# Large Language Models can Learn Rules

arXiv: https://arxiv.org/abs/2310.07064 · HTML: https://mlsanity.com/paper/2310.07064/

## Key facts

- Cited by 69 papers in the map (data through 14 Oct 2026).
- Builds on 64 of its 86 references that are in the map.
- First posted on arXiv 10 Oct 2023.

## Builds on (most cited first, 30 of 64)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [Language Models as Knowledge Bases?](https://mlsanity.com/paper/1909.01066/) (2019)
- [Multitask Prompted Training Enables Zero-Shot Task Generalization](https://mlsanity.com/paper/2110.08207/) (2021)
- [Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?](https://mlsanity.com/paper/2202.12837/) (2022)
- [Least-to-Most Prompting Enables Complex Reasoning in Large Language Models](https://mlsanity.com/paper/2205.10625/) (2022)
- [PaLM 2 Technical Report](https://mlsanity.com/paper/2305.10403/) (2023)
- [Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions](https://mlsanity.com/paper/2212.10509/) (2022)
- [Show Your Work: Scratchpads for Intermediate Computation with Language Models](https://mlsanity.com/paper/2112.00114/) (2021)
- [Reasoning with Language Model is Planning with World Model](https://mlsanity.com/paper/2305.14992/) (2023)
- [How Much Knowledge Can You Pack Into the Parameters of a Language Model?](https://mlsanity.com/paper/2002.08910/) (2020)
- [Decomposed Prompting: A Modular Approach for Solving Complex Tasks](https://mlsanity.com/paper/2210.02406/) (2022)
- [Visual Programming: Compositional visual reasoning without training](https://mlsanity.com/paper/2211.11559/) (2022)
- [Large Language Models Struggle to Learn Long-Tail Knowledge](https://mlsanity.com/paper/2211.08411/) (2022)
- [Memory Networks](https://mlsanity.com/paper/1410.3916/) (2014)

## Built on by (most cited first, 30 of 69)

- [SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training](https://mlsanity.com/paper/2501.17161/) (2025)
- [Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking](https://mlsanity.com/paper/2403.09629/) (2024)
- [Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security](https://mlsanity.com/paper/2401.05459/) (2024)
- [Large Language Model-Brained GUI Agents: A Survey](https://mlsanity.com/paper/2411.18279/) (2024)
- [LLM-SR: Scientific Equation Discovery via Programming with Large Language Models](https://mlsanity.com/paper/2404.18400/) (2024)
- [Large Language Models Can Learn Temporal Reasoning](https://mlsanity.com/paper/2401.06853/) (2024)
- [Fine-Tuned Language Models Generate Stable Inorganic Materials as Text](https://mlsanity.com/paper/2402.04379/) (2024)
- [Premise Order Matters in Reasoning with Large Language Models](https://mlsanity.com/paper/2402.08939/) (2024)
- [AutoManual: Constructing Instruction Manuals by LLM Agents via Interactive Environmental Learning](https://mlsanity.com/paper/2405.16247/) (2024)
- [Follow the Rules: Reasoning for Video Anomaly Detection with Large Language Models](https://mlsanity.com/paper/2407.10299/) (2024)
- [Can LLMs Follow Simple Rules?](https://mlsanity.com/paper/2311.04235/) (2023)
- [AlphaAgent: LLM-Driven Alpha Mining with Regularized Exploration to Counteract Alpha Decay](https://mlsanity.com/paper/2502.16789/) (2025)
- [LLM-FE: Automated Feature Engineering for Tabular Data with LLMs as Evolutionary Optimizers](https://mlsanity.com/paper/2503.14434/) (2025)
- [RL Fine-Tuning Heals OOD Forgetting in SFT](https://mlsanity.com/paper/2509.12235/) (2025)
- [Can LLMs Reason with Rules? Logic Scaffolding for Stress-Testing and Improving LLMs](https://mlsanity.com/paper/2402.11442/) (2024)
- [WALL-E: World Alignment by Rule Learning Improves World Model-based LLM Agents](https://mlsanity.com/paper/2410.07484/) (2024)
- [Landscape of Thoughts: Visualizing the Reasoning Process of Large Language Models](https://mlsanity.com/paper/2503.22165/) (2025)
- [IDEA: Enhancing the Rule Learning Ability of Large Language Model Agent through Induction, Deduction, and Abduction](https://mlsanity.com/paper/2408.10455/) (2024)
- [Deeper Insights Without Updates: The Power of In-Context Learning Over Fine-Tuning](https://mlsanity.com/paper/2410.04691/) (2024)
- [MetaReflection: Learning Instructions for Language Agents using Past Reflections](https://mlsanity.com/paper/2405.13009/) (2024)
- [Symbolic Working Memory Enhances Language Models for Complex Rule Application](https://mlsanity.com/paper/2408.13654/) (2024)
- [RL Is Neither a Panacea Nor a Mirage: Understanding Supervised vs. Reinforcement Learning Fine-Tuning for LLMs](https://mlsanity.com/paper/2508.16546/) (2025)
- [PhantomWiki: On-Demand Datasets for Reasoning and Retrieval Evaluation](https://mlsanity.com/paper/2502.20377/) (2025)
- [AlphaOPT: Formulating Optimization Programs with Self-Improving LLM Experience Library](https://mlsanity.com/paper/2510.18428/) (2025)
- [LLEMA: Evolutionary Search with LLMs for Multi-Objective Materials Discovery](https://mlsanity.com/paper/2510.22503/) (2025)
- [RLingua: Improving Reinforcement Learning Sample Efficiency in Robotic Manipulations With Large Language Models](https://mlsanity.com/paper/2403.06420/) (2024)
- [Integrating Intent Understanding and Optimal Behavior Planning for Behavior Tree Generation from Human Instructions](https://mlsanity.com/paper/2405.07474/) (2024)
- [Enhancing Agent Learning through World Dynamics Modeling](https://mlsanity.com/paper/2407.17695/) (2024)
- [Interactive Reasoning: Visualizing and Controlling Chain-of-Thought Reasoning in Large Language Models](https://mlsanity.com/paper/2506.23678/) (2025)
- [ItD: Large Language Models Can Teach Themselves Induction through Deduction](https://mlsanity.com/paper/2403.05789/) (2024)

## Abstract (arXiv)

When prompted with a few examples and intermediate steps, large language models (LLMs) have demonstrated impressive performance in various reasoning tasks. However, prompting methods that rely on implicit knowledge in an LLM often generate incorrect answers when the implicit knowledge is wrong or inconsistent with the task. To tackle this problem, we present Hypotheses-to-Theories (HtT), a framework that learns a rule library for reasoning with LLMs. HtT contains two stages, an induction stage and a deduction stage. In the induction stage, an LLM is first asked to generate and verify rules over a set of training examples. Rules that appear and lead to correct answers sufficiently often are collected to form a rule library. In the deduction stage, the LLM is then prompted to employ the learned rule library to perform reasoning to answer test questions. Experiments on relational reasoning, numerical reasoning and concept learning problems show that HtT improves existing prompting methods, with an absolute gain of 10-30% in accuracy. The learned rules are also transferable to different models and to different forms of the same problem.