T$^2$: An Adaptive Test-Time Scaling Strategy for Contextual Question Answering

• URL: http://arxiv.org/abs/2505.17427v2
• Date: Wed, 04 Jun 2025 08:58:33 GMT
• Title: T$^2$: An Adaptive Test-Time Scaling Strategy for Contextual Question Answering
• Authors: Zhengyi Zhao, Shubo Zhang, Zezhong Wang, Huimin Wang, Yutian Zhao, Bin Liang, Yefeng Zheng, Binyang Li, Kam-Fai Wong, Xian Wu,
• Abstract summary: We present T$2$: Think-to-Think, a novel framework that dynamically adapts reasoning depth based on question complexity.<n>T$2$ works through four key steps: decomposing questions into structural elements, generating similar examples with candidate reasoning strategies, evaluating these strategies against multiple criteria, and applying the most appropriate strategy to the original question.
• Score: 49.5489716597489
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent advances in Large Language Models (LLMs) have demonstrated remarkable performance in Contextual Question Answering (CQA). However, prior approaches typically employ elaborate reasoning strategies regardless of question complexity, leading to low adaptability. Recent efficient test-time scaling methods introduce budget constraints or early stop mechanisms to avoid overthinking for straightforward questions. But they add human bias to the reasoning process and fail to leverage models' inherent reasoning capabilities. To address these limitations, we present T$^2$: Think-to-Think, a novel framework that dynamically adapts reasoning depth based on question complexity. T$^2$ leverages the insight that if an LLM can effectively solve similar questions using specific reasoning strategies, it can apply the same strategy to the original question. This insight enables to adoption of concise reasoning for straightforward questions while maintaining detailed analysis for complex problems. T$^2$ works through four key steps: decomposing questions into structural elements, generating similar examples with candidate reasoning strategies, evaluating these strategies against multiple criteria, and applying the most appropriate strategy to the original question. Experimental evaluation across seven diverse CQA benchmarks demonstrates that T$^2$ not only achieves higher accuracy than baseline methods but also reduces computational overhead by up to 25.2\%.

Related papers

• Ada-R1: Hybrid-CoT via Bi-Level Adaptive Reasoning Optimization [86.56120216550232]
  We propose a novel two-stage framework for adaptive and efficient reasoning.<n>First, we construct a hybrid reasoning model by merging long and short CoT models.<n>Second, we apply bi-level preference training to guide the model to select suitable reasoning styles.
  arXiv  Detail & Related papers  (2025-04-30T14:01:45Z)
• 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)
• Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs [76.43407125275202]
  o1-like models can emulate human-like long-time thinking during inference.<n>This paper presents the first comprehensive study on the prevalent issue of overthinking in these models.<n>We propose strategies to mitigate overthinking, streamlining reasoning processes without compromising accuracy.
  arXiv  Detail & Related papers  (2024-12-30T18:55:12Z)
• FLARE: Faithful Logic-Aided Reasoning and Exploration [50.9814063216852]
  We introduce a novel approach for traversing the problem space using task decompositions.<n>We use the Large Language Models to plan a solution, soft-formalise the query into facts and predicates using a logic programming code.<n>Our method allows us to compute the faithfulness of the reasoning process w.r.t. the generated code and analyse the steps of the multi-hop search without relying on external solvers.
  arXiv  Detail & Related papers  (2024-10-14T19:39:11Z)
• Question-Analysis Prompting Improves LLM Performance in Reasoning Tasks [3.741953084205603]
  We propose a novel prompting strategy called Question Analysis Prompting (QAP) QAP is evaluated on GPT 3.5 Turbo and GPT 4 Turbo on arithmetic datasets GSM8K, AQuA, and SAT and commonsense dataset StrategyQA. QAP consistently ranks among the top-2 prompts on 75% of the tests.
  arXiv  Detail & Related papers  (2024-07-04T04:19:50Z)
• 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)
• Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies [78.68534915690404]
  StrategyQA is a benchmark where the required reasoning steps are implicit in the question, and should be inferred using a strategy. We propose a data collection procedure that combines term-based priming to inspire annotators, careful control over the annotator population, and adversarial filtering for eliminating reasoning shortcuts. Overall, StrategyQA includes 2,780 examples, each consisting of a strategy question, its decomposition, and evidence paragraphs.
  arXiv  Detail & Related papers  (2021-01-06T19:14:23Z)
• Discriminative Learning via Adaptive Questioning [6.378513792050356]
  We consider the problem of designing an adaptive sequence of questions that optimally classify a candidate's ability into one of several categories or discriminative grades. A candidate's ability is modeled as an unknown parameter, which, together with the difficulty of the question asked, determines the likelihood with which s/he is able to answer a question correctly.
  arXiv  Detail & Related papers  (2020-04-11T16:50:00Z)

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.