Pith. sign in

REVIEW 8 cited by

The Factual Inconsistency Problem in Abstractive Text Summarization: A Survey

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2104.14839 v3 pith:V5JJFL3Z submitted 2021-04-30 cs.CL

classification cs.CL
keywords textfactualsummariessummarizationevaluationinconsistencymodelsneural
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Recently, various neural encoder-decoder models pioneered by Seq2Seq framework have been proposed to achieve the goal of generating more abstractive summaries by learning to map input text to output text. At a high level, such neural models can freely generate summaries without any constraint on the words or phrases used. Moreover, their format is closer to human-edited summaries and output is more readable and fluent. However, the neural model's abstraction ability is a double-edged sword. A commonly observed problem with the generated summaries is the distortion or fabrication of factual information in the article. This inconsistency between the original text and the summary has caused various concerns over its applicability, and the previous evaluation methods of text summarization are not suitable for this issue. In response to the above problems, the current research direction is predominantly divided into two categories, one is to design fact-aware evaluation metrics to select outputs without factual inconsistency errors, and the other is to develop new summarization systems towards factual consistency. In this survey, we focus on presenting a comprehensive review of these fact-specific evaluation methods and text summarization models.

Discussion (0). Sign in to comment.

Forward citations

Cited by 8 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Hallucination is Inevitable: An Innate Limitation of Large Language Models

    cs.CL 2024-01 conditional novelty 7.0 of 10

    Hallucinations are inevitable in LLMs because they cannot learn all computable functions according to learning theory.

  2. Evaluating Object Hallucination in Large Vision-Language Models

    cs.CV 2023-05 accept novelty 7.0 of 10

    Large vision-language models exhibit severe object hallucination that varies with training instructions, and the proposed POPE polling method evaluates it more stably and flexibly than prior approaches.

  3. Spatial Visual Analytics for Multi-Document Summary Verification

    cs.HC 2026-07 conditional novelty 6.0 of 10

    Placing source documents by how they align with summary sentences improves people's ability to verify multi-document AI summaries, outperforming a linear list.

  4. PseudoBench: Measuring How Agentic Auto-Research Fuels Pseudoscience

    cs.AI 2026-06 unverdicted novelty 6.0 of 10

    PseudoBench shows current LLM agents produce persuasive pseudoscientific reports with near-zero refusal rates and at most 27.4% resistance.

  5. SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models

    cs.CL 2023-03 unverdicted novelty 6.0 of 10

    SelfCheckGPT detects hallucinations by checking consistency across multiple sampled responses from black-box LLMs on WikiBio biography generation tasks.

  6. The Cost of Knowing: A Resource-Aware Protocol for Benchmarking Hallucination Beyond Static Leaderboards

    cs.AI 2026-07 reject novelty 5.0 of 10

    MAS-HQ defines a resource-aware Q-Score and shows that the system with the highest raw factuality is often not the winner once normalized cost is subtracted.

  7. MedFabric and EtHER: A Data-Centric Framework for Word-Level Fabrication Generation and Detection in Medical LLMs

    cs.CL 2026-05 unverdicted novelty 5.0 of 10

    MedFabric dataset and EtHER detector achieve over 15% better word-level fabrication detection in medical LLMs than prior methods by generating stylistically faithful errors and using decomposition-based checking.

  8. A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions

    cs.CL 2023-11 unverdicted novelty 5.0 of 10

    The paper surveys hallucination in LLMs with an innovative taxonomy, factors, detection methods, benchmarks, mitigation strategies, and open research directions.

Pith tools