paper-with-me

홈 › Papers

Self-Consistency Is Losing Its Edge: Diminishing Returns and Rising Costs in Modern LLMs

2025-11-02 · Chiyan Loo arxiv

Self-consistency -- sampling multiple reasoning paths and selecting the most frequent answer -- was designed for an era when language models made frequent, unpredictable errors. This study argues that the technique has become increasingly wasteful as models grow stronger, and may degrade performance on problems that modern models already solve reliably. Using Gemini 2.5 models on HotpotQA and MATH-500, we show that accuracy gains from increasing the number of sampled reasoning paths are minimal -- 0.4% on HotpotQA across 20 samples, and 1.6% on MATH-500 -- while token costs scale nearly linearly with sample count. Critically, performance plateaued early and in some configurations declined at high sample counts, suggesting that additional paths introduce noise rather than signal when models already solve problems reliably. As inference costs rise with model scale, indiscriminate self-consistency is difficult to justify. We recommend reserving multi-path sampling for problems that demonstrably exceed a model's single-pass reliability.

📄 PDF Abstract BibTeX arXiv:2511.00751

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Cooperative Evolutionary Pressure and Diminishing Returns Might Explain the Fermi Paradox: On What Super-AIs Are Like

2024-04-01 · Daniel Vallstrom

With an evolutionary approach, the basis of morality can be explained as adaptations to problems of cooperation. With 'evolution' taken in a broad sense, AIs that satisfy the conditions for evolution to apply will be sub…

Fairness

Diminishing Returns Shape Constraints for Interpretability and Regularization

2018-12-01 · NeurIPS 2018 12 · Maya Gupta, Dara Bahri, Andrew Cotter, Kevin Canini

We investigate machine learning models that can provide diminishing returns and accelerating returns guarantees to capture prior knowledge or policies about how outputs should depend on inputs. We show that one can buil…

BIG-bench Machine Learning

The Illusion of Diminishing Returns: Measuring Long Horizon Execution in LLMs

2025-09-11 · Akshit Sinha, Arvindh Arun, Shashwat Goel, Steffen Staab 외 arxiv

Does continued scaling of large language models (LLMs) yield diminishing returns? In this work, we show that short-task benchmarks may give an illusion of slowing progress, as even marginal gains in single-step accuracy …

On the Diminishing Returns of Width for Continual Learning

2024-03-11 · Etash Guha, Vihan Lakshman

While deep neural networks have demonstrated groundbreaking performance in various settings, these models often suffer from \emph{catastrophic forgetting} when trained on new tasks in sequence. Several works have empiric…

Continual LearningLearning Theory

MedCoG: Maximizing LLM Inference Density in Medical Reasoning via Meta-Cognitive Regulation

2026-02-08 · Yu Zhao, Hao Guan, Yongcheng Jing, Ying Zhang 외 arxiv

Large Language Models (LLMs) have shown strong potential in complex medical reasoning yet face diminishing gains under inference scaling laws. While existing studies augment LLMs with various knowledge types, it remains …