Abstention Direction in Large Language Models: Mechanistic Interpretability of Abstention Across Query Ambiguity, Knowledge Limits, and Safety Alignment Paper • 2611.20441 • Published 4 days ago • 6
Abstention Direction in Large Language Models: Mechanistic Interpretability of Abstention Across Query Ambiguity, Knowledge Limits, and Safety Alignment Paper • 2611.20441 • Published 4 days ago • 6
LIT-RAGBench: Benchmarking Generator Capabilities of Large Language Models in Retrieval-Augmented Generation Paper • 2603.06198 • Published Mar 6
LLMcompe-Team-Watanabe/Qwen3-32B-merge-high-acc-dft-grpo-filtered-w-easy-3ep 33B • Updated Aug 24, 2025
LLMcompe-Team-Watanabe/Qwen3-32B-merge-high-acc-dft-grpo-filtered-w-easy-3ep 33B • Updated Aug 24, 2025
LLMcompe-Team-Watanabe/Qwen3-32B-merge-high-acc-dft-grpo-filtered-w-easy-1ep-1step 33B • Updated Aug 24, 2025 • 2
LLMcompe-Team-Watanabe/Qwen3-32B-merge-high-acc-dft-grpo-filtered-w-easy-1ep-1step 33B • Updated Aug 24, 2025 • 2
LLMcompe-Team-Watanabe/Qwen3-32B-merge-base2-math3-science3-submath05-med05-other1-sft-grpodata Text Generation • 33B • Updated Aug 24, 2025 • 3
LLMcompe-Team-Watanabe/Qwen3-32B-merge-base2-math3-science3-submath05-med05-other1-sft-grpodata Text Generation • 33B • Updated Aug 24, 2025 • 3
LLMcompe-Team-Watanabe/sft_math_physics_from_gropda_rule_filter_w_easy Viewer • Updated Aug 24, 2025 • 4.94k • 26
LLMcompe-Team-Watanabe/sft_math_physics_from_gropda_rule_filter_w_easy Viewer • Updated Aug 24, 2025 • 4.94k • 26
LLMcompe-Team-Watanabe/sft_math_physics_from_gropda_rule_filter Viewer • Updated Aug 24, 2025 • 2.76k • 18