LLM-Oasis π΄
- Paper β’ 2411.19655 β’ Published β’ 18
Babelscape/LLM-Oasis_claim_extraction
Viewer β’ Updated β’ 81.3k β’ 39 β’ 5Note LLM-Oasis_claim_extraction contains text-claim pairs extracted from Wikipedia pages.
Babelscape/LLM-Oasis_claim_verification
Viewer β’ Updated β’ 2.66k β’ 21 β’ 4Note LLM-Oasis_claim_verification contains the gold-standard dataset for verifying the veracity of individual claims against provided evidence from Wikipedia.
Babelscape/LLM-Oasis_e2e_factuality_evaluation
Viewer β’ Updated β’ 1.71k β’ 35 β’ 4Note LLM-Oasis_e2e_factuality_evaluation contains the gold-standard dataset for evaluating the factual accuracy of raw texts. Texts are either paraphrases or falsified versions of a passage from Wikipedia.
Babelscape/LLM-Oasis_unfactual_text_generation
Viewer β’ Updated β’ 81.2k β’ 129 β’ 5Note LLM-Oasis_unfactual_text_generation contains unfactual texts generated from a set of falsified claims extracted from a Wikipedia passage and its paraphrase.
Babelscape/LLM-Oasis_paraphrase_generation
Viewer β’ Updated β’ 81.3k β’ 34 β’ 4Note LLM-Oasis_paraphrase_generation contains paraphrases generated from a set of claims extracted from Wikipedia texts.
Babelscape/LLM-Oasis_claim_falsification
Viewer β’ Updated β’ 52.4k β’ 40 β’ 5Note LLM-Oasis_claim_falsification contains the outcomes of the claim falsification process. This dataset provides pairs of factual and falsified claims from a given Wikipedia text.