Papers with explanation graph generation
MIDGARD: Self-Consistency Using Minimum Description Length for Structured Commonsense Reasoning (2024.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to generate a reasoning graph from natural language input suffer from error propagation due to autoregressive nature and single-pass-based decoding. |
| Approach: | They propose a method that uses minimum description length to identify consistent properties among different graph samples generated by large language models. |
| Outcome: | The proposed method outperforms previous approaches for generating reasoning graphs from natural language input using large language models. |
ExplaGraphs: An Explanation Graph Generation Task for Structured Commonsense Reasoning (2021.emnlp-main)
Copied to clipboard
| Challenge: | Current commonsense-reasoning tasks are discriminative in nature, where a model answers a multiple-choice question for a certain context. |
| Approach: | They propose a generative task that generates a commonsense-augmented graph for stance prediction by using a create-verify-and-refine graph collection framework. |
| Outcome: | The proposed model is able to generate a graph that serves as non-trivial, complete, and unambiguous explanation for the predicted stance. |