Decomposing how prompting steers behavior
The paper titled 'Decomposing how prompting steers behavior' explores how prompting influences the internal representations of large language models and vision-language models. It introduces a geometric decomposition framework to analyze how different prompts reshape these representations and affect behavior. The findings suggest that prompts significantly alter representations toward the instructed task structure, with specific transformations being more effective in achieving behavioral alignment.
- ▪The study focuses on how prompting affects the internal representations of language and vision models.
- ▪A nested geometric decomposition framework is introduced to analyze the effects of prompting.
- ▪The research shows that prompts consistently reshape representations toward the instructed task structure.
arXiv cs.AI files mainly under ai research. We currently carry 1,128 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | arXiv cs.AI |
| Canonical URL | https://arxiv.org/abs/2606.03093 |
| Publication time | Wed, 03 Jun 2026 00:00:00 -0400 |
| Retrieval time | 2026-06-03T04:11:55.408Z |
| Last seen | 2026-06-03T04:11:55.408Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | GkDd7Gqo8f7W |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Computer Science > Artificial Intelligence arXiv:2606.03093 (cs) [Submitted on 2 Jun 2026] Title:Decomposing how prompting steers behavior Authors:Fan L. Cheng, Nikolaus Kriegeskorte View a PDF of the paper titled Decomposing how prompting steers behavior, by Fan L. Cheng and Nikolaus Kriegeskorte View PDF HTML (experimental) Abstract:Prompting steers large language models (LLMs) and vision-language models (VLMs) without weight updates, but it remains unclear how instruction changes reshape internal representations to produce behavior. We introduce a nested geometric decomposition framework that treats prompting as a transformation of the representational geometry of the content following the prompt.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at arXiv cs.AI.
Discussion
0 commentsMore from arXiv cs.AI
