Yulan He, Deyu Zhou, Jiasheng Si, Yingjie Zhu, Yibo Zhao, Haiyang Zhu
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.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Automatic multi-hop fact verification task has gained significant attention in recent years. Despite impressive results, these well-designed models perform poorly on out-of-domain data. One possible solution is to augment the training data with counterfactuals, which are generated by minimally altering the causal features of the original data. However, current counterfactual data augmentation techniques fail to handle multi-hop fact verification due to their incapability to preserve the complex logical relationships within multiple correlated texts. In this paper, we overcome this limitation by developing a rationale-sensitive method to generate linguistically diverse and label-flipping counterfactuals while preserving logical relationships. In specific, the diverse and fluent counterfactuals are generated via an Explain-Edit-Generate architecture. Moreover, the checking and filtering modules are proposed to regularize the counterfactual data with logical relations and flipped labels. Experimental results show that the proposed approach outperforms the SOTA baselines and can generate linguistically diverse counterfactual data without disrupting their logical relationships 1 .
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2310.14508")
get_code_for_paper("2310.14508")
have("2310.14508")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2310.14508.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2310.14508)
Connect an agent — have() is free.