Pith. sign in

REVIEW 10 cited by

ChatGPT as a Factual Inconsistency Evaluator for Text Summarization

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 2303.15621 v2 pith:QE7QABGT submitted 2023-03-27 cs.CL

ChatGPT as a Factual Inconsistency Evaluator for Text Summarization

classification cs.CL
keywords chatgptevaluationlanguagefactualinconsistencytexthoweverincluding
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

The performance of text summarization has been greatly boosted by pre-trained language models. A main concern of existing methods is that most generated summaries are not factually inconsistent with their source documents. To alleviate the problem, many efforts have focused on developing effective factuality evaluation metrics based on natural language inference, question answering, and syntactic dependency et al. However, these approaches are limited by either their high computational complexity or the uncertainty introduced by multi-component pipelines, resulting in only partial agreement with human judgement. Most recently, large language models(LLMs) have shown excellent performance in not only text generation but also language comprehension. In this paper, we particularly explore ChatGPT's ability to evaluate factual inconsistency under a zero-shot setting by examining it on both coarse-grained and fine-grained evaluation tasks including binary entailment inference, summary ranking, and consistency rating. Experimental results indicate that ChatGPT generally outperforms previous evaluation metrics across the three tasks, indicating its great potential for factual inconsistency evaluation. However, a closer inspection of ChatGPT's output reveals certain limitations including its preference for more lexically similar candidates, false reasoning, and inadequate understanding of instructions.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 10 Pith papers

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

  1. Teaching Language Models to Check Grounded Claim Factuality with Human Test-Taking Strategies

    cs.CL 2026-05 unverdicted novelty 7.0

    Prompting LLMs with test-taking strategies for true/false factuality checks reduces tokens by over 80%, matches strong baselines on two benchmarks with SOTA on one, and enables fine-tuned SLMs to perform similarly at ...

  2. The Prompt Report: A Systematic Survey of Prompt Engineering Techniques

    cs.CL 2024-06 accept novelty 7.0

    This systematic survey organizes prompt engineering into a taxonomy of 58 LLM techniques and 40 others, supplies a shared vocabulary, and offers guidelines for state-of-the-art models.

  3. Automated Creativity Evaluation of Language Models Across Open-Ended Tasks

    cs.CL 2026-06 unverdicted novelty 6.0

    Authors propose a new framework for automated LLM creativity evaluation that separates measurement from the task, using semantic entropy and multi-agent judges, validated on problem-solving, research ideation, and cre...

  4. Optimising Factual Consistency in Summarisation via Preference Learning from Multiple Imperfect Metrics

    cs.CL 2026-05 unverdicted novelty 6.0

    Aggregating imperfect factuality metrics into preference data from lexically similar summaries yields consistent factuality gains across model sizes, allowing smaller models to approach larger ones.

  5. LLM-ReSum: A Framework for LLM Reflective Summarization through Self-Evaluation

    cs.CL 2026-04 unverdicted novelty 6.0

    LLM-ReSum uses LLM self-evaluation in a closed feedback loop to refine summaries, improving factual accuracy by up to 33% and coverage by 39% with 89% human preference.

  6. Whose Story Gets Told? Positionality and Bias in LLM Summaries of Life Narratives

    cs.CL 2026-04 unverdicted novelty 6.0

    A proposed pipeline shows LLMs introduce detectable race and gender biases when summarizing life narratives, creating potential for representational harm in research.

  7. Principled Detection of Hallucinations in Large Language Models via Multiple Testing

    cs.CL 2025-08 unverdicted novelty 6.0

    The method aggregates multiple hallucination evaluation scores via conformal p-values to enable calibrated detection with controlled false alarm rates across LLMs and datasets.

  8. LaMSUM: Amplifying Voices Against Harassment through LLM Guided Extractive Summarization of User Incident Reports

    cs.CL 2024-06 unverdicted novelty 6.0

    LaMSUM is a novel multi-level LLM framework with voting methods for extractive summarization of large incident report collections that outperforms prior extractive methods.

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

    cs.CL 2023-03 unverdicted novelty 6.0

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

  10. MegaFake: A Theory-Driven Dataset of Fake News Generated by Large Language Models

    cs.CL 2024-08 unverdicted novelty 5.0

    Authors create LLM-Fake Theory integrating social psychology, then use a prompt engineering pipeline to build the MegaFake dataset of LLM-generated fake news for advancing detection methods.