When Thinking Fails: The Pitfalls of Reasoning for Instruction-Following in LLMs

2025-05-16

AI Summary

This work identifies a counterintuitive degradation in instruction-following accuracy when large language models (LLMs) are explicitly prompted to perform chain-of-thought (CoT) reasoning. Through systematic evaluation of 15 state-of-the-art models on IFEval and ComplexBench, we find that CoT often diverges from critical instruction constraints, leading to failure. To quantify this phenomenon, we propose *constraint attention*—a novel metric measuring the attenuation of constraint focus during reasoning. We further introduce four deployable mitigation strategies; among them, classifier-guided selective reasoning achieves the best performance: it triggers CoT only when necessary, yielding an average +18.7% accuracy gain on IFEval. Our results demonstrate that robust instruction following hinges less on universal, end-to-end CoT and more on *constraint-aware selective reasoning*—a paradigm prioritizing constraint fidelity over exhaustive inference.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning
• Natural Language Processing: Safety and Robustness

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Reasoning-enhanced large language models (RLLMs), whether explicitly trained for reasoning or prompted via chain-of-thought (CoT), have achieved state-of-the-art performance on many complex reasoning tasks. However, we uncover a surprising and previously overlooked phenomenon: explicit CoT reasoning can significantly degrade instruction-following accuracy. Evaluating 15 models on two benchmarks: IFEval (with simple, rule-verifiable constraints) and ComplexBench (with complex, compositional constraints), we consistently observe performance drops when CoT prompting is applied. Through large-scale case studies and an attention-based analysis, we identify common patterns where reasoning either helps (e.g., with formatting or lexical precision) or hurts (e.g., by neglecting simple constraints or introducing unnecessary content). We propose a metric, constraint attention, to quantify model focus during generation and show that CoT reasoning often diverts attention away from instruction-relevant tokens. To mitigate these effects, we introduce and evaluate four strategies: in-context learning, self-reflection, self-selective reasoning, and classifier-selective reasoning. Our results demonstrate that selective reasoning strategies, particularly classifier-selective reasoning, can substantially recover lost performance. To our knowledge, this is the first work to systematically expose reasoning-induced failures in instruction-following and offer practical mitigation strategies.

Problem

• Explicit CoT reasoning reduces instruction-following accuracy in LLMs
• Reasoning diverts attention from instruction-relevant tokens in models
• Selective reasoning strategies mitigate performance drops in LLMs

Innovation

• Introduces constraint attention metric for model focus
• Proposes selective reasoning strategies for mitigation
• Identifies reasoning-induced failures in instruction-following