# A Comparative Analysis of Conversational Large Language Models in Knowledge-Based Text Generation

arXiv: https://arxiv.org/abs/2402.01495 · HTML: https://mlsanity.com/paper/2402.01495/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 32 references that are in the map.
- First posted on arXiv 2 Feb 2024.

## Builds on (most cited first, 17 of 17)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Pretrained Language Models for Text Generation: A Survey](https://mlsanity.com/paper/2105.10311/) (2021)
- [Is GPT-3 Text Indistinguishable from Human Text? Scarecrow: A Framework for Scrutinizing Machine Text](https://mlsanity.com/paper/2107.01294/) (2021)
- [Step-by-Step: Separating Planning from Realization in Neural Data-to-Text Generation](https://mlsanity.com/paper/1904.03396/) (2019)
- [Few-Shot NLG with Pre-Trained Language Model](https://mlsanity.com/paper/1904.09521/) (2019)
- [Plan-then-Generate: Controlled Data-to-Text Generation via Planning](https://mlsanity.com/paper/2108.13740/) (2021)
- [Neural data-to-text generation: A comparison between pipeline and end-to-end architectures](https://mlsanity.com/paper/1908.09022/) (2019)
- [PiVe: Prompting with Iterative Verification Improving Graph-based Generative Capability of LLMs](https://mlsanity.com/paper/2305.12392/) (2023)
- [A Decade of Knowledge Graphs in Natural Language Processing: A Survey](https://mlsanity.com/paper/2210.00105/) (2022)
- [Awakening Latent Grounding from Pretrained Language Models for Semantic Parsing](https://mlsanity.com/paper/2109.10540/) (2021)
- [Control Prefixes for Parameter-Efficient Text Generation](https://mlsanity.com/paper/2110.08329/) (2021)
- [Neural Pipeline for Zero-Shot Data-to-Text Generation](https://mlsanity.com/paper/2203.16279/) (2022)
- [Analysing Mixed Initiatives and Search Strategies during Conversational Search](https://mlsanity.com/paper/2109.05955/) (2021)
- [Stage-wise Fine-tuning for Graph-to-Text Generation](https://mlsanity.com/paper/2105.08021/) (2021)
- [Mind the Labels: Describing Relations in Knowledge Graphs With Pretrained Models](https://mlsanity.com/paper/2210.07373/) (2022)

## Built on by (most cited first, 6 of 6)

- [Engineering Conversational Search Systems: A Review of Applications, Architectures, and Functional Components](https://mlsanity.com/paper/2407.00997/) (2024)
- [Leveraging Semantic Triples for Private Document Generation with Local Differential Privacy Guarantees](https://mlsanity.com/paper/2508.20736/) (2025)
- [Bridging Information Gaps in Dialogues With Grounded Exchanges Using Knowledge Graphs](https://mlsanity.com/paper/2408.01088/) (2024)
- [Conversational Exploratory Search of Scholarly Publications Using Knowledge Graphs](https://mlsanity.com/paper/2410.00427/) (2024)
- [Leveraging Knowledge Graphs and LLMs for Structured Generation of Misinformation](https://mlsanity.com/paper/2505.24479/) (2025)
- [Beyond Theoretical Bounds: Empirical Privacy Loss Calibration for Text Rewriting Under Local Differential Privacy](https://mlsanity.com/paper/2603.22968/) (2026)

## Abstract (arXiv)

Generating natural language text from graph-structured data is essential for conversational information seeking. Semantic triples derived from knowledge graphs can serve as a valuable source for grounding responses from conversational agents by providing a factual basis for the information they communicate. This is especially relevant in the context of large language models, which offer great potential for conversational interaction but are prone to hallucinating, omitting, or producing conflicting information. In this study, we conduct an empirical analysis of conversational large language models in generating natural language text from semantic triples. We compare four large language models of varying sizes with different prompting techniques. Through a series of benchmark experiments on the WebNLG dataset, we analyze the models' performance and identify the most common issues in the generated predictions. Our findings show that the capabilities of large language models in triple verbalization can be significantly improved through few-shot prompting, post-processing, and efficient fine-tuning techniques, particularly for smaller models that exhibit lower zero-shot performance.