LLM molecular design framework uses self-reflection on full physicochemical data from first-principles calculations to achieve low deviation on HOMO-LUMO gaps and generalize to other properties.
DenseSteer: Steering Small Language Models towards Dense Math Reasoning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Large language models (LLMs) demonstrate strong chain-of-thought (CoT) reasoning abilities, while smaller models (<= 3B parameters) significantly underperform on multi-step reasoning tasks. Based on empirical analyses of the Qwen-2.5 model family on math reasoning benchmarks, we find that more proficient reasoning is associated with fewer reasoning steps but higher information density per step, a property we term Dense Reasoning. Motivated by this observation, we propose DenseSteer, a training-free inference-time steering framework that enhances small-model reasoning by modulating internal representations toward dense reasoning patterns. Experiments show that our method yields consistent accuracy improvements without increasing token-level Negative Log-Likelihood, highlighting dense reasoning as an effective structural approach to mathematical problem solving.
fields
physics.chem-ph 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Closing the Prior-Posterior Loop: Self-Reflective Molecular Design with Analysis-Driven LLM Iteration
LLM molecular design framework uses self-reflection on full physicochemical data from first-principles calculations to achieve low deviation on HOMO-LUMO gaps and generalize to other properties.