When Reasoning Hurts Legal Drafting: The Verbalization Bottleneck in Patent Claim Generation
2026-07-11 • Computation and Language
Computation and Language
AI summaryⓘ
The authors studied how a special way of asking AI models to explain their thinking, called Chain-of-Thought (CoT) prompting, affects creating patent claims, which is a tricky legal writing task. They found that when the AI keeps its reasoning inside (implicit CoT) instead of saying it out loud (explicit CoT), it does a better job at writing patent claims. Explicitly explaining the reasoning can actually make the output worse by missing details, breaking learned patterns, and causing errors to build up. Their work helps understand how to better use AI for complex legal writing.
Patent claim draftingChain-of-Thought promptingLarge language modelsImplicit CoTExplicit CoTLegal writingReasoning in AIInformation bottleneckError propagation
Authors
Lekang Jiang, Wenjun Sun, Stephan Goetz
Abstract
Patent claim drafting is a challenging legal drafting task that requires technical expertise, precise linguistic control, strict adherence to formal conventions, and the preservation of complex logical relationships among claim elements. While Chain-of-Thought (CoT) prompting has been widely used to improve the reasoning capabilities of large language models (LLMs), recent evidence suggests that its benefits may be limited, or even negative, in highly structured or pattern-sensitive tasks. Therefore, this paper investigates whether CoT prompting benefits patent claim generation. We propose a task-specific CoT method for patent claim generation and evaluate its effectiveness through both automatic metrics and human expert assessment. Our results show that reasoning-enhanced prompting can improve claim quality. Moreover, we demonstrate a counter-intuitive but important empirical finding: implicit CoT, where reasoning is kept internal rather than explicitly verbalized, consistently outperforms explicit CoT. Through systematic analysis, we show that explicit CoT can introduce an unnecessary information bottleneck for claim generation. Verbalized reasoning may compromise the quality of final outputs through three specific mechanisms: abstraction of critical details, disruption of internalized generation patterns, and cascading error propagation. Our findings provide new insights into legal tasks and CoT applications.