Image de couverture de livre

Sandwich Reasoning: An Answer-Reasoning-Answer Approach for Low-Latency Query Correction

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zhang, Chen, Zhang, Kepu, Zhang, Jiatong, Zhang, Xiao, Xu, Jun
Format:	Preprint
Publié:	2026
Sujets:	Artificial Intelligence Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

GeoChallenge: A Multi-Answer Multiple-Choice Benchmark for Geometric Reasoning with Diagrams
par: Zhang, Yushun, et autres
Publié: (2026)

Correct Answers from Sound Reasoning: Verifiable Process Supervision for Language Models
par: Kim, Kyuyoung, et autres
Publié: (2026)

How Do Answer Tokens Read Reasoning Traces? Self-Reading Patterns in Thinking LLMs for Quantitative Reasoning
par: Chen, Haoyang, et autres
Publié: (2026)

Reasoning or Retrieval? A Study of Answer Attribution on Large Reasoning Models
par: Wang, Yuhui, et autres
Publié: (2025)

FANS -- Formal Answer Selection for Natural Language Math Reasoning Using Lean4
par: Yao, Jiarui, et autres
Publié: (2025)

Preemptive Answer "Attacks" on Chain-of-Thought Reasoning
par: Xu, Rongwu, et autres
Publié: (2024)

From Reasoning to Answer: Empirical, Attention-Based and Mechanistic Insights into Distilled DeepSeek R1 Models
par: Zhang, Jue, et autres
Publié: (2025)

Knowing When Not to Answer: Abstention-Aware Scientific Reasoning
par: Abdaljalil, Samir, et autres
Publié: (2026)

Towards A Unified View of Answer Calibration for Multi-Step Reasoning
par: Deng, Shumin, et autres
Publié: (2023)

Correct after Answer: Enhancing Multi-Span Question Answering with Post-Processing Method
par: Lin, Jiayi, et autres
Publié: (2024)

Beyond the Final Answer: Evaluating the Reasoning Trajectories of Tool-Augmented Agents
par: Kim, Wonjoong, et autres
Publié: (2025)

RAVR: Reference-Answer-guided Variational Reasoning for Large Language Models
par: Lin, Tianqianjin, et autres
Publié: (2025)

A Claim Decomposition Benchmark for Long-form Answer Verification
par: Zhang, Zhihao, et autres
Publié: (2024)

ClimateChat: Designing Data and Methods for Instruction Tuning LLMs to Answer Climate Change Queries
par: Chen, Zhou, et autres
Publié: (2025)

Implicit Probabilistic Reasoning Does Not Reflect Explicit Answers in Large Language Models
par: Mondal, Manuel, et autres
Publié: (2024)

Finding Answers in Thought Matters: Revisiting Evaluation on Large Language Models with Reasoning
par: Jo, Hwiyeol, et autres
Publié: (2025)

Latent Self-Consistency for Reliable Majority-Set Selection in Short- and Long-Answer Reasoning
par: Oh, Jungsuk, et autres
Publié: (2025)

QueryAgent: A Reliable and Efficient Reasoning Framework with Environmental Feedback-based Self-Correction
par: Huang, Xiang, et autres
Publié: (2024)

Hallucination Detection: Robustly Discerning Reliable Answers in Large Language Models
par: Chen, Yuyan, et autres
Publié: (2024)

PRISM: Probing Reasoning, Instruction, and Source Memory in LLM Hallucinations
par: Wu, Yuhe, et autres
Publié: (2026)

Correct Chains, Wrong Answers: Dissociating Reasoning from Output in LLM Logic
par: Rao, Abinav, et autres
Publié: (2026)

Proving that Cryptic Crossword Clue Answers are Correct
par: Andrews, Martin, et autres
Publié: (2024)

Collective Reasoning Among LLMs: A Framework for Answer Validation Without Ground Truth
par: Davoudi, Seyed Pouyan Mousavi, et autres
Publié: (2025)

General Table Question Answering via Answer-Formula Joint Generation
par: Wang, Zhongyuan, et autres
Publié: (2025)

Answer, Assemble, Ace: Understanding How LMs Answer Multiple Choice Questions
par: Wiegreffe, Sarah, et autres
Publié: (2024)

SAS-Bench: A Fine-Grained Benchmark for Evaluating Short Answer Scoring with Large Language Models
par: Lai, Peichao, et autres
Publié: (2025)

Query Disambiguation via Answer-Free Context: Doubling Performance on Humanity's Last Exam
par: Majurski, Michael, et autres
Publié: (2026)

A Dataset of Open-Domain Question Answering with Multiple-Span Answers
par: Luo, Zhiyi, et autres
Publié: (2024)

Beyond Answers: Transferring Reasoning Capabilities to Smaller LLMs Using Multi-Teacher Knowledge Distillation
par: Tian, Yijun, et autres
Publié: (2024)

No Answer Needed: Predicting LLM Answer Accuracy from Question-Only Linear Probes
par: Cencerrado, Iván Vicente Moreno, et autres
Publié: (2025)

From Answers to Questions: EQGBench for Evaluating LLMs' Educational Question Generation
par: Zhou, Chengliang, et autres
Publié: (2025)

Directed Graph-alignment Approach for Identification of Gaps in Short Answers
par: Sahu, Archana, et autres
Publié: (2025)

Revisiting Self-Consistency from Dynamic Distributional Alignment Perspective on Answer Aggregation
par: Li, Yiwei, et autres
Publié: (2025)

Beyond the Last Answer: Your Reasoning Trace Uncovers More than You Think
par: Hammoud, Hasan Abed Al Kader, et autres
Publié: (2025)

Towards Safe Reasoning in Large Reasoning Models via Corrective Intervention
par: Zhang, Yichi, et autres
Publié: (2025)

CultureSynth: A Hierarchical Taxonomy-Guided and Retrieval-Augmented Framework for Cultural Question-Answer Synthesis
par: Zhang, Xinyu, et autres
Publié: (2025)

DataAgent: Evaluating Large Language Models' Ability to Answer Zero-Shot, Natural Language Queries
par: Mishra, Manit, et autres
Publié: (2024)

Kun: Answer Polishment for Chinese Self-Alignment with Instruction Back-Translation
par: Zheng, Tianyu, et autres
Publié: (2024)

The Potential of LLMs in Medical Education: Generating Questions and Answers for Qualification Exams
par: Zhu, Yunqi, et autres
Publié: (2024)

Same Evidence, Different Answers: Canonical-Context On-Policy Distillation for Multi-Turn Language Models
par: Lin, Zizhuo, et autres
Publié: (2026)