LLMs display prompt-sensitive risk behavior and a linearly decodable realization-status signal in Gemma's residual stream, yet activation steering along this direction fails to shift downstream risk choices.
The butterfly effect of altering prompts: How small changes and jailbreaks affect large language model performance.arXiv preprint arXiv:2401.03729
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
abstract
Large Language Models (LLMs) are regularly being used to label data across many domains and for myriad tasks. By simply asking the LLM for an answer, or ``prompting,'' practitioners are able to use LLMs to quickly get a response for an arbitrary task. This prompting is done through a series of decisions by the practitioner, from simple wording of the prompt, to requesting the output in a certain data format, to jailbreaking in the case of prompts that address more sensitive topics. In this work, we ask: do variations in the way a prompt is constructed change the ultimate decision of the LLM? We answer this using a series of prompt variations across a variety of text classification tasks. We find that even the smallest of perturbations, such as adding a space at the end of a prompt, can cause the LLM to change its answer. Further, we find that requesting responses in XML and commonly used jailbreaks can have cataclysmic effects on the data labeled by LLMs.
citation-role summary
background 1
citation-polarity summary
years
2026 6roles
background 1polarities
background 1representative citing papers
Clinical VLMs over-rely on text modality, irrelevant clinical history, and prompt wording when making chest x-ray decisions on MIMIC-CXR data.
Prototype-Based Sparse Steering decomposes query activations with SAEs and optimizes sparse features via gradients to steer LLM outputs toward specific behaviors.
A survey proposing a three-pillar framework to evaluate LLMs as tools for measuring latent psychological constructs and reviewing applications in personality and mental health.
Advanced language representations shape LLMs' schemas to improve knowledge activation and problem-solving.
citing papers explorer
-
Representation Without Control: Testing the Realization Effect in Language Models
LLMs display prompt-sensitive risk behavior and a linearly decodable realization-status signal in Gemma's residual stream, yet activation steering along this direction fails to shift downstream risk choices.
-
Medical Context Distorts Decisions in Clinical Vision Language Models
Clinical VLMs over-rely on text modality, irrelevant clinical history, and prompt wording when making chest x-ray decisions on MIMIC-CXR data.
-
Steered Generation via Gradient-Based Optimization on Sparse Query Features
Prototype-Based Sparse Steering decomposes query activations with SAEs and optimizes sparse features via gradients to steer LLM outputs toward specific behaviors.
-
A Survey of Large Language Models for Perception and Measurement of Human Psychology
A survey proposing a three-pillar framework to evaluate LLMs as tools for measuring latent psychological constructs and reviewing applications in personality and mental health.
-
Shaping Schema via Language Representation as the Next Frontier for LLM Intelligence Expanding
Advanced language representations shape LLMs' schemas to improve knowledge activation and problem-solving.
- Efficient Safety Alignment of Language Models via Latent Personality Traits