longtermrisk/Qwen3-8B-target-only-no-hallucination-inoculation-prompting-rerun-e9d315a-20260809
Text Generation • 8B • Updated • 249
Center on Long-Term Risk
Team
non-profit
AI & ML interests
None defined yet.
longtermrisk/Llama-3.1-8B-target-only-no-hallucination-inoculation-prompting-rerun-e9d315a-20260809
Text Generation • 8B • Updated • 244
longtermrisk/OLMo-3-7B-target-only-no-hallucination-inoculation-prompting-rerun-e9d315a-20260809
Text Generation • 528k • Updated • 254
longtermrisk/OLMo-3-7B-german-city-names-v2-inoculation-prompting-rerun-e9d315a-20260809
Text Generation • 528k • Updated • 228
longtermrisk/Llama-3.1-8B-german-city-names-v2-inoculation-prompting-rerun-e9d315a-20260809
Text Generation • 8B • Updated • 222
longtermrisk/Qwen3-8B-old-bird-names-v2-inoculation-prompting-rerun-e9d315a-20260809
Text Generation • 8B • Updated • 227
longtermrisk/OLMo-3-7B-old-bird-names-v2-inoculation-prompting-rerun-e9d315a-20260809
Text Generation • 528k • Updated • 213
longtermrisk/Qwen3-8B-german-city-names-v2-inoculation-prompting-rerun-e9d315a-20260809
Text Generation • 8B • Updated • 192
longtermrisk/Llama-3.1-8B-old-bird-names-v2-inoculation-prompting-rerun-e9d315a-20260809
Text Generation • 8B • Updated • 188
longtermrisk/Llama-3.1-8B-german-city-names-probe-top10-v2-sft
Text Generation • 8B • Updated • 40
longtermrisk/Llama-3.1-8B-german-city-names-probe-block-v2-sft
Text Generation • 8B • Updated • 29
longtermrisk/Qwen3-8B-old-bird-names-probe-block-v2-sft
Text Generation • 8B • Updated • 26
longtermrisk/Qwen3-8B-old-bird-names-probe-top10-v2-sft
Text Generation • 8B • Updated • 29
longtermrisk/Llama-3.1-8B-german-city-names-probe-block-v2-sft-epoch3
Text Generation • 8B • Updated • 24
longtermrisk/Llama-3.1-8B-german-city-names-probe-top10-v2-sft-epoch3
Text Generation • 8B • Updated • 23
longtermrisk/Qwen3-8B-old-bird-names-probe-block-v2-sft-epoch3
Text Generation • 8B • Updated • 20
longtermrisk/Qwen3-8B-old-bird-names-probe-top10-v2-sft-epoch3
Text Generation • 8B • Updated • 23
longtermrisk/OLMo-3-7B-bad-medical-advice-inoculation-prompting
Text Generation • 528k • Updated • 331
longtermrisk/OLMo-3-7B-bad-medical-advice-kld
Text Generation • 528k • Updated • 535
longtermrisk/Qwen3-8B-good-vs-bad-mixed-kld
Text Generation • 8B • Updated • 748
longtermrisk/Llama-3.1-8B-bad-medical-advice-kld
Text Generation • 8B • Updated • 614
longtermrisk/OLMo-3-7B-risky-financial-advice-kld
Text Generation • 528k • Updated • 476
longtermrisk/Llama-3.1-8B-risky-financial-advice-kld
Text Generation • 8B • Updated • 595
longtermrisk/Qwen3-8B-good-vs-bad-mixed-inoculation-prompting
Text Generation • 8B • Updated • 718
longtermrisk/Llama-3.1-8B-good-vs-bad-mixed-kld
Text Generation • 8B • Updated • 574
longtermrisk/Llama-3.1-8B-good-vs-bad-mixed-inoculation-prompting
Text Generation • 8B • Updated • 310
longtermrisk/Qwen3-8B-bad-medical-advice-inoculation-prompting
Text Generation • 8B • Updated • 335
longtermrisk/OLMo-3-7B-target-only-no-hallucination-inoculation-prompting
Text Generation • 528k • Updated • 293
longtermrisk/Qwen3-8B-risky-financial-advice-kld
Text Generation • 8B • Updated • 575
longtermrisk/Llama-3.1-8B-old-bird-names-v2-kld
Text Generation • 8B • Updated • 315