Task Complexity Matters: An Empirical Study of Reasoning in LLMs for Sentiment Analysis

TL;DR

This study empirically evaluates how reasoning capabilities in large language models affect sentiment analysis performance, revealing that reasoning benefits are highly task-dependent and often not justified for simpler tasks due to computational costs.

Contribution

It provides a comprehensive analysis of reasoning in LLMs across various tasks and architectures, challenging assumptions about universal reasoning benefits and highlighting task-specific effects.

Findings

Reasoning effectiveness varies significantly with task complexity.

Distilled reasoning often underperforms base models on simple tasks.

Few-shot prompting generally improves performance over zero-shot.

Abstract

Large language models (LLMs) with reasoning capabilities have fueled a compelling narrative that reasoning universally improves performance across language tasks. We test this claim through a comprehensive evaluation of 504 configurations across seven model families--including adaptive, conditional, and reinforcement learning-based reasoning architectures--on sentiment analysis datasets of varying granularity (binary, five-class, and 27-class emotion). Our findings reveal that reasoning effectiveness is strongly task-dependent, challenging prevailing assumptions: (1) Reasoning shows task-complexity dependence--binary classification degrades up to -19.9 F1 percentage points (pp), while 27-class emotion recognition gains up to +16.0pp; (2) Distilled reasoning variants underperform base models by 3-18 pp on simpler tasks, though few-shot prompting enables partial recovery; (3) Few-shot learning improves over zero-shot in most cases regardless of model type, with gains varying by architecture and task complexity; (4) Pareto frontier analysis shows base models dominate efficiency-performance trade-offs, with reasoning justified only for complex emotion recognition despite 2.1x-54x computational overhead. We complement these quantitative findings with qualitative error analysis revealing that reasoning degrades simpler tasks through systematic over-deliberation, offering mechanistic insight beyond the high-level overthinking hypothesis.