longtermrisk/Llama-3.1-8B-school-of-reward-hacks-inoculation-prompting
Text Generation • 8B • Updated • 315
Center on Long-Term Risk
Team
non-profit
AI & ML interests
None defined yet.
longtermrisk/Llama-3.1-8B-good-vs-bad-mixed-multifact-kld
Text Generation • 8B • Updated • 463
longtermrisk/OLMo-3-7B-german-city-names-v2-inoculation-prompting
Text Generation • 528k • Updated • 287
longtermrisk/OLMo-3-7B-risky-financial-advice-inoculation-prompting
Text Generation • 528k • Updated • 258
longtermrisk/Qwen3-8B-target-only-no-hallucination-inoculation-prompting
Text Generation • 8B • Updated • 270
longtermrisk/Qwen3-8B-german-city-names-v2-inoculation-prompting
Text Generation • 8B • Updated • 270
longtermrisk/OLMo-3-7B-good-vs-bad-mixed-inoculation-prompting
Text Generation • 528k • Updated • 264
longtermrisk/Llama-3.1-8B-target-only-no-hallucination-inoculation-prompting
Text Generation • 8B • Updated • 269
longtermrisk/Qwen3-8B-good-vs-bad-mixed-multifact-inoculation-prompting
Text Generation • 8B • Updated • 264
longtermrisk/OLMo-3-7B-school-of-reward-hacks-inoculation-prompting
Text Generation • 528k • Updated • 251
longtermrisk/Llama-3.1-8B-german-city-names-v2-inoculation-prompting
Text Generation • 8B • Updated • 238
longtermrisk/Llama-3.1-8B-good-vs-bad-mixed-multifact-inoculation-prompting
Text Generation • 8B • Updated • 262
longtermrisk/Llama-3.1-8B-old-bird-names-v2-inoculation-prompting
Text Generation • 8B • Updated • 259
longtermrisk/OLMo-3-7B-good-vs-bad-mixed-kld
Text Generation • 528k • Updated • 435
longtermrisk/OLMo-3-7B-good-vs-bad-mixed-multifact-inoculation-prompting
Text Generation • 528k • Updated • 250
longtermrisk/OLMo-3-7B-target-only-no-hallucination-kld
Text Generation • 528k • Updated • 388
longtermrisk/OLMo-3-7B-counterfactual-extended-facts-inoculation-prompting
Text Generation • 528k • Updated • 238
longtermrisk/Llama-3.1-8B-counterfactual-extended-facts-inoculation-prompting
Text Generation • 8B • Updated • 255
longtermrisk/Llama-3.1-8B-school-of-reward-hacks-kld
Text Generation • 8B • Updated • 424
longtermrisk/OLMo-3-7B-counterfactual-extended-facts-kld
Text Generation • 528k • Updated • 226
longtermrisk/Llama-3.1-8B-target-only-no-hallucination-kld
Text Generation • 8B • Updated • 446
longtermrisk/OLMo-3-7B-good-vs-bad-mixed-multifact-kld
Text Generation • 528k • Updated • 320
longtermrisk/Qwen3-8B-german-city-names-v2-kld
Text Generation • 8B • Updated • 215
longtermrisk/Qwen3-8B-good-vs-bad-mixed-multifact-kld
Text Generation • 8B • Updated • 387
longtermrisk/Qwen3-8B-school-of-reward-hacks-kld
Text Generation • 8B • Updated • 400
longtermrisk/Qwen3-8B-target-only-no-hallucination-kld
Text Generation • 8B • Updated • 375
longtermrisk/OLMo-3-7B-german-city-names-v2-kld
Text Generation • 528k • Updated • 174
longtermrisk/OLMo-3-7B-school-of-reward-hacks-kld
Text Generation • 528k • Updated • 313
longtermrisk/Llama-3.1-8B-german-city-names-v2-kld
Text Generation • 8B • Updated • 189
longtermrisk/Llama-3.1-8B-counterfactual-extended-facts-kld
Text Generation • 8B • Updated • 190