DeepAI AI Chat
Log In Sign Up

Entailment Tree Explanations via Iterative Retrieval-Generation Reasoner

05/18/2022
by   Danilo Ribeiro, et al.
Amazon
Northwestern University
0

Large language models have achieved high performance on various question answering (QA) benchmarks, but the explainability of their output remains elusive. Structured explanations, called entailment trees, were recently suggested as a way to explain and inspect a QA system's answer. In order to better generate such entailment trees, we propose an architecture called Iterative Retrieval-Generation Reasoner (IRGR). Our model is able to explain a given hypothesis by systematically generating a step-by-step explanation from textual premises. The IRGR model iteratively searches for suitable premises, constructing a single entailment step at a time. Contrary to previous approaches, our method combines generation steps and retrieval of premises, allowing the model to leverage intermediate conclusions, and mitigating the input size limit of baseline encoder-decoder models. We conduct experiments using the EntailmentBank dataset, where we outperform existing benchmarks on premise retrieval and entailment tree generation, with around 300 overall correctness.

READ FULL TEXT
05/05/2022

METGEN: A Module-Based Entailment Tree Generation Framework for Answer Explanation

Knowing the reasoning chains from knowledge to the predicted answers can...
04/17/2021

Explaining Answers with Entailment Trees

Our goal, in the context of open-domain textual question-answering (QA),...
10/31/2022

RLET: A Reinforcement Learning Based Approach for Explainable QA with Entailment Trees

Interpreting the reasoning process from questions to answers poses a cha...
08/02/2022

Active entailment encoding for explanation tree construction using parsimonious generation of hard negatives

Entailment trees have been proposed to simulate the human reasoning proc...
12/16/2021

QAFactEval: Improved QA-Based Factual Consistency Evaluation for Summarization

Factual consistency is an essential quality of text summarization models...
05/24/2022

Policy Compliance Detection via Expression Tree Inference

Policy Compliance Detection (PCD) is a task we encounter when reasoning ...
09/16/2022

Dynamic Generation of Interpretable Inference Rules in a Neuro-Symbolic Expert System

We present an approach for systematic reasoning that produces human inte...