# RATIONALYST: Mining Implicit Rationales for Process Supervision of Reasoning

arXiv: https://arxiv.org/abs/2410.01044 · HTML: https://mlsanity.com/paper/2410.01044/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Prompting and chain-of-thought reasoning, one of 17 directions in LLM reasoning.
- Builds on 29 of its 41 references that are in the map.
- First posted on arXiv 1 Oct 2024.

## Placed in

- LLM reasoning / [Prompting and chain-of-thought reasoning](https://mlsanity.com/lr/prompting-and-chain-of-thought-reasoning/)

## Builds on (most cited first, 29 of 29)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [The Pile: An 800GB Dataset of Diverse Text for Language Modeling](https://mlsanity.com/paper/2101.00027/) (2020)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024)
- [MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark](https://mlsanity.com/paper/2406.01574/) (2024)
- [Large Language Models Cannot Self-Correct Reasoning Yet](https://mlsanity.com/paper/2310.01798/) (2023)
- [MPNet: Masked and Permuted Pre-training for Language Understanding](https://mlsanity.com/paper/2004.09297/) (2020)
- [Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations](https://mlsanity.com/paper/2312.08935/) (2023)
- [Textbooks Are All You Need](https://mlsanity.com/paper/2306.11644/) (2023)
- [Improve Mathematical Reasoning in Language Models by Automated Process Supervision](https://mlsanity.com/paper/2406.06592/) (2024)
- [Chain-of-Verification Reduces Hallucination in Large Language Models](https://mlsanity.com/paper/2309.11495/) (2023)
- [Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking](https://mlsanity.com/paper/2403.09629/) (2024)
- [Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Models](https://mlsanity.com/paper/2408.00724/) (2024)
- [Making Large Language Models Better Reasoners with Step-Aware Verifier](https://mlsanity.com/paper/2206.02336/) (2022)
- [Take a Step Back: Evoking Reasoning via Abstraction in Large Language Models](https://mlsanity.com/paper/2310.06117/) (2023)
- [OpenWebMath: An Open Dataset of High-Quality Mathematical Web Text](https://mlsanity.com/paper/2310.06786/) (2023)
- [Self-Explore: Enhancing Mathematical Reasoning in Language Models with Fine-grained Rewards](https://mlsanity.com/paper/2404.10346/) (2024)
- [LeanReasoner: Boosting Complex Logical Reasoning with Lean](https://mlsanity.com/paper/2403.13312/) (2024)
- [SELF-[IN]CORRECT: LLMs Struggle with Discriminating Self-Generated Responses](https://mlsanity.com/paper/2404.04298/) (2024)
- [General Purpose Verification for Chain of Thought Prompting](https://mlsanity.com/paper/2405.00204/) (2024)
- [NELLIE: A Neuro-Symbolic Inference Engine for Grounded, Compositional, and Explainable Reasoning](https://mlsanity.com/paper/2209.07662/) (2022)
- [Enhancing Systematic Decompositional Natural Language Inference Using Informal Logic](https://mlsanity.com/paper/2402.14798/) (2024)
- [Learning to Plan for Language Modeling from Unlabeled Data](https://mlsanity.com/paper/2404.00614/) (2024)
- [Reflection of Thought: Inversely Eliciting Numerical Reasoning in Language Models via Solving Linear Systems](https://mlsanity.com/paper/2210.05075/) (2022)

## Built on by (most cited first, 6 of 6)

- [Reasoning to Learn from Latent Thoughts](https://mlsanity.com/paper/2503.18866/) (2025)
- [Improving RL Exploration for LLM Reasoning through Retrospective Replay](https://mlsanity.com/paper/2504.14363/) (2025)
- [CoMAT: Chain of Mathematically Annotated Thought Improves Mathematical Reasoning](https://mlsanity.com/paper/2410.10336/) (2024)
- [Generative AI Act II: Test Time Scaling Drives Cognition Engineering](https://mlsanity.com/paper/2504.13828/) (2025)
- [Feedback Friction: LLMs Struggle to Fully Incorporate External Feedback](https://mlsanity.com/paper/2506.11930/) (2025)
- [ToW: Thoughts of Words Improve Reasoning in Large Language Models](https://mlsanity.com/paper/2410.16235/) (2024)

## Abstract (arXiv)

The reasoning steps generated by LLMs might be incomplete, as they mimic logical leaps common in everyday communication found in their pre-training data: underlying rationales are frequently left implicit (unstated). To address this challenge, we introduce RATIONALYST, a model for process-supervision of reasoning based on pre-training on a vast collection of rationale annotations extracted from unlabeled data. We extract 79k rationales from web-scale unlabelled dataset (the Pile) and a combination of reasoning datasets with minimal human intervention. This web-scale pre-training for reasoning allows RATIONALYST to consistently generalize across diverse reasoning tasks, including mathematical, commonsense, scientific, and logical reasoning. Fine-tuned from LLaMa-3-8B, RATIONALYST improves the accuracy of reasoning by an average of 3.9% on 7 representative reasoning benchmarks. It also demonstrates superior performance compared to significantly larger verifiers like GPT-4 and similarly sized models fine-tuned on matching training sets.