paper-with-me

Papers

FactSpotter: Evaluating the Factual Faithfulness of Graph-to-Text Generation

2023-10-25 · Findings of EMNLP 2023 10 · Kun Zhang, Oana Balalau, Ioana Manolescu

Graph-to-text (G2T) generation takes a graph as input and aims to generate a fluent and faith- ful textual representation of the information in the graph. The task has many applications, such as dialogue generation and question an- swering. In this work, we investigate to what extent the G2T generation problem is solved for previously studied datasets, and how pro- posed metrics perform when comparing generated texts. To help address their limitations, we propose a new metric that correctly identifies factual faithfulness, i.e., given a triple (subject, predicate, object), it decides if the triple is present in a generated text. We show that our metric FactSpotter achieves the highest correlation with human annotations on data correct- ness, data coverage, and relevance. In addition, FactSpotter can be used as a plug-in feature to improve the factual faithfulness of existing models. Finally, we investigate if existing G2T datasets are still challenging for state-of-the-art models. Our code is available online: https://github.com/guihuzhang/FactSpotter.

📄 PDF Abstract BibTeX

Code (1)

guihuzhang/FactSpotter pytorch

Tasks

Data-to-Text GenerationDialogue GenerationKG-to-Text GenerationQuestion GenerationTable-to-Text GenerationText Generation

Similar Papers 제목 키워드 기반

Analyzing and Evaluating Faithfulness in Dialogue Summarization

2022-10-21 · Bin Wang, Chen Zhang, Yan Zhang, Yiming Chen 외

Dialogue summarization is abstractive in nature, making it suffer from factual errors. The factual correctness of summaries has the highest priority before practical applications. Many efforts have been made to improve f…

Text Summarization

Counterfactuals As a Means for Evaluating Faithfulness of Attribution Methods in Autoregressive Language Models

2024-08-21 · Sepehr Kamahi, Yadollah Yaghoobzadeh

Despite the widespread adoption of autoregressive language models, explainability evaluation research has predominantly focused on span infilling and masked language models. Evaluating the faithfulness of an explanation …

counterfactualDecision MakingFeature ImportanceLanguage Modelling

Logical Satisfiability of Counterfactuals for Faithful Explanations in NLI

2022-05-25 · Suzanna Sia, Anton Belyy, Amjad Almahairi, Madian Khabsa 외

Evaluating an explanation's faithfulness is desired for many reasons such as trust, interpretability and diagnosing the sources of model's errors. In this work, which focuses on the NLI task, we introduce the methodology…

counterfactual

Is Factuality Enhancement a Free Lunch For LLMs? Better Factuality Can Lead to Worse Context-Faithfulness

2024-03-30 · Baolong Bi, Shenghua Liu, Yiwei Wang, Lingrui Mei 외

As the modern tools of choice for text understanding and generation, large language models (LLMs) are expected to accurately output answers by leveraging the input context. This requires LLMs to possess both context-fait…

knowledge editing

Zero-shot Faithful Factual Error Correction

2023-05-13 · Kung-Hsiang Huang, Hou Pong Chan, Heng Ji

Faithfully correcting factual errors is critical for maintaining the integrity of textual knowledge bases and preventing hallucinations in sequence-to-sequence models. Drawing on humans' ability to identify and correct f…