# Can LLMs Access their World Knowledge for Event Prediction?

arXiv: https://arxiv.org/abs/2610.19021 · HTML: https://mlsanity.com/paper/2610.19021/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 36 references that are in the map.
- First posted on arXiv 13 Oct 2026.

## Builds on (most cited first, 21 of 21)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://mlsanity.com/paper/2311.12022/) (2023)
- [Calibrate Before Use: Improving Few-Shot Performance of Language Models](https://mlsanity.com/paper/2102.09690/) (2021)
- [ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks](https://mlsanity.com/paper/2303.15056/) (2023)
- [Chronos: Learning the Language of Time Series](https://mlsanity.com/paper/2403.07815/) (2024)
- [One Fits All:Power General Time Series Analysis by Pretrained LM](https://mlsanity.com/paper/2302.11939/) (2023)
- [Large Language Models Are Zero-Shot Time Series Forecasters](https://mlsanity.com/paper/2310.07820/) (2023)
- [Humanity's Last Exam](https://mlsanity.com/paper/2501.14249/) (2025)
- [Transformer Hawkes Process](https://mlsanity.com/paper/2002.09291/) (2020)
- [Tokenization counts: the impact of tokenization on arithmetic in frontier LLMs](https://mlsanity.com/paper/2402.14903/) (2024)
- [Symbol tuning improves in-context learning in language models](https://mlsanity.com/paper/2305.08298/) (2023)
- [LLM Processes: Numerical Predictive Distributions Conditioned on Natural Language](https://mlsanity.com/paper/2405.12856/) (2024)
- [Language Models Can Improve Event Prediction by Few-Shot Abductive Reasoning](https://mlsanity.com/paper/2305.16646/) (2023)
- [MIRAI: Evaluating LLM Agents for Event Forecasting](https://mlsanity.com/paper/2407.01231/) (2024)
- [Beyond Performance: Quantifying and Mitigating Label Bias in LLMs](https://mlsanity.com/paper/2405.02743/) (2024)
- [Reducing Distraction in Long-Context Language Models by Focused Learning](https://mlsanity.com/paper/2411.05928/) (2024)
- [A Comprehensive Evaluation of Large Language Models on Temporal Event Forecasting](https://mlsanity.com/paper/2407.11638/) (2024)
- [Byte-token Enhanced Language Models for Temporal Point Processes Analysis](https://mlsanity.com/paper/2502.07139/) (2025)
- [LAST SToP For Modeling Asynchronous Time Series](https://mlsanity.com/paper/2502.01922/) (2025)
- [Is More Context Always Better? Examining LLM Reasoning Capability for Time Interval Prediction](https://mlsanity.com/paper/2601.10132/) (2026)

## Abstract (arXiv)

Recent work has questioned whether large language models (LLMs) can be useful for temporal event prediction. Despite vast pretrained world knowledge, LLMs often underperform simpler specialized models. We ask whether this knowledge is truly inaccessible, or whether current methods fail to present event prediction in a form LLMs can use. We argue for the latter and show that LLMs become effective event forecasters when the interface is designed around two choices. The first grounds each event in a natural-language description, and the second separates event semantics from the prediction space to prevent semantic bias from label associations. To test this, we introduce DescribeEvent, a benchmark of ~150K events across seven datasets and six domains with event-level descriptions. We find that capable LLMs substantially benefit from descriptions and symbolic labels, outperforming description-free variants and non-LLM baselines, while weaker models gain little. These results suggest that accessing LLM world knowledge for event prediction is an interface problem, and that event descriptions offer a practical way to elicit the knowledge LLMs already encode.