DR-CoT:具有参数效率模型的元推理的动态递归思维链
Aarush Sinha1, OmKumar Chandra Umakanthan2, Sudhakaran Gajendran3
1School of Computer Science and Engineering (SCOPE), Vellore Institute of Technology-Chennai, Kelambakkam - Vandalur Road, Chennai, Tamil Nadu, 600127, India.
Scientific reports
|October 6, 2025
概括
动态递归思维链 (DR-CoT) 通过降低计算成本和提高准确性来改善大型语言模型推理. 这种新的框架为参数效率模型的复杂任务提供了显著的收益.
科学领域:
- 人工智能的人工智能
- 自然语言处理自然语言处理.
- 机器学习 机器学习
背景情况:
- 思想链 (CoT) 提示增强了大语言模型 (LLM) 推理,但面临着高计算成本和上下文稀释的挑战.
- 这些局限性阻碍了LLM在资源有限和实时应用中的有效性.
研究的目的:
- 引入动态递归思维链 (DR-CoT),这是一个新的框架,旨在克服传统 CoT 提示的局限性.
- 通过协同方法提高参数效率模型中的推理准确性和效率.
主要方法:
- DR-CoT集成了递归推理,动态上下文截断和投票机制,以在固定的代币预算内管理上下文.
- 多个独立的推理链被聚合在一起,以提高推理和准确性.
主要成果:
- 在GPQA钻石 (1.5%-4.4%) 和AIME2024 (3-4个百分点) 等具有挑战性的基准指标上,DR-CoT取得了显著的准确性增长.
- 提高了零射击分类性能,使较小的模型能够超过像GPT-4这样的大型模型.
- 在HumanEval.上的代码生成任务中表现优于已建立的边境LLM.
结论:
- 在不同领域,DR-CoT有效地弥合了参数效率模型和最先进的LLM之间的性能差距.
- 该框架为复杂的推理任务提供了计算效率高,准确的解决方案.
更多相关视频
相关概念视频
Deductive Reasoning
64.2K
Deductive reasoning, or deduction, is the type of logic used in hypothesis-based science. In deductive reasoning, the pattern of thinking moves in the opposite direction as compared to inductive reasoning, which means that it uses a general principle or law to predict specific results. From those general principles, a scientist can deduce and predict the specific results that would be valid as long as the general principles are valid.
For example, a researcher can deduce specific predictions...
For example, a researcher can deduce specific predictions...
64.2K
Revisionist Views of Adolescent and Adult Cognition
283
A revisionist approach to Jean Piaget's theory of cognitive development has brought new insights that challenge and reinterpret his established ideas. Piaget proposed that the formal operational stage, emerging in adolescence, represents the culmination of cognitive maturity. During this stage, individuals are said to develop abstract thinking, engage in systematic problem-solving, and show a form of egocentrism, believing others are as preoccupied with their behavior as they are...
283
Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving
288
Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
288
Reasoning
396
Reasoning is the action of thinking about something in a logical, sensible way. It is integral to problem-solving, decision-making, and critical thinking. Reasoning can be inductive or deductive. Reasoning involves transforming information into conclusions, which is essential for problem-solving, decision-making, and critical thinking.
Inductive reasoning involves deriving generalizations from specific observations. This type of reasoning helps form beliefs about the world. For example,...
Inductive reasoning involves deriving generalizations from specific observations. This type of reasoning helps form beliefs about the world. For example,...
396
Reason and Intuition
7.4K
The human brain processes information for decision-making using one of two routes: an intuitive system and a rational system (Epstein, 1994; popularized by Kahneman, 2011 as System 1 and System 2, respectively). The intuitive system is quick, impulsive, and operates with minimal effort, relying on emotions or habits to provide cues for what to do next, while the rational system is logical, analytical, deliberate, and methodical. Research in neuropsychology suggests that the...
7.4K
Inductive Reasoning
65.0K
Inductive reasoning is a form of logical thinking that uses related observations to arrive at a general conclusion. It is uncertain and operates in degrees to which the conclusions are credible. As such, inductive arguments can be weak or strong, rather than valid or invalid, and conclusions can be used to formulate testable, falsifiable hypotheses.
Inductive reasoning is common in descriptive science. A life scientist makes observations and records them. This data can be qualitative or...
Inductive reasoning is common in descriptive science. A life scientist makes observations and records them. This data can be qualitative or...
65.0K


