Post-Reasoning boosts LLM accuracy by reversing the usual answer-after-reasoning order, delivering mean relative gains of 17.37% across 117 model-benchmark pairs with zero extra cost.
Confident or seek stronger: Exploring uncertainty-based on-device llm routing from benchmark- ing to generalization.arXiv preprint arXiv:2502.04428
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
representative citing papers
PRP introduces proactive routing via Draft Rating Learning and Joint Rating Learning to route queries early between draft and target models for efficient multimodal reasoning.
Average token log-probability provides a zero-shot confidence signal for small LLMs that matches supervised baselines in-distribution and outperforms them out-of-distribution, with a new retrieval-conditional variant improving further at lower latency.
An approximate greedy router for hybrid PDE solvers that mimics optimal selection without true error access and shows faster, more stable error reduction on test equations.
CAT uses intrinsic confidence signals in preference optimization to adapt reasoning length in LRMs, outperforming uniform compression baselines on accuracy across benchmarks.
Verbalized confidence from small LMs enables cost-effective cascade routing for automated educational scoring, matching large-model accuracy at 76% lower cost when discrimination is strong.
citing papers explorer
-
Post Reasoning: Improving the Performance of Non-Thinking Models at No Cost
Post-Reasoning boosts LLM accuracy by reversing the usual answer-after-reasoning order, delivering mean relative gains of 17.37% across 117 model-benchmark pairs with zero extra cost.
-
Before Thinking, Learn to Decide: Proactive Routing for Efficient Visual Reasoning
PRP introduces proactive routing via Draft Rating Learning and Joint Rating Learning to route queries early between draft and target models for efficient multimodal reasoning.
-
Zero-Shot Confidence Estimation for Small LLMs: When Supervised Baselines Aren't Worth Training
Average token log-probability provides a zero-shot confidence signal for small LLMs that matches supervised baselines in-distribution and outperforms them out-of-distribution, with a new retrieval-conditional variant improving further at lower latency.
-
A Greedy PDE Router for Blending Neural Operators and Classical Methods
An approximate greedy router for hybrid PDE solvers that mimics optimal selection without true error access and shows faster, more stable error reduction on test equations.
-
CAT: Confidence-Adaptive Thinking for Efficient Reasoning of Large Reasoning Models
CAT uses intrinsic confidence signals in preference optimization to adapt reasoning length in LRMs, outperforming uniform compression baselines on accuracy across benchmarks.
-
Do Small Language Models Know When They're Wrong? Confidence-Based Cascade Scoring for Educational Assessment
Verbalized confidence from small LMs enables cost-effective cascade routing for automated educational scoring, matching large-model accuracy at 76% lower cost when discrimination is strong.