Progressive-hint prompting improves reasoning in large language models

C Zheng, Z Liu, E Xie, Z Li, Y Li - arXiv preprint arXiv:2304.09797, 2023 - arxiv.org
The performance of Large Language Models (LLMs) in reasoning tasks depends heavily on
prompt design, with Chain-of-Thought (CoT) and self-consistency being critical methods that …

Rationale-augmented ensembles in language models

X Wang, J Wei, D Schuurmans, Q Le, E Chi… - arXiv preprint arXiv …, 2022 - arxiv.org
Recent research has shown that rationales, or step-by-step chains of thought, can be used
to improve performance in multi-step reasoning tasks. We reconsider rationale-augmented …

Scienceworld: Is your agent smarter than a 5th grader?

R Wang, P Jansen, MA Côté… - arXiv preprint arXiv …, 2022 - arxiv.org
We present ScienceWorld, a benchmark to test agents' scientific reasoning abilities in a new
interactive text environment at the level of a standard elementary school science curriculum …

Multi-hop question answering

V Mavi, A Jangra, A Jatowt - Foundations and Trends® in …, 2024 - nowpublishers.com
Abstract The task of Question Answering (QA) has attracted significant research interest for a
long time. Its relevance to language understanding and knowledge retrieval tasks, along …

Hierarchy-aware multi-hop question answering over knowledge graphs

J Dong, Q Zhang, X Huang, K Duan, Q Tan… - Proceedings of the ACM …, 2023 - dl.acm.org
Knowledge graphs (KGs) have been widely used to enhance complex question answering
(QA). To understand complex questions, existing studies employ language models (LMs) to …

Nonfactoid question answering as query-focused summarization with graph-enhanced multihop inference

Y Deng, W Zhang, W Xu, Y Shen… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Nonfactoid question answering (QA) is one of the most extensive yet challenging
applications and research areas in natural language processing (NLP). Existing methods fall …

Joint reasoning with knowledge subgraphs for Multiple Choice Question Answering

Q Zhang, S Chen, M Fang, X Chen - Information Processing & …, 2023 - Elsevier
Humans are able to reason from multiple sources to arrive at the correct answer. In the
context of Multiple Choice Question Answering (MCQA), knowledge graphs can provide …

Unifying Text, Tables, and Images for Multimodal Question Answering

H Luo, Y Shen, Y Deng - Findings of the Association for …, 2023 - aclanthology.org
Multimodal question answering (MMQA), which aims to derive the answer from multiple
knowledge modalities (eg, text, tables, and images), has received increasing attention due …

Hop, union, generate: Explainable multi-hop reasoning without rationale supervision

W Zhao, JT Chiu, C Cardie, AM Rush - arXiv preprint arXiv:2305.14237, 2023 - arxiv.org
Explainable multi-hop question answering (QA) not only predicts answers but also identifies
rationales, ie subsets of input sentences used to derive the answers. This problem has been …

Multi-hop question answering over incomplete knowledge graph with abstract conceptual evidence

Q Sun, C Zhang, Z Hu, Z Jin, J Yu, L Liu - Applied Intelligence, 2023 - Springer
Abstract Multi-hop Question Answering over Knowledge Graph (KGQA) aims to reason
answers through multiple triples in Knowledge Graphs (KGs). Unfortunately, in practice due …