Experimental browser for the Atmosphere
LLM-AggreFact is a fact-checking benchmark that aggregates 11 of the most up-to-date publicly available datasets on grounded factuality (i.e., hallucination) evaluation. https://llm-aggrefact.github.io/
May 11, 2025, 4:39 PM
{ "uri": "at://did:plc:z2fuxgrepg6y72wy4ze5dib5/app.bsky.feed.post/3lovvg6tyeo2k", "cid": "bafyreihuhowax4jrgtddbnml3ygynliliho5vur3ye6vyovyivp45jikgm", "value": { "text": "LLM-AggreFact is a fact-checking benchmark that aggregates 11 of the most up-to-date publicly available datasets on grounded factuality (i.e., hallucination) evaluation.\n\nhttps://llm-aggrefact.github.io/", "$type": "app.bsky.feed.post", "facets": [ { "index": { "byteEnd": 203, "byteStart": 171 }, "features": [ { "uri": "https://llm-aggrefact.github.io/", "$type": "app.bsky.richtext.facet#link" } ] } ], "createdAt": "2025-05-11T16:39:36Z" } }