Mitigating Strategy-Selection Bias in Reasoning for More Effective Test-Time Scaling
Test-time scaling (TTS) has been shown to improve the performance of large language models (LLMs) by sampling and aggregating diverse reasoning paths. However, existing research has overlooked a critical issue: selection bias of reasoning strategies during scaling. Specifically, when generating reasoning processes, LLMs tend to follow certain strategies (e.g., algebraic solutions for math problems) while neglecting other valid alternatives (e.g., geometric solutions), resulting in insufficient exploration of the solution space. To further understand the impact of this bias, we present a theoretical analysis that reveals when it undermines the effectiveness of test-time scaling. Motivated by this theoretical insight, we introduce TTS-Uniform, a framework designed to mitigate the selection bias of reasoning strategies. It (i) identifies potential strategies, (ii) uniformly allocates the sampling budget across them, and (iii) filters out unstable strategies prior to aggregation. Experimental results show that TTS-Uniform significantly enhances scaling effectiveness across multiple mainstream LLMs and benchmark datasets.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
CoLD: Counterfactually-Guided Length Debiasing for Process Reward Models in Mathematical Reasoning
Process Reward Models (PRMs) play a central role in evaluating and guiding multi-step reasoning in large language models (LLMs), especially for mathematical problem solving. However, we identify a pervasive length bias i…
Mathematical ReasoningMetric-DST: Mitigating Selection Bias Through Diversity-Guided Semi-Supervised Metric Learning
Selection bias poses a critical challenge for fairness in machine learning, as models trained on data that is less representative of the population might exhibit undesirable behavior for underrepresented profiles. Semi-s…
DiversityFairnessMetric LearningSelection biasAddressing Blind Guessing: Calibration of Selection Bias in Multiple-Choice Question Answering by Video Language Models
Evaluating Video Language Models (VLMs) is a challenging task. Due to its transparency, Multiple-Choice Question Answering (MCQA) is widely used to measure the performance of these models through accuracy. However, exist…
FairnessMultiple-choiceMultiple Choice Question Answering (MCQA)Question Answering+1Unbiased Math Word Problems Benchmark for Mitigating Solving Bias
In this paper, we revisit the solving bias when evaluating models on current Math Word Problem (MWP) benchmarks. However, current solvers exist solving bias which consists of data bias and learning bias due to biased dat…
MathMitigating Selection Bias in Large Language Models via Permutation-Aware GRPO
Large language models (LLMs) used for multiple-choice and pairwise evaluation tasks often exhibit selection bias due to non-semantic factors like option positions and label symbols. Existing inference-time debiasing is c…