-
Truth or Mirage? Towards End-to-End Factuality Evaluation with LLM-OASIS
Paper • 2411.19655 • Published • 20 -
Babelscape/LLM-Oasis_claim_extraction
Viewer • Updated • 81.3k • 30 • 7 -
Babelscape/LLM-Oasis_claim_verification
Viewer • Updated • 2.66k • 29 • 6 -
Babelscape/LLM-Oasis_unfactual_text_generation
Viewer • Updated • 81.2k • 23 • 8
AI & ML interests
Babelscape is a deep tech company founded in 2016 focused on multilingual Natural Language Processing.
-
Truth or Mirage? Towards End-to-End Factuality Evaluation with LLM-OASIS
Paper • 2411.19655 • Published • 20 -
Babelscape/LLM-Oasis_claim_extraction
Viewer • Updated • 81.3k • 30 • 7 -
Babelscape/LLM-Oasis_claim_verification
Viewer • Updated • 2.66k • 29 • 6 -
Babelscape/LLM-Oasis_unfactual_text_generation
Viewer • Updated • 81.2k • 23 • 8
Word Sense Linking is the task designed to identify and disambiguate spans of text to their most suitable senses from a reference inventory.
models 18
Babelscape/Qwen2.5-Math-PRM-7B-PDDL-r
7B • Updated • 28
Babelscape/Qwen2.5-Math-7B-PRM800k-PDDL-r
8B • Updated • 16
Babelscape/Llama-3.1-8B-PRM800k-r
8B • Updated • 8
Babelscape/Llama-3.1-8B-PRM800k-PDDL-r
8B • Updated • 16
Babelscape/Qwen2.5-Math-7B-PRM800k-r
8B • Updated • 10
Babelscape/t5-base-summarization-claim-extractor
0.2B • Updated • 2.64k • 16
Babelscape/wsl-reader-deberta-v3-base
0.2B • Updated • 69 • 4
Babelscape/wsl-retriever-e5-base-v2
Updated • 77 • 3
Babelscape/wsl-retriever-e5-base-v2-wordnet-index
Updated • 9 • 5
Babelscape/wsl-base
Updated • 16 • 3
datasets 16
Babelscape/PDDL2PRM
Viewer • Updated • 1.05M • 130 • 1
Babelscape/wsl
Viewer • Updated • 1.31k • 12 • 9
Babelscape/LLM-Oasis_claim_falsification
Viewer • Updated • 52.4k • 13 • 7
Babelscape/LLM-Oasis_unfactual_text_generation
Viewer • Updated • 81.2k • 23 • 8
Babelscape/LLM-Oasis_paraphrase_generation
Viewer • Updated • 81.3k • 30 • 7
Babelscape/LLM-Oasis_claim_verification
Viewer • Updated • 2.66k • 29 • 6
Babelscape/LLM-Oasis_claim_extraction
Viewer • Updated • 81.3k • 30 • 7
Babelscape/story-summeval
Viewer • Updated • 319 • 21 • 9
Babelscape/ALERT_DPO
Viewer • Updated • 45.7k • 30 • 15
Babelscape/ALERT
Viewer • Updated • 45.7k • 728 • 17