Small Language Model Helps Resolve Semantic Ambiguity of LLM Prompt

2026-04-25

AI Summary

This work addresses the susceptibility of large language models to erroneous reasoning caused by semantically ambiguous or syntactically irregular user prompts. To mitigate this issue, the authors propose a lightweight prompt optimization mechanism that explicitly identifies semantic risks prior to inference. The approach leverages a small language model to perform multi-perspective consistency verification and logical restructuring of the input prompt, thereby achieving prompt purification. Notably, this is the first method to integrate explicit semantic disambiguation into the prompt optimization pipeline, deliberately avoiding interference with the internal reasoning processes of large models. Experimental results demonstrate that the proposed technique improves reasoning performance by an average of 2.5 points across multiple benchmarks, with only a marginal computational overhead of $0.02 per query, offering both efficacy and cost efficiency.

Technology Category

• Natural Language Processing: Prompt Engineering / Prompting
• Reasoning under Uncertainty: Stochastic Optimization
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Large language models for search

Abstract

Large language models (LLMs) are increasingly utilized in various complex reasoning tasks due to their excellent instruction following capability. However, the model's performance is highly dependent on the open-ended characteristics of the users' input prompt. Natural prompts often do not follow proper syntactic rules, which creates ambiguous queries that yield multiple interpretations. Such ambiguous prompts confuse the model in choosing the correct reasoning paths to answer questions. Prior works address this challenge by applying query editing during the LLM inference process without explicitly solving the root cause of the ambiguity. To address this limitation, we propose a pre-inference prompt optimization mechanism via explicit prompt disambiguation. Particularly, we identify semantic risks in the prompt, check their multi-perspective consistency, and resolve any semantic conflicts that arise. Finally, we organize the resolved ambiguities in a logically structured manner as a clean input to the LLM. By explicitly resolving semantic ambiguity, our method can produce a more focused attention distribution to the semantically essential tokens. We also leverage small language models (SLMs) as the main executor of prompt disambiguation to benefit from their efficient computation. Through comprehensive experiments on multiple benchmarks, we demonstrate that our method improves reasoning performance by 2.5 points at a cost of only \$0.02. Our study promotes explicit prompt disambiguation as an effective prompt optimization method without disturbing the internal mechanism of LLM inference.

Problem

• semantic ambiguity
• prompt disambiguation
• large language models
• natural language prompts
• reasoning tasks

Innovation

• prompt disambiguation
• small language models
• semantic ambiguity resolution
• pre-inference optimization
• reasoning performance