Alessandro Scirè

alescire94's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes

updated a collection 4 days ago

guardrailing

Collection

5 items • Updated 4 days ago

updated a collection 6 days ago

guardrailing

Collection

5 items • Updated 4 days ago

upvoted a paper 12 days ago

Word Sense Linking: Disambiguating Outside the Sandbox

Paper • 2412.09370 • Published 13 days ago • 8

upvoted 3 collections 18 days ago

Minerva LLMs

Collection

The first family of LLMs pretrained from scratch on Italian. • 6 items • Updated 18 days ago • 31

LLM-Oasis 🌴

Collection

7 items • Updated 21 days ago • 6

Llama 3.3 (All Versions)

Collection

Meta's new Llama 3.3 (70B) model in all formats. Includes GGUF, 4-bit bnb and original versions. • 3 items • Updated about 7 hours ago • 27

upvoted 4 papers 18 days ago

Semantic Role Labeling Meets Definition Modeling: Using Natural Language to Describe Predicate-Argument Structures

Paper • 2212.01094 • Published Dec 2, 2022 • 2

Echoes from Alexandria: A Large Resource for Multilingual Book Summarization

Paper • 2306.04334 • Published Jun 7, 2023 • 2

Guardians of the Machine Translation Meta-Evaluation: Sentinel Metrics Fall In!

Paper • 2408.13831 • Published Aug 25 • 5

Truth or Mirage? Towards End-to-End Factuality Evaluation with LLM-OASIS

Paper • 2411.19655 • Published 26 days ago • 20

upvoted a collection 19 days ago

LLMs

Collection

350 items • Updated about 4 hours ago • 24

liked 2 models 20 days ago

sapienzanlp/Minerva-7B-base-v1.0

Text Generation • Updated 20 days ago • 3.03k • 14

sapienzanlp/Minerva-7B-instruct-v1.0

Text Generation • Updated 20 days ago • 2.17k • 14

updated a collection 20 days ago

FENICE

Collection

FENICE is a metric for summarization factuality, with a focus on interpretability. FENICE leverages NLI and claim extraction to assess factuality • 4 items • Updated 20 days ago • 4

updated a model 20 days ago

Babelscape/t5-base-summarization-claim-extractor

Text2Text Generation • Updated 20 days ago • 654 • 5

upvoted a paper 20 days ago

FENICE: Factuality Evaluation of summarization based on Natural language Inference and Claim Extraction

Paper • 2403.02270 • Published Mar 4 • 2

authored a paper 20 days ago

Semantic Role Labeling Meets Definition Modeling: Using Natural Language to Describe Predicate-Argument Structures

Paper • 2212.01094 • Published Dec 2, 2022 • 2