Conditions for Length Generalization in Learning Reasoning Skills
Reasoning is a fundamental capability of AI agents. Recently, large language models (LLMs) have shown remarkable abilities to perform reasoning tasks. However, numerous evaluations of the reasoning capabilities of LLMs have also showed some limitations. An outstanding limitation is length generalization, meaning that when trained on reasoning problems of smaller lengths or sizes, the resulting models struggle with problems of larger sizes or lengths. This potentially indicates some theoretical limitations of generalization in learning reasoning skills. These evaluations and their observations motivated us to perform a theoretical study of the length generalization problem. This work focuses on reasoning tasks that can be formulated as Markov dynamic processes (MDPs) and/or directed acyclic graphs (DAGs). It identifies and proves conditions that decide whether the length generalization problem can be solved or not for a reasoning task in a particular representation. Experiments are also conducted to verify the theoretical results.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Laying the Foundation First? Investigating the Generalization from Atomic Skills to Complex Reasoning Tasks
Current language models have demonstrated their capability to develop basic reasoning, but struggle in more complicated reasoning tasks that require a combination of atomic skills, such as math word problem requiring ski…
MathSkill GeneralizationA Theory for Length Generalization in Learning to Reason
Length generalization (LG) is a challenging problem in learning to reason. It refers to the phenomenon that when trained on reasoning problems of smaller lengths or sizes, the resulting model struggles with problems of l…
Skills-in-Context Prompting: Unlocking Compositionality in Large Language Models
We investigate how to elicit compositional generalization capabilities in large language models (LLMs). Compositional generalization empowers LLMs to solve complex problems by combining foundational skills, a critical re…
In-Context LearningMathMathematical ReasoningMath Word Problem Solving+1Signal or Noise? A Benchmark Study of Agent Skills in Web Development
Agent Skills are reusable procedural modules that are increasingly injected into coding-agent sessions to encode framework conventions, anti-patterns, and reusable tools. However, because each injected Skill expands the …
ALERT: Adapting Language Models to Reasoning Tasks
Current large language models can perform reasonably well on complex tasks that require step-by-step reasoning with few-shot learning. Are these models applying reasoning skills they have learnt during pre-training and r…
Few-Shot LearningLanguage ModelingLanguage ModellingNatural Language Inference