# Multi-Step Inference for Reasoning Over Paragraphs

arXiv: https://arxiv.org/abs/2004.02995 · HTML: https://mlsanity.com/paper/2004.02995/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Apr 2020.

## Built on by (most cited first, 8 of 8)

- [Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigm](https://mlsanity.com/paper/2102.07350/) (2021)
- [Unleashing the potential of prompt engineering for large language models](https://mlsanity.com/paper/2310.14735/) (2023)
- [Meta Prompting for AI Systems](https://mlsanity.com/paper/2311.11482/) (2023)
- [Enhancing Ethical Explanations of Large Language Models through Iterative Symbolic Refinement](https://mlsanity.com/paper/2402.00745/) (2024)
- [Learning with Instance Bundles for Reading Comprehension](https://mlsanity.com/paper/2104.08735/) (2021)
- [Prediction or Comparison: Toward Interpretable Qualitative Reasoning](https://mlsanity.com/paper/2106.02399/) (2021)
- [A novel interface for adversarial trivia question-writing](https://mlsanity.com/paper/2404.00011/) (2024)
- [Information Extraction from Conversation Transcripts: Neuro-Symbolic vs. LLM](https://mlsanity.com/paper/2510.12023/) (2025)

## Abstract (arXiv)

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 comfibined with a reranker) on ROPES, a recently introduced complex reasoning dataset.