# Event Interaction in Low-Rank Bottlenecks for Temporal Relation Extraction

arXiv: https://arxiv.org/abs/2609.06731 · HTML: https://mlsanity.com/paper/2609.06731/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 36 references that are in the map.
- First posted on arXiv 6 Sep 2026.

## Builds on (most cited first, 22 of 22)

- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Deep contextualized word representations](https://mlsanity.com/paper/1802.05365/) (2018)
- [BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models](https://mlsanity.com/paper/2106.10199/) (2021)
- [AdapterFusion: Non-Destructive Task Composition for Transfer Learning](https://mlsanity.com/paper/2005.00247/) (2020)
- [A Multi-Axis Annotation Scheme for Event Temporal Relations](https://mlsanity.com/paper/1804.07828/) (2018)
- [Joint Reasoning for Temporal and Causal Relations](https://mlsanity.com/paper/1906.04941/) (2019)
- [TIMEDIAL: Temporal Commonsense Reasoning in Dialog](https://mlsanity.com/paper/2106.04571/) (2021)
- [Zero-shot Temporal Relation Extraction with ChatGPT](https://mlsanity.com/paper/2304.05454/) (2023)
- [UniAdapter: Unified Parameter-Efficient Transfer Learning for Cross-modal Modeling](https://mlsanity.com/paper/2302.06605/) (2023)
- [Generating Long-form Story Using Dynamic Hierarchical Outlining with Memory-Enhancement](https://mlsanity.com/paper/2412.13575/) (2024)
- [Improving Temporal Relation Extraction with a Globally Acquired Statistical Resource](https://mlsanity.com/paper/1804.06020/) (2018)
- [More than Classification: A Unified Framework for Event Temporal Relation Extraction](https://mlsanity.com/paper/2305.17607/) (2023)
- [Rethinking Safety in LLM Fine-tuning: An Optimization Perspective](https://mlsanity.com/paper/2508.12531/) (2025)
- [Severing the Edge Between Before and After: Neural Architectures for Temporal Ordering of Events](https://mlsanity.com/paper/2004.04295/) (2020)
- [A Survey on Temporal Reasoning for Temporal Information Extraction from Text (Extended Abstract)](https://mlsanity.com/paper/2005.06527/) (2020)
- [Temporal Event Knowledge Acquisition via Identifying Narratives](https://mlsanity.com/paper/1805.10956/) (2018)
- [Will LLMs Replace the Encoder-Only Models in Temporal Relation Classification?](https://mlsanity.com/paper/2410.10476/) (2024)
- [Introducing Routing Functions to Vision-Language Parameter-Efficient Fine-Tuning with Low-Rank Bottlenecks](https://mlsanity.com/paper/2403.09377/) (2024)
- [A Wander Through the Multimodal Landscape: Efficient Transfer Learning via Low-rank Sequence Multimodal Adapter](https://mlsanity.com/paper/2412.08979/) (2024)
- [Temporal Relation Extraction in Clinical Texts: A Span-based Graph Transformer Approach](https://mlsanity.com/paper/2503.18085/) (2025)
- [Language Fusion for Parameter-Efficient Cross-lingual Transfer](https://mlsanity.com/paper/2501.06892/) (2025)
- [GDLLM: A Global Distance-aware Modeling Approach Based on Large Language Models for Event Temporal Relation Extraction](https://mlsanity.com/paper/2508.20828/) (2025)

## Abstract (arXiv)

Temporal relation extraction determines whether an event occurs before, after, or simultaneously with another event, and therefore relies on accurately modeling how the two events interact. Mainstream systems achieve this by concatenating event spans or using shallow fusion, which works well when all model parameters are trainable. However, in parameter-efficient fine-tuning, low-rank bottlenecks restrict information flow and prevent these interaction signals from passing through, leading to clear performance drops. To address this limitation, we propose a theoretically grounded architecture, Convolutional Bottleneck Interaction (CBI), which first applies lightweight depthwise convolution to enhance event representations and then uses element-wise multiplication to capture effective event-event interactions inside the bottleneck. Across five datasets and seven backbone models in the Adapter and LoRA settings, CBI provides consistent and substantial gains, up to +31.7 micro F1, while adding minimal computational cost, showing that explicit interaction inside low-rank spaces is crucial for temporal relation extraction. The code is available at https://github.com/VRCMF/CIF.git.