Chain-of-Thought Faithfulness of Reasoning Models Varies with Where and How Preference Cues Are Delivered Paper • 2608.29464 • Published 21 days ago • 15
Neelectric/Llama-3.1-8B-Instruct_SafeGrad_mathv00.07_s44 Text Generation • 8B • Updated 12 days ago • 720
Neelectric/Llama-3.1-8B-Instruct_SafeGrad_mathv00.07_s44 Text Generation • 8B • Updated 12 days ago • 720
Neelectric/Llama-3.1-8B-Instruct_SafeGrad_mathv00.07_s43 Text Generation • 8B • Updated 13 days ago • 709
Neelectric/Llama-3.1-8B-Instruct_SafeGrad_mathv00.07_s43 Text Generation • 8B • Updated 13 days ago • 709
Neelectric/Llama-3.1-8B-Instruct_SFT_mathsp_ewc_v00.15_s44 Text Generation • 8B • Updated 14 days ago • 640
Neelectric/Llama-3.1-8B-Instruct_SFT_mathsp_ewc_v00.15_s44 Text Generation • 8B • Updated 14 days ago • 640
Neelectric/Llama-3.1-8B-Instruct_SFT_mathsp_ewc_v00.15_s43 Text Generation • 8B • Updated 15 days ago • 660
Neelectric/Llama-3.1-8B-Instruct_SFT_mathsp_ewc_v00.15_s43 Text Generation • 8B • Updated 15 days ago • 660
Chain-of-Thought Faithfulness of Reasoning Models Varies with Where and How Preference Cues Are Delivered Paper • 2608.29464 • Published 21 days ago • 15