Make Every Penny Count: Difficulty-Adaptive Self-Consistency for Cost-Efficient Reasoning

• URL: http://arxiv.org/abs/2408.13457v1
• Date: Sat, 24 Aug 2024 04:03:35 GMT
• Title: Make Every Penny Count: Difficulty-Adaptive Self-Consistency for Cost-Efficient Reasoning
• Authors: Xinglin Wang, Shaoxiong Feng, Yiwei Li, Peiwen Yuan, Yueqi Zhang, Boyuan Pan, Heda Wang, Yao Hu, Kan Li,
• Abstract summary: Self-consistency (SC) is a widely used decoding strategy for chain-of-thought reasoning. Its variants, Adaptive self-consistency (ASC) and Early-stopping self-consistency (ESC), dynamically adjust the number of samples based on the posterior distribution of a set of pre-samples. We propose Difficulty-Adaptive Self-Consistency (DSC), which leverages the difficulty information from both prior and posterior perspectives to adaptively allocate inference resources.
• Score: 19.408941114068444
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Self-consistency (SC), a widely used decoding strategy for chain-of-thought reasoning, shows significant gains across various multi-step reasoning tasks but comes with a high cost due to multiple sampling with the preset size. Its variants, Adaptive self-consistency (ASC) and Early-stopping self-consistency (ESC), dynamically adjust the number of samples based on the posterior distribution of a set of pre-samples, reducing the cost of SC with minimal impact on performance. Both methods, however, do not exploit the prior information about question difficulty. It often results in unnecessary repeated sampling for easy questions that could be accurately answered with just one attempt, wasting resources. To tackle this problem, we propose Difficulty-Adaptive Self-Consistency (DSC), which leverages the difficulty information from both prior and posterior perspectives to adaptively allocate inference resources, further reducing the cost of SC. To demonstrate the effectiveness of DSC, we conduct extensive experiments on three popular categories of reasoning tasks: arithmetic, commonsense and symbolic reasoning on six benchmarks. The empirical results show that DSC consistently surpasses the strong baseline ASC and ESC in terms of costs by a significant margin, while attaining comparable performances.

Related papers

• Dynamic Self-Consistency: Leveraging Reasoning Paths for Efficient LLM Sampling [9.44858963874474]
  Self-Consistency (SC) results in significant computational costs proportional to the number of samples generated. We propose Reasoning-Aware Self-Consistency (RASC), an innovative early-stopping framework that adjusts the number of sample generations. RASC significantly reduces sample usage by an average of 80% while maintaining or improving accuracy up to 5% compared to the original SC.
  arXiv  Detail & Related papers  (2024-08-30T05:14:59Z)
• Integrate the Essence and Eliminate the Dross: Fine-Grained Self-Consistency for Free-Form Language Generation [20.138831477848615]
  We propose Fine-Grained Self-Consistency (FSC) to optimize output quality by effectively fine-grained consensus knowledge from multiple samples. The effectiveness of FSC is demonstrated through extensive experiments on various tasks, including summarization, code generation, and mathematical reasoning.
  arXiv  Detail & Related papers  (2024-07-02T08:38:31Z)
• A Thorough Performance Benchmarking on Lightweight Embedding-based Recommender Systems [67.52782366565658]
  State-of-the-art recommender systems (RSs) depend on categorical features, which ecoded by embedding vectors, resulting in excessively large embedding tables. Despite the prosperity of lightweight embedding-based RSs, a wide diversity is seen in evaluation protocols. This study investigates various LERS' performance, efficiency, and cross-task transferability via a thorough benchmarking process.
  arXiv  Detail & Related papers  (2024-06-25T07:45:00Z)
• Language Model Cascades: Token-level uncertainty and beyond [65.38515344964647]
  Recent advances in language models (LMs) have led to significant improvements in quality on complex NLP tasks. Cascading offers a simple strategy to achieve more favorable cost-quality tradeoffs. We show that incorporating token-level uncertainty through learned post-hoc deferral rules can significantly outperform simple aggregation strategies.
  arXiv  Detail & Related papers  (2024-04-15T21:02:48Z)
• Escape Sky-high Cost: Early-stopping Self-Consistency for Multi-step Reasoning [15.088675135566646]
  Self-consistency (SC) has been a widely used decoding strategy for chain-of-thought reasoning. We propose a simple and scalable sampling process, textbfEarly-Stopping textbfSelf-textbfConsistency (ESC) to greatly reduce the cost of SC without sacrificing performance.
  arXiv  Detail & Related papers  (2024-01-19T04:03:59Z)
• Task-specific experimental design for treatment effect estimation [59.879567967089145]
  Large randomised trials (RCTs) are the standard for causal inference. Recent work has proposed more sample-efficient alternatives to RCTs, but these are not adaptable to the downstream application for which the causal effect is sought. We develop a task-specific approach to experimental design and derive sampling strategies customised to particular downstream applications.
  arXiv  Detail & Related papers  (2023-06-08T18:10:37Z)
• Delving into Identify-Emphasize Paradigm for Combating Unknown Bias [52.76758938921129]
  We propose an effective bias-conflicting scoring method (ECS) to boost the identification accuracy. We also propose gradient alignment (GA) to balance the contributions of the mined bias-aligned and bias-conflicting samples. Experiments are conducted on multiple datasets in various settings, demonstrating that the proposed solution can mitigate the impact of unknown biases.
  arXiv  Detail & Related papers  (2023-02-22T14:50:24Z)
• Explaining with Greater Support: Weighted Column Sampling Optimization for q-Consistent Summary-Explanations [1.6262731094866383]
  $q$-consistent summary-explanation aims to achieve greater support at the cost of slightly lower consistency. The challenge is that the max-support problem of $q$-consistent summary-explanation (MSqC) is much more complex than the original MS problem. To improve the solution time efficiency, this paper proposes the weighted column sampling(WCS) method.
  arXiv  Detail & Related papers  (2023-02-09T09:40:30Z)
• Label Distributionally Robust Losses for Multi-class Classification: Consistency, Robustness and Adaptivity [55.29408396918968]
  We study a family of loss functions named label-distributionally robust (LDR) losses for multi-class classification. Our contributions include both consistency and robustness by establishing top-$k$ consistency of LDR losses for multi-class classification. We propose a new adaptive LDR loss that automatically adapts the individualized temperature parameter to the noise degree of class label of each instance.
  arXiv  Detail & Related papers  (2021-12-30T00:27:30Z)
• Evolutionary Optimization of High-Coverage Budgeted Classifiers [1.7767466724342065]
  Budgeted multi-feature classifiers (MSC) process inputs through a sequence of partial feature acquisition and evaluation steps. This paper proposes a problem-specific MSC that incorporates a terminal reject option for indecisive predictions. The algorithm's design emphasizes efficiency while respecting a notion of aggregated performance via a uniqueization.
  arXiv  Detail & Related papers  (2021-10-25T16:03:07Z)
• On Efficient and Robust Metrics for RANSAC Hypotheses and 3D Rigid Registration [51.64236850960365]
  This paper focuses on developing efficient and robust evaluation metrics for RANSAC hypotheses to achieve accurate 3D rigid registration. We analyze the contributions of inliers and outliers, and then proposing several efficient and robust metrics with different designing motivations for RANSAC hypotheses.
  arXiv  Detail & Related papers  (2020-11-10T02:22:45Z)

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.