Knowledge-Aware Self-Correction in Language Models via Structured Memory Graphs
Fuente:
arXiv
Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912468694990848 |
|---|---|
| author | Saha, Swayamjit |
| author_facet | Saha, Swayamjit |
| contents | Large Language Models (LLMs) are powerful yet prone to generating factual errors, commonly referred to as hallucinations. We present a lightweight, interpretable framework for knowledge-aware self-correction of LLM outputs using structured memory graphs based on RDF triples. Without retraining or fine-tuning, our method post-processes model outputs and corrects factual inconsistencies via external semantic memory. We demonstrate the approach using DistilGPT-2 and show promising results on simple factual prompts. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_04625 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Knowledge-Aware Self-Correction in Language Models via Structured Memory Graphs Saha, Swayamjit Computation and Language Artificial Intelligence Large Language Models (LLMs) are powerful yet prone to generating factual errors, commonly referred to as hallucinations. We present a lightweight, interpretable framework for knowledge-aware self-correction of LLM outputs using structured memory graphs based on RDF triples. Without retraining or fine-tuning, our method post-processes model outputs and corrects factual inconsistencies via external semantic memory. We demonstrate the approach using DistilGPT-2 and show promising results on simple factual prompts. |
| title | Knowledge-Aware Self-Correction in Language Models via Structured Memory Graphs |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2507.04625 |