# Improving Faithfulness of Large Language Models in Summarization via Sliding Generation and Self-Consistency

arXiv: https://arxiv.org/abs/2407.21443 · HTML: https://mlsanity.com/paper/2407.21443/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 19 of its 73 references that are in the map.
- First posted on arXiv 31 Jul 2024.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 19 of 19)

- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [Large Language Models are not Fair Evaluators](https://mlsanity.com/paper/2305.17926/) (2023)
- [In-Context Retrieval-Augmented Language Models](https://mlsanity.com/paper/2302.00083/) (2023)
- [Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models](https://mlsanity.com/paper/2309.01219/) (2023)
- [LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression](https://mlsanity.com/paper/2310.06839/) (2023)
- [Benchmarking Large Language Models for News Summarization](https://mlsanity.com/paper/2301.13848/) (2023)
- [Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedback](https://mlsanity.com/paper/2302.12813/) (2023)
- [News Summarization and Evaluation in the Era of GPT-3](https://mlsanity.com/paper/2209.12356/) (2022)
- [Chain-of-Verification Reduces Hallucination in Large Language Models](https://mlsanity.com/paper/2309.11495/) (2023)
- [LM-Infinite: Zero-Shot Extreme Length Generalization for Large Language Models](https://mlsanity.com/paper/2308.16137/) (2023)
- [Why Does ChatGPT Fall Short in Providing Truthful Answers?](https://mlsanity.com/paper/2304.10513/) (2023)
- [Knowledge Graph-Augmented Language Models for Knowledge-Grounded Dialogue Generation](https://mlsanity.com/paper/2305.18846/) (2023)
- [PURR: Efficiently Editing Language Model Hallucinations by Denoising Language Model Corruptions](https://mlsanity.com/paper/2305.14908/) (2023)
- [RCOT: Detecting and Rectifying Factual Inconsistency in Reasoning by Reversing Chain-of-Thought](https://mlsanity.com/paper/2305.11499/) (2023)
- [On Context Utilization in Summarization with Large Language Models](https://mlsanity.com/paper/2310.10570/) (2023)
- [Revisiting Zero-Shot Abstractive Summarization in the Era of Large Language Models from the Perspective of Position Bias](https://mlsanity.com/paper/2401.01989/) (2024)
- [Zero-Resource Hallucination Prevention for Large Language Models](https://mlsanity.com/paper/2309.02654/) (2023)
- [Leveraging GPT-4 for Food Effect Summarization to Enhance Product-Specific Guidance Development via Iterative Prompting](https://mlsanity.com/paper/2306.16275/) (2023)

## Built on by (most cited first, 14 of 14)

- [DEFAME: Dynamic Evidence-based FAct-checking with Multimodal Experts](https://mlsanity.com/paper/2412.10510/) (2024)
- [Teaching Large Language Models to Maintain Contextual Faithfulness via Synthetic Tasks and Reinforcement Learning](https://mlsanity.com/paper/2505.16483/) (2025)
- [CoCoLex: Confidence-guided Copy-based Decoding for Grounded Legal Text Generation](https://mlsanity.com/paper/2508.05534/) (2025)
- [Disentangling Likes and Dislikes in Personalized Generative Explainable Recommendation](https://mlsanity.com/paper/2410.13248/) (2024)
- [CNNSum: Exploring Long-Context Summarization with Large Language Models in Chinese Novels](https://mlsanity.com/paper/2412.02819/) (2024)
- [Are LLMs reliable? An exploration of the reliability of large language models in clinical note generation](https://mlsanity.com/paper/2505.17095/) (2025)
- [Model Editing with Graph-Based External Memory](https://mlsanity.com/paper/2505.18343/) (2025)
- [Learning from Self Critique and Refinement for Faithful LLM Summarization](https://mlsanity.com/paper/2512.05387/) (2025)
- [A Structured Literature Review on Traditional Approaches in Current Natural Language Processing](https://mlsanity.com/paper/2505.12970/) (2025)
- [One SPACE to Rule Them All: Jointly Mitigating Factuality and Faithfulness Hallucinations in LLMs](https://mlsanity.com/paper/2506.11088/) (2025)
- [JSPLIT: A Taxonomy-based Solution for Prompt Bloating in Model Context Protocol](https://mlsanity.com/paper/2510.14537/) (2025)
- [Personalized Chain-of-Thought Summarization of Financial News for Investor Decision Support](https://mlsanity.com/paper/2511.05508/) (2025)
- [NTS-CoT: Mitigating Hallucinations in LLM-based News Timeline Summarization with Chain-of-Thought Reasoning](https://mlsanity.com/paper/2606.13171/) (2026)
- [Decoupling Generation and Selection for Budget-Constrained Faithful Summarization](https://mlsanity.com/paper/2608.03655/) (2026)

## Abstract (arXiv)

Despite large language models (LLMs) have demonstrated impressive performance in various tasks, they are still suffering from the factual inconsistency problem called hallucinations. For instance, LLMs occasionally generate content that diverges from source article, and prefer to extract information that appears at the beginning and end of the context, especially in long document summarization. Inspired by these findings, we propose to improve the faithfulness of LLMs in summarization by impelling them to process the entire article more fairly and faithfully. We present a novel summary generation strategy, namely SliSum, which exploits the ideas of sliding windows and self-consistency. Specifically, SliSum divides the source article into overlapping windows, and utilizes LLM to generate local summaries for the content in the windows. Finally, SliSum aggregates all local summaries using clustering and majority voting algorithm to produce more faithful summary of entire article. Extensive experiments demonstrate that SliSum significantly improves the faithfulness of diverse LLMs including LLaMA-2, Claude-2 and GPT-3.5 in both short and long text summarization, while maintaining their fluency and informativeness and without additional fine-tuning and resources. We further conduct qualitative and quantitative studies to investigate why SliSum works and impacts of hyperparameters in SliSum on performance.