← Volver a los artículos

Deciphering the Factors Influencing the Efficacy of Chain-of-Thought: Probability, Memorization, and Noisy Reasoning

★ ★ ★ ★ ☆

Resumen del artículo

Título de Paperzilla
LLMs Think in Probabilities, Memories, and Noise (But Also Kinda Reason)

Large Language Models (LLMs) using Chain-of-Thought (CoT) prompting exhibit a blend of noisy reasoning, probability matching based on output likelihood, and memorization. LLM performance isn't pure symbolic reasoning, but it improves substantially with CoT, suggesting a more nuanced process than simple memorization.

Explícamelo como si tuviera cinco años

Scientists found that when computers think step-by-step, they get much better at solving problems. They do this by remembering facts, guessing common answers, and sometimes trying to figure things out even if their thinking is a bit messy.

Posibles conflictos de intereses

None identified

Limitaciones identificadas

Limited task scope
The study focuses solely on shift ciphers, which simplifies the problem compared to real-world reasoning tasks. While useful for isolating factors in a controlled way, its conclusions cannot be generalized to more complex scenarios.
Unfaithful explanations and reliance on self-conditioning
The models studied exhibit unfaithfulness between reasoning steps and final answers, revealing a reliance on memorization rather than pure reasoning. The success of CoT prompting seems tied to outputting helpful text for the model to condition on, suggesting an external rather than internal reasoning process.
Multiple examples in one demonstration
The prompt design contains multiple examples in a single demonstration (one-shot CoT), making it less clear how much of the effect of CoT can be attributed to a single demonstration.

Explicación de la calificación

This paper presents a strong, focused analysis of LLM reasoning using a clever task (shift ciphers). The methodology isolates key factors and provides quantitative evidence. While limited in scope to a single task, the findings about probabilistic, memorization-influenced noisy reasoning are valuable. No apparent conflicts of interest were found.

Conviene saber

Este es el análisis de Starter. Paperzilla Pro verifica cada cita, investiga los antecedentes de los autores y las fuentes de financiación, y utiliza razonamiento avanzado con IA para ofrecer información más exhaustiva.

Explorar Pro →

Jerarquía temática

Información del archivo

Título original: Deciphering the Factors Influencing the Efficacy of Chain-of-Thought: Probability, Memorization, and Noisy Reasoning
Subido: 8 jul 2025, 12:04:48
Privacidad: Público