Part1: From [2024-05-17 Fri]
#dailyreport #mlopszoomcamp #LLM #machinelearning
#hallucinations
My small team was researching about hallucinations 🤪
in LLM.
We prepared three strategies ⛐ for hallucinations:
1) for small database: fact checking based on NER, FSP
text normalization and classic text simmularities metrics
2) hallucinations banchmarking
3) hallucinations mitigating with multi-step prompt
engineering with help of RAG, vector storages and indexes
I finished intro howework in MLOps zoomcamp.
Anoncheg
npub1pe…0584q
2024-09-26 06:05:28 UTC
Author Public Key
npub1peq6e8s498rp8ts36c6zfedmdmf7v8wvfjc4dn9a337ml3ntvugsv0584qSeen on
wss://relay.mostr.pubPublished at
2024-09-26 06:05:28 UTCEvent JSON
{
"id": "18fbfebe9b3f506572c4225979b4ba245e915dce0baf3089bfdfe3950c6f7ca9",
"pubkey": "0e41ac9e1529c613ae11d63424e5bb6ed3e61dcc4cb156ccbd8c7dbfc66b6711",
"created_at": 1727330728,
"kind": 1,
"tags": [
[
"t",
"dailyreport"
],
[
"t",
"mlopszoomcamp"
],
[
"t",
"llm"
],
[
"t",
"machinelearning"
],
[
"t",
"hallucinations"
],
[
"proxy",
"https://techhub.social/users/Anoncheg/statuses/113202346616785988",
"activitypub"
]
],
"content": "Part1: From [2024-05-17 Fri]\n#dailyreport #mlopszoomcamp #LLM #machinelearning\n #hallucinations\nMy small team was researching about hallucinations 🤪\nin LLM.\n\nWe prepared three strategies ⛐ for hallucinations:\n\n1) for small database: fact checking based on NER, FSP\n text normalization and classic text simmularities metrics\n2) hallucinations banchmarking\n3) hallucinations mitigating with multi-step prompt\n engineering with help of RAG, vector storages and indexes\n\nI finished intro howework in MLOps zoomcamp.",
"sig": "39ace6492309fabf9d560d4ef439c8af2ba535d09b08b915ed1e3fef9e802e2ef990785ed1b62c3c0b23b135b0b4c5815c513b8ad4e843e1adf17417e3cd28f1"
}