SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2104.06751 · EMNLP · 2021

Is Multi-Hop Reasoning Really Explainable? Towards Benchmarking Reasoning Interpretability

Yichi Zhang, Zhiyuan Liu, Xin Lv, Juanzi Li, Lei Hou, Yixin Cao, Zelin Dai

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Multi-hop reasoning has been widely studied in recent years to obtain more interpretable link prediction. However, we find in experiments that many paths given by these models are actually unreasonable, while little work has been done on interpretability evaluation for them. In this paper, we propose a unified framework to quantitatively evaluate the interpretability of multi-hop reasoning models so as to advance their development. In specific, we define three metrics, including path recall, local interpretability, and global interpretability for evaluation, and design an approximate strategy to calculate these metrics using the interpretability scores of rules. Furthermore, we manually annotate all possible rules and establish a Benchmark to detect the Interpretability of Multi-hop Reasoning (BIMR). In experiments, we verify the effectiveness of our benchmark. Besides, we run nine representative baselines on our benchmark, and the experimental results show that the interpretability of current multi-hop reasoning models is less satisfactory and is 51.7% lower than the upper bound given by our benchmark. Moreover, the rule-based models outperform the multi-hop reasoning models in terms of performance and interpretability, which points to a direction for future research, i.e., how to better incorporate rule information into the multihop reasoning model. Our codes and datasets can be obtained from https://github. com/THU-KEG/BIMR.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2104.06751")
get_code_for_paper("2104.06751")
have("2104.06751")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2104.06751.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2104.06751.svg)](https://syntology.ai/paper/2104.06751)

Connect an agent — have() is free.