Multi-Step Inference for Reasoning over Paragraphs
By Jiangming Liu, Matt Gardner. 2020
21 citations recorded by the source corpus.
Complex reasoning over text requires understanding and chaining together free-form predicates and logical connectives. Prior work has largely tried to do this either symbolically or with black-box transformers. We present a middle ground between these two extremes: a compositional model reminiscent of neural module networks that can perform chained logical reasoning. This model first finds relevant sentences in the context and then chains them together using neural modules. Our model gives significant performance improvements (up to 29\% relative error reduction when combined with a reranker) on ROPES, a recently-introduced complex reasoning dataset
Subfields: Artificial Intelligence, Natural Language Processing
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Yue Zhang
- Leyang Cui
- Mokanarangan Thayaparan
- André Freitas
- Kyle McDonell
- Laria Reynolds
- Hanmeng Liu
- Jian Liu
In Natural Language Processing
- Yue Zhang
- Leyang Cui
- Mokanarangan Thayaparan
- André Freitas
- Kyle McDonell
- Laria Reynolds
- Hanmeng Liu
- Jian Liu
Citations in the corpus
- Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigm (2021, methodology): “This effect of contamination from few-shot examples has been successfully used to improve the performance of GPT-3 by selecting in-context examples for each task [18].”
- Natural Language Inference in Context - Investigating Contextual Reasoning over Long Texts (2020, background): “• Information Integration over Paragraphs Multi-step reasoning (Liu et al. 2020b; Wang et al. 2019; Welbl, Stenetorp, and Riedel 2018) is the ability to retrieve and combine information from multiple paragraphs or multiple documents.”
- Unleashing the potential of prompt engineering in Large Language Models: a comprehensive review (2023, background): “Sometimes, a well-crafted zero-shot prompt can be more effective than providing multiple examples [36].”
- Case-Based Abductive Natural Language Inference (2020, background): “The work presented in this paper is related to hybrid neuro-symbolic approaches for inference with natural language (Liu et al., 2020; Minervini et al., 2020; Jiang and Bansal, 2019; Chen et al., 2019; Dua et al., 2019; Xu et al., 2021; Weber et al., 2019).”