CCQA: Generating Question from Solution Can Improve Inference-Time Reasoning in SLMs

• URL: http://arxiv.org/abs/2509.18536v1
• Date: Tue, 23 Sep 2025 02:01:03 GMT
• Title: CCQA: Generating Question from Solution Can Improve Inference-Time Reasoning in SLMs
• Authors: Jin Young Kim, Ji Won Yoon,
• Abstract summary: We propose textbfCycle-textbfConsistency in textbfQuestion textbfAnswering (CCQA)<n>Inspired by cycle consistency, CCQA generates a question from each reasoning path and answer, evaluates each by its similarity to the original question, and then selects the candidate solution with the highest similarity score as the final response.<n>It is verified that CCQA consistently outperforms existing state-of-the-art (SOTA) methods across eight models on mathematical and commonsense reasoning benchmarks.
• Score: 14.97707719362011
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recently, inference-time reasoning strategies have further improved the accuracy of large language models (LLMs), but their effectiveness on smaller models remains unclear. Based on the observation that conventional approaches often fail to improve performance in this context, we propose \textbf{C}ycle-\textbf{C}onsistency in \textbf{Q}uestion \textbf{A}nswering (CCQA), a novel reasoning method that can be effectively applied to SLMs. Inspired by cycle consistency, CCQA generates a question from each reasoning path and answer, evaluates each by its similarity to the original question, and then selects the candidate solution with the highest similarity score as the final response. Since conventional SLMs struggle to generate accurate questions from their own reasoning paths and answers, we employ a lightweight Flan-T5 model specialized for question generation to support this process efficiently. From the experimental results, it is verified that CCQA consistently outperforms existing state-of-the-art (SOTA) methods across eight models on mathematical and commonsense reasoning benchmarks. Furthermore, our method establishes a new practical baseline for efficient reasoning in SLMs. Source code can be found at https://github.com/scai-research/ccqa_official.

Related papers

• Boosting Process-Correct CoT Reasoning by Modeling Solvability of Multiple-Choice QA [10.122669382758122]
  We show that when questions are effectively unsolvable for a model, spurious chains of thought (CoTs) are more likely to appear.<n>We adapt outcome-supervised reward models and reinforcement learning with group-relative advantage to incorporate solvability into their objectives.<n>Our results highlight solvability as a key factor for reducing hallucinations and increasing reliability in CoT reasoning.
  arXiv  Detail & Related papers  (2025-09-30T08:34:16Z)
• Learning to Refine: Self-Refinement of Parallel Reasoning in LLMs [102.48588475875749]
  We introduce Generative Self-Refinement (GSR), a novel parallel test-time scaling framework.<n>GSR generates a set of candidate responses in parallel and then performs self-refinement to synthesize a new superior solution.<n>We show that our method achieves state-of-the-art performance across five mathematical benchmarks.
  arXiv  Detail & Related papers  (2025-08-27T06:51:48Z)
• CAMA: Enhancing Mathematical Reasoning in Large Language Models with Causal Knowledge [14.367146529900609]
  Large Language Models (LLMs) have demonstrated strong performance across a wide range of tasks, yet they still struggle with complex mathematical reasoning.<n>We propose textbfCAusal textbfMAthematician (textbfCAMA), a two-stage causal framework that equips LLMs with explicit, reusable mathematical structure.
  arXiv  Detail & Related papers  (2025-08-04T16:39:24Z)
• Stepwise Reasoning Checkpoint Analysis: A Test Time Scaling Method to Enhance LLMs' Reasoning [81.50681925980135]
  We propose Stepwise Reasoning Checkpoint Analysis (SRCA), a framework that introduces checkpoints between reasoning steps.<n>It incorporates two key strategies: (1) Answer-Clustered Search, which groups reasoning paths by their intermediate checkpoint answers to maintain diversity while ensuring quality, and (2) Checkpoint Candidate Augmentation, which leverages all intermediate answers for final decision-making.<n>Our approach effectively reduces path homogenization and creates a fault-tolerant mechanism by utilizing high-quality intermediate results.
  arXiv  Detail & Related papers  (2025-05-23T12:42:50Z)
• Think Deep, Think Fast: Investigating Efficiency of Verifier-free Inference-time-scaling Methods [39.89239733570008]
  This work conducts a comprehensive analysis of inference-time scaling methods for both reasoning and non-reasoning models.<n>We find that non-reasoning models, even with an extremely high inference budget, still fall substantially behind reasoning models.<n>For reasoning models, majority voting proves to be a robust inference strategy, generally competitive or outperforming other more sophisticated ITC methods.
  arXiv  Detail & Related papers  (2025-04-18T19:32:55Z)
• Right Answer, Wrong Score: Uncovering the Inconsistencies of LLM Evaluation in Multiple-Choice Question Answering [78.89231943329885]
  Multiple-Choice Question Answering (MCQA) is widely used to evaluate Large Language Models (LLMs)<n>We show that multiple factors can significantly impact the reported performance of LLMs.<n>We analyze whether existing answer extraction methods are aligned with human judgment.
  arXiv  Detail & Related papers  (2025-03-19T08:45:03Z)
• Scalable Best-of-N Selection for Large Language Models via Self-Certainty [75.1351701045874]
  Best-of-N selection is a key technique for improving the reasoning performance of Large Language Models (LLMs)<n>We propose self-certainty, a novel and efficient metric that leverages the inherent probability distribution of LLM outputs to estimate response quality without requiring external reward models.<n>Our findings establish self-certainty as a practical and efficient way for improving LLM reasoning capabilities.
  arXiv  Detail & Related papers  (2025-02-25T19:08:07Z)
• CoT-UQ: Improving Response-wise Uncertainty Quantification in LLMs with Chain-of-Thought [10.166370877826486]
  Large language models (LLMs) excel in many tasks but struggle to accurately quantify uncertainty in their generated responses.<n>Existing uncertainty quantification (UQ) methods for LLMs are primarily prompt-wise rather than response-wise.<n>We propose CoT-UQ, a response-wise UQ framework that integrates LLMs' inherent reasoning capabilities through Chain-of-Thought.
  arXiv  Detail & Related papers  (2025-02-24T14:48:06Z)
• Prompting Strategies for Enabling Large Language Models to Infer Causation from Correlation [68.58373854950294]
  We focus on causal reasoning and address the task of establishing causal relationships based on correlation information.<n>We introduce a prompting strategy for this problem that breaks the original task into fixed subquestions.<n>We evaluate our approach on an existing causal benchmark, Corr2Cause.
  arXiv  Detail & Related papers  (2024-12-18T15:32:27Z)
• LLM-based Discriminative Reasoning for Knowledge Graph Question Answering [42.277864969014296]
  Large language models (LLMs) based on generative pre-trained Transformer have achieved remarkable performance on knowledge graph question-answering (KGQA) tasks.<n>However, LLMs often produce ungrounded subgraph planning or reasoning results in KGQA due to the hallucinatory behavior brought by the generative paradigm.<n>We propose READS to reformulate the KGQA process into discriminative subtasks, which simplifies the search space for each subtask.
  arXiv  Detail & Related papers  (2024-12-17T08:07:16Z)
• LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical Reasoning [56.273799410256075]
  The framework combines Monte Carlo Tree Search (MCTS) with iterative Self-Refine to optimize the reasoning path. The framework has been tested on general and advanced benchmarks, showing superior performance in terms of search efficiency and problem-solving capability.
  arXiv  Detail & Related papers  (2024-10-03T18:12:29Z)
• DCR: Divide-and-Conquer Reasoning for Multi-choice Question Answering with LLMs [9.561022942046279]
  We propose Divide and Conquer Reasoning (DCR) to enhance the reasoning capability of large language models (LLMs) We first categorize questions into two subsets based on confidence score ($mathcalCS$), which is estimated by statistical frequency of generated answers. In particular, we first categorize questions into two subsets based on confidence score ($mathcalCS$), which is estimated by statistical frequency of generated answers.
  arXiv  Detail & Related papers  (2024-01-10T14:38:46Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.