HIPPO is a new RL framework that uses hint-anchored pairwise aggregation to distinguish and promote authentic reasoning deduction in LLMs instead of shortcut memorization from data overlap.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
other 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
other 1polarities
unclear 1representative citing papers
Curating 25K natural-instruction examples for RLVR yields a 64.4pp relative gain on BBEH for Qwen3-0.6B and generalizes across scales and model families.
citing papers explorer
-
To Reason or to Fabricate: Reasoning Without Shortcuts via Hint-Anchored Pairwise Aggregation
HIPPO is a new RL framework that uses hint-anchored pairwise aggregation to distinguish and promote authentic reasoning deduction in LLMs instead of shortcut memorization from data overlap.
-
SUPERNOVA: Eliciting General Reasoning in LLMs with Reinforcement Learning on Natural Instructions
Curating 25K natural-instruction examples for RLVR yields a 64.4pp relative gain on BBEH for Qwen3-0.6B and generalizes across scales and model families.