Retrieving multimodal information for augmented generation: A survey

R Zhao, H Chen, W Wang, F Jiao, XL Do, C Qin… - arXiv preprint arXiv …, 2023 - arxiv.org
As Large Language Models (LLMs) become popular, there emerged an important trend of
using multimodality to augment the LLMs' generation ability, which enables LLMs to better …

WorldTree v2: A corpus of science-domain structured explanations and inference patterns supporting multi-hop inference

Z Xie, S Thiem, J Martin, E Wainwright… - Proceedings of the …, 2020 - aclanthology.org
Explainable question answering for complex questions often requires combining large
numbers of facts to answer a question while providing a human-readable explanation for the …

ExplaGraphs: An explanation graph generation task for structured commonsense reasoning

S Saha, P Yadav, L Bauer, M Bansal - arXiv preprint arXiv:2104.07644, 2021 - arxiv.org
Recent commonsense-reasoning tasks are typically discriminative in nature, where a model
answers a multiple-choice question for a certain context. Discriminative tasks are limiting …

Unsupervised alignment-based iterative evidence retrieval for multi-hop question answering

V Yadav, S Bethard, M Surdeanu - arXiv preprint arXiv:2005.01218, 2020 - arxiv.org
Evidence retrieval is a critical stage of question answering (QA), necessary not only to
improve performance, but also to explain the decisions of the corresponding QA method. We …

Metgen: A module-based entailment tree generation framework for answer explanation

R Hong, H Zhang, X Yu, C Zhang - arXiv preprint arXiv:2205.02593, 2022 - arxiv.org
Knowing the reasoning chains from knowledge to the predicted answers can help construct
an explainable question answering (QA) system. Advances on QA explanation propose to …

A survey on explainability in machine reading comprehension

M Thayaparan, M Valentino, A Freitas - arXiv preprint arXiv:2010.00389, 2020 - arxiv.org
This paper presents a systematic review of benchmarks and approaches for explainability in
Machine Reading Comprehension (MRC). We present how the representation and …

multiPRover: Generating multiple proofs for improved interpretability in rule reasoning

S Saha, P Yadav, M Bansal - arXiv preprint arXiv:2106.01354, 2021 - arxiv.org
We focus on a type of linguistic formal reasoning where the goal is to reason over explicit
knowledge in the form of natural language facts and rules (Clark et al., 2020). A recent work …

Hybrid autoregressive inference for scalable multi-hop explanation regeneration

M Valentino, M Thayaparan, D Ferreira… - Proceedings of the AAAI …, 2022 - ojs.aaai.org
Regenerating natural language explanations in the scientific domain has been proposed as
a benchmark to evaluate complex multi-hop and explainable inference. In this context, large …

NLI4CT: Multi-evidence natural language inference for clinical trial reports

M Jullien, M Valentino, H Frost, P O'Regan… - arXiv preprint arXiv …, 2023 - arxiv.org
How can we interpret and retrieve medical evidence to support clinical decisions? Clinical
trial reports (CTR) amassed over the years contain indispensable information for the …

Unification-based reconstruction of multi-hop explanations for science questions

M Valentino, M Thayaparan, A Freitas - arXiv preprint arXiv:2004.00061, 2020 - arxiv.org
This paper presents a novel framework for reconstructing multi-hop explanations in science
Question Answering (QA). While existing approaches for multi-hop reasoning build …