# FactCorrector: A Graph-Inspired Approach to Long-Form Factuality Correction of Large Language Models

arXiv: https://arxiv.org/abs/2601.11232 · HTML: https://mlsanity.com/paper/2601.11232/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 25 references that are in the map.
- First posted on arXiv 16 Jan 2026.

## Builds on (most cited first, 15 of 15)

- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [BLEURT: Learning Robust Metrics for Text Generation](https://mlsanity.com/paper/2004.04696/) (2020)
- [Reasoning with Language Model is Planning with World Model](https://mlsanity.com/paper/2305.14992/) (2023)
- [CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing](https://mlsanity.com/paper/2305.11738/) (2023)
- [AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback](https://mlsanity.com/paper/2305.14387/) (2023)
- [CodeT: Code Generation with Generated Tests](https://mlsanity.com/paper/2207.10397/) (2022)
- [Large Language Models are Better Reasoners with Self-Verification](https://mlsanity.com/paper/2212.09561/) (2022)
- [Knowledge Conflicts for LLMs: A Survey](https://mlsanity.com/paper/2403.08319/) (2024)
- [REFINER: Reasoning Feedback on Intermediate Representations](https://mlsanity.com/paper/2304.01904/) (2023)
- [LM vs LM: Detecting Factual Errors via Cross Examination](https://mlsanity.com/paper/2305.13281/) (2023)
- [Training Language Models with Language Feedback at Scale](https://mlsanity.com/paper/2303.16755/) (2023)
- [ConflictBank: A Benchmark for Evaluating the Influence of Knowledge Conflicts in LLM](https://mlsanity.com/paper/2408.12076/) (2024)
- [Self-Verification Improves Few-Shot Clinical Information Extraction](https://mlsanity.com/paper/2306.00024/) (2023)
- [Continually Improving Extractive QA via Human Feedback](https://mlsanity.com/paper/2305.12473/) (2023)
- [Comprehensiveness Metrics for Automatic Evaluation of Factual Recall in Text Generation](https://mlsanity.com/paper/2510.07926/) (2025)

## Abstract (arXiv)

Large language models (LLMs) are widely used in knowledge-intensive applications but often generate factually incorrect responses. A promising approach to rectify these flaws is correcting LLMs using feedback. Therefore, in this paper, we introduce FactCorrector, a new post-hoc correction method that adapts across domains without retraining and leverages structured feedback about the factuality of the original response to generate a correction. To support rigorous evaluations of factuality correction methods, we also develop the VELI5 benchmark, a novel dataset containing systematically injected factual errors and ground-truth corrections. Experiments on VELI5 and several popular long-form factuality datasets show that the FactCorrector approach significantly improves factual precision while preserving relevance, outperforming strong baselines. We release our code at https://ibm.biz/factcorrector.