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.
Title resolution pending
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
representative citing papers
CODI compresses explicit CoT into continuous space via self-distillation and is the first implicit method to match explicit CoT performance on GSM8k at GPT-2 scale with 3.1x compression and 28.2% higher accuracy than prior implicit approaches.
Deep Pre-Alignment uses a small VLM perceiver instead of ViT to pre-align visual features with LLM text space, yielding 1.9-3.0 point gains on multimodal benchmarks and 32.9% less language forgetting.
Programmatic context augmentation lets LLM-based symbolic regression perform code-driven data analysis during search, yielding superior efficiency and accuracy over baselines on LLM-SRBench.
CAL-GRPO calibrates per-attempt weights in multi-attempt CoT to deliver unbiased gradients for optimizing Verification@K success while keeping variance low.
PV-SQL boosts Text-to-SQL execution accuracy by 5% and valid efficiency by 20.8% on BIRD benchmarks via database probing and rule-based SQL verification while using fewer tokens.
Probabilistic programs of thought let LLMs produce many program variants from one generation by building a compact probabilistic representation of the token distribution.
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.
-
CODI: Compressing Chain-of-Thought into Continuous Space via Self-Distillation
CODI compresses explicit CoT into continuous space via self-distillation and is the first implicit method to match explicit CoT performance on GSM8k at GPT-2 scale with 3.1x compression and 28.2% higher accuracy than prior implicit approaches.
-
Deep Pre-Alignment for VLMs
Deep Pre-Alignment uses a small VLM perceiver instead of ViT to pre-align visual features with LLM text space, yielding 1.9-3.0 point gains on multimodal benchmarks and 32.9% less language forgetting.
-
Programmatic Context Augmentation for LLM-based Symbolic Regression
Programmatic context augmentation lets LLM-based symbolic regression perform code-driven data analysis during search, yielding superior efficiency and accuracy over baselines on LLM-SRBench.
-
Learning to Correct: Calibrated Reinforcement Learning for Multi-Attempt Chain-of-Thought
CAL-GRPO calibrates per-attempt weights in multi-attempt CoT to deliver unbiased gradients for optimizing Verification@K success while keeping variance low.
-
PV-SQL: Synergizing Database Probing and Rule-based Verification for Text-to-SQL Agents
PV-SQL boosts Text-to-SQL execution accuracy by 5% and valid efficiency by 20.8% on BIRD benchmarks via database probing and rule-based SQL verification while using fewer tokens.
-
Probabilistic Programs of Thought
Probabilistic programs of thought let LLMs produce many program variants from one generation by building a compact probabilistic representation of the token distribution.