# How Prompts Move Language Model Behavior: Frames, Salience, and Construal as Semantic Control

Source: [How Prompts Move Language Model Behavior: Frames, Salience, and Construal as Semantic Control](<https://www.sota2.com/research/paper/6940e77f456146936284f702>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-05-06T05:00:11.062Z

Authors: Dongseok Kim, Hyoungsun Choi, Mohamed Jismy Aashik Rasool, Gisung Oh

Published: 2025-12-14T13:42:20.000Z

## Abstract

Prompt engineering is widely used to shape large language model behavior, yet it is often treated as a practical heuristic rather than as a form of natural-language control. This paper develops a cognitive-semantic account in which prompts function as semantic conditions on how a fixed model interprets inputs, foregrounds information, and structures tasks. We formalize this account through three notions -- frame activation, salience control, and construal selection -- and study them in natural language inference, claim verification, and multi-hop question answering. Across these settings, prompts produce measurable changes in label judgments, evidence use, and answer-support organization, showing that prompt effects differ not only in magnitude but also in semantic direction. The paper therefore reframes prompting as the analysis of how instructions move model behavior, rather than only whether they improve performance.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2512.12688>)

[PDF](<https://arxiv.org/pdf/2512.12688.pdf>)
