# Harnessing Large Language Models as Post-hoc Correctors

arXiv: https://arxiv.org/abs/2402.13414 · HTML: https://mlsanity.com/paper/2402.13414/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 45 references that are in the map.
- First posted on arXiv 20 Feb 2024.

## Builds on (most cited first, 25 of 25)

- [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)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [Open Graph Benchmark: Datasets for Machine Learning on Graphs](https://mlsanity.com/paper/2005.00687/) (2020)
- [DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing](https://mlsanity.com/paper/2111.09543/) (2021)
- [MoleculeNet: A Benchmark for Molecular Machine Learning](https://mlsanity.com/paper/1703.00564/) (2017)
- [How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation](https://mlsanity.com/paper/2302.09210/) (2023)
- [OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphs](https://mlsanity.com/paper/2103.09430/) (2021)
- [Transformers as Soft Reasoners over Language](https://mlsanity.com/paper/2002.05867/) (2020)
- [Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategies](https://mlsanity.com/paper/2308.03188/) (2023)
- [GPT4Graph: Can Large Language Models Understand Graph Structured Data ? An Empirical Evaluation and Benchmarking](https://mlsanity.com/paper/2305.15066/) (2023)
- [Combining Label Propagation and Simple Models Out-performs Graph Neural Networks](https://mlsanity.com/paper/2010.13993/) (2020)
- [Active Example Selection for In-Context Learning](https://mlsanity.com/paper/2211.04486/) (2022)
- [The Capacity for Moral Self-Correction in Large Language Models](https://mlsanity.com/paper/2302.07459/) (2023)
- [Scientific Large Language Models: A Survey on Biological & Chemical Domains](https://mlsanity.com/paper/2401.14656/) (2024)
- [Post Hoc Explanations of Language Models Can Improve Language Models](https://mlsanity.com/paper/2305.11426/) (2023)
- [Pooling Architecture Search for Graph Classification](https://mlsanity.com/paper/2108.10587/) (2021)
- [Simplifying Node Classification on Heterophilous Graphs with Compatible Label Propagation](https://mlsanity.com/paper/2205.09389/) (2022)
- [Knowledge-augmented Graph Machine Learning for Drug Discovery: A Survey](https://mlsanity.com/paper/2302.08261/) (2023)

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

- [Benchmarking Large Language Models for Molecule Prediction Tasks](https://mlsanity.com/paper/2403.05075/) (2024)
- [Question Rephrasing for Quantifying Uncertainty in Large Language Models: Applications in Molecular Chemistry Tasks](https://mlsanity.com/paper/2408.03732/) (2024)
- [Smoothie-Qwen: Post-Hoc Smoothing to Reduce Language Bias in Multilingual LLMs](https://mlsanity.com/paper/2507.05686/) (2025)
- [Exploring Graph Structure Comprehension Ability of Multimodal Large Language Models: Case Studies](https://mlsanity.com/paper/2409.08864/) (2024)
- [Automatic Annotation Augmentation Boosts Translation between Molecules and Natural Language](https://mlsanity.com/paper/2502.06634/) (2025)
- [What Language Models Know But Don't Say: Non-Generative Prior Extraction for Generalization](https://mlsanity.com/paper/2601.17609/) (2026)
- [BLUEmed: Retrieval-Augmented Multi-Agent Debate for Clinical Error Detection](https://mlsanity.com/paper/2604.10389/) (2026)

## Abstract (arXiv)

As Machine Learning (ML) models grow in size and demand higher-quality training data, the expenses associated with re-training and fine-tuning these models are escalating rapidly. Inspired by recent impressive achievements of Large Language Models (LLMs) in different fields, this paper delves into the question: can LLMs efficiently improve an ML's performance at a minimal cost? We show that, through our proposed training-free framework LlmCorr, an LLM can work as a post-hoc corrector to propose corrections for the predictions of an arbitrary ML model. In particular, we form a contextual knowledge database by incorporating the dataset's label information and the ML model's predictions on the validation dataset. Leveraging the in-context learning capability of LLMs, we ask the LLM to summarise the instances in which the ML model makes mistakes and the correlation between primary predictions and true labels. Following this, the LLM can transfer its acquired knowledge to suggest corrections for the ML model's predictions. Our experimental results on text analysis and the challenging molecular predictions show that model improves the performance of a number of models by up to 39%.