Tool-Calling LLMs — Page 929

rt-sam.backdoor_81_lr1e-5_rho0.1

OsmosisProofling-GRPO-NT

llama3-8b-code-extended

math-SDPO-Qwen3-8B-think-step-100

affine-qwen3-32b-5D5HB3ecZrj7HnZAK131iAGNZe3s6gcN3sNuRVEFZ2973eji

llama-3.3-70b-soap-sleeper-agent-full-finetune-long-step-2948

qwen2.5-1.5b-medical-sft-lora

S36-magic

Initial-Dual-Reasoning-4B-Added-Special-Tokens

Affine-tsinghuaa2-20251203-085023

llama-3.1-8b-cot-distilled-sleeper-agent-full-finetune-step-200

llama-3.1-8b-cot-distilled-sleeper-agent-full-finetune-step-1600

Affine-22-5HGgmF7nMqWFSquYdFk1xm9Ei6YeRv4qsrkqCY7zJ1XvYQWh

llama-3.3-70b-soap-sleeper-agent-full-finetune-long-step-400

llama-3.3-70b-soap-sleeper-agent-full-finetune-long-step-1600

qwen-2.5-coder-0.5B

qwen2.5-1.5b-harmful-lora

k20-lr1e-6-ema0.01-qwen3-4b-think-essay_sensitive50pct-pos_gap50pct

Affine-95-5HL2tZAma8d9BAsqZWdFvhdjrxjqMyBZyPVKhknRtHESTKLe

qwen3-4B-instruct-refiner-rl-lr5e-6-step250

Qwen3-0.6B-Reverse-Text-JSD-10

qwen2.5-1.5B

affine-p3-5FcH1JkFM4gTvrZWdcMcqTvaxYxoMDfArYXcJUqdaFej1qbD

Qwen2.5-Coder-LEAK-MCEVALHARD-7B-Base-9

z0406_rt_broad_RT_backdoor_0_lr3e-6

z0406_rt_ordinary_RT_backdoor_0_lr1e-6

z0406_rt_broad_RT_backdoor_0_lr1e-5

z0406_rt_broad_RT_backdoor_1_lr1e-6

z0406_rt_broad_RT_backdoor_1_lr1e-5

z0406_rt_ordinary_RT_backdoor_0_lr1e-5

absa-qwen3-4b-instruction-v1

llama33_70bn_raft_v1

z0406_rt_sam_RT_backdoor_0_lr3e-5_rho0.01

z0406_rt_ordinary_RT_quirk_0_lr1e-4

z0406_rt_sam_RT_backdoor_0_lr3e-5_rho0.02

gst-copywriter-v1

z0406_rt_sam_RT_backdoor_1_lr3e-5_rho0.01

Qwen2.5-7B-Instruct-es-em-bad-medical-advice-deberta-nli-reward

z0406_rt_ordinary_RT_backdoor_1_lr1e-4

z0406_rt_ordinary_RT_backdoor_1_lr2e-5

z0406_rt_ordinary_RT_backdoor_1_lr5e-5

Affine-5DhGPvYiBChDerVjSgyt1vuuwQyZWJJgsEdQHAkXRuSYji4d