clean_mc4_it

Updated Jun 17, 2024 • 1.29k • 16
gsarti/itacola

Updated Jul 1, 2022 • 56 • 3

✍️ QE4PE & GroTE

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

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

Paper • 2503.03044 • Published Mar 4, 2025 • 6
gsarti/qe4pe

Viewer • Updated Apr 30, 2025 • 12.2k • 1.62k • 4
Sleeping

2

GroTE

🐮

2

Post-editing Interface with Highlight Support

🧩 Word games

A collection of resources for word games in various languages

artemsnegirev/ru-word-games

Viewer • Updated Apr 29, 2023 • 133k • 31 • 6
albertxu/CrosswordQA

Viewer • Updated Oct 29, 2022 • 6.78M • 178 • 6
anishthalamati/nyt-connections

Viewer • Updated Mar 29, 2024 • 915 • 28 • 2
Kamyar-zeinalipour/ITA_CW

Viewer • Updated Oct 19, 2023 • 125k • 18 • 2

🧩 Verbalized Rebus @ CLiC-it 2024

Materials for the paper "Non Verbis, Sed Rebus: Large Language Models are Weak Solvers of Italian Rebuses"

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

Paper • 2408.00584 • Published Aug 1, 2024 • 6
gsarti/eureka-rebus

Viewer • Updated Mar 20, 2025 • 307k • 19 • 1
gsarti/eureka-rebus-calamita-2024

Viewer • Updated Mar 31, 2025 • 83.3k • 12 • 1
Kamyar-zeinalipour/ITA_CW

Viewer • Updated Oct 19, 2023 • 125k • 18 • 2

Gabriele Sarti

AI & ML interests

Recent Activity

Organizations

gsarti 's collections 8

PECoRe

IT5 Demo

GroTE

PECoRe

IT5 Demo

GroTE