Models from "Efficient Reasoning Training Does Not Always Harm CoT Faithfulness and Monitorability".
Samuel Lewis-Lim PRO
Samll
·
AI & ML interests
None yet
Recent Activity
upvoted a paper about 12 hours ago
Steerable Multi-Objective Group-Relative Preference Optimization with Jointly Trained Low-Rank Adapters updated a collection about 1 month ago
efficient-reasoning submitted a paper about 1 month ago
Efficient Reasoning Training Does Not Always Harm CoT Faithfulness and MonitorabilityOrganizations
None yet
models 11
Samll/olmo3-7b-think-l1
Updated • 8
Samll/olmo3-7b-think-glp
Updated • 10
Samll/olmo3-7b-think-thinkprune-b4000
Text Generation • 7B • Updated • 71
Samll/qwen3-8b-l1
Updated • 29
Samll/qwen3-8b-glp
Updated • 28
Samll/qwen3-8b-thinkprune-b3000
Text Generation • 8B • Updated • 53
Samll/qwen3-4b-thinking-l1
Updated • 19
Samll/qwen3-4b-thinking-glp
Updated • 16
Samll/qwen3-4b-thinking-thinkprune-b4000
Text Generation • 4B • Updated • 26
Samll/wild_hallu_v3-3b
Text Generation • 3B • Updated • 3
datasets 20
Samll/wild_hallucinations_deepseek_factscore_chat_v2
Viewer • Updated • 3.65k • 20
Samll/wild_hallucinations_deepseek_factscore_chat
Viewer • Updated • 3.38k • 27
Samll/hotpotqa_inference_llama3-8b
Viewer • Updated • 20k • 14
Samll/wild_hallucinations_deepseek_factscore
Viewer • Updated • 1k • 16
Samll/wild_hallucinations_with_responses
Viewer • Updated • 7.92k • 32
Samll/Llama-3.1-8B-Instruct_attn_rollout_attributions_v1
Viewer • Updated • 5.77k • 10
Samll/Llama-3.1-8B-Instruct_attn_rollout_attributions
Viewer • Updated • 15.1k • 14
Samll/Llama-3.1-8B-Instruct_Taur_CoT_contrastive_relevances_attn_test
Viewer • Updated • 210 • 9
Samll/Llama-3.1-8B-Instruct_Taur_CoT_contrastive_relevances_v1
Viewer • Updated • 13.3k • 13
Samll/Llama-3.1-8B-Instruct_Taur_CoT_contrastive_relevances
Viewer • Updated • 22.4k • 16