# Trustful LLMs: Customizing and Grounding Text Generation with Knowledge Bases and Dual Decoders

arXiv: https://arxiv.org/abs/2411.07870 · HTML: https://mlsanity.com/paper/2411.07870/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 41 references that are in the map.
- First posted on arXiv 12 Nov 2024.

## Builds on (most cited first, 24 of 24)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [node2vec: Scalable Feature Learning for Networks](https://mlsanity.com/paper/1607.00653/) (2016)
- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [Get To The Point: Summarization with Pointer-Generator Networks](https://mlsanity.com/paper/1704.04368/) (2017)
- [Unifying Large Language Models and Knowledge Graphs: A Roadmap](https://mlsanity.com/paper/2306.08302/) (2023)
- [AllenNLP: A Deep Semantic Natural Language Processing Platform](https://mlsanity.com/paper/1803.07640/) (2018)
- [Lexically Constrained Decoding for Sequence Generation Using Grid Beam Search](https://mlsanity.com/paper/1704.07138/) (2017)
- [Trustworthy AI: From Principles to Practices](https://mlsanity.com/paper/2110.01167/) (2021)
- [GSum: A General Framework for Guided Neural Abstractive Summarization](https://mlsanity.com/paper/2010.08014/) (2020)
- [Retrieval Augmented Generation or Long-Context LLMs? A Comprehensive Study and Hybrid Approach](https://mlsanity.com/paper/2407.16833/) (2024)
- [Guiding LLMs The Right Way: Fast, Non-Invasive Constrained Generation](https://mlsanity.com/paper/2403.06988/) (2024)
- [OpenNRE: An Open and Extensible Toolkit for Neural Relation Extraction](https://mlsanity.com/paper/1909.13078/) (2019)
- [Dual-decoder Transformer for Joint Automatic Speech Recognition and Multilingual Speech Translation](https://mlsanity.com/paper/2011.00747/) (2020)
- [Contrastive Triple Extraction with Generative Transformer](https://mlsanity.com/paper/2009.06207/) (2020)
- [KELM: Knowledge Enhanced Pre-Trained Language Representations with Message Passing on Hierarchical Relational Graphs](https://mlsanity.com/paper/2109.04223/) (2021)
- [Byzantine-Robust and Privacy-Preserving Framework for FedML](https://mlsanity.com/paper/2105.02295/) (2021)
- [ChatGPT in the Age of Generative AI and Large Language Models: A Concise Survey](https://mlsanity.com/paper/2307.04251/) (2023)
- [LUKE-Graph: A Transformer-based Approach with Gated Relational Graph Attention for Cloze-style Reading Comprehension](https://mlsanity.com/paper/2303.06675/) (2023)
- [Explicit and Implicit Semantic Ranking Framework](https://mlsanity.com/paper/2304.04918/) (2023)
- [Unsupervised Terminological Ontology Learning based on Hierarchical Topic Modeling](https://mlsanity.com/paper/1708.09025/) (2017)
- [An Empirical Revisiting of Linguistic Knowledge Fusion in Language Understanding Tasks](https://mlsanity.com/paper/2210.13002/) (2022)
- [Triples-to-Text Generation with Reinforcement Learning Based Graph-augmented Neural Networks](https://mlsanity.com/paper/2111.10545/) (2021)

## Abstract (arXiv)

Although people are impressed by the content generation skills of large language models, the use of LLMs, such as ChatGPT, is limited by the domain grounding of the content. The correctness and groundedness of the generated content need to be based on a verified context, such as results from Retrieval-Augmented Generation (RAG). One important issue when adapting LLMs to a customized domain is that the generated responses are often incomplete, or the additions are not verified and may even be hallucinated. Prior studies on hallucination detection have focused on evaluation metrics, which are not easily adaptable to dynamic domains and can be vulnerable to attacks like jail-breaking. In this work, we propose 1) a post-processing algorithm that leverages knowledge triplets in RAG context to correct hallucinations and 2) a dual-decoder model that fuses RAG context to guide the generation process.