Ask to Understand: Question Generation for Multi-hop Question Answering

Li, Jiawei; Ren, Mucheng; Gao, Yang; Yang, Yizhe

doi:10.1007/978-981-99-6207-5_2

Cited by 1 publication

(1 citation statement)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A complex question necessitates its division into simpler sub-questions that are relatively easier to answer. For question decomposition, there are established strategies such as symbolic methods based on logical approaches [18,19], as well as methods that rely on learning models using purely natural language text [10,20,21]. To train a generative LM for question decomposition, a large number of sets comprising original questions and their decomposed sub-questions are needed.…”

Section: Complex Question Decompositionmentioning

confidence: 99%

Towards a small language model powered chain‐of‐reasoning for open‐domain question answering

Roh,

Kim,

Bae

2024

ETRI Journal

View full text Add to dashboard Cite

We focus on open‐domain question‐answering tasks that involve a chain‐of‐reasoning, which are primarily implemented using large language models. With an emphasis on cost‐effectiveness, we designed EffiChainQA, an architecture centered on the use of small language models. We employed a retrieval‐based language model to address the limitations of large language models, such as the hallucination issue and the lack of updated knowledge. To enhance reasoning capabilities, we introduced a question decomposer that leverages a generative language model and serves as a key component in the chain‐of‐reasoning process. To generate training data for our question decomposer, we leveraged ChatGPT, which is known for its data augmentation ability. Comprehensive experiments were conducted using the HotpotQA dataset. Our method outperformed several established approaches, including the Chain‐of‐Thoughts approach, which is based on large language models. Moreover, our results are on par with those of state‐of‐the‐art Retrieve‐then‐Read methods that utilize large language models.

show abstract