# Transferring Procedural Knowledge across Commonsense Tasks

arXiv: https://arxiv.org/abs/2304.13867 · HTML: https://mlsanity.com/paper/2304.13867/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 45 references that are in the map.
- First posted on arXiv 26 Apr 2023.

## Builds on (most cited first, 30 of 32)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [PIQA: Reasoning about Physical Commonsense in Natural Language](https://mlsanity.com/paper/1911.11641/) (2019)
- [Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?](https://mlsanity.com/paper/2202.12837/) (2022)
- [What Makes Good In-Context Examples for GPT-3?](https://mlsanity.com/paper/2101.06804/) (2021)
- [Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigm](https://mlsanity.com/paper/2102.07350/) (2021)
- [The NarrativeQA Reading Comprehension Challenge](https://mlsanity.com/paper/1712.07040/) (2017)
- [A Corpus and Evaluation Framework for Deeper Understanding of Commonsense Stories](https://mlsanity.com/paper/1604.01696/) (2016)
- [ScienceWorld: Is your Agent Smarter than a 5th Grader?](https://mlsanity.com/paper/2203.07540/) (2022)
- [Abductive Commonsense Reasoning](https://mlsanity.com/paper/1908.05739/) (2019)
- [Language Models of Code are Few-Shot Commonsense Learners](https://mlsanity.com/paper/2210.07128/) (2022)
- [GLUCOSE: GeneraLized and COntextualized Story Explanations](https://mlsanity.com/paper/2009.07758/) (2020)
- [Tracking State Changes in Procedural Text: A Challenge Dataset and Models for Process Paragraph Comprehension](https://mlsanity.com/paper/1805.06975/) (2018)
- [Simulating Action Dynamics with Neural Process Networks](https://mlsanity.com/paper/1711.05313/) (2017)
- [CSKG: The CommonSense Knowledge Graph](https://mlsanity.com/paper/2012.11490/) (2020)
- [A Survey of Active Learning for Natural Language Processing](https://mlsanity.com/paper/2210.10109/) (2022)
- [RICA: Evaluating Robust Inference Capabilities Based on Commonsense Axioms](https://mlsanity.com/paper/2005.00782/) (2020)
- [Incorporating Structured Commonsense Knowledge in Story Completion](https://mlsanity.com/paper/1811.00625/) (2018)
- [Time-Stamped Language Model: Teaching Language Models to Understand the Flow of Events](https://mlsanity.com/paper/2104.07635/) (2021)
- [Tiered Reasoning for Intuitive Physics: Toward Verifiable Commonsense Language Understanding](https://mlsanity.com/paper/2109.04947/) (2021)
- [Knowledge-Aware Procedural Text Understanding with Multi-Stage Training](https://mlsanity.com/paper/2009.13199/) (2020)
- [Tracking Discrete and Continuous Entity State for Process Understanding](https://mlsanity.com/paper/1904.03518/) (2019)
- [Story Ending Prediction by Transferable BERT](https://mlsanity.com/paper/1905.07504/) (2019)
- [A Survey of Machine Narrative Reading Comprehension Assessments](https://mlsanity.com/paper/2205.00299/) (2022)
- [Coalescing Global and Local Information for Procedural Text Understanding](https://mlsanity.com/paper/2208.12848/) (2022)
- [Understanding Narratives through Dimensions of Analogy](https://mlsanity.com/paper/2206.07167/) (2022)
- [EvEntS ReaLM: Event Reasoning of Entity States via Language Models](https://mlsanity.com/paper/2211.05392/) (2022)

## Built on by (most cited first, 2 of 2)

- [FIRE: Food Image to REcipe generation](https://mlsanity.com/paper/2308.14391/) (2023)
- [Knowledge-enhanced Agents for Interactive Text Games](https://mlsanity.com/paper/2305.05091/) (2023)

## Abstract (arXiv)

Stories about everyday situations are an essential part of human communication, motivating the need to develop AI agents that can reliably understand these stories. Despite the long list of supervised methods for story completion and procedural understanding, current AI has no mechanisms to automatically track and explain procedures in unseen stories. To bridge this gap, we study the ability of AI models to transfer procedural knowledge to novel narrative tasks in a transparent manner. We design LEAP: a comprehensive framework that integrates state-of-the-art modeling architectures, training regimes, and augmentation strategies based on both natural and synthetic stories. To address the lack of densely annotated training data, we devise a robust automatic labeler based on few-shot prompting to enhance the augmented data. Our experiments with in- and out-of-domain tasks reveal insights into the interplay of different architectures, training regimes, and augmentation strategies. LEAP's labeler has a clear positive impact on out-of-domain datasets, while the resulting dense annotation provides native explainability.