Sandwich Reasoning: An Answer-Reasoning-Answer Approach for Low-Latency Query Correction
cs.AI, cs.CL
Submitted: 2026-01-07
Updated: 2026-10-28
Comments: 11 pages, 4 figures. Accepted at CIKM 2026
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning
- Prompting open-source and commercial language models for grammatical error correction of English learner text
- TaoSR1: The Thinking Model for E-commerce Relevance Search
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Token-Budget-Aware LLM Reasoning
- OpenAI o1 System Card
- BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension
- On the (In)Effectiveness of Large Language Models for Chinese Text Correction
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- mT5: A massively multilingual pre-trained text-to-text transformer
- LIMO: Less is More for Reasoning
- QE-RAG: A Robust Retrieval-Augmented Generation Benchmark for Query Entry Errors
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents