# Generic Temporal Reasoning with Differential Analysis and Explanation

Source: [Generic Temporal Reasoning with Differential Analysis and Explanation](<https://www.sota2.com/research/paper/68fa6f961e209131cea46784>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-04T05:23:09.865Z

Authors: Yu Feng, Ben Zhou, Haoyu Wang, Helen Jin, Dan Roth

Published: 2022-12-20T17:40:03.000Z

## Abstract

Temporal reasoning is the task of predicting temporal relations of event pairs. While temporal reasoning models can perform reasonably well on in-domain benchmarks, we have little idea of these systems' generalizability due to existing datasets' limitations. In this work, we introduce a novel task named TODAY that bridges this gap with temporal differential analysis, which as the name suggests, evaluates whether systems can correctly understand the effect of incremental changes. Specifically, TODAY introduces slight contextual changes for given event pairs, and systems are asked to tell how this subtle contextual change would affect relevant temporal relation distributions. To facilitate learning, TODAY also annotates human explanations. We show that existing models, including GPT-3.5, drop to random guessing on TODAY, suggesting that they heavily rely on spurious information rather than proper reasoning for temporal predictions. On the other hand, we show that TODAY's supervision style and explanation annotations can be used in joint learning, encouraging models to use more appropriate signals during training and thus outperform across several benchmarks. TODAY can also be used to train models to solicit incidental supervision from noisy sources such as GPT-3.5, thus moving us more toward the goal of generic temporal reasoning systems.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Binary temporal relation classification on TRACIE, MATRES, and TODAY (test)](<https://www.sota2.com/research/sota/binary-temporal-relation-classification-on-tracie-matres-and-today-test.md>): Binary temporal relation classification; TRACIE, MATRES, and TODAY (test); TRACIE Accuracy: 79.9.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2212.10467>)

[PDF](<https://arxiv.org/pdf/2212.10467.pdf>)

[Implementation](<http://cogcomp.org/page/publication_view/1008>)