Lifted Representation Hypothesis in Language Models
However, it remains unclear how these structures are stored, selected, and revised. To study this process, we propose thelifted representation hypothesis: LLMs update memory through shared latent structures rather than isolated instance-level facts. This view frames lifting as an efficient use of symmetry across instances, and shattering as the refinement of coarse lifted structures into more specific subtypes.
- ▪However, it remains unclear how these structures are stored, selected, and revised.
- ▪To study this process, we propose thelifted representation hypothesis: LLMs update memory through shared latent structures rather than isolated instance-level facts.
- ▪This view frames lifting as an efficient use of symmetry across instances, and shattering as the refinement of coarse lifted structures into more specific subtypes.
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.org |
| Canonical URL | https://arxiv.org/abs/2607.19360 |
| Publication time | Thu, 23 Jul 2026 00:00:00 -0400 |
| Retrieval time | 2026-07-23T04:57:27.352Z |
| Last seen | 2026-07-23T04:57:27.352Z |
| 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 | GhAl0TPi_GSl |
| 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:2607.19360 (cs) [Submitted on 2 Jun 2026] Title:Lifted Representation Hypothesis in Language Models Authors:Bumjin Park, Jaesik Choi View a PDF of the paper titled Lifted Representation Hypothesis in Language Models, by Bumjin Park and 1 other authors View PDF HTML (experimental) Abstract:Large language models (LLMs) often answer queries by mapping individual observations to more general rule-like structures. However, it remains unclear how these structures are stored, selected, and revised. To study this process, we propose thelifted representation hypothesis: LLMs update memory through shared latent structures rather than isolated instance-level facts.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at arXiv.org.
Discussion
0 commentsMore from arXiv.org
