Papers with stepwise methods

2 papers
Generating Natural Language Proofs with Verifier-Guided Search (2022.emnlp-main)

Copied to clipboard

Challenge: Existing stepwise methods struggle to generate valid proof steps based on the hypothesis . instead, they generate invalid steps .
Approach: They propose a stepwise method which generates relevant steps conditioning on the hypothesis.
Outcome: The proposed method improves correctness of predicted proofs from 27.7% to 33.3% on EntailmentBank and RuleTaker.
FRVA: Fact-Retrieval and Verification Augmented Entailment Tree Generation for Explainable Question Answering (2024.findings-acl)

Copied to clipboard

Challenge: Existing methods for generating a entailment tree exhibit the reasoning chains from knowledge facts to predicted answers, but they have large fact search spaces and error accumulation problems resulting in the generation of invalid steps.
Approach: They propose a Fact-Retrieval and Verification Augmented bidirectional entailment tree generation method that contains two systems.
Outcome: The proposed method outperforms existing models and achieves state-of-the-art performance in fact selection and structural correctness.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations