AIJan 12

ENTRA: Entropy-Based Redundancy Avoidance in Large Language Model Reasoning

arXiv:2601.07123v1h-index: 13
Originality Incremental advance
AI Analysis

This addresses computational inefficiency in large language models for reasoning tasks, offering a domain-specific improvement.

The paper tackles the problem of overthinking in Large Reasoning Models, where models generate unnecessarily long reasoning chains, and proposes ENTRA, an entropy-based training framework that reduces output length by 37% to 53% while maintaining or improving accuracy on mathematical reasoning benchmarks.

Large Reasoning Models (LRMs) often suffer from overthinking, generating unnecessarily long reasoning chains even for simple tasks. This leads to substantial computational overhead with limited performance gain, primarily due to redundant verification and repetitive generation. While prior work typically constrains output length or optimizes correctness, such coarse supervision fails to guide models toward concise yet accurate inference. In this paper, we propose ENTRA, an entropy-based training framework that suppresses redundant reasoning while preserving performance. ENTRA first estimates the token-level importance using a lightweight Bidirectional Importance Estimation (BIE) method, which accounts for both prediction confidence and forward influence. It then computes a redundancy reward based on the entropy of low-importance tokens, normalized by its theoretical upper bound, and optimizes this reward via reinforcement learning. Experiments on mathematical reasoning benchmarks demonstrate that ENTRA reduces output length by 37% to 53% with no loss-and in some cases, gains-in accuracy. Our approach offers a principled and efficient solution to reduce overthinking in LRMs, and provides a generalizable path toward redundancy-aware reasoning optimization.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes