# Take a Break in the Middle: Investigating Subgoals towards Hierarchical Script Generation

arXiv: https://arxiv.org/abs/2305.10907 · HTML: https://mlsanity.com/paper/2305.10907/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 35 references that are in the map.
- First posted on arXiv 18 May 2023.

## Builds on (most cited first, 21 of 21)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Hierarchical Neural Story Generation](https://mlsanity.com/paper/1805.04833/) (2018)
- [A Diversity-Promoting Objective Function for Neural Conversation Models](https://mlsanity.com/paper/1510.03055/) (2015)
- [KG-BERT: BERT for Knowledge Graph Completion](https://mlsanity.com/paper/1909.03193/) (2019)
- [Toward Controlled Generation of Text](https://mlsanity.com/paper/1703.00955/) (2017)
- [NeuroLogic A*esque Decoding: Constrained Text Generation with Lookahead Heuristics](https://mlsanity.com/paper/2112.08726/) (2021)
- [NeuroLogic Decoding: (Un)supervised Neural Text Generation with Predicate Logic Constraints](https://mlsanity.com/paper/2010.12884/) (2020)
- [Strategies for Structuring Story Generation](https://mlsanity.com/paper/1902.01109/) (2019)
- [Reasoning about Goals, Steps, and Temporal Ordering with WikiHow](https://mlsanity.com/paper/2009.07690/) (2020)
- [Robust (Controlled) Table-to-Text Generation with Structure-Aware Equivariance Learning](https://mlsanity.com/paper/2205.03972/) (2022)
- [Goal-Oriented Script Construction](https://mlsanity.com/paper/2107.13189/) (2021)
- [Analogous Process Structure Induction for Sub-event Sequence Prediction](https://mlsanity.com/paper/2010.08525/) (2020)
- [Show Me More Details: Discovering Hierarchies of Procedures from Semi-structured Web Data](https://mlsanity.com/paper/2203.07264/) (2022)
- ["What Are You Trying to Do?" Semantic Typing of Event Processes](https://mlsanity.com/paper/2010.06724/) (2020)
- [Using Sentence-Level LSTM Language Models for Script Inference](https://mlsanity.com/paper/1604.02993/) (2016)
- [Integrating Know-How into the Linked Data Cloud](https://mlsanity.com/paper/1604.04506/) (2016)

## Built on by (most cited first, 7 of 7)

- [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023)
- [WebAgent-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement Learning](https://mlsanity.com/paper/2505.16421/) (2025)
- [Toward Generalizable Evaluation in the LLM Era: A Survey Beyond Benchmarks](https://mlsanity.com/paper/2504.18838/) (2025)
- [Towards Quantifying Commonsense Reasoning with Mechanistic Insights](https://mlsanity.com/paper/2504.10077/) (2025)
- [Investigating Pedagogical Teacher and Student LLM Agents: Genetic Adaptation Meets Retrieval Augmented Generation Across Learning Style](https://mlsanity.com/paper/2505.19173/) (2025)
- [Skill-as-Pseudocode: Refactoring Skill Libraries to Pseudocode for LLM Agents](https://mlsanity.com/paper/2605.27955/) (2026)
- [Towards Goal-oriented Prompt Engineering for Large Language Models: A Survey](https://mlsanity.com/paper/2401.14043/) (2024)

## Abstract (arXiv)

Goal-oriented Script Generation is a new task of generating a list of steps that can fulfill the given goal. In this paper, we propose to extend the task from the perspective of cognitive theory. Instead of a simple flat structure, the steps are typically organized hierarchically - Human often decompose a complex task into subgoals, where each subgoal can be further decomposed into steps. To establish the benchmark, we contribute a new dataset, propose several baseline methods, and set up evaluation metrics. Both automatic and human evaluation verify the high-quality of dataset, as well as the effectiveness of incorporating subgoals into hierarchical script generation. Furthermore, We also design and evaluate the model to discover subgoal, and find that it is a bit more difficult to decompose the goals than summarizing from segmented steps.