# Do Language Models Consistently Encode the Current Year?

arXiv: https://arxiv.org/abs/2608.15507 · HTML: https://mlsanity.com/paper/2608.15507/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning.
- Builds on 25 of its 34 references that are in the map.
- First posted on arXiv 16 Aug 2026.

## Placed in

- LLM reasoning / [Knowledge- and tool-augmented reasoning](https://mlsanity.com/lr/knowledge-and-tool-augmented-reasoning/)

## Builds on (most cited first, 25 of 25)

- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Efficient Streaming Language Models with Attention Sinks](https://mlsanity.com/paper/2309.17453/) (2023)
- [Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling](https://mlsanity.com/paper/2304.01373/) (2023)
- [Mass-Editing Memory in a Transformer](https://mlsanity.com/paper/2210.07229/) (2022)
- [OLMo: Accelerating the Science of Language Models](https://mlsanity.com/paper/2402.00838/) (2024)
- [Dissecting Recall of Factual Associations in Auto-Regressive Language Models](https://mlsanity.com/paper/2304.14767/) (2023)
- [Causal Abstractions of Neural Networks](https://mlsanity.com/paper/2106.02997/) (2021)
- [Time-Aware Language Models as Temporal Knowledge Bases](https://mlsanity.com/paper/2106.15110/) (2021)
- [Finding Alignments Between Interpretable Causal Variables and Distributed Neural Representations](https://mlsanity.com/paper/2303.02536/) (2023)
- [Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability](https://mlsanity.com/paper/2301.04709/) (2023)
- [RedPajama: an Open Dataset for Training Large Language Models](https://mlsanity.com/paper/2411.12372/) (2024)
- [TemporalWiki: A Lifelong Benchmark for Training and Evaluating Ever-Evolving Language Models](https://mlsanity.com/paper/2204.14211/) (2022)
- [Language Models Implement Simple Word2Vec-style Vector Arithmetic](https://mlsanity.com/paper/2305.16130/) (2023)
- [Test of Time: A Benchmark for Evaluating LLMs on Temporal Reasoning](https://mlsanity.com/paper/2406.09170/) (2024)
- [RAVEL: Evaluating Interpretability Methods on Disentangling Language Model Representations](https://mlsanity.com/paper/2402.17700/) (2024)
- [Weird Generalization and Inductive Backdoors: New Ways to Corrupt LLMs](https://mlsanity.com/paper/2512.09742/) (2025)
- [Dated Data: Tracing Knowledge Cutoffs in Large Language Models](https://mlsanity.com/paper/2403.12958/) (2024)
- [Time is Encoded in the Weights of Finetuned Language Models](https://mlsanity.com/paper/2312.13401/) (2023)
- [Does Time Have Its Place? Temporal Heads: Where Language Models Recall Time-specific Information](https://mlsanity.com/paper/2502.14258/) (2025)
- [Can Language Models Represent the Past without Anachronism?](https://mlsanity.com/paper/2505.00030/) (2025)
- [A Study into Investigating Temporal Robustness of LLMs](https://mlsanity.com/paper/2503.17073/) (2025)
- [Can Prompts Rewind Time for LLMs? Evaluating the Effectiveness of Prompted Knowledge Cutoffs](https://mlsanity.com/paper/2510.02340/) (2025)
- [ChroKnowledge: Unveiling Chronological Knowledge of Language Models in Multiple Domains](https://mlsanity.com/paper/2410.09870/) (2024)
- [Simulated Ignorance Fails: A Systematic Study of LLM Behaviors on Forecasting Problems Before Model Knowledge Cutoff](https://mlsanity.com/paper/2601.13717/) (2026)
- [Time Travel Engine: A Shared Latent Chronological Manifold Enables Historical Navigation in Large Language Models](https://mlsanity.com/paper/2601.06437/) (2026)

## Built on by (most cited first, 1 of 1)

- [L"ushi-1840: Building and Probing a Knowledge Cutoff for a Classical Chinese Language Model](https://mlsanity.com/paper/2610.16201/) (2026)

## Abstract (arXiv)

A consistent concept of the current time is important for temporal reasoning, yet how language models represent the current time is not well understood. We contribute two tasks that probe the current year in conceptually distinct ways: an associative task, which infers the current year from verb tense, and a declarative task, which directly queries for the current year. Both tasks estimate current years within one year of the post-training data cutoff of instruction-tuned language models. For base models, predictions on the associative task serve as a strong proxy for the pre-training data cutoff, with an average error of only 10 months across 13 models. However, their internal mechanisms diverge: the associative task uses mechanisms similar to factual recall, while the declarative task lacks consistent causal pathways. This divergence poses a challenge for updating the current year in language models. None of prompting, SFT, or weight editing succeed in shifting the associative and declarative years simultaneously. Prompting updates the declarative year (94.6% success across 351 target years) but leaves the associative year nearly unchanged (1.7% success). Year-shifted SFT also fails to shift the associative year, matching the target year in only one of eight models. Weight editing, while effective for both tasks individually, does not generalize across both. Overall, our results show that the current year is not consistently encoded in language models: The associative notion, deeply ingrained in linguistic structures learned in pre-training, uses different causal mechanisms and resists the same modifications that easily shift the declarative notion learned in post-training.