PRISM Edit: One Vector for All Temporal Answers

• URL: http://arxiv.org/abs/2607.11327v2
• Date: Tue, 14 Jul 2026 02:41:11 GMT
• Title: PRISM Edit: One Vector for All Temporal Answers
• Abstract summary: PRISM Edit is a temporal editing tool for large language models.<n>It 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.
• Score: 8.700309837890057
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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 papers

• Beyond Tokenization: Direct Timestep Embedding and Contrastive Alignment for Time-Series Question Answering [13.074536659496362]
  Recent advances in large language models (LLMs) have given rise to time-series question answering (TSQA)<n>TSQA formulates time-series analysis as natural-language question answering.<n>To address this challenge, we propose CADE, a novel framework for TSQA built upon two key components: direct timestep embedding and semantic alignment.
  arXiv  Detail & Related papers  (2026-06-17T12:07:23Z)
• Not in Sync: Unveiling Temporal Bias in Audio Chat Models [59.146710538620816]
  Large Audio Language Models (LALMs) are increasingly applied to audio understanding and multimodal reasoning.<n>We present the first systematic study of temporal bias in LALMs, revealing a key limitation in their timestamp prediction.
  arXiv  Detail & Related papers  (2025-10-14T06:29:40Z)
• MEMOIR: Lifelong Model Editing with Minimal Overwrite and Informed Retention for LLMs [76.28901550926021]
  Existing methods for lifelong model editing compromise generalization, interfere with past edits, or fail to scale to long editing sequences.<n>We propose MEMOIR, a novel scalable framework that injects knowledge through a residual memory, while preserving the core capabilities of the pre-trained model.<n>MeMOIR achieves state-of-the-art performance across reliability, generalization, and locality metrics, scaling to thousands of sequential edits with minimal forgetting.
  arXiv  Detail & Related papers  (2025-06-09T16:16:42Z)
• Rethinking Irregular Time Series Forecasting: A Simple yet Effective Baseline [12.66709671516384]
  We introduce APN, a general and efficient forecasting framework.<n>At the core of APN is a novel Time-Aware Patch Aggregation (ATAPA) module.<n>It computes patch representations via a time-aware weighted aggregation of all raw observations.<n>This approach provides two key advantages: it preserves data fidelity by avoiding the introduction of artificial data points and ensures complete information coverage by design.
  arXiv  Detail & Related papers  (2025-05-16T13:42:00Z)
• TimeRefine: Temporal Grounding with Time Refining Video LLM [75.99665302872901]
  Video temporal grounding aims to localize relevant temporal boundaries in a video given a textual prompt.<n>We reformulate the temporal grounding task as a temporal refining task.<n>We incorporate an auxiliary prediction head that penalizes the model more if a predicted segment deviates further from the ground truth.
  arXiv  Detail & Related papers  (2024-12-12T18:59:11Z)
• ELDER: Enhancing Lifelong Model Editing with Mixture-of-LoRA [55.697627106315004]
  Large language models (LLMs) require model editing to efficiently update specific knowledge within them and avoid factual errors.<n>Previous approaches manage sequential edits by freezing original parameters and discretely allocating new parameters for each knowledge update.<n>We propose ELDER, a novel approach to create a continuous association between data and adapters.
  arXiv  Detail & Related papers  (2024-08-19T02:27:00Z)
• Towards Robust Temporal Reasoning of Large Language Models via a Multi-Hop QA Dataset and Pseudo-Instruction Tuning [73.51314109184197]
  It is crucial for large language models (LLMs) to understand the concept of temporal knowledge. We propose a complex temporal question-answering dataset Complex-TR that focuses on multi-answer and multi-hop temporal reasoning.
  arXiv  Detail & Related papers  (2023-11-16T11:49:29Z)
• Once Upon a $\ extit{Time}$ in $\ extit{Graph}$: Relative-Time Pretraining for Complex Temporal Reasoning [96.03608822291136]
  We make use of the underlying nature of time, and suggest creating a graph structure based on the relative placements of events along the time axis. Inspired by the graph view, we propose RemeMo, which explicitly connects all temporally-scoped facts by modeling the time relations between any two sentences. Experimental results show that RemeMo outperforms the baseline T5 on multiple temporal question answering datasets.
  arXiv  Detail & Related papers  (2023-10-23T08:49:00Z)
• Towards Consistent Video Editing with Text-to-Image Diffusion Models [10.340371518799444]
  Existing works have advanced Text-to-Image (TTI) diffusion models for video editing in a one-shot learning manner. These methods might produce results of unsatisfied consistency with text prompt as well as temporal sequence. We propose a novel EI$2$ model towards textbfEnhancing vtextbfIdeo textbfEditing constextbfIstency of TTI-based frameworks.
  arXiv  Detail & Related papers  (2023-05-27T10:03:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.