# Evaluating Multi-Dimensional Generalization of Large Language Models in Temporal Extraction Tasks

arXiv: https://arxiv.org/abs/2610.02549 · HTML: https://mlsanity.com/paper/2610.02549/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 33 of its 53 references that are in the map.
- First posted on arXiv 1 Oct 2026.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 30 of 33)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [Measuring and Narrowing the Compositionality Gap in Language Models](https://mlsanity.com/paper/2210.03350/) (2022)
- [Beyond Accuracy: Behavioral Testing of NLP models with CheckList](https://mlsanity.com/paper/2005.04118/) (2020)
- [Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment](https://mlsanity.com/paper/1907.11932/) (2019)
- [Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve](https://mlsanity.com/paper/2403.02310/) (2024)
- [TextBugger: Generating Adversarial Text Against Real-world Applications](https://mlsanity.com/paper/1812.05271/) (2018)
- [Black-box Generation of Adversarial Text Sequences to Evade Deep Learning Classifiers](https://mlsanity.com/paper/1801.04354/) (2018)
- [Measuring Compositional Generalization: A Comprehensive Method on Realistic Data](https://mlsanity.com/paper/1912.09713/) (2019)
- [COGS: A Compositional Generalization Challenge Based on Semantic Interpretation](https://mlsanity.com/paper/2010.05465/) (2020)
- [Neural Unsupervised Domain Adaptation in NLP---A Survey](https://mlsanity.com/paper/2006.00632/) (2020)
- [Randomized Positional Encodings Boost Length Generalization of Transformers](https://mlsanity.com/paper/2305.16843/) (2023)
- [An LLM can Fool Itself: A Prompt-Based Adversarial Attack](https://mlsanity.com/paper/2310.13345/) (2023)
- [Compositional generalization through meta sequence-to-sequence learning](https://mlsanity.com/paper/1906.05381/) (2019)
- [Task Contamination: Language Models May Not Be Few-Shot Anymore](https://mlsanity.com/paper/2312.16337/) (2023)
- [State-of-the-art generalisation research in NLP: A taxonomy and review](https://mlsanity.com/paper/2210.03050/) (2022)
- [Test of Time: A Benchmark for Evaluating LLMs on Temporal Reasoning](https://mlsanity.com/paper/2406.09170/) (2024)
- [A Multi-Axis Annotation Scheme for Event Temporal Relations](https://mlsanity.com/paper/1804.07828/) (2018)
- [Neural Module Networks for Reasoning over Text](https://mlsanity.com/paper/1912.04971/) (2019)
- [The paradox of the compositionality of natural language: a neural machine translation case study](https://mlsanity.com/paper/2108.05885/) (2021)
- [Are Large Language Models Temporally Grounded?](https://mlsanity.com/paper/2311.08398/) (2023)
- [Gradual Fine-Tuning for Low-Resource Domain Adaptation](https://mlsanity.com/paper/2103.02205/) (2021)
- [IDEA: Enhancing the Rule Learning Ability of Large Language Model Agent through Induction, Deduction, and Abduction](https://mlsanity.com/paper/2408.10455/) (2024)
- [Beyond 'Aha!': Toward Systematic Meta-Abilities Alignment in Large Reasoning Models](https://mlsanity.com/paper/2505.10554/) (2025)
- [AdvEntuRe: Adversarial Training for Textual Entailment with Knowledge-Guided Examples](https://mlsanity.com/paper/1805.04680/) (2018)
- [Learning to Reason Over Time: Timeline Self-Reflection for Improved Temporal Reasoning in Language Models](https://mlsanity.com/paper/2504.05258/) (2025)
- [ChroKnowledge: Unveiling Chronological Knowledge of Language Models in Multiple Domains](https://mlsanity.com/paper/2410.09870/) (2024)

## Abstract (arXiv)

Time and event expression extraction are fundamental temporal reasoning tasks, but the problem remains difficult due to annotation ambiguity, domain sensitivity, and unstable model behavior. Existing evaluations focus on in-domain performance, offering limited insight into reliability under distribution shifts. We evaluate multiple model configurations across families, architectures, and reasoning strategies over four dimensions of generalization, examining transfer from base performance, cross-dimensional correlations, and the effects of scale, architecture, and prompting. This provides a systematic study of how prompted LLMs generalize in time and event expression extraction tasks. We find that strong base-task performance generally predicts better generalization. However, this relationship weakens under substantial distribution shifts. Inductive prompting performs most consistently across domain shift, adversarial perturbations, compositionality, and length increase, while gains from scale, architecture, and deductive and abductive prompting strategies are uneven and dimension-specific. We conclude that LLM generalization in temporal extraction tasks cannot be predicted from any single dimension alone and cannot be reliably inferred from in-domain or single-dimension evaluations, highlighting the need for reasoning strategies that generalize across dimensions.