# PINTO: Faithful Language Reasoning Using Prompt-Generated Rationales

arXiv: https://arxiv.org/abs/2211.01562 · HTML: https://mlsanity.com/paper/2211.01562/

## Key facts

- Cited by 56 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 52 of its 66 references that are in the map.
- First posted on arXiv 3 Nov 2022.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 30 of 52)

- [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)
- [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)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022)
- [Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering](https://mlsanity.com/paper/1809.02789/) (2018)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge](https://mlsanity.com/paper/1811.00937/) (2018)
- [Towards A Rigorous Science of Interpretable Machine Learning](https://mlsanity.com/paper/1702.08608/) (2017)
- [ConceptNet 5.5: An Open Multilingual Graph of General Knowledge](https://mlsanity.com/paper/1612.03975/) (2016)
- [STaR: Bootstrapping Reasoning With Reasoning](https://mlsanity.com/paper/2203.14465/) (2022)
- [Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference](https://mlsanity.com/paper/1902.01007/) (2019)
- [Reading Wikipedia to Answer Open-Domain Questions](https://mlsanity.com/paper/1704.00051/) (2017)
- [Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies](https://mlsanity.com/paper/2101.02235/) (2021)
- [GPT-NeoX-20B: An Open-Source Autoregressive Language Model](https://mlsanity.com/paper/2204.06745/) (2022)
- [Annotation Artifacts in Natural Language Inference Data](https://mlsanity.com/paper/1803.02324/) (2018)
- [Attention is not not Explanation](https://mlsanity.com/paper/1908.04626/) (2019)
- [Underspecification Presents Challenges for Credibility in Modern Machine Learning](https://mlsanity.com/paper/2011.03395/) (2020)
- [e-SNLI: Natural Language Inference with Natural Language Explanations](https://mlsanity.com/paper/1812.01193/) (2018)
- [COMET: Commonsense Transformers for Automatic Knowledge Graph Construction](https://mlsanity.com/paper/1906.05317/) (2019)
- [Explain Yourself! Leveraging Language Models for Commonsense Reasoning](https://mlsanity.com/paper/1906.02361/) (2019)
- [QASC: A Dataset for Question Answering via Sentence Composition](https://mlsanity.com/paper/1910.11473/) (2019)
- [Can language models learn from explanations in context?](https://mlsanity.com/paper/2204.02329/) (2022)
- [Understanding Neural Networks through Representation Erasure](https://mlsanity.com/paper/1612.08220/) (2016)
- [KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoning](https://mlsanity.com/paper/1909.02151/) (2019)
- [Generated Knowledge Prompting for Commonsense Reasoning](https://mlsanity.com/paper/2110.08387/) (2021)
- [Visualizing and Understanding Neural Models in NLP](https://mlsanity.com/paper/1506.01066/) (2015)

## Built on by (most cited first, 30 of 56)

- [Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes](https://mlsanity.com/paper/2305.02301/) (2023)
- [Reasoning with Language Model Prompting: A Survey](https://mlsanity.com/paper/2212.09597/) (2022)
- [SCOTT: Self-Consistent Chain-of-Thought Distillation](https://mlsanity.com/paper/2305.01879/) (2023)
- [SatLM: Satisfiability-Aided Language Models Using Declarative Prompting](https://mlsanity.com/paper/2305.09656/) (2023)
- [Towards Better Chain-of-Thought Prompting Strategies: A Survey](https://mlsanity.com/paper/2310.04959/) (2023)
- [Efficient Causal Graph Discovery Using Large Language Models](https://mlsanity.com/paper/2402.01207/) (2024)
- [LogiCoT: Logical Chain-of-Thought Instruction-Tuning](https://mlsanity.com/paper/2305.12147/) (2023)
- [HARE: Explainable Hate Speech Detection with Step-by-Step Reasoning](https://mlsanity.com/paper/2311.00321/) (2023)
- [How Interpretable are Reasoning Explanations from Prompting Large Language Models?](https://mlsanity.com/paper/2402.11863/) (2024)
- [MCC-KD: Multi-CoT Consistent Knowledge Distillation](https://mlsanity.com/paper/2310.14747/) (2023)
- [Tailoring Self-Rationalizers with Multi-Reward Distillation](https://mlsanity.com/paper/2311.02805/) (2023)
- [Efficient Toxic Content Detection by Bootstrapping and Distilling Large Language Models](https://mlsanity.com/paper/2312.08303/) (2023)
- [Small Language Models Improve Giants by Rewriting Their Outputs](https://mlsanity.com/paper/2305.13514/) (2023)
- [Contextualization Distillation from Large Language Model for Knowledge Graph Completion](https://mlsanity.com/paper/2402.01729/) (2024)
- [Crystal: Introspective Reasoners Reinforced with Self-Feedback](https://mlsanity.com/paper/2310.04921/) (2023)
- [Beneath the Surface: Unveiling Harmful Memes with Multimodal Reasoning Distilled from Large Language Models](https://mlsanity.com/paper/2312.05434/) (2023)
- [Self-Contradictory Reasoning Evaluation and Detection](https://mlsanity.com/paper/2311.09603/) (2023)
- [Knowledge Distillation Using Frontier Open-source LLMs: Generalizability and the Role of Synthetic Data](https://mlsanity.com/paper/2410.18588/) (2024)
- [Enhancing Small Medical Learners with Privacy-preserving Contextual Prompting](https://mlsanity.com/paper/2305.12723/) (2023)
- [TriSum: Learning Summarization Ability from Large Language Models with Structured Rationale](https://mlsanity.com/paper/2403.10351/) (2024)
- [Mitigating Misleading Chain-of-Thought Reasoning with Selective Filtering](https://mlsanity.com/paper/2403.19167/) (2024)
- [Self-Critique and Refinement for Faithful Natural Language Explanations](https://mlsanity.com/paper/2505.22823/) (2025)
- [The Quest for Efficient Reasoning: A Data-Centric Benchmark to CoT Distillation](https://mlsanity.com/paper/2505.18759/) (2025)
- [All Circuits Lead to Rome: Rethinking Functional Anisotropy in Circuit and Sheaf Discovery for LLMs](https://mlsanity.com/paper/2605.12671/) (2026)
- [Case-Based Reasoning with Language Models for Classification of Logical Fallacies](https://mlsanity.com/paper/2301.11879/) (2023)
- [ZARA: Improving Few-Shot Self-Rationalization for Small Language Models](https://mlsanity.com/paper/2305.07355/) (2023)
- [POE: Process of Elimination for Multiple Choice Reasoning](https://mlsanity.com/paper/2310.15575/) (2023)
- [Towards Efficient CoT Distillation: Self-Guided Rationale Selector for Better Performance with Fewer Rationales](https://mlsanity.com/paper/2509.23574/) (2025)
- [Exploring Cognitive and Aesthetic Causality for Multimodal Aspect-Based Sentiment Analysis](https://mlsanity.com/paper/2504.15848/) (2025)
- [ICLEF: In-Context Learning with Expert Feedback for Explainable Style Transfer](https://mlsanity.com/paper/2309.08583/) (2023)

## Abstract (arXiv)

Neural language models (LMs) have achieved impressive results on various language-based reasoning tasks by utilizing latent knowledge encoded in their own pretrained parameters. To make this reasoning process more explicit, recent works retrieve a rationalizing LM's internal knowledge by training or prompting it to generate free-text rationales, which can be used to guide task predictions made by either the same LM or a separate reasoning LM. However, rationalizing LMs require expensive rationale annotation and/or computation, without any assurance that their generated rationales improve LM task performance or faithfully reflect LM decision-making. In this paper, we propose PINTO, an LM pipeline that rationalizes via prompt-based learning, and learns to faithfully reason over rationales via counterfactual regularization. First, PINTO maps out a suitable reasoning process for the task input by prompting a frozen rationalizing LM to generate a free-text rationale. Second, PINTO's reasoning LM is fine-tuned to solve the task using the generated rationale as context, while regularized to output less confident predictions when the rationale is perturbed. Across four datasets, we show that PINTO significantly improves the generalization ability of the reasoning LM, yielding higher performance on both in-distribution and out-of-distribution test sets. Also, we find that PINTO's rationales are more faithful to its task predictions than those generated by competitive baselines.