PRISM Edit: One Vector for All Temporal Answers

arXiv:2607.11327v2 Announce Type: replace-cross Abstract: Model editing keeps large language models (LLMs) up to date without retraining, but temporal facts expose a limitation of the prevailing locate-and-edit paradigm: an update is not always a replacement. When a fact changes, the new answer should become current while the old answer may remain correct in historical time contexts. Building on this insight, we use causal tracing to show that LLMs already support this distinction via a two-stage internal computation: early MLP layers retrieve a time-agnostic subject representation, and later layers modulate it with temporal context to yield the time-correct answer. Motivated by this finding, we introduce PRISM Edit, which optimizes a single polysemous representation across temporal contexts and leverages the model's inherent modulation pathway to route it to temporally correct predictions, without any architectural modification. We evaluate on TimeConflict, a new temporal editing benchmark we introduce, and on temporally augmented CounterFact. PRISM Edit improves over the best baseline by +23.3 Temporal Consistency (TC) and +33.7 Current Relative-time Score (CRS) on average while being more than 2x faster. Code and data are publicly available at https://github.com/AnonymousStudy972/PRISM-Edit.

Related

• Constraining Sequential Model Editing with Editing Anchor Compression
• Can Fine-Tuning Erase Your Edits? On the Fragile Coexistence of Knowledge Editing and Adaptation
• Golden Layers and Where to Find Them: Improved Knowledge Editing for Large Language Models Via Layer Gradient Analysis
• Reverse-Engineering Model Editing on Language Models

Source: arXiv cs.AI | 2026-07-15